{"benchmark_line":"gamebench2","economics_chart":{"eligible_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"enabled":true},"game_order":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"games":[{"alias":"GB2-01","name":"Go","slug":"go"},{"alias":"GB2-02","name":"Chess","slug":"chess"},{"alias":"GB2-03","name":"Shogi","slug":"shogi"},{"alias":"GB2-04","name":"Xiangqi","slug":"xiangqi"},{"alias":"GB2-05","name":"Hex","slug":"hex"},{"alias":"GB2-06","name":"International Draughts","slug":"international-draughts"},{"alias":"GB2-07","name":"Game of the Amazons","slug":"game-of-the-amazons"},{"alias":"GB2-08","name":"Tumbleweed","slug":"tumbleweed"}],"generated_at":"2026-10-24T19:43:38Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:37b988a0e154d378","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.42744},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.27234},"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":1.9134900000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.27234},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.427439999999999}},"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":15.613270000000004},"codegen_output_tokens":{"attempt_count":24,"output_max":27674,"output_mean":11074.333333333334,"output_min":2260,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27674,"output_mean":24131.875,"output_min":19038,"run_count":8},"medium":{"attempt_count":8,"output_max":7733,"output_mean":6244.125,"output_min":3722,"run_count":8},"none":{"attempt_count":8,"output_max":3278,"output_mean":2847.0,"output_min":2260,"run_count":8}},"display_name":"GPT-6 Astra","economics":{"all":89.75261910859338,"highest":94.53845591460596,"medium":89.7130097062338,"none":85.00639170494036},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":89.10450351477972,"score":89.10450351477972},"GB2-02":{"attempts":3,"playable":83.13181265181358,"score":83.13181265181358},"GB2-03":{"attempts":3,"playable":89.24866722105503,"score":89.24866722105503},"GB2-04":{"attempts":3,"playable":89.25961001843001,"score":89.25961001843001},"GB2-05":{"attempts":3,"playable":95.42289620970301,"score":95.42289620970301},"GB2-06":{"attempts":3,"playable":86.81572940245407,"score":86.81572940245407},"GB2-07":{"attempts":3,"playable":96.35639047352277,"score":96.35639047352277},"GB2-08":{"attempts":3,"playable":88.68134337698878,"score":88.68134337698878}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":97.26268664315673,"score":97.26268664315673},"GB2-02":{"attempts":1,"playable":95.47612955910778,"score":95.47612955910778},"GB2-03":{"attempts":1,"playable":97.71540014995662,"score":97.71540014995662},"GB2-04":{"attempts":1,"playable":92.60948934848182,"score":92.60948934848182},"GB2-05":{"attempts":1,"playable":98.93327106049324,"score":98.93327106049324},"GB2-06":{"attempts":1,"playable":87.72293906424076,"score":87.72293906424076},"GB2-07":{"attempts":1,"playable":97.81822860478181,"score":97.81822860478181},"GB2-08":{"attempts":1,"playable":88.76950288662896,"score":88.76950288662896}},"medium":{"GB2-01":{"attempts":1,"playable":76.89150206369128,"score":76.89150206369128},"GB2-02":{"attempts":1,"playable":81.28914588314018,"score":81.28914588314018},"GB2-03":{"attempts":1,"playable":94.62489753095527,"score":94.62489753095527},"GB2-04":{"attempts":1,"playable":91.782681885848,"score":91.782681885848},"GB2-05":{"attempts":1,"playable":93.07464003856816,"score":93.07464003856816},"GB2-06":{"attempts":1,"playable":88.62485830618898,"score":88.62485830618898},"GB2-07":{"attempts":1,"playable":96.65952327376192,"score":96.65952327376192},"GB2-08":{"attempts":1,"playable":94.75682866771659,"score":94.75682866771659}},"none":{"GB2-01":{"attempts":1,"playable":93.15932183749119,"score":93.15932183749119},"GB2-02":{"attempts":1,"playable":72.63016251319274,"score":72.63016251319274},"GB2-03":{"attempts":1,"playable":75.40570398225324,"score":75.40570398225324},"GB2-04":{"attempts":1,"playable":83.38665882096022,"score":83.38665882096022},"GB2-05":{"attempts":1,"playable":94.26077753004762,"score":94.26077753004762},"GB2-06":{"attempts":1,"playable":84.09939083693246,"score":84.09939083693246},"GB2-07":{"attempts":1,"playable":94.5914195420246,"score":94.5914195420246},"GB2-08":{"attempts":1,"playable":82.51769857662077,"score":82.51769857662077}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-10-24T19:15:38Z","match_totals_all":{"draws":877,"losses":886,"wins":10501},"match_totals_tracks":{"highest":{"draws":98,"losses":183,"wins":3807},"medium":{"draws":263,"losses":309,"wins":3516},"none":{"draws":516,"losses":394,"wins":3178}},"model_slug":"gpt-6-astra","official_rank_by_reasoning":{"highest":2,"medium":2,"none":4},"overall":{"max":98.93327106049324,"mean":89.75261910859338,"min":72.63016251319274},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":97.26268664315673,"GB2-02":95.47612955910778,"GB2-03":97.71540014995662,"GB2-04":92.60948934848182,"GB2-05":98.93327106049324,"GB2-06":87.72293906424076,"GB2-07":97.81822860478181,"GB2-08":88.76950288662896},"per_game_all":{"GB2-01":89.10450351477972,"GB2-02":83.13181265181358,"GB2-03":89.24866722105503,"GB2-04":89.25961001843001,"GB2-05":95.42289620970301,"GB2-06":86.81572940245407,"GB2-07":96.35639047352277,"GB2-08":88.68134337698878},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":154,"wins":1333},"GB2-02":{"draws":402,"losses":54,"wins":984},"GB2-03":{"draws":174,"losses":89,"wins":1219},"GB2-04":{"draws":159,"losses":90,"wins":1245},"GB2-05":{"draws":0,"losses":70,"wins":1520},"GB2-06":{"draws":81,"losses":180,"wins":1245},"GB2-07":{"draws":0,"losses":47,"wins":1543},"GB2-08":{"draws":0,"losses":202,"wins":1412}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":15,"wins":501},"GB2-02":{"draws":25,"losses":9,"wins":446},"GB2-03":{"draws":9,"losses":6,"wins":479},"GB2-04":{"draws":33,"losses":22,"wins":443},"GB2-05":{"draws":0,"losses":3,"wins":527},"GB2-06":{"draws":31,"losses":53,"wins":418},"GB2-07":{"draws":0,"losses":8,"wins":522},"GB2-08":{"draws":0,"losses":67,"wins":471}},"medium":{"GB2-01":{"draws":37,"losses":111,"wins":368},"GB2-02":{"draws":156,"losses":17,"wins":307},"GB2-03":{"draws":5,"losses":26,"wins":463},"GB2-04":{"draws":42,"losses":22,"wins":434},"GB2-05":{"draws":0,"losses":37,"wins":493},"GB2-06":{"draws":23,"losses":52,"wins":427},"GB2-07":{"draws":0,"losses":14,"wins":516},"GB2-08":{"draws":0,"losses":30,"wins":508}},"none":{"GB2-01":{"draws":24,"losses":28,"wins":464},"GB2-02":{"draws":221,"losses":28,"wins":231},"GB2-03":{"draws":160,"losses":57,"wins":277},"GB2-04":{"draws":84,"losses":46,"wins":368},"GB2-05":{"draws":0,"losses":30,"wins":500},"GB2-06":{"draws":27,"losses":75,"wins":400},"GB2-07":{"draws":0,"losses":25,"wins":505},"GB2-08":{"draws":0,"losses":105,"wins":433}}},"per_game_raw_elo_all":{"GB2-01":2036.948784559856,"GB2-02":1850.6071861624794,"GB2-03":2098.668550978359,"GB2-04":1918.4187396117766,"GB2-05":2599.1001232426474,"GB2-06":2095.0698223134,"GB2-07":2540.8103955733973,"GB2-08":2126.8172849504926},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2279.108304764117,"GB2-02":2112.6318025820756,"GB2-03":2411.636770995474,"GB2-04":1988.5091287280943,"GB2-05":2940.4258873488466,"GB2-06":2115.484748264351,"GB2-07":2659.0456106824686,"GB2-08":2105.7221987964367},"medium":{"GB2-01":1755.5211820018662,"GB2-02":1771.649938668738,"GB2-03":2189.0016491382125,"GB2-04":1965.3923036207486,"GB2-05":2395.0083880815982,"GB2-06":2138.4168144879923,"GB2-07":2552.9157692208328,"GB2-08":2336.186907604874},"none":{"GB2-01":2076.2168669135845,"GB2-02":1667.5398172366238,"GB2-03":1695.3672328013902,"GB2-04":1801.3547864864872,"GB2-05":2461.8660942974966,"GB2-06":2031.3079041878568,"GB2-07":2410.4698068168905,"GB2-08":1938.542748450168}},"per_game_tracks":{"highest":{"GB2-01":97.26268664315673,"GB2-02":95.47612955910778,"GB2-03":97.71540014995662,"GB2-04":92.60948934848182,"GB2-05":98.93327106049324,"GB2-06":87.72293906424076,"GB2-07":97.81822860478181,"GB2-08":88.76950288662896},"medium":{"GB2-01":76.89150206369128,"GB2-02":81.28914588314018,"GB2-03":94.62489753095527,"GB2-04":91.782681885848,"GB2-05":93.07464003856816,"GB2-06":88.62485830618898,"GB2-07":96.65952327376192,"GB2-08":94.75682866771659},"none":{"GB2-01":93.15932183749119,"GB2-02":72.63016251319274,"GB2-03":75.40570398225324,"GB2-04":83.38665882096022,"GB2-05":94.26077753004762,"GB2-06":84.09939083693246,"GB2-07":94.5914195420246,"GB2-08":82.51769857662077}},"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":"2026-10-22T10:58:58Z","reasoning":{"highest":94.53845591460596,"medium":89.7130097062338,"none":85.00639170494036},"reasoning_agg":{"highest":{"max":98.93327106049324,"mean":94.53845591460596,"min":87.72293906424076},"medium":{"max":96.65952327376192,"mean":89.7130097062338,"min":76.89150206369128},"none":{"max":94.5914195420246,"mean":85.00639170494036,"min":72.63016251319274}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.532064209665606},"working_program_strength":{"all":89.75261910859338,"highest":94.53845591460596,"medium":89.7130097062338,"none":85.00639170494036}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:655478e878abe238","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677191999999998},"medium":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.006308},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.0527920000000002}},"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":3.006308},"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":17.677191999999998}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292},"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":88.7727492484825,"highest":95.19630266144368,"medium":92.85102839828984,"none":78.27091668571397},"economics_best_value":{"per_model":{"highest":true,"medium":true},"per_setting":{"highest":true,"medium":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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.1111111111111111},"baseline":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":9,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":89.82181572145417,"score":89.82181572145417},"GB2-02":{"attempts":3,"playable":90.51408865961672,"score":90.51408865961672},"GB2-03":{"attempts":3,"playable":80.84547462007968,"score":80.84547462007968},"GB2-04":{"attempts":3,"playable":84.51167637087885,"score":84.51167637087885},"GB2-05":{"attempts":3,"playable":93.29323438113522,"score":93.29323438113522},"GB2-06":{"attempts":3,"playable":89.69588801011464,"score":89.69588801011464},"GB2-07":{"attempts":3,"playable":94.39784120009715,"score":94.39784120009715},"GB2-08":{"attempts":5,"playable":87.10197502448354,"score":87.10197502448354}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.36389475998953,"score":84.36389475998953},"GB2-02":{"attempts":1,"playable":95.85687455408122,"score":95.85687455408122},"GB2-03":{"attempts":1,"playable":97.11429757753832,"score":97.11429757753832},"GB2-04":{"attempts":1,"playable":94.80300820581203,"score":94.80300820581203},"GB2-05":{"attempts":1,"playable":98.24606459184145,"score":98.24606459184145},"GB2-06":{"attempts":1,"playable":99.41527624723501,"score":99.41527624723501},"GB2-07":{"attempts":1,"playable":97.81822860478181,"score":97.81822860478181},"GB2-08":{"attempts":1,"playable":93.9527767502701,"score":93.9527767502701}},"medium":{"GB2-01":{"attempts":1,"playable":93.91820815934825,"score":93.91820815934825},"GB2-02":{"attempts":1,"playable":95.38090507980687,"score":95.38090507980687},"GB2-03":{"attempts":1,"playable":92.56906805705228,"score":92.56906805705228},"GB2-04":{"attempts":1,"playable":88.54527140390232,"score":88.54527140390232},"GB2-05":{"attempts":1,"playable":89.7334366023455,"score":89.7334366023455},"GB2-06":{"attempts":1,"playable":91.93516878220218,"score":91.93516878220218},"GB2-07":{"attempts":1,"playable":93.49403156360799,"score":93.49403156360799},"GB2-08":{"attempts":2,"playable":97.23213753805337,"score":97.23213753805337}},"none":{"GB2-01":{"attempts":1,"playable":91.18334424502471,"score":91.18334424502471},"GB2-02":{"attempts":1,"playable":80.30448634496206,"score":80.30448634496206},"GB2-03":{"attempts":1,"playable":52.85305822564846,"score":52.85305822564846},"GB2-04":{"attempts":1,"playable":70.18674950292221,"score":70.18674950292221},"GB2-05":{"attempts":1,"playable":91.90020194921873,"score":91.90020194921873},"GB2-06":{"attempts":1,"playable":77.73721900090675,"score":77.73721900090675},"GB2-07":{"attempts":1,"playable":91.88126343190166,"score":91.88126343190166},"GB2-08":{"attempts":2,"playable":70.12101078512715,"score":70.12101078512715}}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:20:59Z","match_totals_all":{"draws":953,"losses":1168,"wins":11219},"match_totals_tracks":{"highest":{"draws":80,"losses":160,"wins":3848},"medium":{"draws":129,"losses":256,"wins":4241},"none":{"draws":744,"losses":752,"wins":3130}},"model_slug":"claude-opus-5-5","official_rank_by_reasoning":{"highest":1,"medium":1,"none":7},"overall":{"max":99.41527624723501,"mean":88.7727492484825,"min":52.85305822564846},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.36389475998953,"GB2-02":95.85687455408122,"GB2-03":97.11429757753832,"GB2-04":94.80300820581203,"GB2-05":98.24606459184145,"GB2-06":99.41527624723501,"GB2-07":97.81822860478181,"GB2-08":93.9527767502701},"per_game_all":{"GB2-01":89.82181572145417,"GB2-02":90.51408865961672,"GB2-03":80.84547462007968,"GB2-04":84.51167637087885,"GB2-05":93.29323438113522,"GB2-06":89.69588801011464,"GB2-07":94.39784120009715,"GB2-08":87.10197502448354},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":144,"wins":1339},"GB2-02":{"draws":143,"losses":70,"wins":1227},"GB2-03":{"draws":352,"losses":131,"wins":999},"GB2-04":{"draws":313,"losses":87,"wins":1094},"GB2-05":{"draws":0,"losses":108,"wins":1482},"GB2-06":{"draws":56,"losses":141,"wins":1309},"GB2-07":{"draws":0,"losses":79,"wins":1511},"GB2-08":{"draws":24,"losses":408,"wins":2258}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":85,"wins":422},"GB2-02":{"draws":25,"losses":7,"wins":448},"GB2-03":{"draws":2,"losses":13,"wins":479},"GB2-04":{"draws":43,"losses":5,"wins":450},"GB2-05":{"draws":0,"losses":7,"wins":523},"GB2-06":{"draws":1,"losses":0,"wins":501},"GB2-07":{"draws":0,"losses":8,"wins":522},"GB2-08":{"draws":0,"losses":35,"wins":503}},"medium":{"GB2-01":{"draws":35,"losses":18,"wins":463},"GB2-02":{"draws":12,"losses":16,"wins":452},"GB2-03":{"draws":23,"losses":29,"wins":442},"GB2-04":{"draws":41,"losses":40,"wins":417},"GB2-05":{"draws":0,"losses":57,"wins":473},"GB2-06":{"draws":18,"losses":36,"wins":448},"GB2-07":{"draws":0,"losses":31,"wins":499},"GB2-08":{"draws":0,"losses":29,"wins":1047}},"none":{"GB2-01":{"draws":21,"losses":41,"wins":454},"GB2-02":{"draws":106,"losses":47,"wins":327},"GB2-03":{"draws":327,"losses":89,"wins":78},"GB2-04":{"draws":229,"losses":42,"wins":227},"GB2-05":{"draws":0,"losses":44,"wins":486},"GB2-06":{"draws":37,"losses":105,"wins":360},"GB2-07":{"draws":0,"losses":40,"wins":490},"GB2-08":{"draws":24,"losses":344,"wins":708}}},"per_game_raw_elo_all":{"GB2-01":1995.6798231952137,"GB2-02":1999.2998172183395,"GB2-03":1966.668627649333,"GB2-04":1866.211790388453,"GB2-05":2462.7986329647233,"GB2-06":2327.738210832697,"GB2-07":2423.335104182784,"GB2-08":2168.7466262666057},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1867.98607563614,"GB2-02":2131.760624825403,"GB2-03":2355.405267699771,"GB2-04":2062.8754879865974,"GB2-05":2816.002936920403,"GB2-06":2848.5646455424658,"GB2-07":2659.0456106824686,"GB2-08":2296.668959719514},"medium":{"GB2-01":2103.6419717575986,"GB2-02":2108.0661688778655,"GB2-03":2091.7909246502095,"GB2-04":1890.485697059457,"GB2-05":2237.02486996321,"GB2-06":2234.180338121902,"GB2-07":2347.0517174201295,"GB2-08":2528.703459354394},"none":{"GB2-01":2015.411422191903,"GB2-02":1758.0726579517495,"GB2-03":1452.809690598019,"GB2-04":1645.2741861193044,"GB2-05":2335.368092010557,"GB2-06":1900.469648833723,"GB2-07":2263.9079844457538,"GB2-08":1680.8674597259082}},"per_game_tracks":{"highest":{"GB2-01":84.36389475998953,"GB2-02":95.85687455408122,"GB2-03":97.11429757753832,"GB2-04":94.80300820581203,"GB2-05":98.24606459184145,"GB2-06":99.41527624723501,"GB2-07":97.81822860478181,"GB2-08":93.9527767502701},"medium":{"GB2-01":93.91820815934825,"GB2-02":95.38090507980687,"GB2-03":92.56906805705228,"GB2-04":88.54527140390232,"GB2-05":89.7334366023455,"GB2-06":91.93516878220218,"GB2-07":93.49403156360799,"GB2-08":97.23213753805337},"none":{"GB2-01":91.18334424502471,"GB2-02":80.30448634496206,"GB2-03":52.85305822564846,"GB2-04":70.18674950292221,"GB2-05":91.90020194921873,"GB2-06":77.73721900090675,"GB2-07":91.88126343190166,"GB2-08":70.12101078512715}},"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":"2026-10-22T10:56:24Z","reasoning":{"highest":95.19630266144368,"medium":92.85102839828984,"none":78.27091668571397},"reasoning_agg":{"highest":{"max":99.41527624723501,"mean":95.19630266144368,"min":84.36389475998953},"medium":{"max":97.23213753805337,"mean":92.85102839828984,"min":88.54527140390232},"none":{"max":91.90020194921873,"mean":78.27091668571397,"min":52.85305822564846}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.92538597572971},"working_program_strength":{"all":88.7727492484825,"highest":95.19630266144368,"medium":92.85102839828984,"none":78.27091668571397}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:d8bfa7468f9efb5e","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":48.7391179312137},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276067},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609}},"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":{"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":48.739117931213684}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781585},"codegen_output_tokens":{"attempt_count":35,"output_max":231035,"output_mean":46647.59375,"output_min":5610,"run_count":32},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":231035,"output_mean":80471.125,"output_min":38285,"run_count":16},"medium":{"attempt_count":9,"output_max":25949,"output_mean":17238.625,"output_min":9715,"run_count":8},"none":{"attempt_count":8,"output_max":10198,"output_mean":8409.5,"output_min":5610,"run_count":8}},"display_name":"Claude Fable 5.1","economics":{"all":88.52295100370141,"highest":94.31889376561342,"medium":84.60026121377865,"none":86.64969803171212},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":11,"evaluated_cells":11,"first_pass_admitted":9,"first_pass_rate":0.8181818181818182,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.18181818181818182}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":85.09286224111976,"score":85.09286224111976},"GB2-02":{"attempts":3,"playable":90.00293773420553,"score":90.00293773420553},"GB2-03":{"attempts":4,"playable":93.63998698272,"score":93.63998698272},"GB2-04":{"attempts":4,"playable":75.26465950901259,"score":75.26465950901259},"GB2-05":{"attempts":3,"playable":91.23670347233765,"score":91.23670347233765},"GB2-06":{"attempts":3,"playable":89.87599332530341,"score":89.87599332530341},"GB2-07":{"attempts":4,"playable":91.97709895488073,"score":91.97709895488073},"GB2-08":{"attempts":3,"playable":91.09336581003146,"score":91.09336581003146}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":93.15932183749119,"score":93.15932183749119},"GB2-02":{"attempts":1,"playable":95.09514932266673,"score":95.09514932266673},"GB2-03":{"attempts":2,"playable":95.1824276433911,"score":95.1824276433911},"GB2-04":{"attempts":2,"playable":87.88223522272406,"score":87.88223522272406},"GB2-05":{"attempts":1,"playable":93.41216585433246,"score":93.41216585433246},"GB2-06":{"attempts":1,"playable":98.16699975991787,"score":98.16699975991787},"GB2-07":{"attempts":2,"playable":93.85790034100701,"score":93.85790034100701},"GB2-08":{"attempts":1,"playable":97.79495014337688,"score":97.79495014337688}},"medium":{"GB2-01":{"attempts":1,"playable":73.8544563852287,"score":73.8544563852287},"GB2-02":{"attempts":1,"playable":91.37056828259476,"score":91.37056828259476},"GB2-03":{"attempts":1,"playable":92.31213488978568,"score":92.31213488978568},"GB2-04":{"attempts":1,"playable":63.82387567490597,"score":63.82387567490597},"GB2-05":{"attempts":1,"playable":88.56483090529314,"score":88.56483090529314},"GB2-06":{"attempts":1,"playable":87.36158937905991,"score":87.36158937905991},"GB2-07":{"attempts":1,"playable":93.85763020300668,"score":93.85763020300668},"GB2-08":{"attempts":1,"playable":85.65700399035438,"score":85.65700399035438}},"none":{"GB2-01":{"attempts":1,"playable":88.26480850063936,"score":88.26480850063936},"GB2-02":{"attempts":1,"playable":83.54309559735506,"score":83.54309559735506},"GB2-03":{"attempts":1,"playable":93.42539841498325,"score":93.42539841498325},"GB2-04":{"attempts":1,"playable":74.08786762940774,"score":74.08786762940774},"GB2-05":{"attempts":1,"playable":91.73311365738736,"score":91.73311365738736},"GB2-06":{"attempts":1,"playable":84.09939083693246,"score":84.09939083693246},"GB2-07":{"attempts":1,"playable":88.2157663206285,"score":88.2157663206285},"GB2-08":{"attempts":1,"playable":89.82814329636311,"score":89.82814329636311}}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-10-24T19:21:00Z","match_totals_all":{"draws":779,"losses":1212,"wins":11793},"match_totals_tracks":{"highest":{"draws":129,"losses":290,"wins":5191},"medium":{"draws":311,"losses":513,"wins":3263},"none":{"draws":339,"losses":409,"wins":3339}},"model_slug":"claude-fable-5-1","official_rank_by_reasoning":{"highest":3,"medium":4,"none":3},"overall":{"max":98.16699975991787,"mean":88.52295100370141,"min":63.82387567490597},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":93.15932183749119,"GB2-02":95.09514932266673,"GB2-03":95.1824276433911,"GB2-04":87.88223522272406,"GB2-05":93.41216585433246,"GB2-06":98.16699975991787,"GB2-07":93.85790034100701,"GB2-08":97.79495014337688},"per_game_all":{"GB2-01":85.09286224111976,"GB2-02":90.00293773420553,"GB2-03":93.63998698272,"GB2-04":75.26465950901259,"GB2-05":91.23670347233765,"GB2-06":89.87599332530341,"GB2-07":91.97709895488073,"GB2-08":91.09336581003146},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":39,"wins":475},"GB2-02":{"draws":23,"losses":12,"wins":445},"GB2-03":{"draws":3,"losses":26,"wins":465},"GB2-04":{"draws":54,"losses":23,"wins":421},"GB2-05":{"draws":0,"losses":35,"wins":495},"GB2-06":{"draws":5,"losses":6,"wins":491},"GB2-07":{"draws":0,"losses":28,"wins":502},"GB2-08":{"draws":0,"losses":11,"wins":527}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":39,"wins":475},"GB2-02":{"draws":23,"losses":12,"wins":445},"GB2-03":{"draws":3,"losses":26,"wins":465},"GB2-04":{"draws":54,"losses":23,"wins":421},"GB2-05":{"draws":0,"losses":35,"wins":495},"GB2-06":{"draws":5,"losses":6,"wins":491},"GB2-07":{"draws":0,"losses":28,"wins":502},"GB2-08":{"draws":0,"losses":11,"wins":527}}},"per_game_raw_elo_all":{"GB2-01":1912.3225513202578,"GB2-02":1955.0146068706672,"GB2-03":2143.8215988781526,"GB2-04":1717.9737451066549,"GB2-05":2309.8035423483007,"GB2-06":2242.184598862877,"GB2-07":2282.254199708254,"GB2-08":2237.2023045867313},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2076.2168669135845,"GB2-02":2094.8379341436557,"GB2-03":2220.907054933918,"GB2-04":1881.954870096943,"GB2-05":2413.2464153883375,"GB2-06":2588.680106071193,"GB2-07":2367.4813747162007,"GB2-08":2555.0692223622145},"medium":{"GB2-01":1716.8981781771543,"GB2-02":1965.069172550173,"GB2-03":2081.199905894069,"GB2-04":1586.9300477668553,"GB2-05":2188.867348172567,"GB2-06":2106.56578632958,"GB2-07":2367.383743409129,"GB2-08":2017.5875835814827},"none":{"GB2-01":1943.8526088700341,"GB2-02":1805.1367139181732,"GB2-03":2129.357835806472,"GB2-04":1685.0363174561664,"GB2-05":2327.296863483997,"GB2-06":2031.3079041878568,"GB2-07":2111.897480999433,"GB2-08":2138.9501078164967}},"per_game_tracks":{"highest":{"GB2-01":93.15932183749119,"GB2-02":95.09514932266673,"GB2-03":95.1824276433911,"GB2-04":87.88223522272406,"GB2-05":93.41216585433246,"GB2-06":98.16699975991787,"GB2-07":93.85790034100701,"GB2-08":97.79495014337688},"medium":{"GB2-01":73.8544563852287,"GB2-02":91.37056828259476,"GB2-03":92.31213488978568,"GB2-04":63.82387567490597,"GB2-05":88.56483090529314,"GB2-06":87.36158937905991,"GB2-07":93.85763020300668,"GB2-08":85.65700399035438},"none":{"GB2-01":88.26480850063936,"GB2-02":83.54309559735506,"GB2-03":93.42539841498325,"GB2-04":74.08786762940774,"GB2-05":91.73311365738736,"GB2-06":84.09939083693246,"GB2-07":88.2157663206285,"GB2-08":89.82814329636311}},"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":"2026-10-22T10:59:24Z","reasoning":{"highest":94.31889376561342,"medium":84.60026121377865,"none":86.64969803171212},"reasoning_agg":{"highest":{"max":98.16699975991787,"mean":94.31889376561342,"min":87.88223522272406},"medium":{"max":93.85763020300668,"mean":84.60026121377865,"min":63.82387567490597},"none":{"max":93.42539841498325,"mean":86.64969803171212,"min":74.08786762940774}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.718632551834773},"working_program_strength":{"all":88.52295100370141,"highest":94.31889376561342,"medium":84.60026121377865,"none":86.64969803171212}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:59bf9dfe6a652969","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":0.674699},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.38850799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6746989999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.388508},"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":3.1954350000000002},"codegen_latency_ms":{"attempt_count":25,"max_ms":926657,"mean_ms":272565.25,"min_ms":42196,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":926657,"mean_ms":625149.0,"min_ms":331732,"run_count":8},"medium":{"attempt_count":9,"max_ms":198934,"mean_ms":135760.75,"min_ms":63072,"run_count":8},"none":{"attempt_count":8,"max_ms":73464,"mean_ms":56786.0,"min_ms":42196,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":33557,"output_mean":11287.458333333334,"output_min":2159,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":33557,"output_mean":24715.125,"output_min":14936,"run_count":8},"medium":{"attempt_count":9,"output_max":9484,"output_mean":6228.625,"output_min":3242,"run_count":8},"none":{"attempt_count":8,"output_max":3711,"output_mean":2918.625,"output_min":2159,"run_count":8}},"display_name":"GPT-6.1 Sol","economics":{"all":85.97782976654126,"highest":92.74287527986023,"medium":87.40714118551489,"none":77.78347283424864},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true,"none":true},"per_setting":{"highest":true,"medium":true,"none":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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":67.64776891688616,"score":67.64776891688616},"GB2-02":{"attempts":3,"playable":79.81301063431327,"score":79.81301063431327},"GB2-03":{"attempts":3,"playable":93.72511755791987,"score":93.72511755791987},"GB2-04":{"attempts":3,"playable":85.33860214032184,"score":85.33860214032184},"GB2-05":{"attempts":3,"playable":94.69038266453408,"score":94.69038266453408},"GB2-06":{"attempts":3,"playable":87.21729201865277,"score":87.21729201865277},"GB2-07":{"attempts":3,"playable":95.40003744988273,"score":95.40003744988273},"GB2-08":{"attempts":3,"playable":83.99042674981928,"score":83.99042674981928}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.03947543109517,"score":76.03947543109517},"GB2-02":{"attempts":1,"playable":94.71396495080717,"score":94.71396495080717},"GB2-03":{"attempts":1,"playable":98.23001077943545,"score":98.23001077943545},"GB2-04":{"attempts":1,"playable":95.07601821232808,"score":95.07601821232808},"GB2-05":{"attempts":1,"playable":97.8982989713203,"score":97.8982989713203},"GB2-06":{"attempts":1,"playable":89.97287078839055,"score":89.97287078839055},"GB2-07":{"attempts":1,"playable":95.89866297570543,"score":95.89866297570543},"GB2-08":{"attempts":1,"playable":94.11370012979971,"score":94.11370012979971}},"medium":{"GB2-01":{"attempts":1,"playable":75.37558196570886,"score":75.37558196570886},"GB2-02":{"attempts":1,"playable":79.71233059680199,"score":79.71233059680199},"GB2-03":{"attempts":1,"playable":96.77070183502808,"score":96.77070183502808},"GB2-04":{"attempts":1,"playable":87.240411628485,"score":87.240411628485},"GB2-05":{"attempts":1,"playable":94.77354746618352,"score":94.77354746618352},"GB2-06":{"attempts":1,"playable":91.66887407194999,"score":91.66887407194999},"GB2-07":{"attempts":1,"playable":95.71002983191815,"score":95.71002983191815},"GB2-08":{"attempts":1,"playable":78.0056520880434,"score":78.0056520880434}},"none":{"GB2-01":{"attempts":1,"playable":51.52824935385446,"score":51.52824935385446},"GB2-02":{"attempts":1,"playable":65.01273635533063,"score":65.01273635533063},"GB2-03":{"attempts":1,"playable":86.17464005929612,"score":86.17464005929612},"GB2-04":{"attempts":1,"playable":73.6993765801524,"score":73.6993765801524},"GB2-05":{"attempts":1,"playable":91.39930155609848,"score":91.39930155609848},"GB2-06":{"attempts":1,"playable":80.0101311956178,"score":80.0101311956178},"GB2-07":{"attempts":1,"playable":94.5914195420246,"score":94.5914195420246},"GB2-08":{"attempts":1,"playable":79.85192803161469,"score":79.85192803161469}}},"id":"gpt-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-10-24T19:17:41Z","match_totals_all":{"draws":909,"losses":1360,"wins":9995},"match_totals_tracks":{"highest":{"draws":108,"losses":255,"wins":3725},"medium":{"draws":219,"losses":439,"wins":3430},"none":{"draws":582,"losses":666,"wins":2840}},"model_slug":"gpt-6-1-sol","official_rank_by_reasoning":{"highest":4,"medium":3,"none":8},"overall":{"max":98.23001077943545,"mean":85.97782976654126,"min":51.52824935385446},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.03947543109517,"GB2-02":94.71396495080717,"GB2-03":98.23001077943545,"GB2-04":95.07601821232808,"GB2-05":97.8982989713203,"GB2-06":89.97287078839055,"GB2-07":95.89866297570543,"GB2-08":94.11370012979971},"per_game_all":{"GB2-01":67.64776891688616,"GB2-02":79.81301063431327,"GB2-03":93.72511755791987,"GB2-04":85.33860214032184,"GB2-05":94.69038266453408,"GB2-06":87.21729201865277,"GB2-07":95.40003744988273,"GB2-08":83.99042674981928},"per_game_match_totals_all":{"GB2-01":{"draws":75,"losses":495,"wins":978},"GB2-02":{"draws":447,"losses":81,"wins":912},"GB2-03":{"draws":34,"losses":84,"wins":1364},"GB2-04":{"draws":244,"losses":109,"wins":1141},"GB2-05":{"draws":0,"losses":83,"wins":1507},"GB2-06":{"draws":107,"losses":160,"wins":1239},"GB2-07":{"draws":0,"losses":62,"wins":1528},"GB2-08":{"draws":2,"losses":286,"wins":1326}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":134,"wins":382},"GB2-02":{"draws":31,"losses":10,"wins":439},"GB2-03":{"draws":1,"losses":7,"wins":486},"GB2-04":{"draws":38,"losses":6,"wins":454},"GB2-05":{"draws":0,"losses":9,"wins":521},"GB2-06":{"draws":38,"losses":37,"wins":427},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":34,"wins":504}},"medium":{"GB2-01":{"draws":11,"losses":132,"wins":373},"GB2-02":{"draws":134,"losses":36,"wins":310},"GB2-03":{"draws":4,"losses":14,"wins":476},"GB2-04":{"draws":39,"losses":48,"wins":411},"GB2-05":{"draws":0,"losses":27,"wins":503},"GB2-06":{"draws":31,"losses":31,"wins":440},"GB2-07":{"draws":0,"losses":19,"wins":511},"GB2-08":{"draws":0,"losses":132,"wins":406}},"none":{"GB2-01":{"draws":64,"losses":229,"wins":223},"GB2-02":{"draws":282,"losses":35,"wins":163},"GB2-03":{"draws":29,"losses":63,"wins":402},"GB2-04":{"draws":167,"losses":55,"wins":276},"GB2-05":{"draws":0,"losses":47,"wins":483},"GB2-06":{"draws":38,"losses":92,"wins":372},"GB2-07":{"draws":0,"losses":25,"wins":505},"GB2-08":{"draws":2,"losses":120,"wins":416}}},"per_game_raw_elo_all":{"GB2-01":1654.6180647602241,"GB2-02":1807.597834142746,"GB2-03":2229.1966707910597,"GB2-04":1873.377150071352,"GB2-05":2524.157597387813,"GB2-06":2115.3479981388714,"GB2-07":2462.9897349961198,"GB2-08":2005.6982645644312},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.3797095714017,"GB2-02":2078.193689159069,"GB2-03":2469.9095461929082,"GB2-04":2073.977997371162,"GB2-05":2767.435307869171,"GB2-06":2174.834740061542,"GB2-07":2495.831868214045,"GB2-08":2304.2406221572055},"medium":{"GB2-01":1735.871485270675,"GB2-02":1750.174638376644,"GB2-03":2327.201929256906,"GB2-04":1865.2520798525404,"GB2-05":2493.5959634644064,"GB2-06":2225.568375388471,"GB2-07":2482.6675299574235,"GB2-08":1836.1470919820663},"none":{"GB2-01":1483.6029994385956,"GB2-02":1594.4251748925246,"GB2-03":1890.4785369233655,"GB2-04":1680.9013729903534,"GB2-05":2311.4415208298624,"GB2-06":1945.6408789666,"GB2-07":2410.4698068168905,"GB2-08":1876.7070795540221}},"per_game_tracks":{"highest":{"GB2-01":76.03947543109517,"GB2-02":94.71396495080717,"GB2-03":98.23001077943545,"GB2-04":95.07601821232808,"GB2-05":97.8982989713203,"GB2-06":89.97287078839055,"GB2-07":95.89866297570543,"GB2-08":94.11370012979971},"medium":{"GB2-01":75.37558196570886,"GB2-02":79.71233059680199,"GB2-03":96.77070183502808,"GB2-04":87.240411628485,"GB2-05":94.77354746618352,"GB2-06":91.66887407194999,"GB2-07":95.71002983191815,"GB2-08":78.0056520880434},"none":{"GB2-01":51.52824935385446,"GB2-02":65.01273635533063,"GB2-03":86.17464005929612,"GB2-04":73.6993765801524,"GB2-05":91.39930155609848,"GB2-06":80.0101311956178,"GB2-07":94.5914195420246,"GB2-08":79.85192803161469}},"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":"2026-10-22T10:44:36Z","reasoning":{"highest":92.74287527986023,"medium":87.40714118551489,"none":77.78347283424864},"reasoning_agg":{"highest":{"max":98.23001077943545,"mean":92.74287527986023,"min":76.03947543109517},"medium":{"max":96.77070183502808,"mean":87.40714118551489,"min":75.37558196570886},"none":{"max":94.5914195420246,"mean":77.78347283424864,"min":51.52824935385446}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.959402445611587},"working_program_strength":{"all":85.97782976654126,"highest":92.74287527986023,"medium":87.40714118551489,"none":77.78347283424864}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-4-argon:7f58079739d57d00","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":3.524096},"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":0.774334},"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":3.5240959999999997}},"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":4.972472},"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":83.29227127834835,"highest":90.10820639655064,"medium":78.73621868284408,"none":81.03238875565032},"economics_best_value":{"per_model":{"none":true},"per_setting":{"none":true}},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":92.9673063378445,"score":92.9673063378445},"GB2-02":{"attempts":3,"playable":79.11969128682507,"score":79.11969128682507},"GB2-03":{"attempts":3,"playable":86.0245261894097,"score":86.0245261894097},"GB2-04":{"attempts":3,"playable":72.13115864651286,"score":72.13115864651286},"GB2-05":{"attempts":3,"playable":91.70842673277548,"score":91.70842673277548},"GB2-06":{"attempts":3,"playable":93.58453969751224,"score":93.58453969751224},"GB2-07":{"attempts":3,"playable":73.86767128100017,"score":73.86767128100017},"GB2-08":{"attempts":3,"playable":76.93485005490676,"score":76.93485005490676}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.32780861434304,"score":95.32780861434304},"GB2-02":{"attempts":1,"playable":94.90458125996425,"score":94.90458125996425},"GB2-03":{"attempts":1,"playable":92.31213488978568,"score":92.31213488978568},"GB2-04":{"attempts":1,"playable":71.36079395604725,"score":71.36079395604725},"GB2-05":{"attempts":1,"playable":96.32824352374972,"score":96.32824352374972},"GB2-06":{"attempts":1,"playable":97.60194585508306,"score":97.60194585508306},"GB2-07":{"attempts":1,"playable":84.26064018680314,"score":84.26064018680314},"GB2-08":{"attempts":1,"playable":88.76950288662896,"score":88.76950288662896}},"medium":{"GB2-01":{"attempts":1,"playable":91.09631959631692,"score":91.09631959631692},"GB2-02":{"attempts":1,"playable":65.31982690083407,"score":65.31982690083407},"GB2-03":{"attempts":1,"playable":80.0114811257773,"score":80.0114811257773},"GB2-04":{"attempts":1,"playable":68.91143468590299,"score":68.91143468590299},"GB2-05":{"attempts":1,"playable":90.39964363457248,"score":90.39964363457248},"GB2-06":{"attempts":1,"playable":92.73107005109678,"score":92.73107005109678},"GB2-07":{"attempts":1,"playable":77.89531519401852,"score":77.89531519401852},"GB2-08":{"attempts":1,"playable":63.52465827423366,"score":63.52465827423366}},"none":{"GB2-01":{"attempts":1,"playable":92.4777908028736,"score":92.4777908028736},"GB2-02":{"attempts":1,"playable":77.1346656996769,"score":77.1346656996769},"GB2-03":{"attempts":1,"playable":85.7499625526661,"score":85.7499625526661},"GB2-04":{"attempts":1,"playable":76.12124729758834,"score":76.12124729758834},"GB2-05":{"attempts":1,"playable":88.39739304000423,"score":88.39739304000423},"GB2-06":{"attempts":1,"playable":90.42060318635687,"score":90.42060318635687},"GB2-07":{"attempts":1,"playable":59.44705846217886,"score":59.44705846217886},"GB2-08":{"attempts":1,"playable":78.51038900385768,"score":78.51038900385768}}},"id":"gemini-4-argon","is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","match_totals_all":{"draws":960,"losses":1716,"wins":9589},"match_totals_tracks":{"highest":{"draws":168,"losses":341,"wins":3579},"medium":{"draws":464,"losses":699,"wins":2925},"none":{"draws":328,"losses":676,"wins":3085}},"model_slug":"gemini-4-argon","official_rank_by_reasoning":{"highest":6,"medium":5,"none":5},"overall":{"max":97.60194585508306,"mean":83.29227127834835,"min":59.44705846217886},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.32780861434304,"GB2-02":94.90458125996425,"GB2-03":92.31213488978568,"GB2-04":71.36079395604725,"GB2-05":96.32824352374972,"GB2-06":97.60194585508306,"GB2-07":84.26064018680314,"GB2-08":88.76950288662896},"per_game_all":{"GB2-01":92.9673063378445,"GB2-02":79.11969128682507,"GB2-03":86.0245261894097,"GB2-04":72.13115864651286,"GB2-05":91.70842673277548,"GB2-06":93.58453969751224,"GB2-07":73.86767128100017,"GB2-08":76.93485005490676},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":123,"wins":1425},"GB2-02":{"draws":348,"losses":141,"wins":951},"GB2-03":{"draws":165,"losses":152,"wins":1166},"GB2-04":{"draws":399,"losses":240,"wins":855},"GB2-05":{"draws":0,"losses":136,"wins":1454},"GB2-06":{"draws":48,"losses":82,"wins":1376},"GB2-07":{"draws":0,"losses":431,"wins":1159},"GB2-08":{"draws":0,"losses":411,"wins":1203}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":27,"wins":489},"GB2-02":{"draws":45,"losses":2,"wins":433},"GB2-03":{"draws":44,"losses":20,"wins":430},"GB2-04":{"draws":71,"losses":115,"wins":312},"GB2-05":{"draws":0,"losses":18,"wins":512},"GB2-06":{"draws":8,"losses":8,"wins":486},"GB2-07":{"draws":0,"losses":84,"wins":446},"GB2-08":{"draws":0,"losses":67,"wins":471}},"medium":{"GB2-01":{"draws":0,"losses":52,"wins":464},"GB2-02":{"draws":159,"losses":95,"wins":226},"GB2-03":{"draws":100,"losses":62,"wins":332},"GB2-04":{"draws":180,"losses":73,"wins":245},"GB2-05":{"draws":0,"losses":53,"wins":477},"GB2-06":{"draws":25,"losses":28,"wins":449},"GB2-07":{"draws":0,"losses":121,"wins":409},"GB2-08":{"draws":0,"losses":215,"wins":323}},"none":{"GB2-01":{"draws":0,"losses":44,"wins":472},"GB2-02":{"draws":144,"losses":44,"wins":292},"GB2-03":{"draws":21,"losses":70,"wins":404},"GB2-04":{"draws":148,"losses":52,"wins":298},"GB2-05":{"draws":0,"losses":65,"wins":465},"GB2-06":{"draws":15,"losses":46,"wins":441},"GB2-07":{"draws":0,"losses":226,"wins":304},"GB2-08":{"draws":0,"losses":129,"wins":409}}},"per_game_raw_elo_all":{"GB2-01":2076.769077384342,"GB2-02":1800.4577173217142,"GB2-03":1909.3292165498635,"GB2-04":1665.7666795232517,"GB2-05":2351.4284648071466,"GB2-06":2325.1412770807656,"GB2-07":1803.7692611024886,"GB2-08":1841.5270032025037},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2163.568706592492,"GB2-02":2086.3821135784938,"GB2-03":2081.199905894069,"GB2-04":1656.8549816259128,"GB2-05":2606.160344127038,"GB2-06":2526.554406591123,"GB2-07":1991.788103247763,"GB2-08":2105.7221987964367},"medium":{"GB2-01":2013.0100475087218,"GB2-02":1597.1661007062594,"GB2-03":1766.405850306314,"GB2-04":1633.021369890526,"GB2-05":2265.910717602672,"GB2-06":2261.249074273592,"GB2-07":1851.0403728166154,"GB2-08":1571.7931576445496},"none":{"GB2-01":2053.728478051812,"GB2-02":1717.82493768039,"GB2-03":1880.381893449207,"GB2-04":1707.4236870533157,"GB2-05":2182.2143326917294,"GB2-06":2187.620350377581,"GB2-07":1568.4793072430878,"GB2-08":1847.065653166525}},"per_game_tracks":{"highest":{"GB2-01":95.32780861434304,"GB2-02":94.90458125996425,"GB2-03":92.31213488978568,"GB2-04":71.36079395604725,"GB2-05":96.32824352374972,"GB2-06":97.60194585508306,"GB2-07":84.26064018680314,"GB2-08":88.76950288662896},"medium":{"GB2-01":91.09631959631692,"GB2-02":65.31982690083407,"GB2-03":80.0114811257773,"GB2-04":68.91143468590299,"GB2-05":90.39964363457248,"GB2-06":92.73107005109678,"GB2-07":77.89531519401852,"GB2-08":63.52465827423366},"none":{"GB2-01":92.4777908028736,"GB2-02":77.1346656996769,"GB2-03":85.7499625526661,"GB2-04":76.12124729758834,"GB2-05":88.39739304000423,"GB2-06":90.42060318635687,"GB2-07":59.44705846217886,"GB2-08":78.51038900385768}},"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":0,"rank_movement_baseline_at":"2026-10-22T11:01:24Z","reasoning":{"highest":90.10820639655064,"medium":78.73621868284408,"none":81.03238875565032},"reasoning_agg":{"highest":{"max":97.60194585508306,"mean":90.10820639655064,"min":71.36079395604725},"medium":{"max":92.73107005109678,"mean":78.73621868284408,"min":63.52465827423366},"none":{"max":92.4777908028736,"mean":81.03238875565032,"min":59.44705846217886}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.37198771370656},"working_program_strength":{"all":83.29227127834835,"highest":90.10820639655064,"medium":78.73621868284408,"none":81.03238875565032}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3-1-pro:282499765e15824a","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":1.4095399999999998},"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":1.6026272}},"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":1.6026272},"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":3.6673020000000003}},"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":82.91117290665933,"highest":85.7222064858837,"medium":82.2558155234708,"none":80.75549671062352},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":false,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"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":65.99633043779303,"score":65.99633043779303},"GB2-02":{"attempts":3,"playable":79.43860017004228,"score":79.43860017004228},"GB2-03":{"attempts":3,"playable":88.26351006295864,"score":88.26351006295864},"GB2-04":{"attempts":3,"playable":81.61033338324795,"score":81.61033338324795},"GB2-05":{"attempts":3,"playable":85.34493525058768,"score":85.34493525058768},"GB2-06":{"attempts":3,"playable":89.86485897456133,"score":89.86485897456133},"GB2-07":{"attempts":3,"playable":79.89652283158819,"score":79.89652283158819},"GB2-08":{"attempts":3,"playable":92.87429214249562,"score":92.87429214249562}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":93.24405892745895,"score":93.24405892745895},"GB2-02":{"attempts":1,"playable":79.71233059680199,"score":79.71233059680199},"GB2-03":{"attempts":1,"playable":87.31110147387331,"score":87.31110147387331},"GB2-04":{"attempts":1,"playable":83.76473507318651,"score":83.76473507318651},"GB2-05":{"attempts":1,"playable":90.39964363457248,"score":90.39964363457248},"GB2-06":{"attempts":1,"playable":85.36970730965055,"score":85.36970730965055},"GB2-07":{"attempts":1,"playable":74.60622867778588,"score":74.60622867778588},"GB2-08":{"attempts":1,"playable":91.36984619373987,"score":91.36984619373987}},"medium":{"GB2-01":{"attempts":1,"playable":61.260266053018356,"score":61.260266053018356},"GB2-02":{"attempts":1,"playable":76.03851207675467,"score":76.03851207675467},"GB2-03":{"attempts":1,"playable":88.69247002480705,"score":88.69247002480705},"GB2-04":{"attempts":1,"playable":82.15483397574346,"score":82.15483397574346},"GB2-05":{"attempts":1,"playable":80.97539386126181,"score":80.97539386126181},"GB2-06":{"attempts":1,"playable":92.1124348070167,"score":92.1124348070167},"GB2-07":{"attempts":1,"playable":85.11900586429789,"score":85.11900586429789},"GB2-08":{"attempts":1,"playable":91.69360752486647,"score":91.69360752486647}},"none":{"GB2-01":{"attempts":1,"playable":43.4846663329018,"score":43.4846663329018},"GB2-02":{"attempts":1,"playable":82.5649578365702,"score":82.5649578365702},"GB2-03":{"attempts":1,"playable":88.78695869019559,"score":88.78695869019559},"GB2-04":{"attempts":1,"playable":78.91143110081387,"score":78.91143110081387},"GB2-05":{"attempts":1,"playable":84.65976825592874,"score":84.65976825592874},"GB2-06":{"attempts":1,"playable":92.1124348070167,"score":92.1124348070167},"GB2-07":{"attempts":1,"playable":79.96433395268078,"score":79.96433395268078},"GB2-08":{"attempts":1,"playable":95.55942270888048,"score":95.55942270888048}}},"id":"moonshotai/kimi-k3.1-pro","is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","match_totals_all":{"draws":1181,"losses":1571,"wins":9024},"match_totals_tracks":{"highest":{"draws":338,"losses":456,"wins":3294},"medium":{"draws":468,"losses":473,"wins":2659},"none":{"draws":375,"losses":642,"wins":3071}},"model_slug":"moonshotai-kimi-k3-1-pro","official_rank_by_reasoning":{"highest":8,"none":6},"overall":{"max":95.55942270888048,"mean":82.91117290665933,"min":43.4846663329018},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":6,"overall_ranking_status":"partial","per_game":{"GB2-01":93.24405892745895,"GB2-02":79.71233059680199,"GB2-03":87.31110147387331,"GB2-04":83.76473507318651,"GB2-05":90.39964363457248,"GB2-06":85.36970730965055,"GB2-07":74.60622867778588,"GB2-08":91.36984619373987},"per_game_all":{"GB2-01":65.99633043779303,"GB2-02":79.43860017004228,"GB2-03":88.26351006295864,"GB2-04":81.61033338324795,"GB2-05":85.34493525058768,"GB2-06":89.86485897456133,"GB2-07":79.89652283158819,"GB2-08":92.87429214249562},"per_game_match_totals_all":{"GB2-01":{"draws":347,"losses":379,"wins":822},"GB2-02":{"draws":374,"losses":126,"wins":940},"GB2-03":{"draws":67,"losses":100,"wins":827},"GB2-04":{"draws":342,"losses":121,"wins":1031},"GB2-05":{"draws":0,"losses":248,"wins":1342},"GB2-06":{"draws":51,"losses":144,"wins":1311},"GB2-07":{"draws":0,"losses":328,"wins":1262},"GB2-08":{"draws":0,"losses":125,"wins":1489}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":39,"wins":476},"GB2-02":{"draws":144,"losses":31,"wins":305},"GB2-03":{"draws":62,"losses":40,"wins":392},"GB2-04":{"draws":114,"losses":29,"wins":355},"GB2-05":{"draws":0,"losses":53,"wins":477},"GB2-06":{"draws":17,"losses":73,"wins":412},"GB2-07":{"draws":0,"losses":140,"wins":390},"GB2-08":{"draws":0,"losses":51,"wins":487}},"medium":{"GB2-01":{"draws":226,"losses":98,"wins":192},"GB2-02":{"draws":121,"losses":61,"wins":298},"GB2-03":{"draws":0,"losses":0,"wins":6},"GB2-04":{"draws":101,"losses":44,"wins":353},"GB2-05":{"draws":0,"losses":108,"wins":422},"GB2-06":{"draws":20,"losses":34,"wins":448},"GB2-07":{"draws":0,"losses":79,"wins":451},"GB2-08":{"draws":0,"losses":49,"wins":489}},"none":{"GB2-01":{"draws":120,"losses":242,"wins":154},"GB2-02":{"draws":109,"losses":34,"wins":337},"GB2-03":{"draws":5,"losses":60,"wins":429},"GB2-04":{"draws":127,"losses":48,"wins":323},"GB2-05":{"draws":0,"losses":87,"wins":443},"GB2-06":{"draws":14,"losses":37,"wins":451},"GB2-07":{"draws":0,"losses":109,"wins":421},"GB2-08":{"draws":0,"losses":25,"wins":513}}},"per_game_raw_elo_all":{"GB2-01":1688.2384863287998,"GB2-02":1748.4235340639525,"GB2-03":1945.316115988213,"GB2-04":1777.010197085514,"GB2-05":2084.9643921506054,"GB2-06":2179.90083072603,"GB2-07":1899.6351554840603,"GB2-08":2258.547966907506},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2079.145543989741,"GB2-02":1750.174638376644,"GB2-03":1919.0097782305443,"GB2-04":1807.0607814001307,"GB2-05":2265.910717602672,"GB2-06":2059.6433068590127,"GB2-07":1791.844133804761,"GB2-08":2191.558205472763},"medium":{"GB2-01":1578.59010718409,"GB2-02":1704.938851869029,"GB2-03":1957.0898060531802,"GB2-04":1783.4493657300795,"GB2-05":1940.6253743948582,"GB2-06":2240.029592659538,"GB2-07":2014.9623301464098,"GB2-08":2203.3889851272907},"none":{"GB2-01":1406.9798078125687,"GB2-02":1790.1571119461844,"GB2-03":1959.8487636809145,"GB2-04":1740.5204441263318,"GB2-05":2048.3570844542855,"GB2-06":2240.0295926595386,"GB2-07":1892.0990025010096,"GB2-08":2380.6967101224654}},"per_game_tracks":{"highest":{"GB2-01":93.24405892745895,"GB2-02":79.71233059680199,"GB2-03":87.31110147387331,"GB2-04":83.76473507318651,"GB2-05":90.39964363457248,"GB2-06":85.36970730965055,"GB2-07":74.60622867778588,"GB2-08":91.36984619373987},"medium":{"GB2-01":61.260266053018356,"GB2-02":76.03851207675467,"GB2-03":88.69247002480705,"GB2-04":82.15483397574346,"GB2-05":80.97539386126181,"GB2-06":92.1124348070167,"GB2-07":85.11900586429789,"GB2-08":91.69360752486647},"none":{"GB2-01":43.4846663329018,"GB2-02":82.5649578365702,"GB2-03":88.78695869019559,"GB2-04":78.91143110081387,"GB2-05":84.65976825592874,"GB2-06":92.1124348070167,"GB2-07":79.96433395268078,"GB2-08":95.55942270888048}},"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":null,"rank_movement_baseline_at":null,"reasoning":{"highest":85.7222064858837,"medium":82.2558155234708,"none":80.75549671062352},"reasoning_agg":{"highest":{"max":93.24405892745895,"mean":85.7222064858837,"min":74.60622867778588},"medium":{"max":92.1124348070167,"mean":82.2558155234708,"min":61.260266053018356},"none":{"max":95.55942270888048,"mean":80.75549671062352,"min":43.4846663329018}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":4.966709775260185},"working_program_strength":{"all":82.91117290665933,"highest":85.7222064858837,"medium":82.2558155234708,"none":80.75549671062352}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:c67dec61197bb515","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":7.138875},"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":4.570124999999999}},"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":7.1388750000000005},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.074450000000002}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":78.23698412523288,"highest":86.1289962195772,"medium":76.57899162867822,"none":72.00296452744323},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["end_turn"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":48,"requested_max_output_token_observations":48,"requested_max_output_tokens":[128000],"total_output_tokens":1230744,"total_reasoning_output_tokens":878158,"total_visible_output_tokens":352586,"visible_token_observations":48},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":2},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":2},"intensive":{"admitted_plugins":13,"evaluated_cells":16,"first_pass_admitted":13,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":3}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":72.79734965425479,"score":72.79734965425479},"GB2-02":{"attempts":6,"playable":75.10106141953143,"score":75.10106141953143},"GB2-03":{"attempts":6,"playable":77.76136347820818,"score":77.76136347820818},"GB2-04":{"attempts":6,"playable":58.06586919265258,"score":58.06586919265258},"GB2-05":{"attempts":6,"playable":90.47952891237976,"score":90.47952891237976},"GB2-06":{"attempts":1,"playable":88.44465665628792,"score":88.44465665628792},"GB2-07":{"attempts":4,"playable":85.39252486061763,"score":85.39252486061763},"GB2-08":{"attempts":6,"playable":82.58062731603759,"score":82.58062731603759}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":70.03224549892303,"score":70.03224549892303},"GB2-02":{"attempts":2,"playable":83.41974449223656,"score":83.41974449223656},"GB2-03":{"attempts":2,"playable":95.01096600350374,"score":95.01096600350374},"GB2-04":{"attempts":2,"playable":80.281129013369,"score":80.281129013369},"GB2-05":{"attempts":2,"playable":93.32970605341754,"score":93.32970605341754},"GB2-07":{"attempts":1,"playable":95.89866297570543,"score":95.89866297570543},"GB2-08":{"attempts":2,"playable":84.9305194998851,"score":84.9305194998851}},"medium":{"GB2-01":{"attempts":2,"playable":71.66004915395223,"score":71.66004915395223},"GB2-02":{"attempts":2,"playable":70.18413264820998,"score":70.18413264820998},"GB2-03":{"attempts":2,"playable":86.6998678791337,"score":86.6998678791337},"GB2-04":{"attempts":2,"playable":44.79243812629741,"score":44.79243812629741},"GB2-05":{"attempts":2,"playable":88.95922178974462,"score":88.95922178974462},"GB2-07":{"attempts":2,"playable":84.28566736422673,"score":84.28566736422673},"GB2-08":{"attempts":2,"playable":89.47156443918291,"score":89.47156443918291}},"none":{"GB2-01":{"attempts":2,"playable":76.69975430988912,"score":76.69975430988912},"GB2-02":{"attempts":2,"playable":71.69930711814777,"score":71.69930711814777},"GB2-03":{"attempts":2,"playable":51.57325655198711,"score":51.57325655198711},"GB2-04":{"attempts":2,"playable":49.12404043829134,"score":49.12404043829134},"GB2-05":{"attempts":2,"playable":89.14965889397716,"score":89.14965889397716},"GB2-06":{"attempts":1,"playable":88.44465665628792,"score":88.44465665628792},"GB2-07":{"attempts":1,"playable":75.99324424192072,"score":75.99324424192072},"GB2-08":{"attempts":2,"playable":73.33979800904476,"score":73.33979800904476}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:14:15Z","match_totals_all":{"draws":2702,"losses":3639,"wins":14616},"match_totals_tracks":{"highest":{"draws":374,"losses":837,"wins":5431},"medium":{"draws":984,"losses":1253,"wins":4934},"none":{"draws":1344,"losses":1549,"wins":4251}},"model_slug":"claude-opus-5","official_rank_by_reasoning":{"highest":7,"medium":6,"none":9},"overall":{"max":95.89866297570543,"mean":78.23698412523288,"min":44.79243812629741},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":70.03224549892303,"GB2-02":83.41974449223656,"GB2-03":95.01096600350374,"GB2-04":80.281129013369,"GB2-05":93.32970605341754,"GB2-07":95.89866297570543,"GB2-08":84.9305194998851},"per_game_all":{"GB2-01":72.79734965425479,"GB2-02":75.10106141953143,"GB2-03":77.76136347820818,"GB2-04":58.06586919265258,"GB2-05":90.47952891237976,"GB2-07":85.39252486061763,"GB2-08":82.58062731603759},"per_game_match_totals_all":{"GB2-01":{"draws":469,"losses":662,"wins":1965},"GB2-02":{"draws":989,"losses":260,"wins":1630},"GB2-03":{"draws":156,"losses":641,"wins":2167},"GB2-04":{"draws":1016,"losses":790,"wins":1182},"GB2-05":{"draws":0,"losses":316,"wins":2864},"GB2-06":{"draws":31,"losses":49,"wins":422},"GB2-07":{"draws":0,"losses":318,"wins":1802},"GB2-08":{"draws":41,"losses":603,"wins":2584}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":317,"wins":698},"GB2-02":{"draws":186,"losses":75,"wins":699},"GB2-03":{"draws":9,"losses":48,"wins":931},"GB2-04":{"draws":162,"losses":127,"wins":707},"GB2-05":{"draws":0,"losses":72,"wins":988},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":180,"wins":896}},"medium":{"GB2-01":{"draws":98,"losses":264,"wins":670},"GB2-02":{"draws":413,"losses":94,"wins":452},"GB2-03":{"draws":16,"losses":141,"wins":831},"GB2-04":{"draws":455,"losses":339,"wins":202},"GB2-05":{"draws":0,"losses":123,"wins":937},"GB2-07":{"draws":0,"losses":168,"wins":892},"GB2-08":{"draws":2,"losses":124,"wins":950}},"none":{"GB2-01":{"draws":354,"losses":81,"wins":597},"GB2-02":{"draws":390,"losses":91,"wins":479},"GB2-03":{"draws":131,"losses":452,"wins":405},"GB2-04":{"draws":399,"losses":324,"wins":273},"GB2-05":{"draws":0,"losses":121,"wins":939},"GB2-06":{"draws":31,"losses":49,"wins":422},"GB2-07":{"draws":0,"losses":132,"wins":398},"GB2-08":{"draws":39,"losses":299,"wins":738}}},"per_game_raw_elo_all":{"GB2-01":1747.816304372978,"GB2-02":1704.58149842682,"GB2-03":1852.2207107042714,"GB2-04":1557.806711194492,"GB2-05":2332.5515946207747,"GB2-07":2120.2730623139373,"GB2-08":1972.8033702834484},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.4201240183363,"GB2-02":1810.5035274518837,"GB2-03":2211.683908863733,"GB2-04":1769.9916599621004,"GB2-05":2565.1352918817092,"GB2-07":2495.831868214045,"GB2-08":2022.7832515262478},"medium":{"GB2-01":1703.6681200090613,"GB2-02":1642.7799426319827,"GB2-03":1903.440030864674,"GB2-04":1434.634044723543,"GB2-05":2219.865508206153,"GB2-07":2048.949806351416,"GB2-08":2151.9015873492563},"none":{"GB2-01":1795.3606690915362,"GB2-02":1660.4610251965933,"GB2-03":1441.538192384407,"GB2-04":1468.7944288978322,"GB2-05":2212.6539837744617,"GB2-06":2133.752761117489,"GB2-07":1816.0375123763517,"GB2-08":1743.7252719748408}},"per_game_tracks":{"highest":{"GB2-01":70.03224549892303,"GB2-02":83.41974449223656,"GB2-03":95.01096600350374,"GB2-04":80.281129013369,"GB2-05":93.32970605341754,"GB2-07":95.89866297570543,"GB2-08":84.9305194998851},"medium":{"GB2-01":71.66004915395223,"GB2-02":70.18413264820998,"GB2-03":86.6998678791337,"GB2-04":44.79243812629741,"GB2-05":88.95922178974462,"GB2-07":84.28566736422673,"GB2-08":89.47156443918291},"none":{"GB2-01":76.69975430988912,"GB2-02":71.69930711814777,"GB2-03":51.57325655198711,"GB2-04":49.12404043829134,"GB2-05":89.14965889397716,"GB2-06":88.44465665628792,"GB2-07":75.99324424192072,"GB2-08":73.33979800904476}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:37:00Z","reasoning":{"highest":86.1289962195772,"medium":76.57899162867822,"none":72.00296452744323},"reasoning_agg":{"highest":{"max":95.89866297570543,"mean":86.1289962195772,"min":70.03224549892303},"medium":{"max":89.47156443918291,"mean":76.57899162867822,"min":44.79243812629741},"none":{"max":89.14965889397716,"mean":72.00296452744323,"min":49.12404043829134}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.126031692133978},"working_program_strength":{"all":78.23698412523288,"highest":86.1289962195772,"medium":76.57899162867822,"none":72.00296452744323}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:6feebbfece79c4cb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265165},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.345568}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265165},"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":0.345568},"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":2.626442500000001},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":74.59859361954352,"highest":80.57433516068687,"medium":76.33464744632997,"none":66.88679825161373},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true,"none":true}},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":37.311787799566154,"score":37.311787799566154},"GB2-02":{"attempts":3,"playable":68.54629993138748,"score":68.54629993138748},"GB2-03":{"attempts":3,"playable":83.85916641179311,"score":83.85916641179311},"GB2-04":{"attempts":3,"playable":68.5705206216792,"score":68.5705206216792},"GB2-05":{"attempts":3,"playable":87.74512988823822,"score":87.74512988823822},"GB2-06":{"attempts":3,"playable":81.81234995111707,"score":81.81234995111707},"GB2-07":{"attempts":3,"playable":82.03232231942248,"score":82.03232231942248},"GB2-08":{"attempts":3,"playable":86.91117203314444,"score":86.91117203314444}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":10.356474095985108,"score":10.356474095985108},"GB2-02":{"attempts":1,"playable":83.44540853825231,"score":83.44540853825231},"GB2-03":{"attempts":1,"playable":94.36774401347516,"score":94.36774401347516},"GB2-04":{"attempts":1,"playable":88.17303257295579,"score":88.17303257295579},"GB2-05":{"attempts":1,"playable":93.75074994840519,"score":93.75074994840519},"GB2-06":{"attempts":1,"playable":90.51003873245514,"score":90.51003873245514},"GB2-07":{"attempts":1,"playable":94.40711413448766,"score":94.40711413448766},"GB2-08":{"attempts":1,"playable":89.5841192494786,"score":89.5841192494786}},"medium":{"GB2-01":{"attempts":1,"playable":39.73753887865891,"score":39.73753887865891},"GB2-02":{"attempts":1,"playable":69.49728578219684,"score":69.49728578219684},"GB2-03":{"attempts":1,"playable":74.93899680263137,"score":74.93899680263137},"GB2-04":{"attempts":1,"playable":73.60219595949253,"score":73.60219595949253},"GB2-05":{"attempts":1,"playable":91.56615209564696,"score":91.56615209564696},"GB2-06":{"attempts":1,"playable":81.55552321081501,"score":81.55552321081501},"GB2-07":{"attempts":1,"playable":94.0402325864306,"score":94.0402325864306},"GB2-08":{"attempts":1,"playable":85.73925425476754,"score":85.73925425476754}},"none":{"GB2-01":{"attempts":1,"playable":61.841350424054454,"score":61.841350424054454},"GB2-02":{"attempts":1,"playable":52.69620547371326,"score":52.69620547371326},"GB2-03":{"attempts":1,"playable":82.27075841927282,"score":82.27075841927282},"GB2-04":{"attempts":1,"playable":43.936333332589264,"score":43.936333332589264},"GB2-05":{"attempts":1,"playable":77.91848762066253,"score":77.91848762066253},"GB2-06":{"attempts":1,"playable":73.37148791008107,"score":73.37148791008107},"GB2-07":{"attempts":1,"playable":57.6496202373492,"score":57.6496202373492},"GB2-08":{"attempts":1,"playable":85.41014259518717,"score":85.41014259518717}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-10-24T19:20:38Z","match_totals_all":{"draws":1584,"losses":2468,"wins":8212},"match_totals_tracks":{"highest":{"draws":244,"losses":696,"wins":3148},"medium":{"draws":625,"losses":703,"wins":2760},"none":{"draws":715,"losses":1069,"wins":2304}},"model_slug":"gpt-6-sol","official_rank_by_reasoning":{"highest":10,"medium":7,"none":10},"overall":{"max":94.40711413448766,"mean":74.59859361954352,"min":10.356474095985108},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":10.356474095985108,"GB2-02":83.44540853825231,"GB2-03":94.36774401347516,"GB2-04":88.17303257295579,"GB2-05":93.75074994840519,"GB2-06":90.51003873245514,"GB2-07":94.40711413448766,"GB2-08":89.5841192494786},"per_game_all":{"GB2-01":37.311787799566154,"GB2-02":68.54629993138748,"GB2-03":83.85916641179311,"GB2-04":68.5705206216792,"GB2-05":87.74512988823822,"GB2-06":81.81234995111707,"GB2-07":82.03232231942248,"GB2-08":86.91117203314444},"per_game_match_totals_all":{"GB2-01":{"draws":207,"losses":893,"wins":448},"GB2-02":{"draws":645,"losses":151,"wins":644},"GB2-03":{"draws":76,"losses":231,"wins":1175},"GB2-04":{"draws":524,"losses":227,"wins":743},"GB2-05":{"draws":0,"losses":204,"wins":1386},"GB2-06":{"draws":112,"losses":247,"wins":1147},"GB2-07":{"draws":0,"losses":290,"wins":1300},"GB2-08":{"draws":20,"losses":225,"wins":1369}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":453,"wins":34},"GB2-02":{"draws":128,"losses":20,"wins":332},"GB2-03":{"draws":4,"losses":28,"wins":462},"GB2-04":{"draws":55,"losses":35,"wins":408},"GB2-05":{"draws":0,"losses":33,"wins":497},"GB2-06":{"draws":28,"losses":39,"wins":435},"GB2-07":{"draws":0,"losses":26,"wins":504},"GB2-08":{"draws":0,"losses":62,"wins":476}},"medium":{"GB2-01":{"draws":162,"losses":240,"wins":114},"GB2-02":{"draws":218,"losses":45,"wins":217},"GB2-03":{"draws":39,"losses":120,"wins":335},"GB2-04":{"draws":160,"losses":59,"wins":279},"GB2-05":{"draws":0,"losses":46,"wins":484},"GB2-06":{"draws":37,"losses":84,"wins":381},"GB2-07":{"draws":0,"losses":28,"wins":502},"GB2-08":{"draws":9,"losses":81,"wins":448}},"none":{"GB2-01":{"draws":16,"losses":200,"wins":300},"GB2-02":{"draws":299,"losses":86,"wins":95},"GB2-03":{"draws":33,"losses":83,"wins":378},"GB2-04":{"draws":309,"losses":133,"wins":56},"GB2-05":{"draws":0,"losses":125,"wins":405},"GB2-06":{"draws":47,"losses":124,"wins":331},"GB2-07":{"draws":0,"losses":236,"wins":294},"GB2-08":{"draws":11,"losses":82,"wins":445}}},"per_game_raw_elo_all":{"GB2-01":1315.0892773725627,"GB2-02":1644.129958173673,"GB2-03":1890.433520131268,"GB2-04":1663.6914844616106,"GB2-05":2205.7471358176776,"GB2-06":1994.7313552152282,"GB2-07":2107.3548542576377,"GB2-08":2053.983329289356},"per_game_raw_elo_tracks":{"highest":{"GB2-01":989.9963178964458,"GB2-02":1803.607181512105,"GB2-03":2175.4153368990574,"GB2-04":1883.0551865002851,"GB2-05":2432.1335679540807,"GB2-06":2190.2217030340503,"GB2-07":2399.3710748417225,"GB2-08":2131.1067948528157},"medium":{"GB2-01":1370.800666616799,"GB2-02":1636.0238474541165,"GB2-03":1688.8577303804338,"GB2-04":1679.8736628032432,"GB2-05":2319.322716228445,"GB2-06":1977.216740543705,"GB2-07":2377.8387488127782,"GB2-08":2019.7717886785351},"none":{"GB2-01":1584.4708476044434,"GB2-02":1492.7588455547973,"GB2-03":1807.0274931143128,"GB2-04":1428.1456040813032,"GB2-05":1865.7851232705068,"GB2-06":1816.755622067929,"GB2-07":1544.8547391184122,"GB2-08":2011.0714043367161}},"per_game_tracks":{"highest":{"GB2-01":10.356474095985108,"GB2-02":83.44540853825231,"GB2-03":94.36774401347516,"GB2-04":88.17303257295579,"GB2-05":93.75074994840519,"GB2-06":90.51003873245514,"GB2-07":94.40711413448766,"GB2-08":89.5841192494786},"medium":{"GB2-01":39.73753887865891,"GB2-02":69.49728578219684,"GB2-03":74.93899680263137,"GB2-04":73.60219595949253,"GB2-05":91.56615209564696,"GB2-06":81.55552321081501,"GB2-07":94.0402325864306,"GB2-08":85.73925425476754},"none":{"GB2-01":61.841350424054454,"GB2-02":52.69620547371326,"GB2-03":82.27075841927282,"GB2-04":43.936333332589264,"GB2-05":77.91848762066253,"GB2-06":73.37148791008107,"GB2-07":57.6496202373492,"GB2-08":85.41014259518717}},"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":"2026-10-22T10:42:49Z","reasoning":{"highest":80.57433516068687,"medium":76.33464744632997,"none":66.88679825161373},"reasoning_agg":{"highest":{"max":94.40711413448766,"mean":80.57433516068687,"min":10.356474095985108},"medium":{"max":94.0402325864306,"mean":76.33464744632997,"min":39.73753887865891},"none":{"max":85.41014259518717,"mean":66.88679825161373,"min":43.936333332589264}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.687536909073145},"working_program_strength":{"all":74.59859361954352,"highest":80.57433516068687,"medium":76.33464744632997,"none":66.88679825161373}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:2d10b9c97aae0a3b","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":6.372553750000001},"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":1.8325049999999998},"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":1.0229249999999999}},"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":1.8325049999999998},"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":68.4147352465851,"highest":81.081752302349,"medium":67.22057354245023,"none":56.94187989495609},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":74.43762050518121,"score":74.43762050518121},"GB2-02":{"attempts":3,"playable":63.057987569483394,"score":63.057987569483394},"GB2-03":{"attempts":3,"playable":65.28763908435594,"score":65.28763908435594},"GB2-04":{"attempts":3,"playable":67.76377124870793,"score":67.76377124870793},"GB2-05":{"attempts":3,"playable":68.76347312438513,"score":68.76347312438513},"GB2-06":{"attempts":3,"playable":62.81984145418943,"score":62.81984145418943},"GB2-07":{"attempts":3,"playable":69.09213294564184,"score":69.09213294564184},"GB2-08":{"attempts":3,"playable":76.09541604073591,"score":76.09541604073591}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":75.1857130798702,"score":75.1857130798702},"GB2-02":{"attempts":1,"playable":75.83886053481548,"score":75.83886053481548},"GB2-03":{"attempts":1,"playable":80.64708204706858,"score":80.64708204706858},"GB2-04":{"attempts":1,"playable":83.85918400105474,"score":83.85918400105474},"GB2-05":{"attempts":1,"playable":75.9133113173181,"score":75.9133113173181},"GB2-06":{"attempts":1,"playable":85.46037853296534,"score":85.46037853296534},"GB2-07":{"attempts":1,"playable":88.73429293807091,"score":88.73429293807091},"GB2-08":{"attempts":1,"playable":83.01519596762861,"score":83.01519596762861}},"medium":{"GB2-01":{"attempts":1,"playable":68.78520673277976,"score":68.78520673277976},"GB2-02":{"attempts":1,"playable":67.56599654082825,"score":67.56599654082825},"GB2-03":{"attempts":1,"playable":62.1597106042574,"score":62.1597106042574},"GB2-04":{"attempts":1,"playable":78.04778833474131,"score":78.04778833474131},"GB2-05":{"attempts":1,"playable":76.82703927164525,"score":76.82703927164525},"GB2-06":{"attempts":1,"playable":41.739194916172536,"score":41.739194916172536},"GB2-07":{"attempts":1,"playable":71.29825209566964,"score":71.29825209566964},"GB2-08":{"attempts":1,"playable":71.34139984350767,"score":71.34139984350767}},"none":{"GB2-01":{"attempts":1,"playable":79.34194170289372,"score":79.34194170289372},"GB2-02":{"attempts":1,"playable":45.76910563280643,"score":45.76910563280643},"GB2-03":{"attempts":1,"playable":53.05612460174187,"score":53.05612460174187},"GB2-04":{"attempts":1,"playable":41.38434141032771,"score":41.38434141032771},"GB2-05":{"attempts":1,"playable":53.55006878419207,"score":53.55006878419207},"GB2-06":{"attempts":1,"playable":61.25995091343043,"score":61.25995091343043},"GB2-07":{"attempts":1,"playable":47.24385380318496,"score":47.24385380318496},"GB2-08":{"attempts":1,"playable":73.92965231107146,"score":73.92965231107146}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-10-24T18:22:52Z","match_totals_all":{"draws":1703,"losses":3268,"wins":7293},"match_totals_tracks":{"highest":{"draws":302,"losses":681,"wins":3105},"medium":{"draws":567,"losses":1150,"wins":2371},"none":{"draws":834,"losses":1437,"wins":1817}},"model_slug":"gpt-5-6-sol","official_rank_by_reasoning":{"highest":9,"medium":12,"none":12},"overall":{"max":88.73429293807091,"mean":68.4147352465851,"min":41.38434141032771},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":75.1857130798702,"GB2-02":75.83886053481548,"GB2-03":80.64708204706858,"GB2-04":83.85918400105474,"GB2-05":75.9133113173181,"GB2-06":85.46037853296534,"GB2-07":88.73429293807091,"GB2-08":83.01519596762861},"per_game_all":{"GB2-01":74.43762050518121,"GB2-02":63.057987569483394,"GB2-03":65.28763908435594,"GB2-04":67.76377124870793,"GB2-05":68.76347312438513,"GB2-06":62.81984145418943,"GB2-07":69.09213294564184,"GB2-08":76.09541604073591},"per_game_match_totals_all":{"GB2-01":{"draws":124,"losses":365,"wins":1059},"GB2-02":{"draws":751,"losses":179,"wins":510},"GB2-03":{"draws":198,"losses":467,"wins":817},"GB2-04":{"draws":533,"losses":235,"wins":726},"GB2-05":{"draws":0,"losses":522,"wins":1068},"GB2-06":{"draws":27,"losses":596,"wins":883},"GB2-07":{"draws":0,"losses":510,"wins":1080},"GB2-08":{"draws":70,"losses":394,"wins":1150}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":132,"wins":371},"GB2-02":{"draws":179,"losses":33,"wins":268},"GB2-03":{"draws":5,"losses":106,"wins":383},"GB2-04":{"draws":89,"losses":41,"wins":368},"GB2-05":{"draws":0,"losses":136,"wins":394},"GB2-06":{"draws":16,"losses":73,"wins":413},"GB2-07":{"draws":0,"losses":58,"wins":472},"GB2-08":{"draws":0,"losses":102,"wins":436}},"medium":{"GB2-01":{"draws":110,"losses":117,"wins":289},"GB2-02":{"draws":215,"losses":56,"wins":209},"GB2-03":{"draws":52,"losses":180,"wins":262},"GB2-04":{"draws":126,"losses":53,"wins":319},"GB2-05":{"draws":0,"losses":131,"wins":399},"GB2-06":{"draws":8,"losses":311,"wins":183},"GB2-07":{"draws":0,"losses":159,"wins":371},"GB2-08":{"draws":56,"losses":143,"wins":339}},"none":{"GB2-01":{"draws":1,"losses":116,"wins":399},"GB2-02":{"draws":357,"losses":90,"wins":33},"GB2-03":{"draws":141,"losses":181,"wins":172},"GB2-04":{"draws":318,"losses":141,"wins":39},"GB2-05":{"draws":0,"losses":255,"wins":275},"GB2-06":{"draws":3,"losses":212,"wins":287},"GB2-07":{"draws":0,"losses":293,"wins":237},"GB2-08":{"draws":14,"losses":149,"wins":375}}},"per_game_raw_elo_all":{"GB2-01":1726.8449248224042,"GB2-02":1586.4835681338388,"GB2-03":1590.8481071678573,"GB2-04":1648.9171283846833,"GB2-05":1715.2085066227835,"GB2-06":1651.950432768412,"GB2-07":1760.4513969639129,"GB2-08":1802.001910906788},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1733.4646317866261,"GB2-02":1702.641168556262,"GB2-03":1777.3775514789406,"GB2-04":1808.5026974730702,"GB2-05":1822.3089543156973,"GB2-06":2061.707734876441,"GB2-07":2130.6252321306247,"GB2-08":1950.5694940891003},"medium":{"GB2-01":1657.9220086422833,"GB2-02":1617.669685178885,"GB2-03":1540.5344078150044,"GB2-04":1729.9458647677309,"GB2-05":1841.6347474156053,"GB2-06":1293.3224795290762,"GB2-07":1737.689946233588,"GB2-08":1703.0714610239525},"none":{"GB2-01":1789.1481340383032,"GB2-02":1439.1398506663688,"GB2-03":1454.6323622096268,"GB2-04":1408.3028229132485,"GB2-05":1481.6818181370472,"GB2-06":1600.8210838997186,"GB2-07":1413.039012527526,"GB2-08":1752.3647776073115}},"per_game_tracks":{"highest":{"GB2-01":75.1857130798702,"GB2-02":75.83886053481548,"GB2-03":80.64708204706858,"GB2-04":83.85918400105474,"GB2-05":75.9133113173181,"GB2-06":85.46037853296534,"GB2-07":88.73429293807091,"GB2-08":83.01519596762861},"medium":{"GB2-01":68.78520673277976,"GB2-02":67.56599654082825,"GB2-03":62.1597106042574,"GB2-04":78.04778833474131,"GB2-05":76.82703927164525,"GB2-06":41.739194916172536,"GB2-07":71.29825209566964,"GB2-08":71.34139984350767},"none":{"GB2-01":79.34194170289372,"GB2-02":45.76910563280643,"GB2-03":53.05612460174187,"GB2-04":41.38434141032771,"GB2-05":53.55006878419207,"GB2-06":61.25995091343043,"GB2-07":47.24385380318496,"GB2-08":73.92965231107146}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:59:24Z","reasoning":{"highest":81.081752302349,"medium":67.22057354245023,"none":56.94187989495609},"reasoning_agg":{"highest":{"max":88.73429293807091,"mean":81.081752302349,"min":75.1857130798702},"medium":{"max":78.04778833474131,"mean":67.22057354245023,"min":41.739194916172536},"none":{"max":79.34194170289372,"mean":56.94187989495609,"min":41.38434141032771}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.139872407392915},"working_program_strength":{"all":68.4147352465851,"highest":81.081752302349,"medium":67.22057354245023,"none":56.94187989495609}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:ad109cd0d8c88daa","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":11.764550000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885},"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":18.260500000000004},"codegen_output_tokens":{"attempt_count":24,"output_max":40578,"output_mean":12704.708333333334,"output_min":2179,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":40578,"output_mean":26899.0,"output_min":17366,"run_count":8},"medium":{"attempt_count":8,"output_max":12403,"output_mean":7955.375,"output_min":4188,"run_count":8},"none":{"attempt_count":8,"output_max":4224,"output_mean":3259.75,"output_min":2179,"run_count":8}},"display_name":"Claude Fable 5","economics":{"all":67.20334005006164,"highest":75.52470268512155,"medium":65.87300202195027,"none":60.212315443113084},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":78.0266502770209,"score":78.0266502770209},"GB2-02":{"attempts":3,"playable":60.72945886091029,"score":60.72945886091029},"GB2-03":{"attempts":3,"playable":47.693787823961664,"score":47.693787823961664},"GB2-04":{"attempts":3,"playable":58.74117135531447,"score":58.74117135531447},"GB2-05":{"attempts":3,"playable":64.90989849569932,"score":64.90989849569932},"GB2-06":{"attempts":3,"playable":82.00577434851455,"score":82.00577434851455},"GB2-07":{"attempts":3,"playable":67.12168618074604,"score":67.12168618074604},"GB2-08":{"attempts":3,"playable":78.39829305832588,"score":78.39829305832588}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":86.1929545201878,"score":86.1929545201878},"GB2-02":{"attempts":1,"playable":80.00853568287216,"score":80.00853568287216},"GB2-03":{"attempts":1,"playable":86.8748551357901,"score":86.8748551357901},"GB2-04":{"attempts":1,"playable":84.23669821330363,"score":84.23669821330363},"GB2-05":{"attempts":1,"playable":56.7920280086787,"score":56.7920280086787},"GB2-06":{"attempts":1,"playable":87.45195488955015,"score":87.45195488955015},"GB2-07":{"attempts":1,"playable":65.67722071137273,"score":65.67722071137273},"GB2-08":{"attempts":1,"playable":56.963374319217245,"score":56.963374319217245}},"medium":{"GB2-01":{"attempts":1,"playable":76.41837549293614,"score":76.41837549293614},"GB2-02":{"attempts":1,"playable":58.626717940825515,"score":58.626717940825515},"GB2-03":{"attempts":1,"playable":20.840192325008562,"score":20.840192325008562},"GB2-04":{"attempts":1,"playable":53.570380060749834,"score":53.570380060749834},"GB2-05":{"attempts":1,"playable":69.24914607257541,"score":69.24914607257541},"GB2-06":{"attempts":1,"playable":81.55552321081501,"score":81.55552321081501},"GB2-07":{"attempts":1,"playable":73.73765235368714,"score":73.73765235368714},"GB2-08":{"attempts":1,"playable":92.98602871900457,"score":92.98602871900457}},"none":{"GB2-01":{"attempts":1,"playable":71.46862081793877,"score":71.46862081793877},"GB2-02":{"attempts":1,"playable":43.55312295903319,"score":43.55312295903319},"GB2-03":{"attempts":1,"playable":35.36631601108635,"score":35.36631601108635},"GB2-04":{"attempts":1,"playable":38.416435791889974,"score":38.416435791889974},"GB2-05":{"attempts":1,"playable":68.68852140584384,"score":68.68852140584384},"GB2-06":{"attempts":1,"playable":77.00984494517849,"score":77.00984494517849},"GB2-07":{"attempts":1,"playable":61.950185477178266,"score":61.950185477178266},"GB2-08":{"attempts":1,"playable":85.24547613675583,"score":85.24547613675583}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-10-24T18:32:54Z","match_totals_all":{"draws":2119,"losses":3162,"wins":6983},"match_totals_tracks":{"highest":{"draws":467,"losses":854,"wins":2767},"medium":{"draws":736,"losses":1075,"wins":2277},"none":{"draws":916,"losses":1233,"wins":1939}},"model_slug":"claude-fable-5","official_rank_by_reasoning":{"highest":12,"medium":15,"none":11},"overall":{"max":92.98602871900457,"mean":67.20334005006164,"min":20.840192325008562},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":86.1929545201878,"GB2-02":80.00853568287216,"GB2-03":86.8748551357901,"GB2-04":84.23669821330363,"GB2-05":56.7920280086787,"GB2-06":87.45195488955015,"GB2-07":65.67722071137273,"GB2-08":56.963374319217245},"per_game_all":{"GB2-01":78.0266502770209,"GB2-02":60.72945886091029,"GB2-03":47.693787823961664,"GB2-04":58.74117135531447,"GB2-05":64.90989849569932,"GB2-06":82.00577434851455,"GB2-07":67.12168618074604,"GB2-08":78.39829305832588},"per_game_match_totals_all":{"GB2-01":{"draws":103,"losses":318,"wins":1127},"GB2-02":{"draws":759,"losses":208,"wins":473},"GB2-03":{"draws":335,"losses":646,"wins":501},"GB2-04":{"draws":662,"losses":307,"wins":525},"GB2-05":{"draws":0,"losses":585,"wins":1005},"GB2-06":{"draws":64,"losses":268,"wins":1174},"GB2-07":{"draws":0,"losses":548,"wins":1042},"GB2-08":{"draws":196,"losses":282,"wins":1136}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":79,"wins":436},"GB2-02":{"draws":125,"losses":39,"wins":316},"GB2-03":{"draws":51,"losses":48,"wins":395},"GB2-04":{"draws":73,"losses":47,"wins":378},"GB2-05":{"draws":0,"losses":238,"wins":292},"GB2-06":{"draws":22,"losses":59,"wins":421},"GB2-07":{"draws":0,"losses":191,"wins":339},"GB2-08":{"draws":195,"losses":153,"wins":190}},"medium":{"GB2-01":{"draws":38,"losses":113,"wins":365},"GB2-02":{"draws":282,"losses":66,"wins":132},"GB2-03":{"draws":97,"losses":355,"wins":42},"GB2-04":{"draws":290,"losses":95,"wins":113},"GB2-05":{"draws":0,"losses":172,"wins":358},"GB2-06":{"draws":29,"losses":88,"wins":385},"GB2-07":{"draws":0,"losses":145,"wins":385},"GB2-08":{"draws":0,"losses":41,"wins":497}},"none":{"GB2-01":{"draws":64,"losses":126,"wins":326},"GB2-02":{"draws":352,"losses":103,"wins":25},"GB2-03":{"draws":187,"losses":243,"wins":64},"GB2-04":{"draws":299,"losses":165,"wins":34},"GB2-05":{"draws":0,"losses":175,"wins":355},"GB2-06":{"draws":13,"losses":121,"wins":368},"GB2-07":{"draws":0,"losses":212,"wins":318},"GB2-08":{"draws":1,"losses":88,"wins":449}}},"per_game_raw_elo_all":{"GB2-01":1779.7207165793432,"GB2-02":1572.0732714408314,"GB2-03":1453.6918359268966,"GB2-04":1567.356420814108,"GB2-05":1638.2029750936865,"GB2-06":1990.7574984487935,"GB2-07":1677.682049989541,"GB2-08":1913.4342425990328},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1901.4440285576334,"GB2-02":1754.1013863227877,"GB2-03":1907.7838985541916,"GB2-04":1814.3341222940992,"GB2-05":1522.9211443427291,"GB2-06":2108.7829046186334,"GB2-07":1653.8223433769099,"GB2-08":1479.441557477467},"medium":{"GB2-01":1749.3025163448278,"GB2-02":1540.0894913263812,"GB2-03":1153.9122122341828,"GB2-04":1502.8188931797224,"GB2-05":1700.3803416209107,"GB2-06":1977.216740543705,"GB2-07":1777.1803451894548,"GB2-08":2254.104249795551},"none":{"GB2-01":1688.4156048355685,"GB2-02":1422.0289366733252,"GB2-03":1299.3793969923156,"GB2-04":1384.9162469685027,"GB2-05":1691.3074393174202,"GB2-06":1886.2728501840415,"GB2-07":1602.0434614022574,"GB2-08":2006.756920524081}},"per_game_tracks":{"highest":{"GB2-01":86.1929545201878,"GB2-02":80.00853568287216,"GB2-03":86.8748551357901,"GB2-04":84.23669821330363,"GB2-05":56.7920280086787,"GB2-06":87.45195488955015,"GB2-07":65.67722071137273,"GB2-08":56.963374319217245},"medium":{"GB2-01":76.41837549293614,"GB2-02":58.626717940825515,"GB2-03":20.840192325008562,"GB2-04":53.570380060749834,"GB2-05":69.24914607257541,"GB2-06":81.55552321081501,"GB2-07":73.73765235368714,"GB2-08":92.98602871900457},"none":{"GB2-01":71.46862081793877,"GB2-02":43.55312295903319,"GB2-03":35.36631601108635,"GB2-04":38.416435791889974,"GB2-05":68.68852140584384,"GB2-06":77.00984494517849,"GB2-07":61.950185477178266,"GB2-08":85.24547613675583}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:59:23Z","reasoning":{"highest":75.52470268512155,"medium":65.87300202195027,"none":60.212315443113084},"reasoning_agg":{"highest":{"max":87.45195488955015,"mean":75.52470268512155,"min":56.7920280086787},"medium":{"max":92.98602871900457,"mean":65.87300202195027,"min":20.840192325008562},"none":{"max":85.24547613675583,"mean":60.212315443113084,"min":35.36631601108635}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":15.31238724200847},"working_program_strength":{"all":67.20334005006164,"highest":75.52470268512155,"medium":65.87300202195027,"none":60.212315443113084}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:5ab3b35616053c81","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":0.9656476}},"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":0.9656476},"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":6.8685884},"codegen_latency_ms":{"attempt_count":30,"max_ms":235793,"mean_ms":83718.41666666667,"min_ms":17910,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":235793,"mean_ms":170391.375,"min_ms":123596,"run_count":8},"medium":{"attempt_count":11,"max_ms":84789,"mean_ms":58477.125,"min_ms":40383,"run_count":8},"none":{"attempt_count":10,"max_ms":29743,"mean_ms":22286.75,"min_ms":17910,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":29674,"output_mean":12261.208333333334,"output_min":3304,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":29674,"output_mean":22547.25,"output_min":16651,"run_count":8},"medium":{"attempt_count":11,"output_max":17493,"output_mean":10166.125,"output_min":6634,"run_count":8},"none":{"attempt_count":10,"output_max":5361,"output_mean":4070.25,"output_min":3304,"run_count":8}},"display_name":"Muse Wonder","economics":{"all":66.35628052149949,"highest":78.7862865500759,"medium":63.48099376011454,"none":56.80156125430801},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":69.12049620375545,"score":69.12049620375545},"GB2-02":{"attempts":3,"playable":55.30437734585333,"score":55.30437734585333},"GB2-03":{"attempts":3,"playable":45.63969548722631,"score":45.63969548722631},"GB2-04":{"attempts":3,"playable":58.42860040294618,"score":58.42860040294618},"GB2-05":{"attempts":3,"playable":87.8665120334198,"score":87.8665120334198},"GB2-06":{"attempts":3,"playable":76.88550635638659,"score":76.88550635638659},"GB2-07":{"attempts":3,"playable":71.88040430720514,"score":71.88040430720514},"GB2-08":{"attempts":3,"playable":65.72465203520312,"score":65.72465203520312}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":85.09791177963304,"score":85.09791177963304},"GB2-02":{"attempts":1,"playable":66.64836654155657,"score":66.64836654155657},"GB2-03":{"attempts":1,"playable":82.9874005959884,"score":82.9874005959884},"GB2-04":{"attempts":1,"playable":81.86990430623399,"score":81.86990430623399},"GB2-05":{"attempts":1,"playable":93.07464003856816,"score":93.07464003856816},"GB2-06":{"attempts":1,"playable":84.55325223111092,"score":84.55325223111092},"GB2-07":{"attempts":1,"playable":74.08524346236605,"score":74.08524346236605},"GB2-08":{"attempts":1,"playable":61.973573445149995,"score":61.973573445149995}},"medium":{"GB2-01":{"attempts":1,"playable":53.286342220818405,"score":53.286342220818405},"GB2-02":{"attempts":1,"playable":56.24003829338188,"score":56.24003829338188},"GB2-03":{"attempts":1,"playable":36.855002746555584,"score":36.855002746555584},"GB2-04":{"attempts":1,"playable":39.54311557804636,"score":39.54311557804636},"GB2-05":{"attempts":1,"playable":85.3483137023518,"score":85.3483137023518},"GB2-06":{"attempts":1,"playable":77.10076872786667,"score":77.10076872786667},"GB2-07":{"attempts":1,"playable":87.52588108846469,"score":87.52588108846469},"GB2-08":{"attempts":1,"playable":71.94848772343101,"score":71.94848772343101}},"none":{"GB2-01":{"attempts":1,"playable":68.97723461081488,"score":68.97723461081488},"GB2-02":{"attempts":1,"playable":43.02472720262155,"score":43.02472720262155},"GB2-03":{"attempts":1,"playable":17.076683119134948,"score":17.076683119134948},"GB2-04":{"attempts":1,"playable":53.87278132455818,"score":53.87278132455818},"GB2-05":{"attempts":1,"playable":85.17658235933942,"score":85.17658235933942},"GB2-06":{"attempts":1,"playable":69.00249811018219,"score":69.00249811018219},"GB2-07":{"attempts":1,"playable":54.03008837078467,"score":54.03008837078467},"GB2-08":{"attempts":1,"playable":63.25189493702834,"score":63.25189493702834}}},"id":"meta/muse-wonder","is_recent_addition":false,"last_measured_at":"2026-10-24T16:50:59Z","match_totals_all":{"draws":2250,"losses":3200,"wins":6813},"match_totals_tracks":{"highest":{"draws":535,"losses":667,"wins":2886},"medium":{"draws":669,"losses":1217,"wins":2202},"none":{"draws":1046,"losses":1316,"wins":1725}},"model_slug":"meta-muse-wonder","official_rank_by_reasoning":{"highest":11,"medium":18,"none":13},"overall":{"max":93.07464003856816,"mean":66.35628052149949,"min":17.076683119134948},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":85.09791177963304,"GB2-02":66.64836654155657,"GB2-03":82.9874005959884,"GB2-04":81.86990430623399,"GB2-05":93.07464003856816,"GB2-06":84.55325223111092,"GB2-07":74.08524346236605,"GB2-08":61.973573445149995},"per_game_all":{"GB2-01":69.12049620375545,"GB2-02":55.30437734585333,"GB2-03":45.63969548722631,"GB2-04":58.42860040294618,"GB2-05":87.8665120334198,"GB2-06":76.88550635638659,"GB2-07":71.88040430720514,"GB2-08":65.72465203520312},"per_game_match_totals_all":{"GB2-01":{"draws":173,"losses":422,"wins":953},"GB2-02":{"draws":936,"losses":200,"wins":304},"GB2-03":{"draws":277,"losses":707,"wins":498},"GB2-04":{"draws":585,"losses":351,"wins":558},"GB2-05":{"draws":0,"losses":204,"wins":1386},"GB2-06":{"draws":100,"losses":334,"wins":1071},"GB2-07":{"draws":0,"losses":464,"wins":1126},"GB2-08":{"draws":179,"losses":518,"wins":917}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":83,"wins":428},"GB2-02":{"draws":270,"losses":33,"wins":177},"GB2-03":{"draws":85,"losses":53,"wins":356},"GB2-04":{"draws":64,"losses":64,"wins":370},"GB2-05":{"draws":0,"losses":37,"wins":493},"GB2-06":{"draws":32,"losses":70,"wins":400},"GB2-07":{"draws":0,"losses":143,"wins":387},"GB2-08":{"draws":79,"losses":184,"wins":275}},"medium":{"GB2-01":{"draws":4,"losses":250,"wins":262},"GB2-02":{"draws":293,"losses":72,"wins":115},"GB2-03":{"draws":103,"losses":278,"wins":113},"GB2-04":{"draws":214,"losses":202,"wins":82},"GB2-05":{"draws":0,"losses":83,"wins":447},"GB2-06":{"draws":30,"losses":112,"wins":360},"GB2-07":{"draws":0,"losses":65,"wins":465},"GB2-08":{"draws":25,"losses":155,"wins":358}},"none":{"GB2-01":{"draws":164,"losses":89,"wins":263},"GB2-02":{"draws":373,"losses":95,"wins":12},"GB2-03":{"draws":89,"losses":376,"wins":29},"GB2-04":{"draws":307,"losses":85,"wins":106},"GB2-05":{"draws":0,"losses":84,"wins":446},"GB2-06":{"draws":38,"losses":152,"wins":311},"GB2-07":{"draws":0,"losses":256,"wins":274},"GB2-08":{"draws":75,"losses":179,"wins":284}}},"per_game_raw_elo_all":{"GB2-01":1680.5033388658278,"GB2-02":1515.969897304547,"GB2-03":1413.5092837716984,"GB2-04":1559.4960553287776,"GB2-05":2177.1007950325898,"GB2-06":1888.4934944011977,"GB2-07":1789.8164611734308,"GB2-08":1610.226265600994},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1881.0300576462735,"GB2-02":1609.1921347606203,"GB2-03":1820.9418418955815,"GB2-04":1779.4467105663387,"GB2-05":2395.0083880815982,"GB2-06":2041.3123259528952,"GB2-07":1783.0067176496561,"GB2-08":1548.6535997189349},"medium":{"GB2-01":1500.422896306607,"GB2-02":1520.7809897236903,"GB2-03":1312.6833460138764,"GB2-04":1393.8446113073871,"GB2-05":2071.0125096054066,"GB2-06":1888.0414076438453,"GB2-07":2088.206173716462,"GB2-08":1714.3654825824976},"none":{"GB2-01":1660.0570626446033,"GB2-02":1417.9365674293301,"GB2-03":1106.9026634056374,"GB2-04":1505.1968441126078,"GB2-05":2065.2814874107644,"GB2-06":1736.1267496068526,"GB2-07":1498.2364921541734,"GB2-08":1567.6597145015498}},"per_game_tracks":{"highest":{"GB2-01":85.09791177963304,"GB2-02":66.64836654155657,"GB2-03":82.9874005959884,"GB2-04":81.86990430623399,"GB2-05":93.07464003856816,"GB2-06":84.55325223111092,"GB2-07":74.08524346236605,"GB2-08":61.973573445149995},"medium":{"GB2-01":53.286342220818405,"GB2-02":56.24003829338188,"GB2-03":36.855002746555584,"GB2-04":39.54311557804636,"GB2-05":85.3483137023518,"GB2-06":77.10076872786667,"GB2-07":87.52588108846469,"GB2-08":71.94848772343101},"none":{"GB2-01":68.97723461081488,"GB2-02":43.02472720262155,"GB2-03":17.076683119134948,"GB2-04":53.87278132455818,"GB2-05":85.17658235933942,"GB2-06":69.00249811018219,"GB2-07":54.03008837078467,"GB2-08":63.25189493702834}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:42:48Z","reasoning":{"highest":78.7862865500759,"medium":63.48099376011454,"none":56.80156125430801},"reasoning_agg":{"highest":{"max":93.07464003856816,"mean":78.7862865500759,"min":61.973573445149995},"medium":{"max":87.52588108846469,"mean":63.48099376011454,"min":36.855002746555584},"none":{"max":85.17658235933942,"mean":56.80156125430801,"min":17.076683119134948}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":21.984725295767888},"working_program_strength":{"all":66.35628052149949,"highest":78.7862865500759,"medium":63.48099376011454,"none":56.80156125430801}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:1bd88701a8bc2787","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":1.25555516},"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":1.25555516},"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":4.397416199999999}},"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":6.084788240000001},"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":65.49970148823179,"highest":73.54229615721877,"medium":71.68133629755313,"none":51.27547200992349},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":29,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":84,"requested_max_output_token_observations":10,"requested_max_output_tokens":[131072],"total_output_tokens":1317942,"total_reasoning_output_tokens":1189870,"total_visible_output_tokens":128072,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":60.013494534263685,"score":40.00899635617579},"GB2-02":{"attempts":3,"playable":57.361469629495765,"score":57.361469629495765},"GB2-03":{"attempts":3,"playable":68.70352234836453,"score":68.70352234836453},"GB2-04":{"attempts":3,"playable":69.52687775712869,"score":69.52687775712869},"GB2-05":{"attempts":3,"playable":72.35542109108546,"score":72.35542109108546},"GB2-06":{"attempts":3,"playable":77.77251150628085,"score":77.77251150628085},"GB2-07":{"attempts":3,"playable":75.75585491387672,"score":75.75585491387672},"GB2-08":{"attempts":3,"playable":62.512958303446574,"score":62.512958303446574}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":73.6357200005782,"score":73.6357200005782},"GB2-03":{"attempts":1,"playable":84.67713571294901,"score":84.67713571294901},"GB2-04":{"attempts":1,"playable":77.08576607355803,"score":77.08576607355803},"GB2-05":{"attempts":1,"playable":90.23312811232972,"score":90.23312811232972},"GB2-06":{"attempts":1,"playable":91.13495744523287,"score":91.13495744523287},"GB2-07":{"attempts":1,"playable":78.58563319409772,"score":78.58563319409772},"GB2-08":{"attempts":1,"playable":92.98602871900458,"score":92.98602871900458}},"medium":{"GB2-01":{"attempts":1,"playable":51.62599243619176,"score":51.62599243619176},"GB2-02":{"attempts":1,"playable":54.26188228703578,"score":54.26188228703578},"GB2-03":{"attempts":1,"playable":78.36652195961076,"score":78.36652195961076},"GB2-04":{"attempts":1,"playable":83.08314624153542,"score":83.08314624153542},"GB2-05":{"attempts":1,"playable":67.19039459119735,"score":67.19039459119735},"GB2-06":{"attempts":1,"playable":92.4662960152218,"score":92.4662960152218},"GB2-07":{"attempts":1,"playable":76.68556035883918,"score":76.68556035883918},"GB2-08":{"attempts":1,"playable":69.77089649079302,"score":69.77089649079302}},"none":{"GB2-01":{"attempts":1,"playable":68.40099663233562,"score":68.40099663233562},"GB2-02":{"attempts":1,"playable":44.18680660087333,"score":44.18680660087333},"GB2-03":{"attempts":1,"playable":43.06690937253382,"score":43.06690937253382},"GB2-04":{"attempts":1,"playable":48.411720956292605,"score":48.411720956292605},"GB2-05":{"attempts":1,"playable":59.64274056972931,"score":59.64274056972931},"GB2-06":{"attempts":1,"playable":49.71628105838787,"score":49.71628105838787},"GB2-07":{"attempts":1,"playable":71.99637118869325,"score":71.99637118869325},"GB2-08":{"attempts":1,"playable":24.78194970054213,"score":24.78194970054213}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-10-24T19:06:22Z","match_totals_all":{"draws":2157,"losses":2839,"wins":6751},"match_totals_tracks":{"highest":{"draws":380,"losses":412,"wins":2780},"medium":{"draws":638,"losses":913,"wins":2536},"none":{"draws":1139,"losses":1514,"wins":1435}},"model_slug":"z-ai-glm-5-3","official_rank_by_reasoning":{"highest":13,"medium":10,"none":19},"overall":{"max":92.98602871900458,"mean":65.49970148823179,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-02":73.6357200005782,"GB2-03":84.67713571294901,"GB2-04":77.08576607355803,"GB2-05":90.23312811232972,"GB2-06":91.13495744523287,"GB2-07":78.58563319409772,"GB2-08":92.98602871900458},"per_game_all":{"GB2-02":57.361469629495765,"GB2-03":68.70352234836453,"GB2-04":69.52687775712869,"GB2-05":72.35542109108546,"GB2-06":77.77251150628085,"GB2-07":75.75585491387672,"GB2-08":62.512958303446574},"per_game_match_totals_all":{"GB2-01":{"draws":171,"losses":349,"wins":512},"GB2-02":{"draws":917,"losses":179,"wins":344},"GB2-03":{"draws":158,"losses":428,"wins":896},"GB2-04":{"draws":560,"losses":196,"wins":737},"GB2-05":{"draws":0,"losses":460,"wins":1130},"GB2-06":{"draws":58,"losses":337,"wins":1111},"GB2-07":{"draws":0,"losses":400,"wins":1190},"GB2-08":{"draws":293,"losses":490,"wins":831}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":213,"losses":27,"wins":240},"GB2-03":{"draws":4,"losses":84,"wins":406},"GB2-04":{"draws":138,"losses":52,"wins":308},"GB2-05":{"draws":0,"losses":54,"wins":476},"GB2-06":{"draws":25,"losses":37,"wins":440},"GB2-07":{"draws":0,"losses":117,"wins":413},"GB2-08":{"draws":0,"losses":41,"wins":497}},"medium":{"GB2-01":{"draws":89,"losses":216,"wins":211},"GB2-02":{"draws":326,"losses":65,"wins":89},"GB2-03":{"draws":26,"losses":108,"wins":360},"GB2-04":{"draws":93,"losses":43,"wins":361},"GB2-05":{"draws":0,"losses":183,"wins":347},"GB2-06":{"draws":24,"losses":30,"wins":448},"GB2-07":{"draws":0,"losses":128,"wins":402},"GB2-08":{"draws":80,"losses":140,"wins":318}},"none":{"GB2-01":{"draws":82,"losses":133,"wins":301},"GB2-02":{"draws":378,"losses":87,"wins":15},"GB2-03":{"draws":128,"losses":236,"wins":130},"GB2-04":{"draws":329,"losses":101,"wins":68},"GB2-05":{"draws":0,"losses":223,"wins":307},"GB2-06":{"draws":9,"losses":270,"wins":223},"GB2-07":{"draws":0,"losses":155,"wins":375},"GB2-08":{"draws":213,"losses":309,"wins":16}}},"per_game_raw_elo_all":{"GB2-02":1536.7283465512428,"GB2-03":1654.2077779513527,"GB2-04":1659.3601515762693,"GB2-05":1828.8610631820775,"GB2-06":1958.6989561669106,"GB2-07":1813.8759434734347,"GB2-08":1683.5560328353367},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1678.1956984017986,"GB2-03":1856.0943701333126,"GB2-04":1718.5254140812187,"GB2-05":2258.58749226116,"GB2-06":2208.88174328455,"GB2-07":1864.3555842494748,"GB2-08":2254.1042497955514},"medium":{"GB2-01":1484.5359962010382,"GB2-02":1505.06014663527,"GB2-03":1739.4553898332294,"GB2-04":1796.848189998153,"GB2-05":1667.7417461685977,"GB2-06":2252.00583912285,"GB2-07":1828.5131944417337,"GB2-08":1674.609601338175},"none":{"GB2-01":1653.6701606352826,"GB2-02":1426.929194616659,"GB2-03":1367.0735738875157,"GB2-04":1462.7068506494359,"GB2-05":1560.2539511164744,"GB2-06":1415.2092860933317,"GB2-07":1748.7590517290957,"GB2-08":1121.954247372284}},"per_game_tracks":{"highest":{"GB2-02":73.6357200005782,"GB2-03":84.67713571294901,"GB2-04":77.08576607355803,"GB2-05":90.23312811232972,"GB2-06":91.13495744523287,"GB2-07":78.58563319409772,"GB2-08":92.98602871900458},"medium":{"GB2-01":51.62599243619176,"GB2-02":54.26188228703578,"GB2-03":78.36652195961076,"GB2-04":83.08314624153542,"GB2-05":67.19039459119735,"GB2-06":92.4662960152218,"GB2-07":76.68556035883918,"GB2-08":69.77089649079302},"none":{"GB2-01":68.40099663233562,"GB2-02":44.18680660087333,"GB2-03":43.06690937253382,"GB2-04":48.411720956292605,"GB2-05":59.64274056972931,"GB2-06":49.71628105838787,"GB2-07":71.99637118869325,"GB2-08":24.78194970054213}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:00:37Z","reasoning":{"highest":73.54229615721877,"medium":71.68133629755313,"none":51.27547200992349},"reasoning_agg":{"highest":{"max":92.98602871900458,"mean":73.54229615721877,"min":0.0},"medium":{"max":92.4662960152218,"mean":71.68133629755313,"min":51.62599243619176},"none":{"max":71.99637118869325,"mean":51.27547200992349,"min":24.78194970054213}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":22.26682414729528},"working_program_strength":{"all":69.00171559095651,"highest":84.04833846539289,"medium":71.68133629755313,"none":51.27547200992349}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:d952d585292a2c76","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":6.2355599999999995},"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":3.189754},"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":0.6637359999999999},"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":64.97088309174565,"highest":73.29928541210377,"medium":73.24863181540096,"none":48.364732047732225},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[450000],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[450000],"total_output_tokens":1623223,"total_reasoning_output_tokens":1401661,"total_visible_output_tokens":221562,"visible_token_observations":29},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":450000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.708964817780576,"score":55.708964817780576},"GB2-02":{"attempts":3,"playable":74.22366266407069,"score":74.22366266407069},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":80.29827230467035,"score":53.5321815364469},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.73235868881648,"score":45.15490579254432},"GB2-05":{"attempts":3,"playable":76.36644574394916,"score":76.36644574394916},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":86.62421148230145,"score":57.7494743215343},"GB2-07":{"attempts":3,"playable":70.07817537138651,"score":70.07817537138651},"GB2-08":{"attempts":3,"playable":86.95325448625279,"score":86.95325448625279}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":59.61203017482296,"score":59.61203017482296},"GB2-02":{"attempts":1,"playable":89.06713811069254,"score":89.06713811069254},"GB2-03":{"attempts":1,"playable":88.00698475405586,"score":88.00698475405586},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":93.41216585433246,"score":93.41216585433246},"GB2-06":{"attempts":1,"playable":90.42060318635687,"score":90.42060318635687},"GB2-07":{"attempts":1,"playable":78.41311704912738,"score":78.41311704912738},"GB2-08":{"attempts":1,"playable":87.4622441674421,"score":87.4622441674421}},"medium":{"GB2-01":{"attempts":1,"playable":79.99855157356521,"score":79.99855157356521},"GB2-02":{"attempts":1,"playable":80.69869067931016,"score":80.69869067931016},"GB2-03":{"attempts":1,"playable":72.58955985528485,"score":72.58955985528485},"GB2-04":{"attempts":1,"playable":92.24230383027668,"score":92.24230383027668},"GB2-05":{"attempts":1,"playable":93.07464003856816,"score":93.07464003856816},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":76.33949863172556,"score":76.33949863172556},"GB2-08":{"attempts":1,"playable":91.04580991447708,"score":91.04580991447708}},"none":{"GB2-01":{"attempts":1,"playable":27.516312704953545,"score":27.516312704953545},"GB2-02":{"attempts":1,"playable":52.90515920220936,"score":52.90515920220936},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.222413547356254,"score":43.222413547356254},"GB2-05":{"attempts":1,"playable":42.61253133894685,"score":42.61253133894685},"GB2-06":{"attempts":1,"playable":82.82781977824602,"score":82.82781977824602},"GB2-07":{"attempts":1,"playable":55.48191043330657,"score":55.48191043330657},"GB2-08":{"attempts":1,"playable":82.35170937683921,"score":82.35170937683921}}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-10-24T19:17:40Z","match_totals_all":{"draws":1036,"losses":2398,"wins":7336},"match_totals_tracks":{"highest":{"draws":162,"losses":542,"wins":2886},"medium":{"draws":217,"losses":515,"wins":2854},"none":{"draws":657,"losses":1341,"wins":1596}},"model_slug":"x-ai-grok-4-7","official_rank_by_reasoning":{"highest":14,"medium":8,"none":24},"overall":{"max":93.41216585433246,"mean":64.97088309174565,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.61203017482296,"GB2-02":89.06713811069254,"GB2-03":88.00698475405586,"GB2-05":93.41216585433246,"GB2-06":90.42060318635687,"GB2-07":78.41311704912738,"GB2-08":87.4622441674421},"per_game_all":{"GB2-01":55.708964817780576,"GB2-02":74.22366266407069,"GB2-05":76.36644574394916,"GB2-07":70.07817537138651,"GB2-08":86.95325448625279},"per_game_match_totals_all":{"GB2-01":{"draws":202,"losses":614,"wins":732},"GB2-02":{"draws":493,"losses":141,"wins":806},"GB2-03":{"draws":112,"losses":163,"wins":713},"GB2-04":{"draws":177,"losses":243,"wins":576},"GB2-05":{"draws":0,"losses":384,"wins":1206},"GB2-06":{"draws":52,"losses":123,"wins":829},"GB2-07":{"draws":0,"losses":496,"wins":1094},"GB2-08":{"draws":0,"losses":234,"wins":1380}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":213,"wins":290},"GB2-02":{"draws":50,"losses":30,"wins":400},"GB2-03":{"draws":84,"losses":25,"wins":385},"GB2-05":{"draws":0,"losses":35,"wins":495},"GB2-06":{"draws":15,"losses":46,"wins":441},"GB2-07":{"draws":0,"losses":118,"wins":412},"GB2-08":{"draws":0,"losses":75,"wins":463}},"medium":{"GB2-01":{"draws":34,"losses":96,"wins":386},"GB2-02":{"draws":110,"losses":43,"wins":327},"GB2-03":{"draws":28,"losses":138,"wins":328},"GB2-04":{"draws":45,"losses":18,"wins":435},"GB2-05":{"draws":0,"losses":37,"wins":493},"GB2-07":{"draws":0,"losses":130,"wins":400},"GB2-08":{"draws":0,"losses":53,"wins":485}},"none":{"GB2-01":{"draws":155,"losses":305,"wins":56},"GB2-02":{"draws":333,"losses":68,"wins":79},"GB2-04":{"draws":132,"losses":225,"wins":141},"GB2-05":{"draws":0,"losses":312,"wins":218},"GB2-06":{"draws":37,"losses":77,"wins":388},"GB2-07":{"draws":0,"losses":248,"wins":282},"GB2-08":{"draws":0,"losses":106,"wins":432}}},"per_game_raw_elo_all":{"GB2-01":1534.973553446104,"GB2-02":1721.9227392524047,"GB2-05":2051.092244260232,"GB2-07":1733.3456417050681,"GB2-08":2060.594657463395},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1562.0771106768516,"GB2-02":1907.9344413159254,"GB2-03":1937.6854910155594,"GB2-05":2413.2464153883375,"GB2-06":2187.620350377581,"GB2-07":1860.994334735094,"GB2-08":2067.202364501209},"medium":{"GB2-01":1798.6140874810376,"GB2-02":1763.4393368470508,"GB2-03":1657.6127451484795,"GB2-04":1977.9838001015034,"GB2-05":2395.0083880815982,"GB2-07":1822.2415379106521,"GB2-08":2180.0148084456905},"none":{"GB2-01":1244.2294621804222,"GB2-02":1494.3944395942378,"GB2-04":1422.6119777808458,"GB2-05":1345.0219293107593,"GB2-06":2003.8891336270544,"GB2-07":1516.8010524694585,"GB2-08":1934.566799443285}},"per_game_tracks":{"highest":{"GB2-01":59.61203017482296,"GB2-02":89.06713811069254,"GB2-03":88.00698475405586,"GB2-05":93.41216585433246,"GB2-06":90.42060318635687,"GB2-07":78.41311704912738,"GB2-08":87.4622441674421},"medium":{"GB2-01":79.99855157356521,"GB2-02":80.69869067931016,"GB2-03":72.58955985528485,"GB2-04":92.24230383027668,"GB2-05":93.07464003856816,"GB2-07":76.33949863172556,"GB2-08":91.04580991447708},"none":{"GB2-01":27.516312704953545,"GB2-02":52.90515920220936,"GB2-04":43.222413547356254,"GB2-05":42.61253133894685,"GB2-06":82.82781977824602,"GB2-07":55.48191043330657,"GB2-08":82.35170937683921}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:58:58Z","reasoning":{"highest":73.29928541210377,"medium":73.24863181540096,"none":48.364732047732225},"reasoning_agg":{"highest":{"max":93.41216585433246,"mean":73.29928541210377,"min":0.0},"medium":{"max":93.07464003856816,"mean":73.24863181540096,"min":0.0},"none":{"max":82.82781977824602,"mean":48.364732047732225,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.934553364371546},"working_program_strength":{"all":74.25243781913788,"highest":83.77061189954716,"medium":83.71272207474395,"none":55.273979483122545}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash-1017:11c892b6e18e7c72","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":0.046843572}},"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":0.04684357200000001},"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":0.9873648599999999},"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":63.43231767473308,"highest":71.8705529576342,"medium":66.7179597939197,"none":51.70844027264532},"economics_best_value":{"per_model":{"all":true,"medium":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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":75.47865761691084,"score":75.47865761691084},"GB2-02":{"attempts":3,"playable":56.27989702999357,"score":56.27989702999357},"GB2-03":{"attempts":3,"playable":45.950046564397915,"score":45.950046564397915},"GB2-04":{"attempts":3,"playable":60.66892594209116,"score":60.66892594209116},"GB2-05":{"attempts":3,"playable":62.7375618306749,"score":62.7375618306749},"GB2-06":{"attempts":3,"playable":69.28689965033237,"score":69.28689965033237},"GB2-07":{"attempts":3,"playable":59.913522321125406,"score":59.913522321125406},"GB2-08":{"attempts":3,"playable":77.14303044233846,"score":77.14303044233846}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.88122716100659,"score":68.88122716100659},"GB2-02":{"attempts":1,"playable":80.99404606848135,"score":80.99404606848135},"GB2-03":{"attempts":1,"playable":46.80728017489208,"score":46.80728017489208},"GB2-04":{"attempts":1,"playable":70.18674950292221,"score":70.18674950292221},"GB2-05":{"attempts":1,"playable":73.89143137095178,"score":73.89143137095178},"GB2-06":{"attempts":1,"playable":77.98949970361225,"score":77.98949970361225},"GB2-07":{"attempts":1,"playable":72.86771546098988,"score":72.86771546098988},"GB2-08":{"attempts":1,"playable":83.34647421821748,"score":83.34647421821748}},"medium":{"GB2-01":{"attempts":1,"playable":84.27193212166382,"score":84.27193212166382},"GB2-02":{"attempts":1,"playable":43.87001850459841,"score":43.87001850459841},"GB2-03":{"attempts":1,"playable":51.12197703936891,"score":51.12197703936891},"GB2-04":{"attempts":1,"playable":69.1078648951399,"score":69.1078648951399},"GB2-05":{"attempts":1,"playable":61.72675721544808,"score":61.72675721544808},"GB2-06":{"attempts":1,"playable":83.85199930266273,"score":83.85199930266273},"GB2-07":{"attempts":1,"playable":73.56377534670133,"score":73.56377534670133},"GB2-08":{"attempts":1,"playable":66.22935392577443,"score":66.22935392577443}},"none":{"GB2-01":{"attempts":1,"playable":73.2828135680621,"score":73.2828135680621},"GB2-02":{"attempts":1,"playable":43.97562651690093,"score":43.97562651690093},"GB2-03":{"attempts":1,"playable":39.92088247893277,"score":39.92088247893277},"GB2-04":{"attempts":1,"playable":42.71216342821136,"score":42.71216342821136},"GB2-05":{"attempts":1,"playable":52.59449690562482,"score":52.59449690562482},"GB2-06":{"attempts":1,"playable":46.01919994472211,"score":46.01919994472211},"GB2-07":{"attempts":1,"playable":33.309076155685,"score":33.309076155685},"GB2-08":{"attempts":1,"playable":81.85326318302347,"score":81.85326318302347}}},"id":"deepseek/deepseek-v4.1-flash-1017","is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:09Z","match_totals_all":{"draws":2175,"losses":3639,"wins":6446},"match_totals_tracks":{"highest":{"draws":567,"losses":942,"wins":2577},"medium":{"draws":640,"losses":1118,"wins":2329},"none":{"draws":968,"losses":1579,"wins":1540}},"model_slug":"deepseek-deepseek-v4-1-flash-1017","official_rank_by_reasoning":{"highest":15,"medium":14,"none":17},"overall":{"max":84.27193212166382,"mean":63.43231767473308,"min":33.309076155685},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.88122716100659,"GB2-02":80.99404606848135,"GB2-03":46.80728017489208,"GB2-04":70.18674950292221,"GB2-05":73.89143137095178,"GB2-06":77.98949970361225,"GB2-07":72.86771546098988,"GB2-08":83.34647421821748},"per_game_all":{"GB2-01":75.47865761691084,"GB2-02":56.27989702999357,"GB2-03":45.950046564397915,"GB2-04":60.66892594209116,"GB2-05":62.7375618306749,"GB2-06":69.28689965033237,"GB2-07":59.913522321125406,"GB2-08":77.14303044233846},"per_game_match_totals_all":{"GB2-01":{"draws":166,"losses":327,"wins":1055},"GB2-02":{"draws":836,"losses":233,"wins":371},"GB2-03":{"draws":358,"losses":679,"wins":445},"GB2-04":{"draws":766,"losses":229,"wins":499},"GB2-05":{"draws":0,"losses":619,"wins":971},"GB2-06":{"draws":49,"losses":480,"wins":973},"GB2-07":{"draws":0,"losses":663,"wins":927},"GB2-08":{"draws":0,"losses":409,"wins":1205}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":107,"losses":118,"wins":291},"GB2-02":{"draws":97,"losses":48,"wins":335},"GB2-03":{"draws":86,"losses":239,"wins":169},"GB2-04":{"draws":257,"losses":28,"wins":213},"GB2-05":{"draws":0,"losses":147,"wins":383},"GB2-06":{"draws":20,"losses":112,"wins":368},"GB2-07":{"draws":0,"losses":150,"wins":380},"GB2-08":{"draws":0,"losses":100,"wins":438}},"medium":{"GB2-01":{"draws":0,"losses":90,"wins":426},"GB2-02":{"draws":361,"losses":97,"wins":22},"GB2-03":{"draws":54,"losses":234,"wins":206},"GB2-04":{"draws":200,"losses":62,"wins":236},"GB2-05":{"draws":0,"losses":212,"wins":318},"GB2-06":{"draws":25,"losses":77,"wins":399},"GB2-07":{"draws":0,"losses":146,"wins":384},"GB2-08":{"draws":0,"losses":200,"wins":338}},"none":{"GB2-01":{"draws":59,"losses":119,"wins":338},"GB2-02":{"draws":378,"losses":88,"wins":14},"GB2-03":{"draws":218,"losses":206,"wins":70},"GB2-04":{"draws":309,"losses":139,"wins":50},"GB2-05":{"draws":0,"losses":260,"wins":270},"GB2-06":{"draws":4,"losses":291,"wins":206},"GB2-07":{"draws":0,"losses":367,"wins":163},"GB2-08":{"draws":0,"losses":109,"wins":429}}},"per_game_raw_elo_all":{"GB2-01":1745.1047421625997,"GB2-02":1539.099113462571,"GB2-03":1392.2041795344091,"GB2-04":1566.2705287003062,"GB2-05":1613.415262772913,"GB2-06":1763.2273602874382,"GB2-07":1591.4209687905502,"GB2-08":1831.9161495205615},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1658.9887648236206,"GB2-02":1767.5199604711777,"GB2-03":1399.5425766394778,"GB2-04":1645.2741861193044,"GB2-05":1782.1009811098731,"GB2-06":1905.4204977222103,"GB2-07":1762.8282806744726,"GB2-08":1958.6729174234388},"medium":{"GB2-01":1866.3849844858903,"GB2-02":1424.4804152842908,"GB2-03":1437.3800791015906,"GB2-04":1634.8877296324138,"GB2-05":1588.4533127688787,"GB2-06":2025.9057673929765,"GB2-07":1774.2859686034894,"GB2-08":1614.341763535914},"none":{"GB2-01":1709.9404771782877,"GB2-02":1425.296964632244,"GB2-03":1339.6898828621593,"GB2-04":1418.6496703492,"GB2-05":1469.6914944399866,"GB2-06":1358.355815747127,"GB2-07":1237.1486570936886,"GB2-08":1922.7337676023315}},"per_game_tracks":{"highest":{"GB2-01":68.88122716100659,"GB2-02":80.99404606848135,"GB2-03":46.80728017489208,"GB2-04":70.18674950292221,"GB2-05":73.89143137095178,"GB2-06":77.98949970361225,"GB2-07":72.86771546098988,"GB2-08":83.34647421821748},"medium":{"GB2-01":84.27193212166382,"GB2-02":43.87001850459841,"GB2-03":51.12197703936891,"GB2-04":69.1078648951399,"GB2-05":61.72675721544808,"GB2-06":83.85199930266273,"GB2-07":73.56377534670133,"GB2-08":66.22935392577443},"none":{"GB2-01":73.2828135680621,"GB2-02":43.97562651690093,"GB2-03":39.92088247893277,"GB2-04":42.71216342821136,"GB2-05":52.59449690562482,"GB2-06":46.01919994472211,"GB2-07":33.309076155685,"GB2-08":81.85326318302347}},"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":0,"rank_movement_baseline_at":"2026-10-22T11:01:43Z","reasoning":{"highest":71.8705529576342,"medium":66.7179597939197,"none":51.70844027264532},"reasoning_agg":{"highest":{"max":83.34647421821748,"mean":71.8705529576342,"min":46.80728017489208},"medium":{"max":84.27193212166382,"mean":66.7179597939197,"min":43.87001850459841},"none":{"max":81.85326318302347,"mean":51.70844027264532,"min":33.309076155685}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":20.162112684988884},"working_program_strength":{"all":63.43231767473308,"highest":71.8705529576342,"medium":66.7179597939197,"none":51.70844027264532}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:455c32eab08ae82c","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":0.4863780000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.32749799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.48637800000000003},"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":0.32749799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385362}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199237999999999},"codegen_output_tokens":{"attempt_count":28,"output_max":70064,"output_mean":18803.166666666668,"output_min":1228,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":70064,"output_mean":51989.0,"output_min":25995,"run_count":8},"medium":{"attempt_count":11,"output_max":4348,"output_mean":2842.75,"output_min":1552,"run_count":8},"none":{"attempt_count":8,"output_max":2376,"output_mean":1577.75,"output_min":1228,"run_count":8}},"display_name":"Claude Sonnet 5.5","economics":{"all":61.68081730862078,"highest":91.85620858463477,"medium":52.01045685543626,"none":41.17578648579133},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.54482555755948,"score":59.54482555755948},"GB2-02":{"attempts":3,"playable":61.693989529230976,"score":61.693989529230976},"GB2-03":{"attempts":3,"playable":58.71620038242805,"score":58.71620038242805},"GB2-04":{"attempts":3,"playable":56.76948231186617,"score":56.76948231186617},"GB2-05":{"attempts":3,"playable":43.73551635656543,"score":43.73551635656543},"GB2-06":{"attempts":3,"playable":61.59738880806021,"score":61.59738880806021},"GB2-07":{"attempts":3,"playable":70.60135297964827,"score":70.60135297964827},"GB2-08":{"attempts":3,"playable":80.7877825436077,"score":80.7877825436077}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.27950765645659,"score":80.27950765645659},"GB2-02":{"attempts":1,"playable":95.76171266657369,"score":95.76171266657369},"GB2-03":{"attempts":1,"playable":95.22523283537527,"score":95.22523283537527},"GB2-04":{"attempts":1,"playable":83.76473507318653,"score":83.76473507318653},"GB2-05":{"attempts":1,"playable":97.37478772900437,"score":97.37478772900437},"GB2-06":{"attempts":1,"playable":89.79353267729566,"score":89.79353267729566},"GB2-07":{"attempts":1,"playable":93.67556809558342,"score":93.67556809558342},"GB2-08":{"attempts":1,"playable":98.97459194360266,"score":98.97459194360266}},"medium":{"GB2-01":{"attempts":1,"playable":46.826719662367374,"score":46.826719662367374},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":32.157579623915815,"score":32.157579623915815},"GB2-04":{"attempts":1,"playable":41.48654071812786,"score":41.48654071812786},"GB2-05":{"attempts":1,"playable":19.50592326272738,"score":19.50592326272738},"GB2-06":{"attempts":1,"playable":77.10076872786667,"score":77.10076872786667},"GB2-07":{"attempts":1,"playable":71.99637118869325,"score":71.99637118869325},"GB2-08":{"attempts":1,"playable":84.09073881023504,"score":84.09073881023504}},"none":{"GB2-01":{"attempts":1,"playable":51.52824935385446,"score":51.52824935385446},"GB2-02":{"attempts":1,"playable":46.40124307156255,"score":46.40124307156255},"GB2-03":{"attempts":1,"playable":48.76578868799309,"score":48.76578868799309},"GB2-04":{"attempts":1,"playable":45.05717114428411,"score":45.05717114428411},"GB2-05":{"attempts":1,"playable":14.325838077964523,"score":14.325838077964523},"GB2-06":{"attempts":1,"playable":17.897865019018337,"score":17.897865019018337},"GB2-07":{"attempts":1,"playable":46.13211965466816,"score":46.13211965466816},"GB2-08":{"attempts":1,"playable":59.29801687698541,"score":59.29801687698541}}},"id":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:04:54Z","match_totals_all":{"draws":2127,"losses":3812,"wins":6325},"match_totals_tracks":{"highest":{"draws":316,"losses":187,"wins":3585},"medium":{"draws":935,"losses":1560,"wins":1593},"none":{"draws":876,"losses":2065,"wins":1147}},"model_slug":"claude-sonnet-5-5","official_rank_by_reasoning":{"highest":5,"medium":34,"none":41},"overall":{"max":98.97459194360266,"mean":61.68081730862078,"min":14.325838077964523},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.27950765645659,"GB2-02":95.76171266657369,"GB2-03":95.22523283537527,"GB2-04":83.76473507318653,"GB2-05":97.37478772900437,"GB2-06":89.79353267729566,"GB2-07":93.67556809558342,"GB2-08":98.97459194360266},"per_game_all":{"GB2-01":59.54482555755948,"GB2-02":61.693989529230976,"GB2-03":58.71620038242805,"GB2-04":56.76948231186617,"GB2-05":43.73551635656543,"GB2-06":61.59738880806021,"GB2-07":70.60135297964827,"GB2-08":80.7877825436077},"per_game_match_totals_all":{"GB2-01":{"draws":217,"losses":549,"wins":782},"GB2-02":{"draws":769,"losses":183,"wins":488},"GB2-03":{"draws":330,"losses":484,"wins":668},"GB2-04":{"draws":693,"losses":321,"wins":480},"GB2-05":{"draws":0,"losses":903,"wins":687},"GB2-06":{"draws":46,"losses":587,"wins":873},"GB2-07":{"draws":0,"losses":484,"wins":1106},"GB2-08":{"draws":72,"losses":301,"wins":1241}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":157,"losses":33,"wins":326},"GB2-02":{"draws":24,"losses":8,"wins":448},"GB2-03":{"draws":0,"losses":25,"wins":469},"GB2-04":{"draws":92,"losses":40,"wins":366},"GB2-05":{"draws":0,"losses":12,"wins":518},"GB2-06":{"draws":36,"losses":39,"wins":427},"GB2-07":{"draws":0,"losses":30,"wins":500},"GB2-08":{"draws":7,"losses":0,"wins":531}},"medium":{"GB2-01":{"draws":14,"losses":278,"wins":224},"GB2-02":{"draws":376,"losses":94,"wins":10},"GB2-03":{"draws":215,"losses":244,"wins":35},"GB2-04":{"draws":319,"losses":140,"wins":39},"GB2-05":{"draws":0,"losses":432,"wins":98},"GB2-06":{"draws":4,"losses":125,"wins":373},"GB2-07":{"draws":0,"losses":155,"wins":375},"GB2-08":{"draws":7,"losses":92,"wins":439}},"none":{"GB2-01":{"draws":46,"losses":238,"wins":232},"GB2-02":{"draws":369,"losses":81,"wins":30},"GB2-03":{"draws":115,"losses":215,"wins":164},"GB2-04":{"draws":282,"losses":141,"wins":75},"GB2-05":{"draws":0,"losses":459,"wins":71},"GB2-06":{"draws":6,"losses":423,"wins":73},"GB2-07":{"draws":0,"losses":299,"wins":231},"GB2-08":{"draws":58,"losses":209,"wins":271}}},"per_game_raw_elo_all":{"GB2-01":1575.0648983618369,"GB2-02":1662.6569383538408,"GB2-03":1636.4861251009204,"GB2-04":1550.9921841808448,"GB2-05":1534.5580920389236,"GB2-06":1661.0071229163095,"GB2-07":1835.0340504311487,"GB2-08":2071.903505900073},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1802.7304129960928,"GB2-02":2126.841377926183,"GB2-03":2222.738244640171,"GB2-04":1807.060781400131,"GB2-05":2705.2555975362725,"GB2-06":2169.818453410323,"GB2-07":2357.124000619623,"GB2-08":2727.826919616034},"medium":{"GB2-01":1438.8612826508222,"GB2-02":1417.117036832385,"GB2-03":1270.08724139915,"GB2-04":1409.1012818375616,"GB2-05":1000.8222691239494,"GB2-06":1888.0414076438453,"GB2-07":1748.7590517290957,"GB2-08":1977.172232451367},"none":{"GB2-01":1483.6029994385956,"GB2-02":1444.0124003029546,"GB2-03":1416.6328892634401,"GB2-04":1436.814489304842,"GB2-05":897.5964094565486,"GB2-06":925.1615076947598,"GB2-07":1399.219098944727,"GB2-08":1510.7113656328177}},"per_game_tracks":{"highest":{"GB2-01":80.27950765645659,"GB2-02":95.76171266657369,"GB2-03":95.22523283537527,"GB2-04":83.76473507318653,"GB2-05":97.37478772900437,"GB2-06":89.79353267729566,"GB2-07":93.67556809558342,"GB2-08":98.97459194360266},"medium":{"GB2-01":46.826719662367374,"GB2-02":42.91901284955672,"GB2-03":32.157579623915815,"GB2-04":41.48654071812786,"GB2-05":19.50592326272738,"GB2-06":77.10076872786667,"GB2-07":71.99637118869325,"GB2-08":84.09073881023504},"none":{"GB2-01":51.52824935385446,"GB2-02":46.40124307156255,"GB2-03":48.76578868799309,"GB2-04":45.05717114428411,"GB2-05":14.325838077964523,"GB2-06":17.897865019018337,"GB2-07":46.13211965466816,"GB2-08":59.29801687698541}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:31:22Z","reasoning":{"highest":91.85620858463477,"medium":52.01045685543626,"none":41.17578648579133},"reasoning_agg":{"highest":{"max":98.97459194360266,"mean":91.85620858463477,"min":80.27950765645659},"medium":{"max":84.09073881023504,"mean":52.01045685543626,"min":19.50592326272738},"none":{"max":59.29801687698541,"mean":41.17578648579133,"min":14.325838077964523}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":50.680422098843444},"working_program_strength":{"all":61.68081730862078,"highest":91.85620858463477,"medium":52.01045685543626,"none":41.17578648579133}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:8e3e5018c841df4d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.13107158333333335,"median":0.12371399999999999,"min":0.027072,"recorded_attempt_count":27,"run_count":24,"total":3.1457180000000005},"codegen_latency_ms":{"attempt_count":27,"max_ms":669574,"mean_ms":286694.0416666667,"min_ms":31621,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":669574,"mean_ms":551119.125,"min_ms":414817,"run_count":8},"medium":{"attempt_count":10,"max_ms":376458,"mean_ms":270365.25,"min_ms":196147,"run_count":8},"none":{"attempt_count":8,"max_ms":49571,"mean_ms":38597.75,"min_ms":31621,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":43739,"output_mean":18621.333333333332,"output_min":1925,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":43739,"output_mean":35745.125,"output_min":27954,"run_count":8},"medium":{"attempt_count":10,"output_max":24183,"output_mean":17614.25,"output_min":12541,"run_count":8},"none":{"attempt_count":8,"output_max":3323,"output_mean":2504.625,"output_min":1925,"run_count":8}},"display_name":"Grok 4.6","economics":{"all":60.944982134369006,"highest":65.95350517978456,"medium":71.59015827493185,"none":45.2912829483906},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":59.94503342585028,"score":59.94503342585028},"GB2-02":{"attempts":3,"playable":60.57910011033698,"score":60.57910011033698},"GB2-03":{"attempts":3,"playable":54.63231875003337,"score":54.63231875003337},"GB2-04":{"attempts":3,"playable":56.157210774593544,"score":56.157210774593544},"GB2-05":{"attempts":3,"playable":73.00127493996223,"score":73.00127493996223},"GB2-06":{"attempts":3,"playable":53.12628409404471,"score":53.12628409404471},"GB2-07":{"attempts":3,"playable":70.05180594138533,"score":70.05180594138533},"GB2-08":{"attempts":3,"playable":60.06682903874562,"score":60.06682903874562}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":50.55035802020542,"score":50.55035802020542},"GB2-02":{"attempts":1,"playable":83.29267891559549,"score":83.29267891559549},"GB2-03":{"attempts":1,"playable":51.73396848497532,"score":51.73396848497532},"GB2-04":{"attempts":1,"playable":60.19323896001715,"score":60.19323896001715},"GB2-05":{"attempts":1,"playable":85.00458172061191,"score":85.00458172061191},"GB2-06":{"attempts":1,"playable":65.97077248141947,"score":65.97077248141947},"GB2-07":{"attempts":1,"playable":75.99324424192072,"score":75.99324424192072},"GB2-08":{"attempts":1,"playable":54.88919861353103,"score":54.88919861353103}},"medium":{"GB2-01":{"attempts":1,"playable":62.51884491570073,"score":62.51884491570073},"GB2-02":{"attempts":1,"playable":54.57460291081705,"score":54.57460291081705},"GB2-03":{"attempts":1,"playable":67.42895798779823,"score":67.42895798779823},"GB2-04":{"attempts":1,"playable":65.36209942804454,"score":65.36209942804454},"GB2-05":{"attempts":1,"playable":82.74399611813354,"score":82.74399611813354},"GB2-06":{"attempts":1,"playable":79.73739120710323,"score":79.73739120710323},"GB2-07":{"attempts":1,"playable":76.51255334488603,"score":76.51255334488603},"GB2-08":{"attempts":1,"playable":83.84282028697147,"score":83.84282028697147}},"none":{"GB2-01":{"attempts":1,"playable":66.7658973416447,"score":66.7658973416447},"GB2-02":{"attempts":1,"playable":43.87001850459841,"score":43.87001850459841},"GB2-03":{"attempts":1,"playable":44.73402977732657,"score":44.73402977732657},"GB2-04":{"attempts":1,"playable":42.91629393571892,"score":42.91629393571892},"GB2-05":{"attempts":1,"playable":51.25524698114122,"score":51.25524698114122},"GB2-06":{"attempts":1,"playable":13.670688593611466,"score":13.670688593611466},"GB2-07":{"attempts":1,"playable":57.6496202373492,"score":57.6496202373492},"GB2-08":{"attempts":1,"playable":41.46846821573435,"score":41.46846821573435}}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-10-24T19:17:18Z","match_totals_all":{"draws":3043,"losses":3511,"wins":5709},"match_totals_tracks":{"highest":{"draws":874,"losses":1045,"wins":2168},"medium":{"draws":787,"losses":834,"wins":2467},"none":{"draws":1382,"losses":1632,"wins":1074}},"model_slug":"x-ai-grok-4-6","official_rank_by_reasoning":{"highest":24,"medium":11,"none":29},"overall":{"max":85.00458172061191,"mean":60.944982134369006,"min":13.670688593611466},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.55035802020542,"GB2-02":83.29267891559549,"GB2-03":51.73396848497532,"GB2-04":60.19323896001715,"GB2-05":85.00458172061191,"GB2-06":65.97077248141947,"GB2-07":75.99324424192072,"GB2-08":54.88919861353103},"per_game_all":{"GB2-01":59.94503342585028,"GB2-02":60.57910011033698,"GB2-03":54.63231875003337,"GB2-04":56.157210774593544,"GB2-05":73.00127493996223,"GB2-06":53.12628409404471,"GB2-07":70.05180594138533,"GB2-08":60.06682903874562},"per_game_match_totals_all":{"GB2-01":{"draws":444,"losses":431,"wins":673},"GB2-02":{"draws":745,"losses":216,"wins":478},"GB2-03":{"draws":590,"losses":434,"wins":458},"GB2-04":{"draws":835,"losses":263,"wins":396},"GB2-05":{"draws":0,"losses":450,"wins":1140},"GB2-06":{"draws":54,"losses":718,"wins":734},"GB2-07":{"draws":0,"losses":497,"wins":1093},"GB2-08":{"draws":375,"losses":502,"wins":737}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":252,"losses":140,"wins":124},"GB2-02":{"draws":67,"losses":51,"wins":361},"GB2-03":{"draws":102,"losses":207,"wins":185},"GB2-04":{"draws":272,"losses":71,"wins":155},"GB2-05":{"draws":0,"losses":85,"wins":445},"GB2-06":{"draws":34,"losses":171,"wins":297},"GB2-07":{"draws":0,"losses":132,"wins":398},"GB2-08":{"draws":147,"losses":188,"wins":203}},"medium":{"GB2-01":{"draws":131,"losses":139,"wins":246},"GB2-02":{"draws":301,"losses":76,"wins":103},"GB2-03":{"draws":94,"losses":132,"wins":268},"GB2-04":{"draws":248,"losses":57,"wins":193},"GB2-05":{"draws":0,"losses":98,"wins":432},"GB2-06":{"draws":13,"losses":106,"wins":383},"GB2-07":{"draws":0,"losses":129,"wins":401},"GB2-08":{"draws":0,"losses":97,"wins":441}},"none":{"GB2-01":{"draws":61,"losses":152,"wins":303},"GB2-02":{"draws":377,"losses":89,"wins":14},"GB2-03":{"draws":394,"losses":95,"wins":5},"GB2-04":{"draws":315,"losses":135,"wins":48},"GB2-05":{"draws":0,"losses":267,"wins":263},"GB2-06":{"draws":7,"losses":441,"wins":54},"GB2-07":{"draws":0,"losses":236,"wins":294},"GB2-08":{"draws":228,"losses":217,"wins":93}}},"per_game_raw_elo_all":{"GB2-01":1567.168261411517,"GB2-02":1577.7475154089936,"GB2-03":1473.493663637352,"GB2-04":1525.6065568479753,"GB2-05":1834.0720364046763,"GB2-06":1489.8987162632013,"GB2-07":1728.7536613981777,"GB2-08":1574.834600612861},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1474.2792447247443,"GB2-02":1801.2311589068277,"GB2-03":1442.8140827080117,"GB2-04":1556.1310632559102,"GB2-05":2059.5954080734778,"GB2-06":1681.9662899405555,"GB2-07":1816.0375123763517,"GB2-08":1452.9217103722087},"medium":{"GB2-01":1591.3698976991986,"GB2-02":1507.5309720358628,"GB2-03":1596.1313554052444,"GB2-04":1600.4529718801668,"GB2-05":1989.6528337676345,"GB2-06":1940.1477049773132,"GB2-07":1825.368732699769,"GB2-08":1970.9633600530583},"none":{"GB2-01":1635.8556418106084,"GB2-02":1424.4804152842908,"GB2-03":1381.535552798799,"GB2-04":1420.2356354078493,"GB2-05":1452.9678673729168,"GB2-06":847.5821538717355,"GB2-07":1544.8547391184122,"GB2-08":1300.6187314133158}},"per_game_tracks":{"highest":{"GB2-01":50.55035802020542,"GB2-02":83.29267891559549,"GB2-03":51.73396848497532,"GB2-04":60.19323896001715,"GB2-05":85.00458172061191,"GB2-06":65.97077248141947,"GB2-07":75.99324424192072,"GB2-08":54.88919861353103},"medium":{"GB2-01":62.51884491570073,"GB2-02":54.57460291081705,"GB2-03":67.42895798779823,"GB2-04":65.36209942804454,"GB2-05":82.74399611813354,"GB2-06":79.73739120710323,"GB2-07":76.51255334488603,"GB2-08":83.84282028697147},"none":{"GB2-01":66.7658973416447,"GB2-02":43.87001850459841,"GB2-03":44.73402977732657,"GB2-04":42.91629393571892,"GB2-05":51.25524698114122,"GB2-06":13.670688593611466,"GB2-07":57.6496202373492,"GB2-08":41.46846821573435}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:30:31Z","reasoning":{"highest":65.95350517978456,"medium":71.59015827493185,"none":45.2912829483906},"reasoning_agg":{"highest":{"max":85.00458172061191,"mean":65.95350517978456,"min":50.55035802020542},"medium":{"max":83.84282028697147,"mean":71.59015827493185,"min":54.57460291081705},"none":{"max":66.7658973416447,"mean":45.2912829483906,"min":13.670688593611466}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":26.29887532654125},"working_program_strength":{"all":60.944982134369006,"highest":65.95350517978456,"medium":71.59015827493185,"none":45.2912829483906}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:b8343a8c4f242bb9","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":0.5746151281850016},"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":1.97564625},"codegen_output_tokens":{"attempt_count":25,"output_max":73160,"output_mean":20095.833333333332,"output_min":1712,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":73160,"output_mean":40784.875,"output_min":28671,"run_count":8},"medium":{"attempt_count":8,"output_max":31721,"output_mean":16792.0,"output_min":5265,"run_count":8},"none":{"attempt_count":8,"output_max":3473,"output_mean":2710.625,"output_min":1712,"run_count":8}},"display_name":"Gemini 3.8 Flash","economics":{"all":60.729651613409295,"highest":66.01127712716996,"medium":60.68951104757495,"none":55.48816666548297},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":61.070928709820436,"score":61.070928709820436},"GB2-02":{"attempts":3,"playable":50.22140022135065,"score":50.22140022135065},"GB2-03":{"attempts":3,"playable":68.86649697957102,"score":68.86649697957102},"GB2-04":{"attempts":3,"playable":51.08168503866966,"score":51.08168503866966},"GB2-05":{"attempts":3,"playable":59.305524275612356,"score":59.305524275612356},"GB2-06":{"attempts":3,"playable":80.39611633269293,"score":80.39611633269293},"GB2-07":{"attempts":3,"playable":56.66104758923617,"score":56.66104758923617},"GB2-08":{"attempts":3,"playable":58.23401376032115,"score":58.23401376032115}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.431416699974676,"score":55.431416699974676},"GB2-02":{"attempts":1,"playable":69.80147050514735,"score":69.80147050514735},"GB2-03":{"attempts":1,"playable":70.786808220575,"score":70.786808220575},"GB2-04":{"attempts":1,"playable":46.481805880558724,"score":46.481805880558724},"GB2-05":{"attempts":1,"playable":67.19039459119736,"score":67.19039459119736},"GB2-06":{"attempts":1,"playable":88.62485830618898,"score":88.62485830618898},"GB2-07":{"attempts":1,"playable":69.548740928269,"score":69.548740928269},"GB2-08":{"attempts":1,"playable":60.22472188544856,"score":60.22472188544856}},"medium":{"GB2-01":{"attempts":1,"playable":71.18164857121542,"score":71.18164857121542},"GB2-02":{"attempts":1,"playable":40.06041394087035,"score":40.06041394087035},"GB2-03":{"attempts":1,"playable":84.58863002997235,"score":84.58863002997235},"GB2-04":{"attempts":1,"playable":60.89173791398878,"score":60.89173791398878},"GB2-05":{"attempts":1,"playable":55.07708699776691,"score":55.07708699776691},"GB2-06":{"attempts":1,"playable":79.1009853822152,"score":79.1009853822152},"GB2-07":{"attempts":1,"playable":57.4694310894711,"score":57.4694310894711},"GB2-08":{"attempts":1,"playable":37.14615445509959,"score":37.14615445509959}},"none":{"GB2-01":{"attempts":1,"playable":56.59972085827122,"score":56.59972085827122},"GB2-02":{"attempts":1,"playable":40.80231621803426,"score":40.80231621803426},"GB2-03":{"attempts":1,"playable":51.22405268816572,"score":51.22405268816572},"GB2-04":{"attempts":1,"playable":45.87151132146148,"score":45.87151132146148},"GB2-05":{"attempts":1,"playable":55.64909123787278,"score":55.64909123787278},"GB2-06":{"attempts":1,"playable":73.46250530967461,"score":73.46250530967461},"GB2-07":{"attempts":1,"playable":42.964970749968394,"score":42.964970749968394},"GB2-08":{"attempts":1,"playable":77.33116494041529,"score":77.33116494041529}}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T19:13:27Z","match_totals_all":{"draws":2516,"losses":3827,"wins":5921},"match_totals_tracks":{"highest":{"draws":457,"losses":1250,"wins":2381},"medium":{"draws":1064,"losses":1166,"wins":1858},"none":{"draws":995,"losses":1411,"wins":1682}},"model_slug":"google-gemini-3-8-flash","official_rank_by_reasoning":{"highest":23,"medium":21,"none":15},"overall":{"max":88.62485830618898,"mean":60.729651613409295,"min":37.14615445509959},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.431416699974676,"GB2-02":69.80147050514735,"GB2-03":70.786808220575,"GB2-04":46.481805880558724,"GB2-05":67.19039459119736,"GB2-06":88.62485830618898,"GB2-07":69.548740928269,"GB2-08":60.22472188544856},"per_game_all":{"GB2-01":61.070928709820436,"GB2-02":50.22140022135065,"GB2-03":68.86649697957102,"GB2-04":51.08168503866966,"GB2-05":59.305524275612356,"GB2-06":80.39611633269293,"GB2-07":56.66104758923617,"GB2-08":58.23401376032115},"per_game_match_totals_all":{"GB2-01":{"draws":317,"losses":477,"wins":754},"GB2-02":{"draws":934,"losses":273,"wins":233},"GB2-03":{"draws":189,"losses":414,"wins":879},"GB2-04":{"draws":699,"losses":407,"wins":388},"GB2-05":{"draws":0,"losses":674,"wins":916},"GB2-06":{"draws":51,"losses":301,"wins":1154},"GB2-07":{"draws":0,"losses":722,"wins":868},"GB2-08":{"draws":326,"losses":559,"wins":729}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":46,"losses":218,"wins":252},"GB2-02":{"draws":195,"losses":55,"wins":230},"GB2-03":{"draws":7,"losses":158,"wins":329},"GB2-04":{"draws":90,"losses":230,"wins":178},"GB2-05":{"draws":0,"losses":183,"wins":347},"GB2-06":{"draws":29,"losses":49,"wins":424},"GB2-07":{"draws":0,"losses":169,"wins":361},"GB2-08":{"draws":90,"losses":188,"wins":260}},"medium":{"GB2-01":{"draws":77,"losses":121,"wins":318},"GB2-02":{"draws":365,"losses":113,"wins":2},"GB2-03":{"draws":97,"losses":38,"wins":359},"GB2-04":{"draws":301,"losses":53,"wins":144},"GB2-05":{"draws":0,"losses":247,"wins":283},"GB2-06":{"draws":8,"losses":112,"wins":382},"GB2-07":{"draws":0,"losses":237,"wins":293},"GB2-08":{"draws":216,"losses":245,"wins":77}},"none":{"GB2-01":{"draws":194,"losses":138,"wins":184},"GB2-02":{"draws":374,"losses":105,"wins":1},"GB2-03":{"draws":85,"losses":218,"wins":191},"GB2-04":{"draws":308,"losses":124,"wins":66},"GB2-05":{"draws":0,"losses":244,"wins":286},"GB2-06":{"draws":14,"losses":140,"wins":348},"GB2-07":{"draws":0,"losses":316,"wins":214},"GB2-08":{"draws":20,"losses":126,"wins":392}}},"per_game_raw_elo_all":{"GB2-01":1579.536242287438,"GB2-02":1478.1479971900199,"GB2-03":1642.531785869096,"GB2-04":1484.2883151506446,"GB2-05":1558.9952135350977,"GB2-06":1961.432059371629,"GB2-07":1537.6737517450777,"GB2-08":1533.529505045836},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1521.0901878578472,"GB2-02":1638.9835947721772,"GB2-03":1635.146855806305,"GB2-04":1447.8128072735615,"GB2-05":1667.741746168598,"GB2-06":2138.4168144879923,"GB2-07":1710.6615145054095,"GB2-08":1523.58416647196},"medium":{"GB2-01":1685.0824986008504,"GB2-02":1394.8226749637631,"GB2-03":1854.1635380926596,"GB2-04":1561.9491302662261,"GB2-05":1500.9805398499777,"GB2-06":1927.4121127174935,"GB2-07":1542.5056812302485,"GB2-08":1255.2553655614633},"none":{"GB2-01":1532.4360404036165,"GB2-02":1400.6377218341197,"GB2-03":1438.2849637083232,"GB2-04":1443.1030079121458,"GB2-05":1508.263354586718,"GB2-06":1818.4672509094014,"GB2-07":1359.854059499575,"GB2-08":1821.7489831040841}},"per_game_tracks":{"highest":{"GB2-01":55.431416699974676,"GB2-02":69.80147050514735,"GB2-03":70.786808220575,"GB2-04":46.481805880558724,"GB2-05":67.19039459119736,"GB2-06":88.62485830618898,"GB2-07":69.548740928269,"GB2-08":60.22472188544856},"medium":{"GB2-01":71.18164857121542,"GB2-02":40.06041394087035,"GB2-03":84.58863002997235,"GB2-04":60.89173791398878,"GB2-05":55.07708699776691,"GB2-06":79.1009853822152,"GB2-07":57.4694310894711,"GB2-08":37.14615445509959},"none":{"GB2-01":56.59972085827122,"GB2-02":40.80231621803426,"GB2-03":51.22405268816572,"GB2-04":45.87151132146148,"GB2-05":55.64909123787278,"GB2-06":73.46250530967461,"GB2-07":42.964970749968394,"GB2-08":77.33116494041529}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:21:52Z","reasoning":{"highest":66.01127712716996,"medium":60.68951104757495,"none":55.48816666548297},"reasoning_agg":{"highest":{"max":88.62485830618898,"mean":66.01127712716996,"min":46.481805880558724},"medium":{"max":84.58863002997235,"mean":60.68951104757495,"min":37.14615445509959},"none":{"max":77.33116494041529,"mean":55.48816666548297,"min":40.80231621803426}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.52311046168699},"working_program_strength":{"all":60.729651613409295,"highest":66.01127712716996,"medium":60.68951104757495,"none":55.48816666548297}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:07660eac5f818c9a","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":0.41740124999999995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975000000002},"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":1.9894712499999998}},"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":2.59798225},"codegen_latency_ms":{"attempt_count":27,"max_ms":344702,"mean_ms":125679.0,"min_ms":18724,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":344702,"mean_ms":258574.75,"min_ms":141477,"run_count":8},"medium":{"attempt_count":8,"max_ms":148027,"mean_ms":92816.75,"min_ms":70623,"run_count":8},"none":{"attempt_count":9,"max_ms":39588,"mean_ms":25645.5,"min_ms":18724,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":82251,"output_mean":22811.583333333332,"output_min":2043,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":82251,"output_mean":55365.125,"output_min":27171,"run_count":8},"medium":{"attempt_count":8,"output_max":15366,"output_mean":10008.75,"output_min":7655,"run_count":8},"none":{"attempt_count":9,"output_max":5638,"output_mean":3060.875,"output_min":2043,"run_count":8}},"display_name":"Muse Spark 1.3","economics":{"all":59.73437194273961,"highest":70.94241017754064,"medium":66.75146520107162,"none":41.509240449606544},"economics_best_value":{"per_model":{"medium":true}},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.56796548887031,"score":59.56796548887031},"GB2-02":{"attempts":3,"playable":56.001384488092675,"score":56.001384488092675},"GB2-03":{"attempts":3,"playable":67.29688074736718,"score":67.29688074736718},"GB2-04":{"attempts":3,"playable":52.914052291520825,"score":52.914052291520825},"GB2-05":{"attempts":3,"playable":59.962892181568,"score":59.962892181568},"GB2-06":{"attempts":3,"playable":69.40052498170442,"score":69.40052498170442},"GB2-07":{"attempts":3,"playable":50.278805570343174,"score":50.278805570343174},"GB2-08":{"attempts":3,"playable":62.45246979245017,"score":62.45246979245017}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.79692199807486,"score":76.79692199807486},"GB2-02":{"attempts":1,"playable":62.85797993351466,"score":62.85797993351466},"GB2-03":{"attempts":1,"playable":83.16608038694694,"score":83.16608038694694},"GB2-04":{"attempts":1,"playable":51.349114684283556,"score":51.349114684283556},"GB2-05":{"attempts":1,"playable":79.36413717655897,"score":79.36413717655897},"GB2-06":{"attempts":1,"playable":84.734745938481,"score":84.734745938481},"GB2-07":{"attempts":1,"playable":58.18969892496987,"score":58.18969892496987},"GB2-08":{"attempts":1,"playable":71.08060237749517,"score":71.08060237749517}},"medium":{"GB2-01":{"attempts":1,"playable":75.09074857030564,"score":75.09074857030564},"GB2-02":{"attempts":1,"playable":57.79758453520385,"score":57.79758453520385},"GB2-03":{"attempts":1,"playable":63.24144946762152,"score":63.24144946762152},"GB2-04":{"attempts":1,"playable":64.27265832281395,"score":64.27265832281395},"GB2-05":{"attempts":1,"playable":59.45300217683459,"score":59.45300217683459},"GB2-06":{"attempts":1,"playable":81.8281986280816,"score":81.8281986280816},"GB2-07":{"attempts":1,"playable":54.57515492922831,"score":54.57515492922831},"GB2-08":{"attempts":1,"playable":77.75292497848348,"score":77.75292497848348}},"none":{"GB2-01":{"attempts":1,"playable":26.816225898230446,"score":26.816225898230446},"GB2-02":{"attempts":1,"playable":47.348588995559524,"score":47.348588995559524},"GB2-03":{"attempts":1,"playable":55.483112387533076,"score":55.483112387533076},"GB2-04":{"attempts":1,"playable":43.120383867464966,"score":43.120383867464966},"GB2-05":{"attempts":1,"playable":41.07153719131046,"score":41.07153719131046},"GB2-06":{"attempts":1,"playable":41.63863037855069,"score":41.63863037855069},"GB2-07":{"attempts":1,"playable":38.071562856831356,"score":38.071562856831356},"GB2-08":{"attempts":1,"playable":38.52388202137185,"score":38.52388202137185}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-10-24T19:02:08Z","match_totals_all":{"draws":2257,"losses":4091,"wins":5916},"match_totals_tracks":{"highest":{"draws":529,"losses":1005,"wins":2554},"medium":{"draws":625,"losses":1136,"wins":2327},"none":{"draws":1103,"losses":1950,"wins":1035}},"model_slug":"meta-muse-spark-1-3","official_rank_by_reasoning":{"highest":16,"medium":13,"none":39},"overall":{"max":84.734745938481,"mean":59.73437194273961,"min":26.816225898230446},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.79692199807486,"GB2-02":62.85797993351466,"GB2-03":83.16608038694694,"GB2-04":51.349114684283556,"GB2-05":79.36413717655897,"GB2-06":84.734745938481,"GB2-07":58.18969892496987,"GB2-08":71.08060237749517},"per_game_all":{"GB2-01":59.56796548887031,"GB2-02":56.001384488092675,"GB2-03":67.29688074736718,"GB2-04":52.914052291520825,"GB2-05":59.962892181568,"GB2-06":69.40052498170442,"GB2-07":50.278805570343174,"GB2-08":62.45246979245017},"per_game_match_totals_all":{"GB2-01":{"draws":104,"losses":603,"wins":841},"GB2-02":{"draws":935,"losses":191,"wins":314},"GB2-03":{"draws":179,"losses":445,"wins":858},"GB2-04":{"draws":660,"losses":399,"wins":435},"GB2-05":{"draws":0,"losses":661,"wins":929},"GB2-06":{"draws":63,"losses":470,"wins":973},"GB2-07":{"draws":0,"losses":828,"wins":762},"GB2-08":{"draws":316,"losses":494,"wins":804}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":128,"wins":384},"GB2-02":{"draws":269,"losses":52,"wins":159},"GB2-03":{"draws":37,"losses":76,"wins":381},"GB2-04":{"draws":132,"losses":185,"wins":181},"GB2-05":{"draws":0,"losses":117,"wins":413},"GB2-06":{"draws":36,"losses":67,"wins":399},"GB2-07":{"draws":0,"losses":233,"wins":297},"GB2-08":{"draws":51,"losses":147,"wins":340}},"medium":{"GB2-01":{"draws":0,"losses":139,"wins":377},"GB2-02":{"draws":302,"losses":60,"wins":118},"GB2-03":{"draws":59,"losses":171,"wins":264},"GB2-04":{"draws":247,"losses":63,"wins":188},"GB2-05":{"draws":0,"losses":224,"wins":306},"GB2-06":{"draws":12,"losses":95,"wins":395},"GB2-07":{"draws":0,"losses":253,"wins":277},"GB2-08":{"draws":5,"losses":131,"wins":402}},"none":{"GB2-01":{"draws":100,"losses":336,"wins":80},"GB2-02":{"draws":364,"losses":79,"wins":37},"GB2-03":{"draws":83,"losses":198,"wins":213},"GB2-04":{"draws":281,"losses":151,"wins":66},"GB2-05":{"draws":0,"losses":320,"wins":210},"GB2-06":{"draws":15,"losses":308,"wins":179},"GB2-07":{"draws":0,"losses":342,"wins":188},"GB2-08":{"draws":260,"losses":216,"wins":62}}},"per_game_raw_elo_all":{"GB2-01":1574.2763876997014,"GB2-02":1520.0701135728716,"GB2-03":1617.5511770390724,"GB2-04":1499.374302506979,"GB2-05":1594.278781934038,"GB2-06":1773.3423169720256,"GB2-07":1451.8686740110068,"GB2-08":1599.5516588032376},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1754.271527547111,"GB2-02":1575.5630641220496,"GB2-03":1824.4978623654088,"GB2-04":1485.4598238633628,"GB2-05":1899.7558058863815,"GB2-06":2045.3487155341793,"GB2-07":1551.915763318257,"GB2-08":1698.2698313128},"medium":{"GB2-01":1732.2651083119972,"GB2-02":1533.3336042551318,"GB2-03":1551.4928732605044,"GB2-04":1590.8428820832087,"GB2-05":1557.7286468155671,"GB2-06":1982.876629248204,"GB2-07":1505.187392174844,"GB2-08":1830.7266180589972},"none":{"GB2-01":1236.2925272399957,"GB2-02":1451.3136723414332,"GB2-03":1476.6627954913042,"GB2-04":1421.8202015743657,"GB2-05":1325.351893100165,"GB2-06":1291.801606133694,"GB2-07":1298.5028665399188,"GB2-08":1269.6585270379153}},"per_game_tracks":{"highest":{"GB2-01":76.79692199807486,"GB2-02":62.85797993351466,"GB2-03":83.16608038694694,"GB2-04":51.349114684283556,"GB2-05":79.36413717655897,"GB2-06":84.734745938481,"GB2-07":58.18969892496987,"GB2-08":71.08060237749517},"medium":{"GB2-01":75.09074857030564,"GB2-02":57.79758453520385,"GB2-03":63.24144946762152,"GB2-04":64.27265832281395,"GB2-05":59.45300217683459,"GB2-06":81.8281986280816,"GB2-07":54.57515492922831,"GB2-08":77.75292497848348},"none":{"GB2-01":26.816225898230446,"GB2-02":47.348588995559524,"GB2-03":55.483112387533076,"GB2-04":43.120383867464966,"GB2-05":41.07153719131046,"GB2-06":41.63863037855069,"GB2-07":38.071562856831356,"GB2-08":38.52388202137185}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:00:07Z","reasoning":{"highest":70.94241017754064,"medium":66.75146520107162,"none":41.509240449606544},"reasoning_agg":{"highest":{"max":84.734745938481,"mean":70.94241017754064,"min":51.349114684283556},"medium":{"max":81.8281986280816,"mean":66.75146520107162,"min":54.57515492922831},"none":{"max":55.483112387533076,"mean":41.509240449606544,"min":26.816225898230446}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.433169727934093},"working_program_strength":{"all":59.73437194273961,"highest":70.94241017754064,"medium":66.75146520107162,"none":41.509240449606544}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-open:49b386635d2620f4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.10417243749999998,"median":0.11212245,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":8,"run_count":8,"total":0.8333794999999999},"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":0.33876985},"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":0.22147360000000002}},"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":0.33876985},"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":0.22147360000000002},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.10417243749999998,"median":0.11212245,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":8,"run_count":8,"total":0.8333795}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.05806762291666667,"median":0.032108575,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":27,"run_count":24,"total":1.3936229499999997},"codegen_latency_ms":{"attempt_count":26,"max_ms":402561,"mean_ms":134621.65217391305,"min_ms":29772,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":7,"max_ms":402561,"mean_ms":285010.28571428574,"min_ms":177131,"run_count":7},"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":11455.5,"output_min":2743,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":34389,"output_mean":23554.125,"output_min":8453,"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":58.29942882965514,"highest":63.63397353452956,"medium":54.98167781556992,"none":56.28263513886594},"economics_best_value":{"per_model":{"none":true}},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[943718],"finish_reason_observations":26,"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":[943718],"total_output_tokens":274932,"total_reasoning_output_tokens":170578,"total_visible_output_tokens":104354,"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":"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":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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":7,"evaluated_cells":7,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"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_excluded_game_aliases":["GB2-02"],"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":69.59053473709328,"score":69.59053473709328},"GB2-02":{"attempts":2,"playable":44.98548814948998,"score":44.98548814948998},"GB2-03":{"attempts":3,"playable":52.822554704093164,"score":52.822554704093164},"GB2-04":{"attempts":3,"playable":44.473596560275325,"score":44.473596560275325},"GB2-05":{"attempts":3,"playable":52.18431393516722,"score":52.18431393516722},"GB2-06":{"attempts":3,"playable":63.02893498580992,"score":63.02893498580992},"GB2-07":{"attempts":3,"playable":54.82070367380464,"score":54.82070367380464},"GB2-08":{"attempts":3,"playable":78.2731420964944,"score":78.2731420964944}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":92.30642018956263,"score":92.30642018956263},"GB2-03":{"attempts":1,"playable":67.71859696082454,"score":67.71859696082454},"GB2-04":{"attempts":1,"playable":39.4407359106655,"score":39.4407359106655},"GB2-05":{"attempts":1,"playable":40.68614877540387,"score":40.68614877540387},"GB2-06":{"attempts":1,"playable":50.006072961364325,"score":50.006072961364325},"GB2-07":{"attempts":1,"playable":74.258958335622,"score":74.258958335622},"GB2-08":{"attempts":1,"playable":81.02088160826408,"score":81.02088160826408}},"medium":{"GB2-01":{"attempts":1,"playable":51.723727143498564,"score":51.723727143498564},"GB2-02":{"attempts":1,"playable":44.39793855579591,"score":44.39793855579591},"GB2-03":{"attempts":1,"playable":33.65815029918553,"score":33.65815029918553},"GB2-04":{"attempts":1,"playable":47.29490538890763,"score":47.29490538890763},"GB2-05":{"attempts":1,"playable":57.55316637011255,"score":57.55316637011255},"GB2-06":{"attempts":1,"playable":77.63500626973475,"score":77.63500626973475},"GB2-07":{"attempts":1,"playable":57.4694310894711,"score":57.4694310894711},"GB2-08":{"attempts":1,"playable":70.12109740785326,"score":70.12109740785326}},"none":{"GB2-01":{"attempts":1,"playable":64.74145687821866,"score":64.74145687821866},"GB2-02":{"attempts":1,"playable":45.57303774318406,"score":45.57303774318406},"GB2-03":{"attempts":1,"playable":57.09091685226942,"score":57.09091685226942},"GB2-04":{"attempts":1,"playable":46.68514838125286,"score":46.68514838125286},"GB2-05":{"attempts":1,"playable":58.31362665998524,"score":58.31362665998524},"GB2-06":{"attempts":1,"playable":61.4457257263307,"score":61.4457257263307},"GB2-07":{"attempts":1,"playable":32.733721596320805,"score":32.733721596320805},"GB2-08":{"attempts":1,"playable":83.67744727336586,"score":83.67744727336586}}},"id":"meta/muse-spark-open","is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:55Z","match_totals_all":{"draws":2129,"losses":4120,"wins":5533},"match_totals_tracks":{"highest":{"draws":344,"losses":1211,"wins":2053},"medium":{"draws":971,"losses":1438,"wins":1678},"none":{"draws":814,"losses":1471,"wins":1802}},"model_slug":"meta-muse-spark-open","official_rank_by_reasoning":{"medium":28,"none":14},"overall":{"max":92.30642018956263,"mean":58.29942882965514,"min":32.733721596320805},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":19,"overall_ranking_status":"partial","per_game":{"GB2-01":92.30642018956263,"GB2-03":67.71859696082454,"GB2-04":39.4407359106655,"GB2-05":40.68614877540387,"GB2-06":50.006072961364325,"GB2-07":74.258958335622,"GB2-08":81.02088160826408},"per_game_all":{"GB2-01":69.59053473709328,"GB2-03":52.822554704093164,"GB2-04":44.473596560275325,"GB2-05":52.18431393516722,"GB2-06":63.02893498580992,"GB2-07":54.82070367380464,"GB2-08":78.2731420964944},"per_game_match_totals_all":{"GB2-01":{"draws":200,"losses":398,"wins":950},"GB2-02":{"draws":708,"losses":190,"wins":61},"GB2-03":{"draws":297,"losses":605,"wins":580},"GB2-04":{"draws":879,"losses":415,"wins":200},"GB2-05":{"draws":0,"losses":786,"wins":804},"GB2-06":{"draws":45,"losses":587,"wins":873},"GB2-07":{"draws":0,"losses":749,"wins":841},"GB2-08":{"draws":0,"losses":390,"wins":1224}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":45,"wins":471},"GB2-03":{"draws":59,"losses":148,"wins":287},"GB2-04":{"draws":267,"losses":176,"wins":55},"GB2-05":{"draws":0,"losses":322,"wins":208},"GB2-06":{"draws":18,"losses":264,"wins":220},"GB2-07":{"draws":0,"losses":142,"wins":388},"GB2-08":{"draws":0,"losses":114,"wins":424}},"medium":{"GB2-01":{"draws":126,"losses":197,"wins":193},"GB2-02":{"draws":360,"losses":95,"wins":25},"GB2-03":{"draws":135,"losses":277,"wins":82},"GB2-04":{"draws":326,"losses":108,"wins":64},"GB2-05":{"draws":0,"losses":234,"wins":296},"GB2-06":{"draws":24,"losses":112,"wins":365},"GB2-07":{"draws":0,"losses":237,"wins":293},"GB2-08":{"draws":0,"losses":178,"wins":360}},"none":{"GB2-01":{"draws":74,"losses":156,"wins":286},"GB2-02":{"draws":348,"losses":95,"wins":36},"GB2-03":{"draws":103,"losses":180,"wins":211},"GB2-04":{"draws":286,"losses":131,"wins":81},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":3,"losses":211,"wins":288},"GB2-07":{"draws":0,"losses":370,"wins":160},"GB2-08":{"draws":0,"losses":98,"wins":440}}},"per_game_raw_elo_all":{"GB2-01":1716.0596986908502,"GB2-03":1458.275028484558,"GB2-04":1432.1681002279581,"GB2-05":1465.2865488594532,"GB2-06":1640.7073944786773,"GB2-07":1519.3356439993233,"GB2-08":1850.3409424107751},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2048.3484897589897,"GB2-03":1599.3700029341435,"GB2-04":1393.036107119621,"GB2-05":1320.3948206853097,"GB2-06":1419.7018142211114,"GB2-07":1785.9392151995444,"GB2-08":1903.3125077916886},"medium":{"GB2-01":1485.4691301907546,"GB2-02":1428.5603177629207,"GB2-03":1283.9053226921492,"GB2-04":1454.0864295199099,"GB2-05":1532.7714060011447,"GB2-06":1898.4678224029115,"GB2-07":1542.5056812302485,"GB2-08":1680.8623066256919},"none":{"GB2-01":1614.3614761228055,"GB2-02":1437.6281363019727,"GB2-03":1491.5497598273819,"GB2-04":1449.3817640443433,"GB2-05":1542.6934198919057,"GB2-06":1603.952546812009,"GB2-07":1229.5620355681772,"GB2-08":1966.8480128149452}},"per_game_tracks":{"highest":{"GB2-01":92.30642018956263,"GB2-03":67.71859696082454,"GB2-04":39.4407359106655,"GB2-05":40.68614877540387,"GB2-06":50.006072961364325,"GB2-07":74.258958335622,"GB2-08":81.02088160826408},"medium":{"GB2-01":51.723727143498564,"GB2-02":44.39793855579591,"GB2-03":33.65815029918553,"GB2-04":47.29490538890763,"GB2-05":57.55316637011255,"GB2-06":77.63500626973475,"GB2-07":57.4694310894711,"GB2-08":70.12109740785326},"none":{"GB2-01":64.74145687821866,"GB2-02":45.57303774318406,"GB2-03":57.09091685226942,"GB2-04":46.68514838125286,"GB2-05":58.31362665998524,"GB2-06":61.4457257263307,"GB2-07":32.733721596320805,"GB2-08":83.67744727336586}},"program_outcomes":{"all":{"counted_attempts":23,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":20,"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":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":63.63397353452956,"medium":54.98167781556992,"none":56.28263513886594},"reasoning_agg":{"highest":{"max":92.30642018956263,"mean":63.63397353452956,"min":39.4407359106655},"medium":{"max":77.63500626973475,"mean":54.98167781556992,"min":33.65815029918553},"none":{"max":83.67744727336586,"mean":56.28263513886594,"min":32.733721596320805}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.652295718959643},"working_program_strength":{"all":58.29942882965514,"highest":63.63397353452956,"medium":54.98167781556992,"none":56.28263513886594}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:16749021a47b42c6","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":0.5964052},"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":1.6998543999999995},"codegen_latency_ms":{"attempt_count":34,"max_ms":187781,"mean_ms":106806.625,"min_ms":66051,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":187781,"mean_ms":116991.125,"min_ms":74353,"run_count":8},"medium":{"attempt_count":9,"max_ms":137371,"mean_ms":104700.625,"min_ms":79776,"run_count":8},"none":{"attempt_count":14,"max_ms":128385,"mean_ms":98728.125,"min_ms":66051,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":15570,"output_mean":7807.958333333333,"output_min":4284,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":15570,"output_mean":8557.875,"output_min":4867,"run_count":8},"medium":{"attempt_count":9,"output_max":9385,"output_mean":7450.25,"output_min":5674,"run_count":8},"none":{"attempt_count":14,"output_max":10165,"output_mean":7415.75,"output_min":4284,"run_count":8}},"display_name":"Grok 4.5","economics":{"all":58.17139978404203,"highest":63.54400243156745,"medium":61.759007146641245,"none":49.211189773917404},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":73.35565185695744,"score":73.35565185695744},"GB2-02":{"attempts":3,"playable":51.83241822489887,"score":51.83241822489887},"GB2-03":{"attempts":3,"playable":39.33300080462233,"score":39.33300080462233},"GB2-04":{"attempts":3,"playable":43.256125163846185,"score":43.256125163846185},"GB2-05":{"attempts":3,"playable":61.29663083034052,"score":61.29663083034052},"GB2-06":{"attempts":3,"playable":47.6224203348223,"score":47.6224203348223},"GB2-07":{"attempts":3,"playable":61.496683366109714,"score":61.496683366109714},"GB2-08":{"attempts":3,"playable":87.17826769073895,"score":87.17826769073895}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":83.71921728723662,"score":83.71921728723662},"GB2-02":{"attempts":1,"playable":59.35129587161831,"score":59.35129587161831},"GB2-03":{"attempts":1,"playable":45.66846375602359,"score":45.66846375602359},"GB2-04":{"attempts":1,"playable":44.34405872322509,"score":44.34405872322509},"GB2-05":{"attempts":1,"playable":73.70690782137578,"score":73.70690782137578},"GB2-06":{"attempts":1,"playable":54.597929343275354,"score":54.597929343275354},"GB2-07":{"attempts":1,"playable":56.567254552745226,"score":56.567254552745226},"GB2-08":{"attempts":1,"playable":90.39689209703965,"score":90.39689209703965}},"medium":{"GB2-01":{"attempts":1,"playable":83.90363175169728,"score":83.90363175169728},"GB2-02":{"attempts":1,"playable":52.48719210835273,"score":52.48719210835273},"GB2-03":{"attempts":1,"playable":56.58936304738873,"score":56.58936304738873},"GB2-04":{"attempts":1,"playable":42.61008302835759,"score":42.61008302835759},"GB2-05":{"attempts":1,"playable":67.3778990654472,"score":67.3778990654472},"GB2-06":{"attempts":1,"playable":44.9286297433851,"score":44.9286297433851},"GB2-07":{"attempts":1,"playable":58.549346153038584,"score":58.549346153038584},"GB2-08":{"attempts":1,"playable":87.6259122754628,"score":87.6259122754628}},"none":{"GB2-01":{"attempts":1,"playable":52.4441065319384,"score":52.4441065319384},"GB2-02":{"attempts":1,"playable":43.65876669472558,"score":43.65876669472558},"GB2-03":{"attempts":1,"playable":15.741175610454677,"score":15.741175610454677},"GB2-04":{"attempts":1,"playable":42.81423373995587,"score":42.81423373995587},"GB2-05":{"attempts":1,"playable":42.805085604198595,"score":42.805085604198595},"GB2-06":{"attempts":1,"playable":43.34070191780644,"score":43.34070191780644},"GB2-07":{"attempts":1,"playable":69.37344939254533,"score":69.37344939254533},"GB2-08":{"attempts":1,"playable":83.51199869971443,"score":83.51199869971443}}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:06:41Z","match_totals_all":{"draws":2578,"losses":4060,"wins":5625},"match_totals_tracks":{"highest":{"draws":683,"losses":1224,"wins":2181},"medium":{"draws":851,"losses":1217,"wins":2020},"none":{"draws":1044,"losses":1619,"wins":1424}},"model_slug":"x-ai-grok-4-5","official_rank_by_reasoning":{"highest":31,"medium":20,"none":23},"overall":{"max":90.39689209703965,"mean":58.17139978404203,"min":15.741175610454677},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":83.71921728723662,"GB2-02":59.35129587161831,"GB2-03":45.66846375602359,"GB2-04":44.34405872322509,"GB2-05":73.70690782137578,"GB2-06":54.597929343275354,"GB2-07":56.567254552745226,"GB2-08":90.39689209703965},"per_game_all":{"GB2-01":73.35565185695744,"GB2-02":51.83241822489887,"GB2-03":39.33300080462233,"GB2-04":43.256125163846185,"GB2-05":61.29663083034052,"GB2-06":47.6224203348223,"GB2-07":61.496683366109714,"GB2-08":87.17826769073895},"per_game_match_totals_all":{"GB2-01":{"draws":394,"losses":244,"wins":909},"GB2-02":{"draws":909,"losses":264,"wins":267},"GB2-03":{"draws":318,"losses":789,"wins":375},"GB2-04":{"draws":913,"losses":416,"wins":165},"GB2-05":{"draws":0,"losses":641,"wins":949},"GB2-06":{"draws":38,"losses":836,"wins":632},"GB2-07":{"draws":0,"losses":643,"wins":947},"GB2-08":{"draws":6,"losses":227,"wins":1381}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":104,"losses":41,"wins":371},"GB2-02":{"draws":237,"losses":85,"wins":158},"GB2-03":{"draws":113,"losses":231,"wins":150},"GB2-04":{"draws":213,"losses":179,"wins":106},"GB2-05":{"draws":0,"losses":148,"wins":382},"GB2-06":{"draws":14,"losses":242,"wins":246},"GB2-07":{"draws":0,"losses":242,"wins":288},"GB2-08":{"draws":2,"losses":56,"wins":480}},"medium":{"GB2-01":{"draws":44,"losses":70,"wins":402},"GB2-02":{"draws":307,"losses":83,"wins":90},"GB2-03":{"draws":134,"losses":167,"wins":193},"GB2-04":{"draws":346,"losses":121,"wins":31},"GB2-05":{"draws":0,"losses":182,"wins":348},"GB2-06":{"draws":16,"losses":291,"wins":195},"GB2-07":{"draws":0,"losses":231,"wins":299},"GB2-08":{"draws":4,"losses":72,"wins":462}},"none":{"GB2-01":{"draws":246,"losses":133,"wins":136},"GB2-02":{"draws":365,"losses":96,"wins":19},"GB2-03":{"draws":71,"losses":391,"wins":32},"GB2-04":{"draws":354,"losses":116,"wins":28},"GB2-05":{"draws":0,"losses":311,"wins":219},"GB2-06":{"draws":8,"losses":303,"wins":191},"GB2-07":{"draws":0,"losses":170,"wins":360},"GB2-08":{"draws":0,"losses":99,"wins":439}}},"per_game_raw_elo_all":{"GB2-01":1736.435265861833,"GB2-02":1486.6703334113201,"GB2-03":1321.6625392500102,"GB2-04":1422.866781145123,"GB2-05":1598.8983706416145,"GB2-06":1383.710774346447,"GB2-07":1598.4775579396398,"GB2-08":2064.1172053273217},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1856.9084848181706,"GB2-02":1546.0400951856425,"GB2-03":1389.6449405007947,"GB2-04":1431.301366705571,"GB2-05":1778.5905328151002,"GB2-06":1491.8305184953633,"GB2-07":1530.7926292013765,"GB2-08":2157.707830465399},"medium":{"GB2-01":1860.0429814145891,"GB2-02":1491.1244959522712,"GB2-03":1486.87764512392,"GB2-04":1417.856145436089,"GB2-05":1670.640188212546,"GB2-06":1341.7199233214048,"GB2-07":1556.6351967291405,"GB2-08":2071.8924604761623},"none":{"GB2-01":1492.3543313527389,"GB2-02":1422.8464090960465,"GB2-03":1088.4650321253164,"GB2-04":1419.4428312937089,"GB2-05":1347.464390897197,"GB2-06":1317.581881222573,"GB2-07":1708.0048478884025,"GB2-08":1962.7513250404033}},"per_game_tracks":{"highest":{"GB2-01":83.71921728723662,"GB2-02":59.35129587161831,"GB2-03":45.66846375602359,"GB2-04":44.34405872322509,"GB2-05":73.70690782137578,"GB2-06":54.597929343275354,"GB2-07":56.567254552745226,"GB2-08":90.39689209703965},"medium":{"GB2-01":83.90363175169728,"GB2-02":52.48719210835273,"GB2-03":56.58936304738873,"GB2-04":42.61008302835759,"GB2-05":67.3778990654472,"GB2-06":44.9286297433851,"GB2-07":58.549346153038584,"GB2-08":87.6259122754628},"none":{"GB2-01":52.4441065319384,"GB2-02":43.65876669472558,"GB2-03":15.741175610454677,"GB2-04":42.81423373995587,"GB2-05":42.805085604198595,"GB2-06":43.34070191780644,"GB2-07":69.37344939254533,"GB2-08":83.51199869971443}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:44:15Z","reasoning":{"highest":63.54400243156745,"medium":61.759007146641245,"none":49.211189773917404},"reasoning_agg":{"highest":{"max":90.39689209703965,"mean":63.54400243156745,"min":44.34405872322509},"medium":{"max":87.6259122754628,"mean":61.759007146641245,"min":42.61008302835759},"none":{"max":83.51199869971443,"mean":49.211189773917404,"min":15.741175610454677}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":14.332812657650045},"working_program_strength":{"all":58.17139978404203,"highest":63.54400243156745,"medium":61.759007146641245,"none":49.211189773917404}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:d01e9c0cb656f07b","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":0.21156558},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558},"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":0.06816269999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296143999999996}},"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":57.568896081676144,"highest":68.28954637734213,"medium":52.432710085425484,"none":51.98443178226083},"economics_best_value":{"per_model":{"all":true,"none":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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":61.81961532338249,"score":61.81961532338249},"GB2-02":{"attempts":3,"playable":54.51664017797939,"score":54.51664017797939},"GB2-03":{"attempts":3,"playable":63.55291790406098,"score":63.55291790406098},"GB2-04":{"attempts":3,"playable":62.097488474160315,"score":62.097488474160315},"GB2-05":{"attempts":3,"playable":56.35054920854276,"score":56.35054920854276},"GB2-06":{"attempts":3,"playable":67.2918820184054,"score":67.2918820184054},"GB2-07":{"attempts":3,"playable":66.05792163333804,"score":66.05792163333804},"GB2-08":{"attempts":3,"playable":28.864153913539823,"score":28.864153913539823}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":42.00705767065865,"score":42.00705767065865},"GB2-02":{"attempts":1,"playable":68.98984774443838,"score":68.98984774443838},"GB2-03":{"attempts":1,"playable":85.03068928486006,"score":85.03068928486006},"GB2-04":{"attempts":1,"playable":78.04778833474131,"score":78.04778833474131},"GB2-05":{"attempts":1,"playable":78.64277245193433,"score":78.64277245193433},"GB2-06":{"attempts":1,"playable":82.0099718829976,"score":82.0099718829976},"GB2-07":{"attempts":1,"playable":72.86771546098988,"score":72.86771546098988},"GB2-08":{"attempts":1,"playable":38.72052818811685,"score":38.72052818811685}},"medium":{"GB2-01":{"attempts":1,"playable":77.55290850222757,"score":77.55290850222757},"GB2-02":{"attempts":1,"playable":52.48719210835273,"score":52.48719210835273},"GB2-03":{"attempts":1,"playable":57.89171594678625,"score":57.89171594678625},"GB2-04":{"attempts":1,"playable":55.98609646692755,"score":55.98609646692755},"GB2-05":{"attempts":1,"playable":40.68614877540387,"score":40.68614877540387},"GB2-06":{"attempts":1,"playable":55.82834994609773,"score":55.82834994609773},"GB2-07":{"attempts":1,"playable":59.805585785165846,"score":59.805585785165846},"GB2-08":{"attempts":1,"playable":19.223683152442394,"score":19.223683152442394}},"none":{"GB2-01":{"attempts":1,"playable":65.89887979726126,"score":65.89887979726126},"GB2-02":{"attempts":1,"playable":42.072880681147076,"score":42.072880681147076},"GB2-03":{"attempts":1,"playable":47.73634848053664,"score":47.73634848053664},"GB2-04":{"attempts":1,"playable":52.258580620812076,"score":52.258580620812076},"GB2-05":{"attempts":1,"playable":49.72272639829008,"score":49.72272639829008},"GB2-06":{"attempts":1,"playable":64.03732422612089,"score":64.03732422612089},"GB2-07":{"attempts":1,"playable":65.5004636538584,"score":65.5004636538584},"GB2-08":{"attempts":1,"playable":28.64825040006022,"score":28.64825040006022}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-10-24T19:12:16Z","match_totals_all":{"draws":2671,"losses":4155,"wins":5438},"match_totals_tracks":{"highest":{"draws":650,"losses":1057,"wins":2381},"medium":{"draws":870,"losses":1615,"wins":1603},"none":{"draws":1151,"losses":1483,"wins":1454}},"model_slug":"z-ai-glm-5-3-flashx","official_rank_by_reasoning":{"highest":21,"medium":32,"none":16},"overall":{"max":85.03068928486006,"mean":57.568896081676144,"min":19.223683152442394},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.00705767065865,"GB2-02":68.98984774443838,"GB2-03":85.03068928486006,"GB2-04":78.04778833474131,"GB2-05":78.64277245193433,"GB2-06":82.0099718829976,"GB2-07":72.86771546098988,"GB2-08":38.72052818811685},"per_game_all":{"GB2-01":61.81961532338249,"GB2-02":54.51664017797939,"GB2-03":63.55291790406098,"GB2-04":62.097488474160315,"GB2-05":56.35054920854276,"GB2-06":67.2918820184054,"GB2-07":66.05792163333804,"GB2-08":28.864153913539823},"per_game_match_totals_all":{"GB2-01":{"draws":115,"losses":565,"wins":868},"GB2-02":{"draws":940,"losses":209,"wins":291},"GB2-03":{"draws":164,"losses":507,"wins":811},"GB2-04":{"draws":795,"losses":193,"wins":506},"GB2-05":{"draws":0,"losses":718,"wins":872},"GB2-06":{"draws":62,"losses":510,"wins":934},"GB2-07":{"draws":0,"losses":566,"wins":1024},"GB2-08":{"draws":595,"losses":887,"wins":132}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":308,"wins":205},"GB2-02":{"draws":221,"losses":46,"wins":213},"GB2-03":{"draws":6,"losses":81,"wins":407},"GB2-04":{"draws":158,"losses":37,"wins":303},"GB2-05":{"draws":0,"losses":121,"wins":409},"GB2-06":{"draws":30,"losses":85,"wins":387},"GB2-07":{"draws":0,"losses":150,"wins":380},"GB2-08":{"draws":232,"losses":229,"wins":77}},"medium":{"GB2-01":{"draws":6,"losses":123,"wins":387},"GB2-02":{"draws":351,"losses":61,"wins":68},"GB2-03":{"draws":53,"losses":201,"wins":240},"GB2-04":{"draws":292,"losses":82,"wins":124},"GB2-05":{"draws":0,"losses":322,"wins":208},"GB2-06":{"draws":23,"losses":231,"wins":248},"GB2-07":{"draws":0,"losses":224,"wins":306},"GB2-08":{"draws":145,"losses":371,"wins":22}},"none":{"GB2-01":{"draws":106,"losses":134,"wins":276},"GB2-02":{"draws":368,"losses":102,"wins":10},"GB2-03":{"draws":105,"losses":225,"wins":164},"GB2-04":{"draws":345,"losses":74,"wins":79},"GB2-05":{"draws":0,"losses":275,"wins":255},"GB2-06":{"draws":9,"losses":194,"wins":299},"GB2-07":{"draws":0,"losses":192,"wins":338},"GB2-08":{"draws":218,"losses":287,"wins":33}}},"per_game_raw_elo_all":{"GB2-01":1594.5737532838166,"GB2-02":1510.9336798636523,"GB2-03":1590.2059381861147,"GB2-04":1581.4773544827701,"GB2-05":1545.6019890537239,"GB2-06":1715.4683168225085,"GB2-07":1662.4579190788002,"GB2-08":1163.570009873188},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1392.7874252880815,"GB2-02":1631.1297773096026,"GB2-03":1863.9148330410185,"GB2-04":1729.9458647677309,"GB2-05":1882.5068346279356,"GB2-06":1986.666031906463,"GB2-07":1762.8282806744726,"GB2-08":1271.716876480573},"medium":{"GB2-01":1764.354497658784,"GB2-02":1491.1244959522712,"GB2-03":1499.0665313925056,"GB2-04":1521.9398214968735,"GB2-05":1320.3948206853097,"GB2-06":1511.5199359830701,"GB2-07":1573.2363575518716,"GB2-08":1053.7429307115697},"none":{"GB2-01":1626.5793369045841,"GB2-02":1410.5467663290833,"GB2-03":1407.6364501248202,"GB2-04":1492.5463771837062,"GB2-05":1433.904311847927,"GB2-06":1648.2189825779924,"GB2-07":1651.3091190100563,"GB2-08":1165.2502224274208}},"per_game_tracks":{"highest":{"GB2-01":42.00705767065865,"GB2-02":68.98984774443838,"GB2-03":85.03068928486006,"GB2-04":78.04778833474131,"GB2-05":78.64277245193433,"GB2-06":82.0099718829976,"GB2-07":72.86771546098988,"GB2-08":38.72052818811685},"medium":{"GB2-01":77.55290850222757,"GB2-02":52.48719210835273,"GB2-03":57.89171594678625,"GB2-04":55.98609646692755,"GB2-05":40.68614877540387,"GB2-06":55.82834994609773,"GB2-07":59.805585785165846,"GB2-08":19.223683152442394},"none":{"GB2-01":65.89887979726126,"GB2-02":42.072880681147076,"GB2-03":47.73634848053664,"GB2-04":52.258580620812076,"GB2-05":49.72272639829008,"GB2-06":64.03732422612089,"GB2-07":65.5004636538584,"GB2-08":28.64825040006022}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:55:49Z","reasoning":{"highest":68.28954637734213,"medium":52.432710085425484,"none":51.98443178226083},"reasoning_agg":{"highest":{"max":85.03068928486006,"mean":68.28954637734213,"min":38.72052818811685},"medium":{"max":77.55290850222757,"mean":52.432710085425484,"min":19.223683152442394},"none":{"max":65.89887979726126,"mean":51.98443178226083,"min":28.64825040006022}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":16.305114595081307},"working_program_strength":{"all":57.568896081676144,"highest":68.28954637734213,"medium":52.432710085425484,"none":51.98443178226083}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:455a86fa0ec4fe60","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":0.09558079999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.024963199999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.0955808},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.024963199999999998},"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":57.26805848148279,"highest":74.86026551578493,"medium":57.64195520319024,"none":39.301954725473195},"economics_best_value":{"per_model":{"all":true,"highest":true},"per_setting":{"highest":true}},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":933853,"total_reasoning_output_tokens":827092,"total_visible_output_tokens":106761,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":40.81553555902979,"score":40.81553555902979},"GB2-02":{"attempts":3,"playable":58.620488853851676,"score":58.620488853851676},"GB2-03":{"attempts":2,"playable":55.44098900738541,"score":55.44098900738541},"GB2-04":{"attempts":3,"playable":63.128732590921345,"score":63.128732590921345},"GB2-05":{"attempts":3,"playable":53.390244902272975,"score":53.390244902272975},"GB2-06":{"attempts":3,"playable":70.0263303102278,"score":70.0263303102278},"GB2-07":{"attempts":3,"playable":58.68070067005389,"score":58.68070067005389},"GB2-08":{"attempts":3,"playable":51.56835378865288,"score":51.56835378865288}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.51408322163268,"score":41.51408322163268},"GB2-02":{"attempts":1,"playable":70.51041338339073,"score":70.51041338339073},"GB2-04":{"attempts":1,"playable":79.9641381012123,"score":79.9641381012123},"GB2-05":{"attempts":1,"playable":86.37316335214994,"score":86.37316335214994},"GB2-06":{"attempts":1,"playable":91.84645561861775,"score":91.84645561861775},"GB2-07":{"attempts":1,"playable":67.08878624683307,"score":67.08878624683307},"GB2-08":{"attempts":1,"playable":86.72481868665795,"score":86.72481868665795}},"medium":{"GB2-01":{"attempts":1,"playable":45.55004384089156,"score":45.55004384089156},"GB2-02":{"attempts":1,"playable":62.96078643709099,"score":62.96078643709099},"GB2-03":{"attempts":1,"playable":67.81506864223701,"score":67.81506864223701},"GB2-04":{"attempts":1,"playable":67.7311496416083,"score":67.7311496416083},"GB2-05":{"attempts":1,"playable":57.55316637011255,"score":57.55316637011255},"GB2-06":{"attempts":1,"playable":68.90320012252495,"score":68.90320012252495},"GB2-07":{"attempts":1,"playable":56.928372096193414,"score":56.928372096193414},"GB2-08":{"attempts":1,"playable":33.69385447486321,"score":33.69385447486321}},"none":{"GB2-01":{"attempts":1,"playable":35.382479614565106,"score":35.382479614565106},"GB2-02":{"attempts":1,"playable":42.390266741073305,"score":42.390266741073305},"GB2-03":{"attempts":1,"playable":43.06690937253382,"score":43.06690937253382},"GB2-04":{"attempts":1,"playable":41.69091002994343,"score":41.69091002994343},"GB2-05":{"attempts":1,"playable":16.244404984556446,"score":16.244404984556446},"GB2-06":{"attempts":1,"playable":49.32933518954072,"score":49.32933518954072},"GB2-07":{"attempts":1,"playable":52.02494366713518,"score":52.02494366713518},"GB2-08":{"attempts":1,"playable":34.28638820443749,"score":34.28638820443749}}},"id":"claude-haiku-5-5","is_recent_addition":false,"last_measured_at":"2026-10-24T16:28:13Z","match_totals_all":{"draws":2618,"losses":4069,"wins":5083},"match_totals_tracks":{"highest":{"draws":410,"losses":747,"wins":2437},"medium":{"draws":944,"losses":1368,"wins":1776},"none":{"draws":1264,"losses":1954,"wins":870}},"model_slug":"claude-haiku-5-5","official_rank_by_reasoning":{"medium":24,"none":45},"overall":{"max":91.84645561861775,"mean":57.26805848148279,"min":16.244404984556446},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":22,"overall_ranking_status":"partial","per_game":{"GB2-01":41.51408322163268,"GB2-02":70.51041338339073,"GB2-04":79.9641381012123,"GB2-05":86.37316335214994,"GB2-06":91.84645561861775,"GB2-07":67.08878624683307,"GB2-08":86.72481868665795},"per_game_all":{"GB2-01":40.81553555902979,"GB2-02":58.620488853851676,"GB2-04":63.128732590921345,"GB2-05":53.390244902272975,"GB2-06":70.0263303102278,"GB2-07":58.68070067005389,"GB2-08":51.56835378865288},"per_game_match_totals_all":{"GB2-01":{"draws":257,"losses":818,"wins":473},"GB2-02":{"draws":849,"losses":195,"wins":396},"GB2-03":{"draws":276,"losses":339,"wins":373},"GB2-04":{"draws":647,"losses":250,"wins":597},"GB2-05":{"draws":0,"losses":760,"wins":830},"GB2-06":{"draws":62,"losses":463,"wins":981},"GB2-07":{"draws":0,"losses":690,"wins":900},"GB2-08":{"draws":527,"losses":554,"wins":533}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":34,"losses":295,"wins":187},"GB2-02":{"draws":216,"losses":41,"wins":223},"GB2-04":{"draws":120,"losses":46,"wins":332},"GB2-05":{"draws":0,"losses":77,"wins":453},"GB2-06":{"draws":39,"losses":26,"wins":437},"GB2-07":{"draws":0,"losses":183,"wins":347},"GB2-08":{"draws":1,"losses":79,"wins":458}},"medium":{"GB2-01":{"draws":133,"losses":225,"wins":158},"GB2-02":{"draws":252,"losses":60,"wins":168},"GB2-03":{"draws":94,"losses":130,"wins":270},"GB2-04":{"draws":208,"losses":65,"wins":225},"GB2-05":{"draws":0,"losses":234,"wins":296},"GB2-06":{"draws":6,"losses":169,"wins":327},"GB2-07":{"draws":0,"losses":240,"wins":290},"GB2-08":{"draws":251,"losses":245,"wins":42}},"none":{"GB2-01":{"draws":90,"losses":298,"wins":128},"GB2-02":{"draws":381,"losses":94,"wins":5},"GB2-03":{"draws":182,"losses":209,"wins":103},"GB2-04":{"draws":319,"losses":139,"wins":40},"GB2-05":{"draws":0,"losses":449,"wins":81},"GB2-06":{"draws":17,"losses":268,"wins":217},"GB2-07":{"draws":0,"losses":267,"wins":263},"GB2-08":{"draws":275,"losses":230,"wins":33}}},"per_game_raw_elo_all":{"GB2-01":1380.7995891664048,"GB2-02":1545.1411288189795,"GB2-04":1595.5050865006858,"GB2-05":1525.6557867172562,"GB2-06":1791.6125307343636,"GB2-07":1560.8130570677706,"GB2-08":1496.9863126059063},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1388.0331001288532,"GB2-02":1645.9605007401337,"GB2-04":1753.8613640985388,"GB2-05":2106.3572047906237,"GB2-06":2231.288584424532,"GB2-07":1674.130380858424,"GB2-08":2046.4888752421161},"medium":{"GB2-01":1426.7074825404716,"GB2-02":1576.4492246915574,"GB2-03":1600.453608676899,"GB2-04":1621.9570433985127,"GB2-05":1532.7714060011447,"GB2-06":1734.32918925184,"GB2-07":1535.471612291689,"GB2-08":1219.124605300737},"none":{"GB2-01":1327.6581848298893,"GB2-02":1413.0136610252475,"GB2-03":1367.0735738875157,"GB2-04":1410.6968520050061,"GB2-05":937.8387493600003,"GB2-06":1409.2198185267189,"GB2-07":1472.8371780531993,"GB2-08":1225.345457274866}},"per_game_tracks":{"highest":{"GB2-01":41.51408322163268,"GB2-02":70.51041338339073,"GB2-04":79.9641381012123,"GB2-05":86.37316335214994,"GB2-06":91.84645561861775,"GB2-07":67.08878624683307,"GB2-08":86.72481868665795},"medium":{"GB2-01":45.55004384089156,"GB2-02":62.96078643709099,"GB2-03":67.81506864223701,"GB2-04":67.7311496416083,"GB2-05":57.55316637011255,"GB2-06":68.90320012252495,"GB2-07":56.928372096193414,"GB2-08":33.69385447486321},"none":{"GB2-01":35.382479614565106,"GB2-02":42.390266741073305,"GB2-03":43.06690937253382,"GB2-04":41.69091002994343,"GB2-05":16.244404984556446,"GB2-06":49.32933518954072,"GB2-07":52.02494366713518,"GB2-08":34.28638820443749}},"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":74.86026551578493,"medium":57.64195520319024,"none":39.301954725473195},"reasoning_agg":{"highest":{"max":91.84645561861775,"mean":74.86026551578493,"min":41.51408322163268},"medium":{"max":68.90320012252495,"mean":57.64195520319024,"min":33.69385447486321},"none":{"max":52.02494366713518,"mean":39.301954725473195,"min":16.244404984556446}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":35.55831079031174},"working_program_strength":{"all":57.26805848148279,"highest":74.86026551578493,"medium":57.64195520319024,"none":39.301954725473195}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:bf561de6bfd6a4fd","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":0.119209325},"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":0.046288649999999994},"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":0.029847899999999997}},"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":0.029847899999999997},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.119209325}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.008139411458333334,"median":0.005035225,"min":0.001111625,"recorded_attempt_count":28,"run_count":24,"total":0.19534587500000003},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214245,"mean_ms":417506.625,"min_ms":32605,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1196482,"mean_ms":748510.375,"min_ms":448704,"run_count":8},"medium":{"attempt_count":8,"max_ms":672648,"mean_ms":296260.625,"min_ms":146516,"run_count":8},"none":{"attempt_count":11,"max_ms":1214245,"mean_ms":207748.875,"min_ms":32605,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":65809,"output_mean":27118.375,"output_min":2294,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":65809,"output_mean":50033.0,"output_min":27276,"run_count":8},"medium":{"attempt_count":8,"output_max":58608,"output_mean":20833.875,"output_min":10904,"run_count":8},"none":{"attempt_count":11,"output_max":54017,"output_mean":10488.25,"output_min":2294,"run_count":8}},"display_name":"GLM-5.3 Flash","economics":{"all":56.98239249669937,"highest":59.02684113882392,"medium":63.71433592182957,"none":48.20600042944462},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":58.115496193862064,"score":58.115496193862064},"GB2-02":{"attempts":3,"playable":52.42008111385584,"score":52.42008111385584},"GB2-03":{"attempts":3,"playable":71.86109760910831,"score":71.86109760910831},"GB2-04":{"attempts":3,"playable":72.45878397138482,"score":72.45878397138482},"GB2-05":{"attempts":3,"playable":53.47792814240511,"score":53.47792814240511},"GB2-06":{"attempts":3,"playable":47.53999197581094,"score":47.53999197581094},"GB2-07":{"attempts":3,"playable":72.39756418431575,"score":72.39756418431575},"GB2-08":{"attempts":3,"playable":27.588196782852112,"score":27.588196782852112}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":65.99526034138175,"score":65.99526034138175},"GB2-02":{"attempts":1,"playable":65.93344404311824,"score":65.93344404311824},"GB2-03":{"attempts":1,"playable":78.36652195961076,"score":78.36652195961076},"GB2-04":{"attempts":1,"playable":78.81557387145317,"score":78.81557387145317},"GB2-05":{"attempts":1,"playable":74.26013979792762,"score":74.26013979792762},"GB2-06":{"attempts":1,"playable":17.215563096589744,"score":17.215563096589744},"GB2-07":{"attempts":1,"playable":69.72396956266648,"score":69.72396956266648},"GB2-08":{"attempts":1,"playable":21.904256437843557,"score":21.904256437843557}},"medium":{"GB2-01":{"attempts":1,"playable":71.0859611389594,"score":71.0859611389594},"GB2-02":{"attempts":1,"playable":46.40124307156255,"score":46.40124307156255},"GB2-03":{"attempts":1,"playable":80.82825529792981,"score":80.82825529792981},"GB2-04":{"attempts":1,"playable":73.99077969067254,"score":73.99077969067254},"GB2-05":{"attempts":1,"playable":48.572063531600925,"score":48.572063531600925},"GB2-06":{"attempts":1,"playable":81.37373053627438,"score":81.37373053627438},"GB2-07":{"attempts":1,"playable":75.6467935367553,"score":75.6467935367553},"GB2-08":{"attempts":1,"playable":31.81586057088171,"score":31.81586057088171}},"none":{"GB2-01":{"attempts":1,"playable":37.265267101245016,"score":37.265267101245016},"GB2-02":{"attempts":1,"playable":44.92555622688671,"score":44.92555622688671},"GB2-03":{"attempts":1,"playable":56.38851556978438,"score":56.38851556978438},"GB2-04":{"attempts":1,"playable":64.56999835202876,"score":64.56999835202876},"GB2-05":{"attempts":1,"playable":37.60158109768678,"score":37.60158109768678},"GB2-06":{"attempts":1,"playable":44.0306822945687,"score":44.0306822945687},"GB2-07":{"attempts":1,"playable":71.82192945352548,"score":71.82192945352548},"GB2-08":{"attempts":1,"playable":29.044473339831068,"score":29.044473339831068}}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T19:18:28Z","match_totals_all":{"draws":2283,"losses":4407,"wins":5573},"match_totals_tracks":{"highest":{"draws":458,"losses":1534,"wins":2096},"medium":{"draws":801,"losses":1168,"wins":2119},"none":{"draws":1024,"losses":1705,"wins":1358}},"model_slug":"z-ai-glm-5-3-flash","official_rank_by_reasoning":{"highest":34,"medium":17,"none":26},"overall":{"max":81.37373053627438,"mean":56.98239249669937,"min":17.215563096589744},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":65.99526034138175,"GB2-02":65.93344404311824,"GB2-03":78.36652195961076,"GB2-04":78.81557387145317,"GB2-05":74.26013979792762,"GB2-06":17.215563096589744,"GB2-07":69.72396956266648,"GB2-08":21.904256437843557},"per_game_all":{"GB2-01":58.115496193862064,"GB2-02":52.42008111385584,"GB2-03":71.86109760910831,"GB2-04":72.45878397138482,"GB2-05":53.47792814240511,"GB2-06":47.53999197581094,"GB2-07":72.39756418431575,"GB2-08":27.588196782852112},"per_game_match_totals_all":{"GB2-01":{"draws":242,"losses":559,"wins":747},"GB2-02":{"draws":959,"losses":230,"wins":251},"GB2-03":{"draws":145,"losses":391,"wins":946},"GB2-04":{"draws":500,"losses":184,"wins":810},"GB2-05":{"draws":0,"losses":764,"wins":826},"GB2-06":{"draws":77,"losses":797,"wins":631},"GB2-07":{"draws":0,"losses":458,"wins":1132},"GB2-08":{"draws":360,"losses":1024,"wins":230}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":184,"wins":327},"GB2-02":{"draws":249,"losses":47,"wins":184},"GB2-03":{"draws":8,"losses":117,"wins":369},"GB2-04":{"draws":138,"losses":43,"wins":317},"GB2-05":{"draws":0,"losses":145,"wins":385},"GB2-06":{"draws":14,"losses":422,"wins":66},"GB2-07":{"draws":0,"losses":168,"wins":362},"GB2-08":{"draws":44,"losses":408,"wins":86}},"medium":{"GB2-01":{"draws":20,"losses":150,"wins":346},"GB2-02":{"draws":347,"losses":92,"wins":41},"GB2-03":{"draws":23,"losses":96,"wins":375},"GB2-04":{"draws":160,"losses":57,"wins":281},"GB2-05":{"draws":0,"losses":281,"wins":249},"GB2-06":{"draws":29,"losses":89,"wins":384},"GB2-07":{"draws":0,"losses":134,"wins":396},"GB2-08":{"draws":222,"losses":269,"wins":47}},"none":{"GB2-01":{"draws":217,"losses":225,"wins":74},"GB2-02":{"draws":363,"losses":91,"wins":26},"GB2-03":{"draws":114,"losses":178,"wins":202},"GB2-04":{"draws":202,"losses":84,"wins":212},"GB2-05":{"draws":0,"losses":338,"wins":192},"GB2-06":{"draws":34,"losses":286,"wins":181},"GB2-07":{"draws":0,"losses":156,"wins":374},"GB2-08":{"draws":94,"losses":347,"wins":97}}},"per_game_raw_elo_all":{"GB2-01":1552.6917056666935,"GB2-02":1493.1106252443594,"GB2-03":1668.3454799480314,"GB2-04":1672.2598609572176,"GB2-05":1496.2859190226807,"GB2-06":1404.939523663644,"GB2-07":1756.4004314001495,"GB2-08":1152.2140581213932},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1627.6050883284406,"GB2-02":1602.6857899246536,"GB2-03":1739.4553898332294,"GB2-04":1739.3308905455158,"GB2-05":1789.1910599679723,"GB2-06":913.3005579808784,"GB2-07":1713.326124574186,"GB2-08":1087.7797069087133},"medium":{"GB2-01":1683.9752020971323,"GB2-02":1444.0124003029546,"GB2-03":1780.5669915844842,"GB2-04":1683.9989273131637,"GB2-05":1419.6120056647526,"GB2-06":1973.459107138626,"GB2-07":1809.898335799961,"GB2-08":1199.2979203475327},"none":{"GB2-01":1346.4948265745074,"GB2-02":1432.6336855054699,"GB2-03":1485.0140584263813,"GB2-04":1593.4497650129733,"GB2-05":1280.054691435317,"GB2-06":1328.0589058714277,"GB2-07":1745.9768338263013,"GB2-08":1169.5645471079335}},"per_game_tracks":{"highest":{"GB2-01":65.99526034138175,"GB2-02":65.93344404311824,"GB2-03":78.36652195961076,"GB2-04":78.81557387145317,"GB2-05":74.26013979792762,"GB2-06":17.215563096589744,"GB2-07":69.72396956266648,"GB2-08":21.904256437843557},"medium":{"GB2-01":71.0859611389594,"GB2-02":46.40124307156255,"GB2-03":80.82825529792981,"GB2-04":73.99077969067254,"GB2-05":48.572063531600925,"GB2-06":81.37373053627438,"GB2-07":75.6467935367553,"GB2-08":31.81586057088171},"none":{"GB2-01":37.265267101245016,"GB2-02":44.92555622688671,"GB2-03":56.38851556978438,"GB2-04":64.56999835202876,"GB2-05":37.60158109768678,"GB2-06":44.0306822945687,"GB2-07":71.82192945352548,"GB2-08":29.044473339831068}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:30:37Z","reasoning":{"highest":59.02684113882392,"medium":63.71433592182957,"none":48.20600042944462},"reasoning_agg":{"highest":{"max":78.81557387145317,"mean":59.02684113882392,"min":17.215563096589744},"medium":{"max":81.37373053627438,"mean":63.71433592182957,"min":31.81586057088171},"none":{"max":71.82192945352548,"mean":48.20600042944462,"min":29.044473339831068}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":15.508335492384951},"working_program_strength":{"all":56.98239249669937,"highest":59.02684113882392,"medium":63.71433592182957,"none":48.20600042944462}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:9608b8753702fb91","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.2669949999999996},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.2669949999999996},"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":0.7687025},"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":15.187937500000002},"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":55.232023986126386,"highest":63.57611531852896,"medium":55.28727474241438,"none":46.83268189743579},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":976201,"total_reasoning_output_tokens":819733,"total_visible_output_tokens":156468,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":91.13315596579696,"score":91.13315596579696},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.17628558229197,"score":28.784190388194645},"GB2-03":{"attempts":3,"playable":40.1635534773306,"score":40.1635534773306},"GB2-04":{"attempts":3,"playable":43.23435108420038,"score":43.23435108420038},"GB2-05":{"attempts":3,"playable":73.08745898579599,"score":73.08745898579599},"GB2-06":{"attempts":3,"playable":73.95309784176904,"score":73.95309784176904},"GB2-07":{"attempts":3,"playable":46.82747387527311,"score":46.82747387527311},"GB2-08":{"attempts":3,"playable":44.67291027065034,"score":44.67291027065034}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.24577905413261,"score":95.24577905413261},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":43.797201455561606,"score":43.797201455561606},"GB2-04":{"attempts":1,"playable":57.39145667910414,"score":57.39145667910414},"GB2-05":{"attempts":1,"playable":85.86190961737239,"score":85.86190961737239},"GB2-06":{"attempts":1,"playable":81.64641693622644,"score":81.64641693622644},"GB2-07":{"attempts":1,"playable":77.72262815741374,"score":77.72262815741374},"GB2-08":{"attempts":1,"playable":66.94353064842078,"score":66.94353064842078}},"medium":{"GB2-01":{"attempts":1,"playable":97.5000084183964,"score":97.5000084183964},"GB2-02":{"attempts":1,"playable":46.82241426322508,"score":46.82241426322508},"GB2-03":{"attempts":1,"playable":44.21386443386448,"score":44.21386443386448},"GB2-04":{"attempts":1,"playable":32.97324956079199,"score":32.97324956079199},"GB2-05":{"attempts":1,"playable":71.48454585910889,"score":71.48454585910889},"GB2-06":{"attempts":1,"playable":77.1916918401126,"score":77.1916918401126},"GB2-07":{"attempts":1,"playable":33.88359395115432,"score":33.88359395115432},"GB2-08":{"attempts":1,"playable":38.22882961266135,"score":38.22882961266135}},"none":{"GB2-01":{"attempts":1,"playable":80.65368042486189,"score":80.65368042486189},"GB2-02":{"attempts":1,"playable":39.53015690135886,"score":39.53015690135886},"GB2-03":{"attempts":1,"playable":32.47959454256572,"score":32.47959454256572},"GB2-04":{"attempts":1,"playable":39.33834701270501,"score":39.33834701270501},"GB2-05":{"attempts":1,"playable":61.9159214809067,"score":61.9159214809067},"GB2-06":{"attempts":1,"playable":63.02118474896806,"score":63.02118474896806},"GB2-07":{"attempts":1,"playable":28.876199517251244,"score":28.876199517251244},"GB2-08":{"attempts":1,"playable":28.846370550868887,"score":28.846370550868887}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-10-24T19:04:27Z","match_totals_all":{"draws":2488,"losses":3979,"wins":5317},"match_totals_tracks":{"highest":{"draws":504,"losses":793,"wins":2311},"medium":{"draws":985,"losses":1418,"wins":1685},"none":{"draws":999,"losses":1768,"wins":1321}},"model_slug":"gpt-5-4","official_rank_by_reasoning":{"highest":30,"medium":27,"none":28},"overall":{"max":97.5000084183964,"mean":55.232023986126386,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.24577905413261,"GB2-03":43.797201455561606,"GB2-04":57.39145667910414,"GB2-05":85.86190961737239,"GB2-06":81.64641693622644,"GB2-07":77.72262815741374,"GB2-08":66.94353064842078},"per_game_all":{"GB2-01":91.13315596579696,"GB2-03":40.1635534773306,"GB2-04":43.23435108420038,"GB2-05":73.08745898579599,"GB2-06":73.95309784176904,"GB2-07":46.82747387527311,"GB2-08":44.67291027065034},"per_game_match_totals_all":{"GB2-01":{"draws":71,"losses":115,"wins":1362},"GB2-02":{"draws":717,"losses":203,"wins":40},"GB2-03":{"draws":538,"losses":672,"wins":272},"GB2-04":{"draws":824,"losses":460,"wins":210},"GB2-05":{"draws":0,"losses":451,"wins":1139},"GB2-06":{"draws":67,"losses":399,"wins":1040},"GB2-07":{"draws":0,"losses":876,"wins":714},"GB2-08":{"draws":271,"losses":803,"wins":540}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":21,"wins":482},"GB2-03":{"draws":143,"losses":225,"wins":126},"GB2-04":{"draws":266,"losses":88,"wins":144},"GB2-05":{"draws":0,"losses":80,"wins":450},"GB2-06":{"draws":38,"losses":83,"wins":381},"GB2-07":{"draws":0,"losses":122,"wins":408},"GB2-08":{"draws":44,"losses":174,"wins":320}},"medium":{"GB2-01":{"draws":7,"losses":10,"wins":499},"GB2-02":{"draws":367,"losses":80,"wins":33},"GB2-03":{"draws":223,"losses":183,"wins":88},"GB2-04":{"draws":258,"losses":212,"wins":28},"GB2-05":{"draws":0,"losses":160,"wins":370},"GB2-06":{"draws":21,"losses":116,"wins":365},"GB2-07":{"draws":0,"losses":364,"wins":166},"GB2-08":{"draws":109,"losses":293,"wins":136}},"none":{"GB2-01":{"draws":51,"losses":84,"wins":381},"GB2-02":{"draws":350,"losses":123,"wins":7},"GB2-03":{"draws":172,"losses":264,"wins":58},"GB2-04":{"draws":300,"losses":160,"wins":38},"GB2-05":{"draws":0,"losses":211,"wins":319},"GB2-06":{"draws":8,"losses":200,"wins":294},"GB2-07":{"draws":0,"losses":390,"wins":140},"GB2-08":{"draws":118,"losses":336,"wins":84}}},"per_game_raw_elo_all":{"GB2-01":2088.6477504281193,"GB2-03":1341.16842486795,"GB2-04":1421.9814839587414,"GB2-05":1805.889788918843,"GB2-06":1833.2145114152866,"GB2-07":1423.2561711775033,"GB2-08":1353.3499345782054},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2159.676841623652,"GB2-03":1373.409436445119,"GB2-04":1533.2167867055991,"GB2-05":2088.4778028549845,"GB2-06":1979.1002013268774,"GB2-07":1847.7640701425046,"GB2-08":1626.0683496896277},"medium":{"GB2-01":2297.989634952514,"GB2-02":1447.2582851561106,"GB2-03":1377.0235044387446,"GB2-04":1340.5006704001069,"GB2-05":1738.1326376904728,"GB2-06":1889.8116551817711,"GB2-07":1244.6802546226072,"GB2-08":1266.571653617999},"none":{"GB2-01":1808.2767747081923,"GB2-02":1390.6512891910147,"GB2-03":1273.0723337199865,"GB2-04":1392.226994770518,"GB2-05":1591.0589262110714,"GB2-06":1630.7316777372116,"GB2-07":1177.3241887673983,"GB2-08":1167.4098004269892}},"per_game_tracks":{"highest":{"GB2-01":95.24577905413261,"GB2-03":43.797201455561606,"GB2-04":57.39145667910414,"GB2-05":85.86190961737239,"GB2-06":81.64641693622644,"GB2-07":77.72262815741374,"GB2-08":66.94353064842078},"medium":{"GB2-01":97.5000084183964,"GB2-02":46.82241426322508,"GB2-03":44.21386443386448,"GB2-04":32.97324956079199,"GB2-05":71.48454585910889,"GB2-06":77.1916918401126,"GB2-07":33.88359395115432,"GB2-08":38.22882961266135},"none":{"GB2-01":80.65368042486189,"GB2-02":39.53015690135886,"GB2-03":32.47959454256572,"GB2-04":39.33834701270501,"GB2-05":61.9159214809067,"GB2-06":63.02118474896806,"GB2-07":28.876199517251244,"GB2-08":28.846370550868887}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:20:30Z","reasoning":{"highest":63.576115318528956,"medium":55.28727474241438,"none":46.83268189743579},"reasoning_agg":{"highest":{"max":95.24577905413261,"mean":63.576115318528956,"min":0.0},"medium":{"max":97.5000084183964,"mean":55.28727474241438,"min":32.97324956079199},"none":{"max":80.65368042486189,"mean":46.83268189743579,"min":28.846370550868887}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.743433421093165},"working_program_strength":{"all":58.25945804891347,"highest":72.65841750689025,"medium":55.28727474241438,"none":46.83268189743579}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:8a79f157db205041","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":0.969774}},"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":5.032520000000001},"codegen_latency_ms":{"attempt_count":30,"max_ms":1906796,"mean_ms":726982.5833333334,"min_ms":135091,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1906796,"mean_ms":1528927.125,"min_ms":1229561,"run_count":8},"medium":{"attempt_count":10,"max_ms":878124,"mean_ms":297986.875,"min_ms":135091,"run_count":8},"none":{"attempt_count":10,"max_ms":640944,"mean_ms":354033.75,"min_ms":208254,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78760,"output_mean":31343.75,"output_min":6298,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":78760,"output_mean":62794.5,"output_min":52930,"run_count":8},"medium":{"attempt_count":10,"output_max":40870,"output_mean":14338.625,"output_min":6298,"run_count":8},"none":{"attempt_count":10,"output_max":30162,"output_mean":16898.125,"output_min":10952,"run_count":8}},"display_name":"Qwen3.8 Max 0902","economics":{"all":55.135639209267445,"highest":70.2031684709861,"medium":44.9911433579242,"none":50.212605798892014},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":48.37590723850843,"score":48.37590723850843},"GB2-02":{"attempts":3,"playable":46.710940633367436,"score":46.710940633367436},"GB2-03":{"attempts":3,"playable":61.2106066814485,"score":61.2106066814485},"GB2-04":{"attempts":3,"playable":56.12696331563024,"score":56.12696331563024},"GB2-05":{"attempts":3,"playable":65.33413635148666,"score":65.33413635148666},"GB2-06":{"attempts":3,"playable":68.39312796344382,"score":68.39312796344382},"GB2-07":{"attempts":3,"playable":50.76272841871988,"score":50.76272841871988},"GB2-08":{"attempts":3,"playable":44.17070307153458,"score":44.17070307153458}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.60769363702794,"score":76.60769363702794},"GB2-02":{"attempts":1,"playable":49.554919179943454,"score":49.554919179943454},"GB2-03":{"attempts":1,"playable":71.35766291351186,"score":71.35766291351186},"GB2-04":{"attempts":1,"playable":84.7079553467461,"score":84.7079553467461},"GB2-05":{"attempts":1,"playable":92.40238159029738,"score":92.40238159029738},"GB2-06":{"attempts":1,"playable":64.40623096139267,"score":64.40623096139267},"GB2-07":{"attempts":1,"playable":76.33949863172556,"score":76.33949863172556},"GB2-08":{"attempts":1,"playable":46.2490055072439,"score":46.2490055072439}},"medium":{"GB2-01":{"attempts":1,"playable":26.315842223157926,"score":26.315842223157926},"GB2-02":{"attempts":1,"playable":48.50502203901178,"score":48.50502203901178},"GB2-03":{"attempts":1,"playable":56.48895541638651,"score":56.48895541638651},"GB2-04":{"attempts":1,"playable":45.87151132146148,"score":45.87151132146148},"GB2-05":{"attempts":1,"playable":43.76759439134459,"score":43.76759439134459},"GB2-06":{"attempts":1,"playable":59.49032113903592,"score":59.49032113903592},"GB2-07":{"attempts":1,"playable":36.553746130278796,"score":36.553746130278796},"GB2-08":{"attempts":1,"playable":42.93615420271661,"score":42.93615420271661}},"none":{"GB2-01":{"attempts":1,"playable":42.20418585533942,"score":42.20418585533942},"GB2-02":{"attempts":1,"playable":42.072880681147076,"score":42.072880681147076},"GB2-03":{"attempts":1,"playable":55.78520171444714,"score":55.78520171444714},"GB2-04":{"attempts":1,"playable":37.801423278683124,"score":37.801423278683124},"GB2-05":{"attempts":1,"playable":59.83243307281801,"score":59.83243307281801},"GB2-06":{"attempts":1,"playable":81.28283178990286,"score":81.28283178990286},"GB2-07":{"attempts":1,"playable":39.394940494155286,"score":39.394940494155286},"GB2-08":{"attempts":1,"playable":43.32694950464323,"score":43.32694950464323}}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-10-24T19:04:31Z","match_totals_all":{"draws":3115,"losses":4229,"wins":4920},"match_totals_tracks":{"highest":{"draws":816,"losses":887,"wins":2385},"medium":{"draws":1056,"losses":1831,"wins":1201},"none":{"draws":1243,"losses":1511,"wins":1334}},"model_slug":"qwen-qwen3-8-max-0902","official_rank_by_reasoning":{"highest":17,"medium":46,"none":22},"overall":{"max":92.40238159029738,"mean":55.135639209267445,"min":26.315842223157926},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.60769363702794,"GB2-02":49.554919179943454,"GB2-03":71.35766291351186,"GB2-04":84.7079553467461,"GB2-05":92.40238159029738,"GB2-06":64.40623096139267,"GB2-07":76.33949863172556,"GB2-08":46.2490055072439},"per_game_all":{"GB2-01":48.37590723850843,"GB2-02":46.710940633367436,"GB2-03":61.2106066814485,"GB2-04":56.12696331563024,"GB2-05":65.33413635148666,"GB2-06":68.39312796344382,"GB2-07":50.76272841871988,"GB2-08":44.17070307153458},"per_game_match_totals_all":{"GB2-01":{"draws":306,"losses":675,"wins":567},"GB2-02":{"draws":1040,"losses":272,"wins":128},"GB2-03":{"draws":274,"losses":494,"wins":714},"GB2-04":{"draws":699,"losses":327,"wins":468},"GB2-05":{"draws":0,"losses":569,"wins":1021},"GB2-06":{"draws":99,"losses":474,"wins":933},"GB2-07":{"draws":0,"losses":815,"wins":775},"GB2-08":{"draws":697,"losses":603,"wins":314}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":130,"wins":384},"GB2-02":{"draws":331,"losses":85,"wins":64},"GB2-03":{"draws":93,"losses":112,"wins":289},"GB2-04":{"draws":88,"losses":37,"wins":373},"GB2-05":{"draws":0,"losses":41,"wins":489},"GB2-06":{"draws":53,"losses":170,"wins":279},"GB2-07":{"draws":0,"losses":130,"wins":400},"GB2-08":{"draws":249,"losses":182,"wins":107}},"medium":{"GB2-01":{"draws":95,"losses":341,"wins":80},"GB2-02":{"draws":351,"losses":80,"wins":49},"GB2-03":{"draws":91,"losses":189,"wins":214},"GB2-04":{"draws":314,"losses":121,"wins":63},"GB2-05":{"draws":0,"losses":306,"wins":224},"GB2-06":{"draws":16,"losses":215,"wins":271},"GB2-07":{"draws":0,"losses":350,"wins":180},"GB2-08":{"draws":189,"losses":229,"wins":120}},"none":{"GB2-01":{"draws":209,"losses":204,"wins":103},"GB2-02":{"draws":358,"losses":107,"wins":15},"GB2-03":{"draws":90,"losses":193,"wins":211},"GB2-04":{"draws":297,"losses":169,"wins":32},"GB2-05":{"draws":0,"losses":222,"wins":308},"GB2-06":{"draws":30,"losses":89,"wins":383},"GB2-07":{"draws":0,"losses":335,"wins":195},"GB2-08":{"draws":259,"losses":192,"wins":87}}},"per_game_raw_elo_all":{"GB2-01":1459.0065813519268,"GB2-02":1446.373656239314,"GB2-03":1535.8396979707668,"GB2-04":1548.2956842045794,"GB2-05":1760.8748783146093,"GB2-06":1732.4851642436863,"GB2-07":1472.212656862049,"GB2-08":1329.5645532679682},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.781149959917,"GB2-02":1468.3421291082454,"GB2-03":1642.133192188134,"GB2-04":1821.7724029413016,"GB2-05":2360.2106574021764,"GB2-06":1654.6100236056898,"GB2-07":1822.2415379106521,"GB2-08":1352.0813357632758},"medium":{"GB2-01":1230.55295234807,"GB2-02":1460.2320732806131,"GB2-03":1485.9454849439408,"GB2-04":1443.1030079121458,"GB2-05":1359.6288115807854,"GB2-06":1571.260619711627,"GB2-07":1279.1866527664802,"GB2-08":1316.2166825652105},"none":{"GB2-01":1394.6856417477936,"GB2-02":1410.5467663290833,"GB2-03":1479.4404167802263,"GB2-04":1380.0116417602903,"GB2-05":1562.7851659608664,"GB2-06":1971.5848494137424,"GB2-07":1315.2097799090157,"GB2-08":1320.3956414754186}},"per_game_tracks":{"highest":{"GB2-01":76.60769363702794,"GB2-02":49.554919179943454,"GB2-03":71.35766291351186,"GB2-04":84.7079553467461,"GB2-05":92.40238159029738,"GB2-06":64.40623096139267,"GB2-07":76.33949863172556,"GB2-08":46.2490055072439},"medium":{"GB2-01":26.315842223157926,"GB2-02":48.50502203901178,"GB2-03":56.48895541638651,"GB2-04":45.87151132146148,"GB2-05":43.76759439134459,"GB2-06":59.49032113903592,"GB2-07":36.553746130278796,"GB2-08":42.93615420271661},"none":{"GB2-01":42.20418585533942,"GB2-02":42.072880681147076,"GB2-03":55.78520171444714,"GB2-04":37.801423278683124,"GB2-05":59.83243307281801,"GB2-06":81.28283178990286,"GB2-07":39.394940494155286,"GB2-08":43.32694950464323}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:32:29Z","reasoning":{"highest":70.2031684709861,"medium":44.9911433579242,"none":50.212605798892014},"reasoning_agg":{"highest":{"max":92.40238159029738,"mean":70.2031684709861,"min":46.2490055072439},"medium":{"max":59.49032113903592,"mean":44.9911433579242,"min":26.315842223157926},"none":{"max":81.28283178990286,"mean":50.212605798892014,"min":37.801423278683124}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.212025113061898},"working_program_strength":{"all":55.135639209267445,"highest":70.2031684709861,"medium":44.9911433579242,"none":50.212605798892014}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:27c4ceead9a6b15f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819534},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.818811367247394},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819534}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.22795366666666664,"median":0.16679960729572763,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":5.470888},"codegen_output_tokens":{"attempt_count":27,"output_max":128921,"output_mean":35057.208333333336,"output_min":6291,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":128921,"output_mean":72806.0,"output_min":45821,"run_count":8},"medium":{"attempt_count":8,"output_max":25498,"output_mean":11826.75,"output_min":6291,"run_count":8},"none":{"attempt_count":9,"output_max":34088,"output_mean":20538.875,"output_min":10484,"run_count":8}},"display_name":"Qwen3.8 2.4T A95B","economics":{"all":54.55086393904514,"highest":68.92387224561665,"medium":43.589513879244144,"none":51.13920569227464},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":49.434305160978646,"score":49.434305160978646},"GB2-02":{"attempts":3,"playable":48.98468571062074,"score":48.98468571062074},"GB2-03":{"attempts":3,"playable":58.59247546437596,"score":58.59247546437596},"GB2-04":{"attempts":3,"playable":44.06648671950813,"score":44.06648671950813},"GB2-05":{"attempts":3,"playable":51.67722633990957,"score":51.67722633990957},"GB2-06":{"attempts":3,"playable":63.4199696844909,"score":63.4199696844909},"GB2-07":{"attempts":3,"playable":48.597322612943856,"score":48.597322612943856},"GB2-08":{"attempts":3,"playable":71.63443981953337,"score":71.63443981953337}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":58.64124744323907,"score":58.64124744323907},"GB2-02":{"attempts":1,"playable":53.74037125719317,"score":53.74037125719317},"GB2-03":{"attempts":1,"playable":82.09111701079256,"score":82.09111701079256},"GB2-04":{"attempts":1,"playable":46.78680280288333,"score":46.78680280288333},"GB2-05":{"attempts":1,"playable":69.0623453559618,"score":69.0623453559618},"GB2-06":{"attempts":1,"playable":80.55559591622435,"score":80.55559591622435},"GB2-07":{"attempts":1,"playable":69.548740928269,"score":69.548740928269},"GB2-08":{"attempts":1,"playable":90.96475725036993,"score":90.96475725036993}},"medium":{"GB2-01":{"attempts":1,"playable":53.18874174514917,"score":53.18874174514917},"GB2-02":{"attempts":1,"playable":43.65876669472558,"score":43.65876669472558},"GB2-03":{"attempts":1,"playable":43.48439531201801,"score":43.48439531201801},"GB2-04":{"attempts":1,"playable":39.235948909955745,"score":39.235948909955745},"GB2-05":{"attempts":1,"playable":50.489237534470966,"score":50.489237534470966},"GB2-06":{"attempts":1,"playable":46.405753968620125,"score":46.405753968620125},"GB2-07":{"attempts":1,"playable":32.157524947754865,"score":32.157524947754865},"GB2-08":{"attempts":1,"playable":40.09574192125872,"score":40.09574192125872}},"none":{"GB2-01":{"attempts":1,"playable":36.4729262945477,"score":36.4729262945477},"GB2-02":{"attempts":1,"playable":49.554919179943454,"score":49.554919179943454},"GB2-03":{"attempts":1,"playable":50.20191407031732,"score":50.20191407031732},"GB2-04":{"attempts":1,"playable":46.1767084456853,"score":46.1767084456853},"GB2-05":{"attempts":1,"playable":35.48009612929596,"score":35.48009612929596},"GB2-06":{"attempts":1,"playable":63.29855916862823,"score":63.29855916862823},"GB2-07":{"attempts":1,"playable":44.08570196280772,"score":44.08570196280772},"GB2-08":{"attempts":1,"playable":83.84282028697147,"score":83.84282028697147}}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-10-24T19:05:18Z","match_totals_all":{"draws":3164,"losses":4252,"wins":4848},"match_totals_tracks":{"highest":{"draws":845,"losses":910,"wins":2333},"medium":{"draws":1328,"losses":1749,"wins":1011},"none":{"draws":991,"losses":1593,"wins":1504}},"model_slug":"qwen-qwen3-8-2-4t-a95b","official_rank_by_reasoning":{"highest":19,"medium":49,"none":20},"overall":{"max":90.96475725036993,"mean":54.55086393904514,"min":32.157524947754865},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.64124744323907,"GB2-02":53.74037125719317,"GB2-03":82.09111701079256,"GB2-04":46.78680280288333,"GB2-05":69.0623453559618,"GB2-06":80.55559591622435,"GB2-07":69.548740928269,"GB2-08":90.96475725036993},"per_game_all":{"GB2-01":49.434305160978646,"GB2-02":48.98468571062074,"GB2-03":58.59247546437596,"GB2-04":44.06648671950813,"GB2-05":51.67722633990957,"GB2-06":63.4199696844909,"GB2-07":48.597322612943856,"GB2-08":71.63443981953337},"per_game_match_totals_all":{"GB2-01":{"draws":599,"losses":515,"wins":434},"GB2-02":{"draws":1057,"losses":231,"wins":152},"GB2-03":{"draws":228,"losses":550,"wins":704},"GB2-04":{"draws":947,"losses":387,"wins":160},"GB2-05":{"draws":0,"losses":793,"wins":797},"GB2-06":{"draws":106,"losses":549,"wins":851},"GB2-07":{"draws":0,"losses":852,"wins":738},"GB2-08":{"draws":227,"losses":375,"wins":1012}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":151,"losses":149,"wins":216},"GB2-02":{"draws":337,"losses":62,"wins":81},"GB2-03":{"draws":13,"losses":94,"wins":387},"GB2-04":{"draws":301,"losses":123,"wins":74},"GB2-05":{"draws":0,"losses":173,"wins":357},"GB2-06":{"draws":42,"losses":87,"wins":373},"GB2-07":{"draws":0,"losses":169,"wins":361},"GB2-08":{"draws":1,"losses":53,"wins":484}},"medium":{"GB2-01":{"draws":261,"losses":122,"wins":133},"GB2-02":{"draws":359,"losses":99,"wins":22},"GB2-03":{"draws":160,"losses":218,"wins":116},"GB2-04":{"draws":293,"losses":164,"wins":41},"GB2-05":{"draws":0,"losses":271,"wins":259},"GB2-06":{"draws":31,"losses":276,"wins":195},"GB2-07":{"draws":0,"losses":373,"wins":157},"GB2-08":{"draws":224,"losses":226,"wins":88}},"none":{"GB2-01":{"draws":187,"losses":244,"wins":85},"GB2-02":{"draws":361,"losses":70,"wins":49},"GB2-03":{"draws":55,"losses":238,"wins":201},"GB2-04":{"draws":353,"losses":100,"wins":45},"GB2-05":{"draws":0,"losses":349,"wins":181},"GB2-06":{"draws":33,"losses":186,"wins":283},"GB2-07":{"draws":0,"losses":310,"wins":220},"GB2-08":{"draws":2,"losses":96,"wins":440}}},"per_game_raw_elo_all":{"GB2-01":1463.5162746172682,"GB2-02":1464.0463193972325,"GB2-03":1534.52257040552,"GB2-04":1429.0139533662998,"GB2-05":1464.0864039556316,"GB2-06":1652.1494703209567,"GB2-07":1435.4573280652974,"GB2-08":1811.4257490742032},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1552.4556314554038,"GB2-02":1500.950419987405,"GB2-03":1803.6233592995716,"GB2-04":1450.1660885258214,"GB2-05":1697.340944658651,"GB2-06":1956.694861311571,"GB2-07":1710.6615145054095,"GB2-08":2177.171338335227},"medium":{"GB2-01":1499.4867395989825,"GB2-02":1422.8464090960465,"GB2-03":1370.6959407523425,"GB2-04":1391.4172660451848,"GB2-05":1443.4324601712833,"GB2-06":1364.265294843241,"GB2-07":1221.9171825304297,"GB2-08":1286.142548834324},"none":{"GB2-01":1338.606452797419,"GB2-02":1468.3421291082454,"GB2-03":1429.2484111646452,"GB2-04":1445.4585055278935,"GB2-05":1251.4858070369596,"GB2-06":1635.4882548080586,"GB2-07":1373.793287160052,"GB2-08":1970.9633600530583}},"per_game_tracks":{"highest":{"GB2-01":58.64124744323907,"GB2-02":53.74037125719317,"GB2-03":82.09111701079256,"GB2-04":46.78680280288333,"GB2-05":69.0623453559618,"GB2-06":80.55559591622435,"GB2-07":69.548740928269,"GB2-08":90.96475725036993},"medium":{"GB2-01":53.18874174514917,"GB2-02":43.65876669472558,"GB2-03":43.48439531201801,"GB2-04":39.235948909955745,"GB2-05":50.489237534470966,"GB2-06":46.405753968620125,"GB2-07":32.157524947754865,"GB2-08":40.09574192125872},"none":{"GB2-01":36.4729262945477,"GB2-02":49.554919179943454,"GB2-03":50.20191407031732,"GB2-04":46.1767084456853,"GB2-05":35.48009612929596,"GB2-06":63.29855916862823,"GB2-07":44.08570196280772,"GB2-08":83.84282028697147}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:11:51Z","reasoning":{"highest":68.92387224561665,"medium":43.589513879244144,"none":51.13920569227464},"reasoning_agg":{"highest":{"max":90.96475725036993,"mean":68.92387224561665,"min":46.78680280288333},"medium":{"max":53.18874174514917,"mean":43.589513879244144,"min":32.157524947754865},"none":{"max":83.84282028697147,"mean":51.13920569227464,"min":35.48009612929596}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.334358366372506},"working_program_strength":{"all":54.55086393904514,"highest":68.92387224561665,"medium":43.589513879244144,"none":51.13920569227464}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:0a96bef3bb84fe9d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.392731284},"codegen_latency_ms":{"attempt_count":26,"max_ms":176041,"mean_ms":89449.0,"min_ms":6041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":176041,"mean_ms":153558.625,"min_ms":128316,"run_count":8},"medium":{"attempt_count":9,"max_ms":152315,"mean_ms":102702.875,"min_ms":61501,"run_count":8},"none":{"attempt_count":9,"max_ms":25470,"mean_ms":12085.5,"min_ms":6041,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":50785,"output_mean":25087.541666666668,"output_min":1796,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50785,"output_mean":42017.75,"output_min":28632,"run_count":8},"medium":{"attempt_count":9,"output_max":44567,"output_mean":29519.625,"output_min":16614,"run_count":8},"none":{"attempt_count":9,"output_max":8282,"output_mean":3725.25,"output_min":1796,"run_count":8}},"display_name":"DeepSeek V4.1 Flash","economics":{"all":53.76994993201739,"highest":68.93732826967819,"medium":55.72922801802724,"none":36.64329350834672},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":59.147784540787285,"score":59.147784540787285},"GB2-02":{"attempts":3,"playable":52.590515595844884,"score":52.590515595844884},"GB2-03":{"attempts":3,"playable":54.869367087243695,"score":54.869367087243695},"GB2-04":{"attempts":3,"playable":50.86730909109142,"score":50.86730909109142},"GB2-05":{"attempts":3,"playable":55.59148777312149,"score":55.59148777312149},"GB2-06":{"attempts":3,"playable":62.35140347674025,"score":62.35140347674025},"GB2-07":{"attempts":3,"playable":56.978348781179164,"score":56.978348781179164},"GB2-08":{"attempts":3,"playable":37.763383110130874,"score":37.763383110130874}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.48585845489573,"score":63.48585845489573},"GB2-02":{"attempts":1,"playable":57.48637702622682,"score":57.48637702622682},"GB2-03":{"attempts":1,"playable":60.380650068586604,"score":60.380650068586604},"GB2-04":{"attempts":1,"playable":75.15428482707536,"score":75.15428482707536},"GB2-05":{"attempts":1,"playable":82.5682498438426,"score":82.5682498438426},"GB2-06":{"attempts":1,"playable":82.2826138194998,"score":82.2826138194998},"GB2-07":{"attempts":1,"playable":75.82004365233398,"score":75.82004365233398},"GB2-08":{"attempts":1,"playable":54.320548464964645,"score":54.320548464964645}},"medium":{"GB2-01":{"attempts":1,"playable":68.11270615327604,"score":68.11270615327604},"GB2-02":{"attempts":1,"playable":58.21228908016076,"score":58.21228908016076},"GB2-03":{"attempts":1,"playable":55.78520171444714,"score":55.78520171444714},"GB2-04":{"attempts":1,"playable":38.72382122309945,"score":38.72382122309945},"GB2-05":{"attempts":1,"playable":53.932046299693056,"score":53.932046299693056},"GB2-06":{"attempts":1,"playable":76.73706904473035,"score":76.73706904473035},"GB2-07":{"attempts":1,"playable":69.548740928269,"score":69.548740928269},"GB2-08":{"attempts":1,"playable":24.78194970054213,"score":24.78194970054213}},"none":{"GB2-01":{"attempts":1,"playable":45.8447890141901,"score":45.8447890141901},"GB2-02":{"attempts":1,"playable":42.072880681147076,"score":42.072880681147076},"GB2-03":{"attempts":1,"playable":48.44224947869734,"score":48.44224947869734},"GB2-04":{"attempts":1,"playable":38.72382122309945,"score":38.72382122309945},"GB2-05":{"attempts":1,"playable":30.274167175828847,"score":30.274167175828847},"GB2-06":{"attempts":1,"playable":28.03452756599059,"score":28.03452756599059},"GB2-07":{"attempts":1,"playable":25.566261762934516,"score":25.566261762934516},"GB2-08":{"attempts":1,"playable":34.18765116488585,"score":34.18765116488585}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T19:20:59Z","match_totals_all":{"draws":3240,"losses":4329,"wins":4694},"match_totals_tracks":{"highest":{"draws":778,"losses":964,"wins":2346},"medium":{"draws":1210,"losses":1297,"wins":1581},"none":{"draws":1252,"losses":2068,"wins":767}},"model_slug":"deepseek-deepseek-v4-1-flash","official_rank_by_reasoning":{"highest":18,"medium":26,"none":50},"overall":{"max":82.5682498438426,"mean":53.76994993201739,"min":24.78194970054213},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.48585845489573,"GB2-02":57.48637702622682,"GB2-03":60.380650068586604,"GB2-04":75.15428482707536,"GB2-05":82.5682498438426,"GB2-06":82.2826138194998,"GB2-07":75.82004365233398,"GB2-08":54.320548464964645},"per_game_all":{"GB2-01":59.147784540787285,"GB2-02":52.590515595844884,"GB2-03":54.869367087243695,"GB2-04":50.86730909109142,"GB2-05":55.59148777312149,"GB2-06":62.35140347674025,"GB2-07":56.978348781179164,"GB2-08":37.763383110130874},"per_game_match_totals_all":{"GB2-01":{"draws":472,"losses":429,"wins":647},"GB2-02":{"draws":991,"losses":212,"wins":237},"GB2-03":{"draws":317,"losses":568,"wins":596},"GB2-04":{"draws":732,"losses":391,"wins":371},"GB2-05":{"draws":0,"losses":728,"wins":862},"GB2-06":{"draws":90,"losses":563,"wins":853},"GB2-07":{"draws":0,"losses":709,"wins":881},"GB2-08":{"draws":638,"losses":729,"wins":247}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":189,"wins":306},"GB2-02":{"draws":293,"losses":66,"wins":121},"GB2-03":{"draws":56,"losses":187,"wins":251},"GB2-04":{"draws":154,"losses":54,"wins":290},"GB2-05":{"draws":0,"losses":99,"wins":431},"GB2-06":{"draws":35,"losses":81,"wins":386},"GB2-07":{"draws":0,"losses":133,"wins":397},"GB2-08":{"draws":219,"losses":155,"wins":164}},"medium":{"GB2-01":{"draws":289,"losses":31,"wins":196},"GB2-02":{"draws":314,"losses":52,"wins":114},"GB2-03":{"draws":146,"losses":165,"wins":183},"GB2-04":{"draws":262,"losses":182,"wins":54},"GB2-05":{"draws":0,"losses":253,"wins":277},"GB2-06":{"draws":26,"losses":116,"wins":360},"GB2-07":{"draws":0,"losses":169,"wins":361},"GB2-08":{"draws":173,"losses":329,"wins":36}},"none":{"GB2-01":{"draws":162,"losses":209,"wins":145},"GB2-02":{"draws":384,"losses":94,"wins":2},"GB2-03":{"draws":115,"losses":216,"wins":162},"GB2-04":{"draws":316,"losses":155,"wins":27},"GB2-05":{"draws":0,"losses":376,"wins":154},"GB2-06":{"draws":29,"losses":366,"wins":107},"GB2-07":{"draws":0,"losses":407,"wins":123},"GB2-08":{"draws":246,"losses":245,"wins":47}}},"per_game_raw_elo_all":{"GB2-01":1560.4381733092896,"GB2-02":1492.688077477517,"GB2-03":1472.0584011237713,"GB2-04":1490.444384996168,"GB2-05":1549.5709836904896,"GB2-06":1653.3729682886699,"GB2-07":1551.2092829792864,"GB2-08":1264.0340745877568},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1601.302243243401,"GB2-02":1530.8116475166503,"GB2-03":1522.9330263274542,"GB2-04":1696.6149823459034,"GB2-05":1984.5694269895403,"GB2-06":1992.3752768299123,"GB2-07":1812.959986263113,"GB2-08":1445.838247118601},"medium":{"GB2-01":1650.4968799789253,"GB2-02":1536.705818586817,"GB2-03":1479.4404167802263,"GB2-04":1387.3590863213005,"GB2-05":1486.49182184943,"GB2-06":1880.9771471495328,"GB2-07":1710.6615145054095,"GB2-08":1121.954247372284},"none":{"GB2-01":1429.5153967055423,"GB2-02":1410.5467663290833,"GB2-03":1413.801760263633,"GB2-04":1387.3590863213005,"GB2-05":1177.651702232498,"GB2-06":1086.766480886565,"GB2-07":1130.006348169337,"GB2-08":1224.3097292723855}},"per_game_tracks":{"highest":{"GB2-01":63.48585845489573,"GB2-02":57.48637702622682,"GB2-03":60.380650068586604,"GB2-04":75.15428482707536,"GB2-05":82.5682498438426,"GB2-06":82.2826138194998,"GB2-07":75.82004365233398,"GB2-08":54.320548464964645},"medium":{"GB2-01":68.11270615327604,"GB2-02":58.21228908016076,"GB2-03":55.78520171444714,"GB2-04":38.72382122309945,"GB2-05":53.932046299693056,"GB2-06":76.73706904473035,"GB2-07":69.548740928269,"GB2-08":24.78194970054213},"none":{"GB2-01":45.8447890141901,"GB2-02":42.072880681147076,"GB2-03":48.44224947869734,"GB2-04":38.72382122309945,"GB2-05":30.274167175828847,"GB2-06":28.03452756599059,"GB2-07":25.566261762934516,"GB2-08":34.18765116488585}},"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":2,"rank_movement_baseline_at":"2026-10-22T10:32:10Z","reasoning":{"highest":68.93732826967819,"medium":55.72922801802724,"none":36.64329350834672},"reasoning_agg":{"highest":{"max":82.5682498438426,"mean":68.93732826967819,"min":54.320548464964645},"medium":{"max":76.73706904473035,"mean":55.72922801802724,"min":24.78194970054213},"none":{"max":48.44224947869734,"mean":36.64329350834672,"min":25.566261762934516}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":32.29403476133147},"working_program_strength":{"all":53.76994993201739,"highest":68.93732826967819,"medium":55.72922801802724,"none":36.64329350834672}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:f4440149415afa63","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":53.58902732847468,"highest":64.75969024345711,"medium":51.106486359911486,"none":44.900905382055434},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":131,"total_output_tokens":812278,"total_reasoning_output_tokens":673611,"total_visible_output_tokens":138667,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":51.4898778691449,"score":51.4898778691449},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":60.979635616187345,"score":40.65309041079156},"GB2-03":{"attempts":3,"playable":59.68735427590993,"score":59.68735427590993},"GB2-04":{"attempts":3,"playable":44.438300487615415,"score":44.438300487615415},"GB2-05":{"attempts":3,"playable":57.75361399809637,"score":57.75361399809637},"GB2-06":{"attempts":3,"playable":60.37751461783724,"score":60.37751461783724},"GB2-07":{"attempts":3,"playable":61.022934532403134,"score":61.022934532403134},"GB2-08":{"attempts":3,"playable":53.28953243599887,"score":53.28953243599887}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.13914815310555,"score":55.13914815310555},"GB2-02":{"attempts":1,"playable":78.7231504340342,"score":78.7231504340342},"GB2-03":{"attempts":1,"playable":72.49504199504798,"score":72.49504199504798},"GB2-04":{"attempts":1,"playable":56.38792158133602,"score":56.38792158133602},"GB2-05":{"attempts":1,"playable":70.36832724160911,"score":70.36832724160911},"GB2-06":{"attempts":1,"playable":81.01012705259966,"score":81.01012705259966},"GB2-07":{"attempts":1,"playable":67.79294071654301,"score":67.79294071654301},"GB2-08":{"attempts":1,"playable":36.16086477338143,"score":36.16086477338143}},"medium":{"GB2-01":{"attempts":1,"playable":52.79825579150371,"score":52.79825579150371},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":41.077463671328005,"score":41.077463671328005},"GB2-04":{"attempts":1,"playable":35.33824961448706,"score":35.33824961448706},"GB2-05":{"attempts":1,"playable":52.403277218209034,"score":52.403277218209034},"GB2-06":{"attempts":1,"playable":60.60900022975133,"score":60.60900022975133},"GB2-07":{"attempts":1,"playable":77.20430002383503,"score":77.20430002383503},"GB2-08":{"attempts":1,"playable":89.4213443301777,"score":89.4213443301777}},"none":{"GB2-01":{"attempts":1,"playable":46.532229662825436,"score":46.532229662825436},"GB2-02":{"attempts":1,"playable":43.236120798340494,"score":43.236120798340494},"GB2-03":{"attempts":1,"playable":65.48955716135379,"score":65.48955716135379},"GB2-04":{"attempts":1,"playable":41.58873026702318,"score":41.58873026702318},"GB2-05":{"attempts":1,"playable":50.489237534470966,"score":50.489237534470966},"GB2-06":{"attempts":1,"playable":39.51341657116074,"score":39.51341657116074},"GB2-07":{"attempts":1,"playable":38.071562856831356,"score":38.071562856831356},"GB2-08":{"attempts":1,"playable":34.28638820443749,"score":34.28638820443749}}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-10-24T19:06:54Z","match_totals_all":{"draws":2715,"losses":4101,"wins":4968},"match_totals_tracks":{"highest":{"draws":1013,"losses":1031,"wins":2044},"medium":{"draws":575,"losses":1272,"wins":1761},"none":{"draws":1127,"losses":1798,"wins":1163}},"model_slug":"tencent-hy4-preview","official_rank_by_reasoning":{"highest":26,"medium":35,"none":31},"overall":{"max":89.4213443301777,"mean":53.58902732847468,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.13914815310555,"GB2-02":78.7231504340342,"GB2-03":72.49504199504798,"GB2-04":56.38792158133602,"GB2-05":70.36832724160911,"GB2-06":81.01012705259966,"GB2-07":67.79294071654301,"GB2-08":36.16086477338143},"per_game_all":{"GB2-01":51.4898778691449,"GB2-03":59.68735427590993,"GB2-04":44.438300487615415,"GB2-05":57.75361399809637,"GB2-06":60.37751461783724,"GB2-07":61.022934532403134,"GB2-08":53.28953243599887},"per_game_match_totals_all":{"GB2-01":{"draws":361,"losses":603,"wins":584},"GB2-02":{"draws":513,"losses":132,"wins":315},"GB2-03":{"draws":418,"losses":442,"wins":622},"GB2-04":{"draws":843,"losses":433,"wins":218},"GB2-05":{"draws":0,"losses":698,"wins":892},"GB2-06":{"draws":51,"losses":623,"wins":832},"GB2-07":{"draws":0,"losses":646,"wins":944},"GB2-08":{"draws":529,"losses":524,"wins":561}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":245,"losses":120,"wins":151},"GB2-02":{"draws":128,"losses":44,"wins":308},"GB2-03":{"draws":49,"losses":128,"wins":317},"GB2-04":{"draws":260,"losses":96,"wins":142},"GB2-05":{"draws":0,"losses":166,"wins":364},"GB2-06":{"draws":21,"losses":95,"wins":386},"GB2-07":{"draws":0,"losses":179,"wins":351},"GB2-08":{"draws":310,"losses":203,"wins":25}},"medium":{"GB2-01":{"draws":33,"losses":238,"wins":245},"GB2-03":{"draws":267,"losses":176,"wins":51},"GB2-04":{"draws":261,"losses":199,"wins":38},"GB2-05":{"draws":0,"losses":261,"wins":269},"GB2-06":{"draws":14,"losses":210,"wins":278},"GB2-07":{"draws":0,"losses":125,"wins":405},"GB2-08":{"draws":0,"losses":63,"wins":475}},"none":{"GB2-01":{"draws":83,"losses":245,"wins":188},"GB2-02":{"draws":385,"losses":88,"wins":7},"GB2-03":{"draws":102,"losses":138,"wins":254},"GB2-04":{"draws":322,"losses":138,"wins":38},"GB2-05":{"draws":0,"losses":271,"wins":259},"GB2-06":{"draws":16,"losses":318,"wins":168},"GB2-07":{"draws":0,"losses":342,"wins":188},"GB2-08":{"draws":219,"losses":258,"wins":61}}},"per_game_raw_elo_all":{"GB2-01":1483.3555244512925,"GB2-03":1527.0553731405453,"GB2-04":1431.7185385196765,"GB2-05":1543.2269629021791,"GB2-06":1605.1964373295948,"GB2-07":1606.9955628200653,"GB2-08":1532.082001140863},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1518.2626489350769,"GB2-02":1737.390446537357,"GB2-03":1656.4045930927587,"GB2-04":1525.1513153560804,"GB2-05":1718.9498926017775,"GB2-06":1965.9798163360524,"GB2-07":1684.429878863529,"GB2-08":1244.9616517094255},"medium":{"GB2-01":1495.7443982721907,"GB2-03":1349.7822082945813,"GB2-04":1360.1050111579111,"GB2-05":1467.2985359334762,"GB2-06":1589.8913421837797,"GB2-07":1838.0539430567485,"GB2-08":2125.938894438297},"none":{"GB2-01":1436.0595261466094,"GB2-02":1419.5745480878245,"GB2-03":1574.9793180342958,"GB2-04":1409.8992890450377,"GB2-05":1443.4324601712833,"GB2-06":1259.7181534689526,"GB2-07":1298.5028665399188,"GB2-08":1225.345457274866}},"per_game_tracks":{"highest":{"GB2-01":55.13914815310555,"GB2-02":78.7231504340342,"GB2-03":72.49504199504798,"GB2-04":56.38792158133602,"GB2-05":70.36832724160911,"GB2-06":81.01012705259966,"GB2-07":67.79294071654301,"GB2-08":36.16086477338143},"medium":{"GB2-01":52.79825579150371,"GB2-03":41.077463671328005,"GB2-04":35.33824961448706,"GB2-05":52.403277218209034,"GB2-06":60.60900022975133,"GB2-07":77.20430002383503,"GB2-08":89.4213443301777},"none":{"GB2-01":46.532229662825436,"GB2-02":43.236120798340494,"GB2-03":65.48955716135379,"GB2-04":41.58873026702318,"GB2-05":50.489237534470966,"GB2-06":39.51341657116074,"GB2-07":38.071562856831356,"GB2-08":34.28638820443749}},"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":-1,"rank_movement_baseline_at":"2026-10-22T10:49:56Z","reasoning":{"highest":64.75969024345711,"medium":51.10648635991148,"none":44.900905382055434},"reasoning_agg":{"highest":{"max":81.01012705259966,"mean":64.75969024345711,"min":36.16086477338143},"medium":{"max":89.4213443301777,"mean":51.10648635991148,"min":0.0},"none":{"max":65.48955716135379,"mean":44.900905382055434,"min":34.28638820443749}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":19.85878486140168},"working_program_strength":{"all":56.022669536089516,"highest":64.75969024345711,"medium":58.407412982755986,"none":44.900905382055434}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:7070428b78df5af4","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":1.1471405000000001},"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":0.37616799999999995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.376168},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.714719},"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":53.57797477730201,"highest":59.67176708891218,"medium":59.100326361155275,"none":41.96183088183857},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":87,"requested_max_output_token_observations":9,"requested_max_output_tokens":[943718],"total_output_tokens":341760,"total_reasoning_output_tokens":238816,"total_visible_output_tokens":102944,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":67.88474290382362,"score":67.88474290382362},"GB2-02":{"attempts":3,"playable":45.79998113846781,"score":45.79998113846781},"GB2-03":{"attempts":3,"playable":52.89563485910421,"score":52.89563485910421},"GB2-04":{"attempts":3,"playable":47.32663683537695,"score":47.32663683537695},"GB2-05":{"attempts":3,"playable":54.363333509183974,"score":54.363333509183974},"GB2-06":{"attempts":2,"playable":23.381335579604865,"score":23.381335579604865},"GB2-07":{"attempts":3,"playable":57.896430290853495,"score":57.896430290853495},"GB2-08":{"attempts":3,"playable":67.16937284148435,"score":67.16937284148435}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.56018468707377,"score":80.56018468707377},"GB2-02":{"attempts":1,"playable":48.39995804802052,"score":48.39995804802052},"GB2-03":{"attempts":1,"playable":61.07381382798566,"score":61.07381382798566},"GB2-04":{"attempts":1,"playable":49.52711291065132,"score":49.52711291065132},"GB2-05":{"attempts":1,"playable":61.537543054055796,"score":61.537543054055796},"GB2-06":{"attempts":1,"playable":27.052490288319685,"score":27.052490288319685},"GB2-07":{"attempts":1,"playable":74.77978494231873,"score":74.77978494231873},"GB2-08":{"attempts":1,"playable":74.443248952872,"score":74.443248952872}},"medium":{"GB2-01":{"attempts":1,"playable":85.8287769231521,"score":85.8287769231521},"GB2-02":{"attempts":1,"playable":47.032922926642925,"score":47.032922926642925},"GB2-03":{"attempts":1,"playable":51.530094750066446,"score":51.530094750066446},"GB2-04":{"attempts":1,"playable":44.75161543158207,"score":44.75161543158207},"GB2-05":{"attempts":1,"playable":49.91440011487013,"score":49.91440011487013},"GB2-07":{"attempts":1,"playable":64.26118148091865,"score":64.26118148091865},"GB2-08":{"attempts":1,"playable":70.3832929008546,"score":70.3832929008546}},"none":{"GB2-01":{"attempts":1,"playable":37.265267101245016,"score":37.265267101245016},"GB2-02":{"attempts":1,"playable":41.96706244073995,"score":41.96706244073995},"GB2-03":{"attempts":1,"playable":46.08299599926055,"score":46.08299599926055},"GB2-04":{"attempts":1,"playable":47.701182163897485,"score":47.701182163897485},"GB2-05":{"attempts":1,"playable":51.638057358625986,"score":51.638057358625986},"GB2-06":{"attempts":1,"playable":19.71018087089005,"score":19.71018087089005},"GB2-07":{"attempts":1,"playable":34.64832444932314,"score":34.64832444932314},"GB2-08":{"attempts":1,"playable":56.68157667072642,"score":56.68157667072642}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-10-24T18:36:08Z","match_totals_all":{"draws":2406,"losses":4530,"wins":4826},"match_totals_tracks":{"highest":{"draws":689,"losses":1383,"wins":2016},"medium":{"draws":782,"losses":1145,"wins":1659},"none":{"draws":935,"losses":2002,"wins":1151}},"model_slug":"meta-muse-spark-1-2","official_rank_by_reasoning":{"highest":33,"medium":23,"none":36},"overall":{"max":85.8287769231521,"mean":53.57797477730201,"min":19.71018087089005},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.56018468707377,"GB2-02":48.39995804802052,"GB2-03":61.07381382798566,"GB2-04":49.52711291065132,"GB2-05":61.537543054055796,"GB2-06":27.052490288319685,"GB2-07":74.77978494231873,"GB2-08":74.443248952872},"per_game_all":{"GB2-01":67.88474290382362,"GB2-02":45.79998113846781,"GB2-03":52.89563485910421,"GB2-04":47.32663683537695,"GB2-05":54.363333509183974,"GB2-07":57.896430290853495,"GB2-08":67.16937284148435},"per_game_match_totals_all":{"GB2-01":{"draws":192,"losses":429,"wins":927},"GB2-02":{"draws":1078,"losses":266,"wins":96},"GB2-03":{"draws":190,"losses":661,"wins":631},"GB2-04":{"draws":891,"losses":367,"wins":236},"GB2-05":{"draws":0,"losses":752,"wins":838},"GB2-06":{"draws":22,"losses":792,"wins":190},"GB2-07":{"draws":0,"losses":698,"wins":892},"GB2-08":{"draws":33,"losses":565,"wins":1016}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":109,"wins":405},"GB2-02":{"draws":368,"losses":72,"wins":40},"GB2-03":{"draws":19,"losses":202,"wins":273},"GB2-04":{"draws":270,"losses":125,"wins":103},"GB2-05":{"draws":0,"losses":213,"wins":317},"GB2-06":{"draws":20,"losses":375,"wins":107},"GB2-07":{"draws":0,"losses":139,"wins":391},"GB2-08":{"draws":10,"losses":148,"wins":380}},"medium":{"GB2-01":{"draws":23,"losses":70,"wins":423},"GB2-02":{"draws":363,"losses":81,"wins":36},"GB2-03":{"draws":106,"losses":206,"wins":182},"GB2-04":{"draws":269,"losses":149,"wins":80},"GB2-05":{"draws":0,"losses":274,"wins":256},"GB2-07":{"draws":0,"losses":199,"wins":331},"GB2-08":{"draws":21,"losses":166,"wins":351}},"none":{"GB2-01":{"draws":167,"losses":250,"wins":99},"GB2-02":{"draws":347,"losses":113,"wins":20},"GB2-03":{"draws":65,"losses":253,"wins":176},"GB2-04":{"draws":352,"losses":93,"wins":53},"GB2-05":{"draws":0,"losses":265,"wins":265},"GB2-06":{"draws":2,"losses":417,"wins":83},"GB2-07":{"draws":0,"losses":360,"wins":170},"GB2-08":{"draws":2,"losses":251,"wins":285}}},"per_game_raw_elo_all":{"GB2-01":1682.6326877609383,"GB2-02":1439.341864034575,"GB2-03":1454.6596996759502,"GB2-04":1454.334286675133,"GB2-05":1493.2938306137519,"GB2-07":1561.1063338168708,"GB2-08":1641.2847765158997},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1806.883862918333,"GB2-02":1459.4213256044306,"GB2-03":1529.732293654265,"GB2-04":1471.328221994153,"GB2-05":1585.8552016310275,"GB2-06":1071.7913748910646,"GB2-07":1794.8170946790685,"GB2-08":1762.5029571474101},"medium":{"GB2-01":1894.5193737899742,"GB2-02":1448.8806588761174,"GB2-03":1441.0014639494655,"GB2-04":1434.4530888117813,"GB2-05":1436.286012770563,"GB2-07":1633.8598408058735,"GB2-08":1685.5788886197383},"none":{"GB2-01":1346.4948265745074,"GB2-02":1409.723607623177,"GB2-03":1393.2453414241197,"GB2-04":1457.221549219465,"GB2-05":1457.7402774396653,"GB2-06":955.7821720986217,"GB2-07":1254.642065965671,"GB2-08":1475.7724837805508}},"per_game_tracks":{"highest":{"GB2-01":80.56018468707377,"GB2-02":48.39995804802052,"GB2-03":61.07381382798566,"GB2-04":49.52711291065132,"GB2-05":61.537543054055796,"GB2-06":27.052490288319685,"GB2-07":74.77978494231873,"GB2-08":74.443248952872},"medium":{"GB2-01":85.8287769231521,"GB2-02":47.032922926642925,"GB2-03":51.530094750066446,"GB2-04":44.75161543158207,"GB2-05":49.91440011487013,"GB2-07":64.26118148091865,"GB2-08":70.3832929008546},"none":{"GB2-01":37.265267101245016,"GB2-02":41.96706244073995,"GB2-03":46.08299599926055,"GB2-04":47.701182163897485,"GB2-05":51.638057358625986,"GB2-06":19.71018087089005,"GB2-07":34.64832444932314,"GB2-08":56.68157667072642}},"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":-1,"rank_movement_baseline_at":"2026-10-22T09:52:25Z","reasoning":{"highest":59.67176708891218,"medium":59.100326361155275,"none":41.96183088183857},"reasoning_agg":{"highest":{"max":80.56018468707377,"mean":59.67176708891218,"min":27.052490288319685},"medium":{"max":85.8287769231521,"mean":59.100326361155275,"min":44.75161543158207},"none":{"max":56.68157667072642,"mean":41.96183088183857,"min":19.71018087089005}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.70993620707361},"working_program_strength":{"all":53.57797477730201,"highest":59.67176708891218,"medium":59.100326361155275,"none":41.96183088183857}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:0d9c66a7efaa96af","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":0.8934513}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000001},"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":13.077675975},"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":52.46494373904992,"highest":64.44312238545328,"medium":52.40131854062887,"none":40.55039029106762},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":14,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2,"infra_failures_excluded":2},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2,"infra_failures_excluded":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-02","GB2-03","GB2-07"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":53.21304603037553,"score":53.21304603037553},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":44.275798674295224,"score":38.023671744411324},"GB2-03":{"attempts":6,"playable":58.01877215456429,"score":58.01877215456429},"GB2-04":{"attempts":6,"playable":48.70312713253865,"score":48.70312713253865},"GB2-05":{"attempts":6,"playable":67.14080131938617,"score":67.14080131938617},"GB2-06":{"attempts":6,"playable":63.46052586357353,"score":63.46052586357353},"GB2-07":{"attempts":6,"playable":49.136883029890576,"score":49.136883029890576},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":53.8404774169779,"score":42.02272263765933}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":55.76764154073839,"score":55.76764154073839},"GB2-02":{"attempts":2,"playable":54.989227931368966,"score":54.989227931368966},"GB2-03":{"attempts":2,"playable":69.0036612502482,"score":69.0036612502482},"GB2-04":{"attempts":2,"playable":62.37675019790042,"score":62.37675019790042},"GB2-05":{"attempts":2,"playable":83.85522753719866,"score":83.85522753719866},"GB2-06":{"attempts":2,"playable":82.97409269011435,"score":82.97409269011435},"GB2-07":{"attempts":2,"playable":51.38388530968991,"score":51.38388530968991},"GB2-08":{"attempts":2,"playable":55.19449262636733,"score":55.19449262636733}},"medium":{"GB2-01":{"attempts":2,"playable":72.36631037981078,"score":72.36631037981078},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":37.51276157930343,"score":18.756380789651715},"GB2-03":{"attempts":2,"playable":49.00266093865487,"score":49.00266093865487},"GB2-04":{"attempts":2,"playable":41.3807927137414,"score":41.3807927137414},"GB2-05":{"attempts":2,"playable":69.95700555132022,"score":69.95700555132022},"GB2-06":{"attempts":2,"playable":83.78061679033559,"score":83.78061679033559},"GB2-07":{"attempts":2,"playable":48.51351682356067,"score":48.51351682356067},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":70.9065286759114,"score":35.4532643379557}},"none":{"GB2-01":{"attempts":2,"playable":31.50518617057742,"score":31.50518617057742},"GB2-02":{"attempts":2,"playable":40.32540651221328,"score":40.32540651221328},"GB2-03":{"attempts":2,"playable":56.0499942747898,"score":56.0499942747898},"GB2-04":{"attempts":2,"playable":42.35183848597413,"score":42.35183848597413},"GB2-05":{"attempts":2,"playable":47.61017086963963,"score":47.61017086963963},"GB2-06":{"attempts":2,"playable":23.626868110270635,"score":23.626868110270635},"GB2-07":{"attempts":2,"playable":47.513246956421156,"score":47.513246956421156},"GB2-08":{"attempts":2,"playable":35.42041094865495,"score":35.42041094865495}}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T19:15:38Z","match_totals_all":{"draws":5278,"losses":8500,"wins":9733},"match_totals_tracks":{"highest":{"draws":1528,"losses":2320,"wins":4329},"medium":{"draws":1405,"losses":2299,"wins":3454},"none":{"draws":2345,"losses":3881,"wins":1950}},"model_slug":"google-gemini-3-6-flash","official_rank_by_reasoning":{"highest":27,"medium":33,"none":43},"overall":{"max":83.85522753719866,"mean":52.46494373904992,"min":18.756380789651715},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.76764154073839,"GB2-02":54.989227931368966,"GB2-03":69.0036612502482,"GB2-04":62.37675019790042,"GB2-05":83.85522753719866,"GB2-06":82.97409269011435,"GB2-07":51.38388530968991,"GB2-08":55.19449262636733},"per_game_all":{"GB2-01":53.21304603037553,"GB2-02":44.275798674295224,"GB2-03":58.01877215456429,"GB2-04":48.70312713253865,"GB2-05":67.14080131938617,"GB2-06":63.46052586357353,"GB2-07":49.136883029890576,"GB2-08":53.8404774169779},"per_game_match_totals_all":{"GB2-01":{"draws":698,"losses":1154,"wins":1244},"GB2-02":{"draws":1641,"losses":524,"wins":235},"GB2-03":{"draws":314,"losses":1197,"wins":1454},"GB2-04":{"draws":1782,"losses":691,"wins":515},"GB2-05":{"draws":0,"losses":1083,"wins":2097},"GB2-06":{"draws":147,"losses":1096,"wins":1769},"GB2-07":{"draws":0,"losses":1693,"wins":1487},"GB2-08":{"draws":696,"losses":1062,"wins":932}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":245,"losses":355,"wins":432},"GB2-02":{"draws":575,"losses":161,"wins":224},"GB2-03":{"draws":53,"losses":316,"wins":620},"GB2-04":{"draws":479,"losses":152,"wins":365},"GB2-05":{"draws":0,"losses":181,"wins":879},"GB2-06":{"draws":20,"losses":179,"wins":805},"GB2-07":{"draws":0,"losses":541,"wins":519},"GB2-08":{"draws":156,"losses":435,"wins":485}},"medium":{"GB2-01":{"draws":269,"losses":166,"wins":597},"GB2-02":{"draws":335,"losses":140,"wins":5},"GB2-03":{"draws":89,"losses":494,"wins":405},"GB2-04":{"draws":614,"losses":293,"wins":89},"GB2-05":{"draws":0,"losses":330,"wins":730},"GB2-06":{"draws":47,"losses":157,"wins":800},"GB2-07":{"draws":0,"losses":571,"wins":489},"GB2-08":{"draws":51,"losses":148,"wins":339}},"none":{"GB2-01":{"draws":184,"losses":633,"wins":215},"GB2-02":{"draws":731,"losses":223,"wins":6},"GB2-03":{"draws":172,"losses":387,"wins":429},"GB2-04":{"draws":689,"losses":246,"wins":61},"GB2-05":{"draws":0,"losses":572,"wins":488},"GB2-06":{"draws":80,"losses":760,"wins":164},"GB2-07":{"draws":0,"losses":581,"wins":479},"GB2-08":{"draws":489,"losses":479,"wins":108}}},"per_game_raw_elo_all":{"GB2-01":1534.037846144479,"GB2-02":1428.1485064099616,"GB2-03":1507.2654832955302,"GB2-04":1467.409791044113,"GB2-05":1768.452565772983,"GB2-06":1689.8175404640135,"GB2-07":1437.478692026389,"GB2-08":1476.4694349890299},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1530.2475567174756,"GB2-02":1512.9014101783036,"GB2-03":1614.0682824775586,"GB2-04":1578.3411244219155,"GB2-05":2066.828127760226,"GB2-06":2030.3118489793205,"GB2-07":1464.782971505261,"GB2-08":1497.1239578738396},"medium":{"GB2-01":1784.4536753217203,"GB2-02":1374.6432237877098,"GB2-03":1424.6937170939598,"GB2-04":1408.1347510779142,"GB2-05":1830.9247977670561,"GB2-06":2025.1367244232974,"GB2-07":1430.0064492296785,"GB2-08":1695.0816320264578},"none":{"GB2-01":1287.4123063942413,"GB2-02":1396.9008852638717,"GB2-03":1483.0344503150718,"GB2-04":1415.7534976325094,"GB2-05":1407.6047717916672,"GB2-06":1014.004047989423,"GB2-07":1417.6466553442274,"GB2-08":1237.2027150667927}},"per_game_tracks":{"highest":{"GB2-01":55.76764154073839,"GB2-02":54.989227931368966,"GB2-03":69.0036612502482,"GB2-04":62.37675019790042,"GB2-05":83.85522753719866,"GB2-06":82.97409269011435,"GB2-07":51.38388530968991,"GB2-08":55.19449262636733},"medium":{"GB2-01":72.36631037981078,"GB2-02":37.51276157930343,"GB2-03":49.00266093865487,"GB2-04":41.3807927137414,"GB2-05":69.95700555132022,"GB2-06":83.78061679033559,"GB2-07":48.51351682356067,"GB2-08":70.9065286759114},"none":{"GB2-01":31.50518617057742,"GB2-02":40.32540651221328,"GB2-03":56.0499942747898,"GB2-04":42.35183848597413,"GB2-05":47.61017086963963,"GB2-06":23.626868110270635,"GB2-07":47.513246956421156,"GB2-08":35.42041094865495}},"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":1,"rank_movement_baseline_at":"2026-10-22T10:53:58Z","reasoning":{"highest":64.44312238545328,"medium":52.40131854062887,"none":40.55039029106762},"reasoning_agg":{"highest":{"max":83.85522753719866,"mean":64.44312238545328,"min":51.38388530968991},"medium":{"max":83.78061679033559,"mean":52.40131854062887,"min":18.756380789651715},"none":{"max":56.0499942747898,"mean":40.55039029106762,"min":23.626868110270635}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":23.892732094385657},"working_program_strength":{"all":54.72367895270023,"highest":64.44312238545328,"medium":59.1775241815798,"none":40.55039029106762}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:821e38656eecb7ec","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399969999999997},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5826720000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399969999999997},"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":2.391147}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816},"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":52.35047091772464,"highest":64.99095104413249,"medium":54.72004229682714,"none":37.34041941221432},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":59.68718872849263,"score":59.68718872849263},"GB2-02":{"attempts":3,"playable":44.39733302147537,"score":44.39733302147537},"GB2-03":{"attempts":3,"playable":59.69449619453946,"score":59.69449619453946},"GB2-04":{"attempts":3,"playable":45.106996466128145,"score":45.106996466128145},"GB2-05":{"attempts":3,"playable":44.220181107697464,"score":44.220181107697464},"GB2-06":{"attempts":3,"playable":52.53199781140677,"score":52.53199781140677},"GB2-07":{"attempts":3,"playable":59.00498873230246,"score":59.00498873230246},"GB2-08":{"attempts":3,"playable":54.16058527975489,"score":54.16058527975489}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.08059305560386,"score":77.08059305560386},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":80.9187705096003,"score":80.9187705096003},"GB2-04":{"attempts":1,"playable":41.07768520323326,"score":41.07768520323326},"GB2-05":{"attempts":1,"playable":63.23863974067977,"score":63.23863974067977},"GB2-06":{"attempts":1,"playable":52.31212074508953,"score":52.31212074508953},"GB2-07":{"attempts":1,"playable":75.82004365233398,"score":75.82004365233398},"GB2-08":{"attempts":1,"playable":86.56074259696247,"score":86.56074259696247}},"medium":{"GB2-01":{"attempts":1,"playable":51.23496986431073,"score":51.23496986431073},"GB2-02":{"attempts":1,"playable":44.92555622688671,"score":44.92555622688671},"GB2-03":{"attempts":1,"playable":62.15971060425738,"score":62.15971060425738},"GB2-04":{"attempts":1,"playable":53.26785706592201,"score":53.26785706592201},"GB2-05":{"attempts":1,"playable":47.61240137428857,"score":47.61240137428857},"GB2-06":{"attempts":1,"playable":57.89922019242724,"score":57.89922019242724},"GB2-07":{"attempts":1,"playable":64.26118148091865,"score":64.26118148091865},"GB2-08":{"attempts":1,"playable":56.39944156560579,"score":56.39944156560579}},"none":{"GB2-01":{"attempts":1,"playable":50.74600326556329,"score":50.74600326556329},"GB2-02":{"attempts":1,"playable":45.347429987982665,"score":45.347429987982665},"GB2-03":{"attempts":1,"playable":36.005007469760734,"score":36.005007469760734},"GB2-04":{"attempts":1,"playable":40.97544712922916,"score":40.97544712922916},"GB2-05":{"attempts":1,"playable":21.80950220812403,"score":21.80950220812403},"GB2-06":{"attempts":1,"playable":47.38465249670354,"score":47.38465249670354},"GB2-07":{"attempts":1,"playable":36.93374106365475,"score":36.93374106365475},"GB2-08":{"attempts":1,"playable":19.52157167669641,"score":19.52157167669641}}},"id":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-10-24T19:21:04Z","match_totals_all":{"draws":3087,"losses":4574,"wins":4603},"match_totals_tracks":{"highest":{"draws":725,"losses":1135,"wins":2228},"medium":{"draws":1149,"losses":1378,"wins":1561},"none":{"draws":1213,"losses":2061,"wins":814}},"model_slug":"fireworks-ember-1","official_rank_by_reasoning":{"highest":25,"medium":29,"none":49},"overall":{"max":86.56074259696247,"mean":52.35047091772464,"min":19.52157167669641},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.08059305560386,"GB2-02":42.91901284955672,"GB2-03":80.9187705096003,"GB2-04":41.07768520323326,"GB2-05":63.23863974067977,"GB2-06":52.31212074508953,"GB2-07":75.82004365233398,"GB2-08":86.56074259696247},"per_game_all":{"GB2-01":59.68718872849263,"GB2-02":44.39733302147537,"GB2-03":59.69449619453946,"GB2-04":45.106996466128145,"GB2-05":44.220181107697464,"GB2-06":52.53199781140677,"GB2-07":59.00498873230246,"GB2-08":54.16058527975489},"per_game_match_totals_all":{"GB2-01":{"draws":466,"losses":423,"wins":659},"GB2-02":{"draws":1068,"losses":291,"wins":81},"GB2-03":{"draws":297,"losses":498,"wins":687},"GB2-04":{"draws":898,"losses":396,"wins":200},"GB2-05":{"draws":0,"losses":910,"wins":680},"GB2-06":{"draws":66,"losses":746,"wins":694},"GB2-07":{"draws":0,"losses":680,"wins":910},"GB2-08":{"draws":292,"losses":630,"wins":692}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":124,"wins":383},"GB2-02":{"draws":364,"losses":100,"wins":16},"GB2-03":{"draws":16,"losses":99,"wins":379},"GB2-04":{"draws":313,"losses":145,"wins":40},"GB2-05":{"draws":0,"losses":204,"wins":326},"GB2-06":{"draws":18,"losses":252,"wins":232},"GB2-07":{"draws":0,"losses":133,"wins":397},"GB2-08":{"draws":5,"losses":78,"wins":455}},"medium":{"GB2-01":{"draws":257,"losses":134,"wins":125},"GB2-02":{"draws":357,"losses":94,"wins":29},"GB2-03":{"draws":42,"losses":185,"wins":267},"GB2-04":{"draws":303,"losses":90,"wins":105},"GB2-05":{"draws":0,"losses":286,"wins":244},"GB2-06":{"draws":19,"losses":222,"wins":261},"GB2-07":{"draws":0,"losses":199,"wins":331},"GB2-08":{"draws":171,"losses":168,"wins":199}},"none":{"GB2-01":{"draws":200,"losses":165,"wins":151},"GB2-02":{"draws":347,"losses":97,"wins":36},"GB2-03":{"draws":239,"losses":214,"wins":41},"GB2-04":{"draws":282,"losses":161,"wins":55},"GB2-05":{"draws":0,"losses":420,"wins":110},"GB2-06":{"draws":29,"losses":272,"wins":201},"GB2-07":{"draws":0,"losses":348,"wins":182},"GB2-08":{"draws":116,"losses":384,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1571.6591857393717,"GB2-02":1428.5463454809812,"GB2-03":1542.60376350724,"GB2-04":1437.150958973596,"GB2-05":1353.1128729734808,"GB2-06":1460.0092874663926,"GB2-07":1576.9533239051245,"GB2-08":1523.9143751040963},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1758.0295478266967,"GB2-02":1417.117036832385,"GB2-03":1782.171102335592,"GB2-04":1405.9046606856264,"GB2-05":1609.5214703601505,"GB2-06":1455.684808567795,"GB2-07":1812.959986263113,"GB2-08":2041.9679739150072},"medium":{"GB2-01":1480.8047718428918,"GB2-02":1432.6336855054699,"GB2-03":1540.5344078150042,"GB2-04":1500.443896651615,"GB2-05":1407.6884198970465,"GB2-06":1545.0795509010397,"GB2-07":1633.8598408058735,"GB2-08":1472.1204807431063},"none":{"GB2-01":1476.143237548527,"GB2-02":1435.8883141050883,"GB2-03":1305.1057803711246,"GB2-04":1405.1043195835468,"GB2-05":1042.1287286632455,"GB2-06":1379.2635029303433,"GB2-07":1284.0401446463877,"GB2-08":1057.6546706541744}},"per_game_tracks":{"highest":{"GB2-01":77.08059305560386,"GB2-02":42.91901284955672,"GB2-03":80.9187705096003,"GB2-04":41.07768520323326,"GB2-05":63.23863974067977,"GB2-06":52.31212074508953,"GB2-07":75.82004365233398,"GB2-08":86.56074259696247},"medium":{"GB2-01":51.23496986431073,"GB2-02":44.92555622688671,"GB2-03":62.15971060425738,"GB2-04":53.26785706592201,"GB2-05":47.61240137428857,"GB2-06":57.89922019242724,"GB2-07":64.26118148091865,"GB2-08":56.39944156560579},"none":{"GB2-01":50.74600326556329,"GB2-02":45.347429987982665,"GB2-03":36.005007469760734,"GB2-04":40.97544712922916,"GB2-05":21.80950220812403,"GB2-06":47.38465249670354,"GB2-07":36.93374106365475,"GB2-08":19.52157167669641}},"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":-1,"rank_movement_baseline_at":"2026-10-22T10:28:10Z","reasoning":{"highest":64.99095104413249,"medium":54.72004229682714,"none":37.34041941221432},"reasoning_agg":{"highest":{"max":86.56074259696247,"mean":64.99095104413249,"min":41.07768520323326},"medium":{"max":64.26118148091865,"mean":54.72004229682714,"min":44.92555622688671},"none":{"max":50.74600326556329,"mean":37.34041941221432,"min":19.52157167669641}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.65053163191817},"working_program_strength":{"all":52.35047091772464,"highest":64.99095104413249,"medium":54.72004229682714,"none":37.34041941221432}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:bcf866c226eb9ef2","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":52.23085955693165,"highest":68.34252015128969,"medium":47.08506901464458,"none":41.26498950486066},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":26,"evaluated_cells":30,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":21,"first_pass_rate":0.7241379310344828,"game_attempts":{"GB2-01":{"admitted":2,"model_code_failures":1},"GB2-02":{"admitted":3},"GB2-03":{"admitted":7,"model_code_failures":2},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":2,"performance_rejections":1},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.10344827586206896,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":5,"repaired_rate":0.1724137931034483},"baseline":{"admitted_plugins":28,"evaluated_cells":30,"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":8,"model_code_failures":1},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":2,"model_code_failures":1}},"model_code_failure_rate":0.06666666666666667,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":9,"repaired_rate":0.3},"intensive":{"admitted_plugins":25,"evaluated_cells":25,"first_pass_admitted":22,"first_pass_rate":0.88,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":5,"infra_failures_excluded":4},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.12}},"headline_games_all":{"GB2-01":{"attempts":9,"failed_attempts":1,"playable":54.479920623371164,"score":47.55551285710104},"GB2-02":{"attempts":8,"playable":55.80418240432791,"score":55.80418240432791},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":58.03216491985745,"score":52.08372285479544},"GB2-04":{"attempts":9,"playable":59.56840853989658,"score":59.56840853989658},"GB2-05":{"attempts":9,"playable":54.55281699878619,"score":54.55281699878619},"GB2-06":{"attempts":8,"playable":46.8300734305127,"score":46.8300734305127},"GB2-07":{"attempts":9,"playable":50.60668513705763,"score":50.60668513705763},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":54.24838955293427,"score":50.845474232975675}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":3,"playable":58.58808708695517,"score":58.58808708695517},"GB2-02":{"attempts":2,"playable":74.06893408228214,"score":74.06893408228214},"GB2-03":{"attempts":5,"playable":71.18582903954284,"score":71.18582903954284},"GB2-04":{"attempts":3,"playable":71.7054691321352,"score":71.7054691321352},"GB2-05":{"attempts":3,"playable":62.64081524278857,"score":62.64081524278857},"GB2-06":{"attempts":3,"playable":69.54507913145515,"score":69.54507913145515},"GB2-07":{"attempts":3,"playable":66.63660556187308,"score":66.63660556187308},"GB2-08":{"attempts":3,"playable":72.3693419332854,"score":72.3693419332854}},"medium":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":62.31966989643103,"score":41.54644659762069},"GB2-02":{"attempts":3,"playable":50.108075673945955,"score":50.108075673945955},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":57.697270036644746,"score":44.87565447294591},"GB2-04":{"attempts":3,"playable":57.45181241893852,"score":57.45181241893852},"GB2-05":{"attempts":3,"playable":49.32646732693406,"score":49.32646732693406},"GB2-06":{"attempts":2,"playable":28.076428372482543,"score":28.076428372482543},"GB2-07":{"attempts":3,"playable":45.54607840839895,"score":45.54607840839895},"GB2-08":{"attempts":3,"playable":59.74958884589007,"score":59.74958884589007}},"none":{"GB2-01":{"attempts":3,"playable":42.532004886727286,"score":42.532004886727286},"GB2-02":{"attempts":3,"playable":43.23553745675563,"score":43.23553745675563},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":45.213395683384775,"score":40.18968505189758},"GB2-04":{"attempts":3,"playable":49.547944068616005,"score":49.547944068616005},"GB2-05":{"attempts":3,"playable":51.691168426635954,"score":51.691168426635954},"GB2-06":{"attempts":3,"playable":42.86871278760041,"score":42.86871278760041},"GB2-07":{"attempts":3,"playable":39.63737144090086,"score":39.63737144090086},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":30.626237879627343,"score":20.417491919751562}}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-10-24T19:18:13Z","match_totals_all":{"draws":8462,"losses":15015,"wins":16710},"match_totals_tracks":{"highest":{"draws":1368,"losses":3647,"wins":7756},"medium":{"draws":2903,"losses":5128,"wins":5189},"none":{"draws":4191,"losses":6240,"wins":3765}},"model_slug":"stealth-ox-alpha","official_rank_by_reasoning":{"highest":20,"medium":44,"none":40},"overall":{"max":74.06893408228214,"mean":52.23085955693165,"min":20.417491919751562},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.58808708695518,"GB2-02":74.06893408228214,"GB2-03":71.18582903954282,"GB2-04":71.7054691321352,"GB2-05":62.64081524278857,"GB2-06":69.54507913145515,"GB2-07":66.63660556187308,"GB2-08":72.3693419332854},"per_game_all":{"GB2-01":54.479920623371164,"GB2-02":55.8041824043279,"GB2-03":58.03216491985745,"GB2-04":59.56840853989658,"GB2-05":54.55281699878619,"GB2-06":46.8300734305127,"GB2-07":50.60668513705763,"GB2-08":54.24838955293427},"per_game_match_totals_all":{"GB2-01":{"draws":659,"losses":1675,"wins":1794},"GB2-02":{"draws":2496,"losses":599,"wins":745},"GB2-03":{"draws":1878,"losses":3748,"wins":4253},"GB2-04":{"draws":2374,"losses":698,"wins":1410},"GB2-05":{"draws":0,"losses":2246,"wins":2524},"GB2-06":{"draws":145,"losses":2095,"wins":1774},"GB2-07":{"draws":0,"losses":2445,"wins":2325},"GB2-08":{"draws":910,"losses":1509,"wins":1885}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":73,"losses":637,"wins":838},"GB2-02":{"draws":352,"losses":86,"wins":522},"GB2-03":{"draws":143,"losses":715,"wins":1611},"GB2-04":{"draws":567,"losses":160,"wins":767},"GB2-05":{"draws":0,"losses":621,"wins":969},"GB2-06":{"draws":92,"losses":453,"wins":961},"GB2-07":{"draws":0,"losses":556,"wins":1034},"GB2-08":{"draws":141,"losses":419,"wins":1054}},"medium":{"GB2-01":{"draws":218,"losses":302,"wins":512},"GB2-02":{"draws":1035,"losses":226,"wins":179},"GB2-03":{"draws":384,"losses":1395,"wins":1679},"GB2-04":{"draws":872,"losses":226,"wins":396},"GB2-05":{"draws":0,"losses":831,"wins":759},"GB2-06":{"draws":21,"losses":738,"wins":243},"GB2-07":{"draws":0,"losses":894,"wins":696},"GB2-08":{"draws":373,"losses":516,"wins":725}},"none":{"GB2-01":{"draws":368,"losses":736,"wins":444},"GB2-02":{"draws":1109,"losses":287,"wins":44},"GB2-03":{"draws":1351,"losses":1638,"wins":963},"GB2-04":{"draws":935,"losses":312,"wins":247},"GB2-05":{"draws":0,"losses":794,"wins":796},"GB2-06":{"draws":32,"losses":904,"wins":570},"GB2-07":{"draws":0,"losses":995,"wins":595},"GB2-08":{"draws":396,"losses":574,"wins":106}}},"per_game_raw_elo_all":{"GB2-01":1513.6309925268422,"GB2-02":1527.9640179346422,"GB2-03":1525.0803457206118,"GB2-04":1563.3626949463942,"GB2-05":1498.2419515789063,"GB2-06":1376.6898763185911,"GB2-07":1452.01501518687,"GB2-08":1491.3406014640625},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1555.0915206612638,"GB2-02":1691.5827743144132,"GB2-03":1674.1137515646565,"GB2-04":1684.3459021105919,"GB2-05":1606.8938876228467,"GB2-06":1777.0926759857248,"GB2-07":1672.3725257121887,"GB2-08":1753.5994697232065},"medium":{"GB2-01":1589.9029830982047,"GB2-02":1472.7509759690886,"GB2-03":1515.8680389336264,"GB2-04":1534.008012268059,"GB2-05":1429.031537697704,"GB2-06":1040.9108316524962,"GB2-07":1380.886563189816,"GB2-08":1534.191813313307},"none":{"GB2-01":1395.8984738210584,"GB2-02":1419.5583035204247,"GB2-03":1385.2592466635529,"GB2-04":1471.7341704605312,"GB2-05":1458.800429416168,"GB2-06":1312.0661213175529,"GB2-07":1302.7859566586053,"GB2-08":1186.2305213556745}},"per_game_tracks":{"highest":{"GB2-01":58.58808708695518,"GB2-02":74.06893408228214,"GB2-03":71.18582903954282,"GB2-04":71.7054691321352,"GB2-05":62.64081524278857,"GB2-06":69.54507913145515,"GB2-07":66.63660556187308,"GB2-08":72.3693419332854},"medium":{"GB2-01":62.31966989643103,"GB2-02":50.10807567394594,"GB2-03":57.697270036644746,"GB2-04":57.45181241893852,"GB2-05":49.32646732693406,"GB2-06":28.076428372482543,"GB2-07":45.54607840839895,"GB2-08":59.74958884589007},"none":{"GB2-01":42.532004886727286,"GB2-02":43.23553745675563,"GB2-03":45.213395683384775,"GB2-04":49.547944068616005,"GB2-05":51.691168426635954,"GB2-06":42.86871278760041,"GB2-07":39.63737144090086,"GB2-08":30.626237879627343}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:41:54Z","reasoning":{"highest":68.34252015128969,"medium":47.08506901464458,"none":41.26498950486066},"reasoning_agg":{"highest":{"max":74.06893408228214,"mean":68.34252015128969,"min":58.58808708695517},"medium":{"max":59.74958884589007,"mean":47.08506901464458,"min":28.076428372482543},"none":{"max":51.691168426635954,"mean":41.26498950486066,"min":20.417491919751562}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.077530646429032},"working_program_strength":{"all":54.26533020084298,"highest":68.34252015128969,"medium":51.284423872458234,"none":43.169046578781035}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:5f504bf8d13cd087","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":7.44989},"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":1.7435249999999998},"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":1.262825}},"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":10.456240000000001},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":51.76614108852136,"highest":64.12444294242178,"medium":48.34109596906026,"none":42.83288435408205},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":31,"output_token_observations":25,"total_output_tokens":356249},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.5352526760376,"score":55.5352526760376},"GB2-02":{"attempts":3,"playable":53.67287743505847,"score":53.67287743505847},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":30.97469913129941,"score":10.324899710433137},"GB2-04":{"attempts":3,"playable":52.24975871178535,"score":52.24975871178535},"GB2-05":{"attempts":3,"playable":40.03511238245383,"score":40.03511238245383},"GB2-06":{"attempts":3,"playable":70.58663803054348,"score":70.58663803054348},"GB2-07":{"attempts":3,"playable":65.73693281683494,"score":65.73693281683494},"GB2-08":{"attempts":3,"playable":65.98765694502413,"score":65.98765694502413}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.78520673277976,"score":68.78520673277976},"GB2-02":{"attempts":1,"playable":79.41587163315971,"score":79.41587163315971},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":72.14175288896605,"score":72.14175288896605},"GB2-05":{"attempts":1,"playable":49.339289015443974,"score":49.339289015443974},"GB2-06":{"attempts":1,"playable":83.19121972431873,"score":83.19121972431873},"GB2-07":{"attempts":1,"playable":76.85852015076901,"score":76.85852015076901},"GB2-08":{"attempts":1,"playable":83.26368339393711,"score":83.26368339393711}},"medium":{"GB2-01":{"attempts":1,"playable":41.41546186717055,"score":41.41546186717055},"GB2-02":{"attempts":1,"playable":42.178687497765914,"score":42.178687497765914},"GB2-03":{"attempts":1,"playable":30.97469913129941,"score":30.97469913129941},"GB2-04":{"attempts":1,"playable":42.507992568198404,"score":42.507992568198404},"GB2-05":{"attempts":1,"playable":48.18828069688791,"score":48.18828069688791},"GB2-06":{"attempts":1,"playable":79.72395295397472,"score":79.72395295397472},"GB2-07":{"attempts":1,"playable":68.14461971211765,"score":68.14461971211765},"GB2-08":{"attempts":1,"playable":33.595073325067546,"score":33.595073325067546}},"none":{"GB2-01":{"attempts":1,"playable":56.40508942816248,"score":56.40508942816248},"GB2-02":{"attempts":1,"playable":39.424073174249784,"score":39.424073174249784},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.09953067819158,"score":42.09953067819158},"GB2-05":{"attempts":1,"playable":22.57776743502962,"score":22.57776743502962},"GB2-06":{"attempts":1,"playable":48.844741413337,"score":48.844741413337},"GB2-07":{"attempts":1,"playable":52.20765858761817,"score":52.20765858761817},"GB2-08":{"attempts":1,"playable":81.10421411606772,"score":81.10421411606772}}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-10-24T19:04:49Z","match_totals_all":{"draws":2507,"losses":3866,"wins":4902},"match_totals_tracks":{"highest":{"draws":484,"losses":779,"wins":2331},"medium":{"draws":1216,"losses":1585,"wins":1286},"none":{"draws":807,"losses":1502,"wins":1285}},"model_slug":"claude-opus-4-8","official_rank_by_reasoning":{"highest":29,"medium":42,"none":33},"overall":{"max":83.26368339393711,"mean":51.76614108852136,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.78520673277976,"GB2-02":79.41587163315971,"GB2-04":72.14175288896605,"GB2-05":49.339289015443974,"GB2-06":83.19121972431873,"GB2-07":76.85852015076901,"GB2-08":83.26368339393711},"per_game_all":{"GB2-01":55.5352526760376,"GB2-02":53.67287743505847,"GB2-04":52.24975871178535,"GB2-05":40.03511238245383,"GB2-06":70.58663803054348,"GB2-07":65.73693281683494,"GB2-08":65.98765694502413},"per_game_match_totals_all":{"GB2-01":{"draws":257,"losses":592,"wins":699},"GB2-02":{"draws":901,"losses":238,"wins":301},"GB2-03":{"draws":152,"losses":281,"wins":61},"GB2-04":{"draws":859,"losses":308,"wins":327},"GB2-05":{"draws":0,"losses":976,"wins":614},"GB2-06":{"draws":68,"losses":451,"wins":986},"GB2-07":{"draws":0,"losses":570,"wins":1020},"GB2-08":{"draws":270,"losses":450,"wins":894}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":68,"losses":138,"wins":310},"GB2-02":{"draws":181,"losses":14,"wins":285},"GB2-04":{"draws":203,"losses":45,"wins":250},"GB2-05":{"draws":0,"losses":277,"wins":253},"GB2-06":{"draws":31,"losses":78,"wins":393},"GB2-07":{"draws":0,"losses":127,"wins":403},"GB2-08":{"draws":1,"losses":100,"wins":437}},"medium":{"GB2-01":{"draws":75,"losses":275,"wins":166},"GB2-02":{"draws":385,"losses":93,"wins":2},"GB2-03":{"draws":152,"losses":281,"wins":61},"GB2-04":{"draws":327,"losses":131,"wins":40},"GB2-05":{"draws":0,"losses":283,"wins":247},"GB2-06":{"draws":9,"losses":108,"wins":384},"GB2-07":{"draws":0,"losses":177,"wins":353},"GB2-08":{"draws":268,"losses":237,"wins":33}},"none":{"GB2-01":{"draws":114,"losses":179,"wins":223},"GB2-02":{"draws":335,"losses":131,"wins":14},"GB2-04":{"draws":329,"losses":132,"wins":37},"GB2-05":{"draws":0,"losses":416,"wins":114},"GB2-06":{"draws":28,"losses":265,"wins":209},"GB2-07":{"draws":0,"losses":266,"wins":264},"GB2-08":{"draws":1,"losses":113,"wins":424}}},"per_game_raw_elo_all":{"GB2-01":1525.1811669358115,"GB2-02":1515.8252326540767,"GB2-04":1498.5591940687318,"GB2-05":1299.8006922330826,"GB2-06":1784.4169784385742,"GB2-07":1665.4786474204939,"GB2-08":1693.3216845196105},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1657.9220086422833,"GB2-02":1746.2910914919823,"GB2-04":1664.7325231006726,"GB2-05":1429.1409970526179,"GB2-06":2011.640211203316,"GB2-07":1831.6752943024442,"GB2-08":1956.6404539329194},"medium":{"GB2-01":1387.0806702396007,"GB2-02":1411.3694893247707,"GB2-03":1259.0191538079791,"GB2-04":1417.0622493909254,"GB2-05":1414.844790431763,"GB2-06":1939.8776110017893,"GB2-07":1689.6190691972947,"GB2-08":1218.0861949364878},"none":{"GB2-01":1530.54082192555,"GB2-02":1389.8151171454763,"GB2-04":1413.882809714598,"GB2-05":1055.4162892148665,"GB2-06":1401.7331131106175,"GB2-07":1475.1415787617423,"GB2-08":1905.238404689424}},"per_game_tracks":{"highest":{"GB2-01":68.78520673277976,"GB2-02":79.41587163315971,"GB2-04":72.14175288896605,"GB2-05":49.339289015443974,"GB2-06":83.19121972431873,"GB2-07":76.85852015076901,"GB2-08":83.26368339393711},"medium":{"GB2-01":41.41546186717055,"GB2-02":42.178687497765914,"GB2-03":30.97469913129941,"GB2-04":42.507992568198404,"GB2-05":48.18828069688791,"GB2-06":79.72395295397472,"GB2-07":68.14461971211765,"GB2-08":33.595073325067546},"none":{"GB2-01":56.40508942816248,"GB2-02":39.424073174249784,"GB2-04":42.09953067819158,"GB2-05":22.57776743502962,"GB2-06":48.844741413337,"GB2-07":52.20765858761817,"GB2-08":81.10421411606772}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:32:14Z","reasoning":{"highest":64.12444294242178,"medium":48.34109596906026,"none":42.83288435408205},"reasoning_agg":{"highest":{"max":83.26368339393711,"mean":64.12444294242178,"min":0.0},"medium":{"max":79.72395295397472,"mean":48.34109596906026,"min":30.97469913129941},"none":{"max":81.10421411606772,"mean":42.83288435408205,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.291558588339733},"working_program_strength":{"all":56.859347150259644,"highest":73.28507764848203,"medium":48.34109596906026,"none":48.951867833236626}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:ae38f82fed4234a4","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":1.5865090123478316},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870414}},"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":1.5865090123478316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.13084687320145388,"mean":0.0871504498983802,"median":0.08084431374719805,"min":0.0619993303028941,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.6972035991870416},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.164549388465127}},"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":4.982416500000002},"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":51.211938085751314,"highest":64.34445660024012,"medium":57.169951256093924,"none":32.121406400919895},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":11,"first_pass_rate":0.6875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.1875},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":71.1115194900767,"score":71.1115194900767},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":49.139922017658385,"score":42.533883702229424},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":55.08975273224891,"score":51.17671883793673},"GB2-04":{"attempts":4,"playable":45.45812708752772,"score":45.45812708752772},"GB2-05":{"attempts":4,"playable":45.087873232489024,"score":45.087873232489024},"GB2-06":{"attempts":4,"playable":63.10150873273477,"score":63.10150873273477},"GB2-07":{"attempts":4,"playable":50.5344776486578,"score":50.5344776486578},"GB2-08":{"attempts":4,"playable":40.69139595435835,"score":40.69139595435835}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.48473770293332,"score":90.48473770293332},"GB2-02":{"attempts":1,"playable":62.85797993351466,"score":62.85797993351466},"GB2-03":{"attempts":1,"playable":72.87286752540582,"score":72.87286752540582},"GB2-04":{"attempts":1,"playable":39.95254142394899,"score":39.95254142394899},"GB2-05":{"attempts":1,"playable":52.02073491032271,"score":52.02073491032271},"GB2-06":{"attempts":1,"playable":75.55492346606826,"score":75.55492346606826},"GB2-07":{"attempts":1,"playable":52.20765858761817,"score":52.20765858761817},"GB2-08":{"attempts":1,"playable":68.80420925210903,"score":68.80420925210903}},"medium":{"GB2-01":{"attempts":1,"playable":73.37813132109414,"score":73.37813132109414},"GB2-02":{"attempts":1,"playable":44.92555622688671,"score":44.92555622688671},"GB2-03":{"attempts":1,"playable":68.91818730546785,"score":68.91818730546785},"GB2-04":{"attempts":1,"playable":54.47721464135905,"score":54.47721464135905},"GB2-05":{"attempts":1,"playable":67.19039459119736,"score":67.19039459119736},"GB2-06":{"attempts":1,"playable":73.64452688619541,"score":73.64452688619541},"GB2-07":{"attempts":1,"playable":54.21186199904023,"score":54.21186199904023},"GB2-08":{"attempts":1,"playable":20.613737077510645,"score":20.613737077510645}},"none":{"GB2-01":{"attempts":2,"playable":49.47168944620261,"score":49.47168944620261},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.63622989257377,"score":19.818114946286887},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":23.478203365873036,"score":11.739101682936518},"GB2-04":{"attempts":2,"playable":41.94462519727513,"score":41.94462519727513},"GB2-05":{"attempts":2,"playable":16.052490195946994,"score":16.052490195946994},"GB2-06":{"attempts":2,"playable":40.105075845940625,"score":40.105075845940625},"GB2-07":{"attempts":2,"playable":45.183912359314995,"score":45.183912359314995},"GB2-08":{"attempts":2,"playable":32.65624153345537,"score":32.65624153345537}}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T19:15:48Z","match_totals_all":{"draws":3264,"losses":6484,"wins":5629},"match_totals_tracks":{"highest":{"draws":675,"losses":1212,"wins":2201},"medium":{"draws":829,"losses":1433,"wins":1825},"none":{"draws":1760,"losses":3839,"wins":1603}},"model_slug":"google-gemini-3-5-flash","official_rank_by_reasoning":{"highest":28,"medium":25,"none":56},"overall":{"max":90.48473770293332,"mean":51.211938085751314,"min":11.739101682936518},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.48473770293332,"GB2-02":62.85797993351466,"GB2-03":72.87286752540582,"GB2-04":39.95254142394899,"GB2-05":52.02073491032271,"GB2-06":75.55492346606826,"GB2-07":52.20765858761817,"GB2-08":68.80420925210903},"per_game_all":{"GB2-01":71.1115194900767,"GB2-02":49.139922017658385,"GB2-03":55.08975273224891,"GB2-04":45.45812708752772,"GB2-05":45.087873232489024,"GB2-06":63.10150873273477,"GB2-07":50.5344776486578,"GB2-08":40.69139595435835},"per_game_match_totals_all":{"GB2-01":{"draws":220,"losses":636,"wins":1208},"GB2-02":{"draws":1029,"losses":242,"wins":169},"GB2-03":{"draws":154,"losses":636,"wins":691},"GB2-04":{"draws":1188,"losses":543,"wins":261},"GB2-05":{"draws":0,"losses":1346,"wins":774},"GB2-06":{"draws":30,"losses":901,"wins":1077},"GB2-07":{"draws":0,"losses":1128,"wins":992},"GB2-08":{"draws":643,"losses":1052,"wins":457}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":45,"wins":450},"GB2-02":{"draws":265,"losses":54,"wins":161},"GB2-03":{"draws":39,"losses":131,"wins":324},"GB2-04":{"draws":264,"losses":175,"wins":59},"GB2-05":{"draws":0,"losses":263,"wins":267},"GB2-06":{"draws":11,"losses":130,"wins":361},"GB2-07":{"draws":0,"losses":266,"wins":264},"GB2-08":{"draws":75,"losses":148,"wins":315}},"medium":{"GB2-01":{"draws":14,"losses":141,"wins":361},"GB2-02":{"draws":403,"losses":71,"wins":6},"GB2-03":{"draws":46,"losses":148,"wins":299},"GB2-04":{"draws":287,"losses":92,"wins":119},"GB2-05":{"draws":0,"losses":183,"wins":347},"GB2-06":{"draws":10,"losses":141,"wins":351},"GB2-07":{"draws":0,"losses":255,"wins":275},"GB2-08":{"draws":69,"losses":402,"wins":67}},"none":{"GB2-01":{"draws":185,"losses":450,"wins":397},"GB2-02":{"draws":361,"losses":117,"wins":2},"GB2-03":{"draws":69,"losses":357,"wins":68},"GB2-04":{"draws":637,"losses":276,"wins":83},"GB2-05":{"draws":0,"losses":900,"wins":160},"GB2-06":{"draws":9,"losses":630,"wins":365},"GB2-07":{"draws":0,"losses":607,"wins":453},"GB2-08":{"draws":499,"losses":502,"wins":75}}},"per_game_raw_elo_all":{"GB2-01":1724.0903917376297,"GB2-02":1466.561189030769,"GB2-03":1485.9687776837518,"GB2-04":1439.88404903787,"GB2-05":1354.4610736577447,"GB2-06":1650.6778876559238,"GB2-07":1454.333554782782,"GB2-08":1312.5070755680288},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1996.6679728124827,"GB2-02":1575.5630641220496,"GB2-03":1661.2553423426248,"GB2-04":1397.072709325324,"GB2-05":1462.5168962575933,"GB2-06":1858.192765073702,"GB2-07":1475.1415787617423,"GB2-08":1657.6270852037603},"medium":{"GB2-01":1711.0944636585812,"GB2-02":1432.6336855054699,"GB2-03":1613.0251768004696,"GB2-04":1509.9623000666104,"GB2-05":1667.741746168598,"GB2-06":1821.8942473852683,"GB2-07":1500.55213154943,"GB2-08":1071.70546826136},"none":{"GB2-01":1464.5087387418248,"GB2-02":1391.4868174647875,"GB2-03":1183.6258139081613,"GB2-04":1412.617137721676,"GB2-05":933.1245785470428,"GB2-06":1271.9466505088017,"GB2-07":1387.3069540371732,"GB2-08":1208.1886732389657}},"per_game_tracks":{"highest":{"GB2-01":90.48473770293332,"GB2-02":62.85797993351466,"GB2-03":72.87286752540582,"GB2-04":39.95254142394899,"GB2-05":52.02073491032271,"GB2-06":75.55492346606826,"GB2-07":52.20765858761817,"GB2-08":68.80420925210903},"medium":{"GB2-01":73.37813132109414,"GB2-02":44.92555622688671,"GB2-03":68.91818730546785,"GB2-04":54.47721464135905,"GB2-05":67.19039459119736,"GB2-06":73.64452688619541,"GB2-07":54.21186199904023,"GB2-08":20.613737077510645},"none":{"GB2-01":49.47168944620261,"GB2-02":39.63622989257377,"GB2-03":23.478203365873036,"GB2-04":41.94462519727513,"GB2-05":16.052490195946994,"GB2-06":40.105075845940625,"GB2-07":45.183912359314995,"GB2-08":32.65624153345537}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:29:16Z","reasoning":{"highest":64.34445660024012,"medium":57.169951256093924,"none":32.121406400919895},"reasoning_agg":{"highest":{"max":90.48473770293332,"mean":64.34445660024012,"min":39.95254142394899},"medium":{"max":73.64452688619541,"mean":57.169951256093924,"min":20.613737077510645},"none":{"max":49.47168944620261,"mean":32.121406400919895,"min":11.739101682936518}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":32.22305019932023},"working_program_strength":{"all":52.526822111968954,"highest":64.34445660024012,"medium":57.169951256093924,"none":36.06605847957282}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:9d14cd9c426a28cb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"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":1.1380199999999998}},"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":3.5428550000000003},"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":50.62184918420413,"highest":61.23475654547167,"medium":53.09433199049003,"none":37.53645901665069},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"total_output_tokens":851788},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":65.70113754719837,"score":65.70113754719837},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":48.79063188131709,"score":32.52708792087806},"GB2-03":{"attempts":3,"playable":43.127407631404935,"score":43.127407631404935},"GB2-04":{"attempts":3,"playable":39.4386906497792,"score":39.4386906497792},"GB2-05":{"attempts":3,"playable":68.80428579026157,"score":68.80428579026157},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":55.673008482268116,"score":37.11533898817874},"GB2-07":{"attempts":3,"playable":62.04628202513561,"score":62.04628202513561},"GB2-08":{"attempts":3,"playable":56.21456292079656,"score":56.21456292079656}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.93397394003647,"score":80.93397394003647},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":51.12197703936891,"score":51.12197703936891},"GB2-04":{"attempts":1,"playable":36.57045054563494,"score":36.57045054563494},"GB2-05":{"attempts":1,"playable":77.1914917137311,"score":77.1914917137311},"GB2-06":{"attempts":1,"playable":82.0099718829976,"score":82.0099718829976},"GB2-07":{"attempts":1,"playable":87.0093264136215,"score":87.0093264136215},"GB2-08":{"attempts":1,"playable":75.04086082838288,"score":75.04086082838288}},"medium":{"GB2-01":{"attempts":1,"playable":64.93446883724793,"score":64.93446883724793},"GB2-02":{"attempts":1,"playable":55.720030956549635,"score":55.720030956549635},"GB2-03":{"attempts":1,"playable":39.49943996769355,"score":39.49943996769355},"GB2-04":{"attempts":1,"playable":39.95254142394899,"score":39.95254142394899},"GB2-05":{"attempts":1,"playable":77.00934253699388,"score":77.00934253699388},"GB2-06":{"attempts":1,"playable":29.336045081538625,"score":29.336045081538625},"GB2-07":{"attempts":1,"playable":61.057956804953974,"score":61.057956804953974},"GB2-08":{"attempts":1,"playable":57.24483031499368,"score":57.24483031499368}},"none":{"GB2-01":{"attempts":1,"playable":51.23496986431073,"score":51.23496986431073},"GB2-02":{"attempts":1,"playable":41.861232806084544,"score":41.861232806084544},"GB2-03":{"attempts":1,"playable":38.76080588715236,"score":38.76080588715236},"GB2-04":{"attempts":1,"playable":41.79307997975365,"score":41.79307997975365},"GB2-05":{"attempts":1,"playable":52.21202312005973,"score":52.21202312005973},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":38.071562856831356,"score":38.071562856831356},"GB2-08":{"attempts":1,"playable":36.35799761901313,"score":36.35799761901313}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-10-24T18:49:01Z","match_totals_all":{"draws":3267,"losses":3642,"wins":4373},"match_totals_tracks":{"highest":{"draws":692,"losses":793,"wins":2123},"medium":{"draws":1205,"losses":1405,"wins":1478},"none":{"draws":1370,"losses":1444,"wins":772}},"model_slug":"gpt-5-5","official_rank_by_reasoning":{"highest":32,"medium":31,"none":48},"overall":{"max":87.0093264136215,"mean":50.62184918420413,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.93397394003647,"GB2-03":51.12197703936891,"GB2-04":36.57045054563494,"GB2-05":77.1914917137311,"GB2-06":82.0099718829976,"GB2-07":87.0093264136215,"GB2-08":75.04086082838288},"per_game_all":{"GB2-01":65.70113754719837,"GB2-03":43.127407631404935,"GB2-04":39.4386906497792,"GB2-05":68.80428579026157,"GB2-07":62.04628202513561,"GB2-08":56.21456292079656},"per_game_match_totals_all":{"GB2-01":{"draws":717,"losses":204,"wins":627},"GB2-02":{"draws":688,"losses":164,"wins":108},"GB2-03":{"draws":437,"losses":680,"wins":365},"GB2-04":{"draws":873,"losses":492,"wins":129},"GB2-05":{"draws":0,"losses":521,"wins":1069},"GB2-06":{"draws":41,"losses":454,"wins":509},"GB2-07":{"draws":0,"losses":627,"wins":963},"GB2-08":{"draws":511,"losses":500,"wins":603}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":126,"losses":45,"wins":345},"GB2-03":{"draws":144,"losses":189,"wins":161},"GB2-04":{"draws":283,"losses":182,"wins":33},"GB2-05":{"draws":0,"losses":129,"wins":401},"GB2-06":{"draws":30,"losses":85,"wins":387},"GB2-07":{"draws":0,"losses":68,"wins":462},"GB2-08":{"draws":109,"losses":95,"wins":334}},"medium":{"GB2-01":{"draws":280,"losses":52,"wins":184},"GB2-02":{"draws":304,"losses":69,"wins":107},"GB2-03":{"draws":164,"losses":235,"wins":95},"GB2-04":{"draws":288,"losses":163,"wins":47},"GB2-05":{"draws":0,"losses":130,"wins":400},"GB2-06":{"draws":11,"losses":369,"wins":122},"GB2-07":{"draws":0,"losses":217,"wins":313},"GB2-08":{"draws":158,"losses":170,"wins":210}},"none":{"GB2-01":{"draws":311,"losses":107,"wins":98},"GB2-02":{"draws":384,"losses":95,"wins":1},"GB2-03":{"draws":129,"losses":256,"wins":109},"GB2-04":{"draws":302,"losses":147,"wins":49},"GB2-05":{"draws":0,"losses":262,"wins":268},"GB2-07":{"draws":0,"losses":342,"wins":188},"GB2-08":{"draws":244,"losses":235,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1636.5575228506368,"GB2-03":1367.6345670665607,"GB2-04":1392.8955633549187,"GB2-05":1720.0190164934254,"GB2-07":1653.268503709768,"GB2-08":1501.5329710019068},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1812.4813479891566,"GB2-03":1437.3800791015906,"GB2-04":1370.1200025826765,"GB2-05":1849.5648702531842,"GB2-06":1986.666031906463,"GB2-07":2071.3205814977314,"GB2-08":1774.449547314202},"medium":{"GB2-01":1616.3864487198625,"GB2-02":1516.6263128800113,"GB2-03":1336.0018586551807,"GB2-04":1397.072709325324,"GB2-05":1845.5851417864187,"GB2-06":1106.517102257221,"GB2-07":1589.9820630916538,"GB2-08":1483.1279329990552},"none":{"GB2-01":1480.8047718428918,"GB2-02":1408.9000049575616,"GB2-03":1329.521763442911,"GB2-04":1411.4939781567564,"GB2-05":1464.9070374406729,"GB2-07":1298.5028665399188,"GB2-08":1247.021432692463}},"per_game_tracks":{"highest":{"GB2-01":80.93397394003647,"GB2-03":51.12197703936891,"GB2-04":36.57045054563494,"GB2-05":77.1914917137311,"GB2-06":82.0099718829976,"GB2-07":87.0093264136215,"GB2-08":75.04086082838288},"medium":{"GB2-01":64.93446883724793,"GB2-02":55.720030956549635,"GB2-03":39.49943996769355,"GB2-04":39.95254142394899,"GB2-05":77.00934253699388,"GB2-06":29.336045081538625,"GB2-07":61.057956804953974,"GB2-08":57.24483031499368},"none":{"GB2-01":51.23496986431073,"GB2-02":41.861232806084544,"GB2-03":38.76080588715236,"GB2-04":41.79307997975365,"GB2-05":52.21202312005973,"GB2-07":38.071562856831356,"GB2-08":36.35799761901313}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:59:28Z","reasoning":{"highest":61.23475654547167,"medium":53.09433199049003,"none":37.53645901665069},"reasoning_agg":{"highest":{"max":87.0093264136215,"mean":61.23475654547167,"min":0.0},"medium":{"max":77.00934253699388,"mean":53.09433199049003,"min":29.336045081538625},"none":{"max":52.21202312005973,"mean":37.53645901665069,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":23.69829752882098},"working_program_strength":{"all":55.32524040144805,"highest":69.98257890911047,"medium":53.09433199049003,"none":42.89881030474364}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:28f20064a86160e5","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":4.659586000000001},"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":0.957684},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.45275},"codegen_latency_ms":{"attempt_count":30,"max_ms":1708792,"mean_ms":723489.2413793104,"min_ms":155474,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1708792,"mean_ms":1260718.7692307692,"min_ms":853424,"run_count":13},"medium":{"attempt_count":8,"max_ms":700604,"mean_ms":265043.125,"min_ms":183145,"run_count":8},"none":{"attempt_count":8,"max_ms":461859,"mean_ms":308937.375,"min_ms":155474,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":76211,"output_mean":34293.10344827586,"output_min":8500,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":76211,"output_mean":56804.769230769234,"output_min":37117,"run_count":13},"medium":{"attempt_count":8,"output_max":40473,"output_mean":14733.75,"output_min":10090,"run_count":8},"none":{"attempt_count":8,"output_max":26415,"output_mean":17271.0,"output_min":8500,"run_count":8}},"display_name":"Qwen3.8 Max","economics":{"all":50.00072628886439,"highest":51.08301079155329,"medium":50.58538671053644,"none":48.33378136450345},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":33.90684832789466,"score":33.90684832789466},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":45.052416039759585,"score":36.40911647475024},"GB2-03":{"attempts":3,"playable":51.0174050826634,"score":51.0174050826634},"GB2-04":{"attempts":3,"playable":48.782398718546425,"score":48.782398718546425},"GB2-05":{"attempts":3,"playable":68.7045973149584,"score":68.7045973149584},"GB2-06":{"attempts":3,"playable":40.86961953556672,"score":40.86961953556672},"GB2-07":{"attempts":3,"playable":63.34169748124227,"score":63.34169748124227},"GB2-08":{"attempts":3,"playable":56.97412737529302,"score":56.97412737529302}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":32.601582303855444,"score":32.601582303855444},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":51.85979739005609,"score":25.929898695028044},"GB2-03":{"attempts":1,"playable":57.69171155645705,"score":57.69171155645705},"GB2-04":{"attempts":1,"playable":66.54800849483952,"score":66.54800849483952},"GB2-05":{"attempts":1,"playable":47.42038827962544,"score":47.42038827962544},"GB2-06":{"attempts":1,"playable":52.12075316960467,"score":52.12075316960467},"GB2-07":{"attempts":1,"playable":78.0679586400933,"score":78.0679586400933},"GB2-08":{"attempts":1,"playable":48.28378519292282,"score":48.28378519292282}},"medium":{"GB2-01":{"attempts":1,"playable":42.302736781598085,"score":42.302736781598085},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":56.38851556978438,"score":56.38851556978438},"GB2-04":{"attempts":1,"playable":37.90394757154637,"score":37.90394757154637},"GB2-05":{"attempts":1,"playable":68.12724355055535,"score":68.12724355055535},"GB2-06":{"attempts":1,"playable":49.42613185517056,"score":49.42613185517056},"GB2-07":{"attempts":1,"playable":39.96076261494025,"score":39.96076261494025},"GB2-08":{"attempts":1,"playable":67.65474289113979,"score":67.65474289113979}},"none":{"GB2-01":{"attempts":1,"playable":26.816225898230446,"score":26.816225898230446},"GB2-02":{"attempts":1,"playable":40.378437879665945,"score":40.378437879665945},"GB2-03":{"attempts":1,"playable":38.971988121748765,"score":38.971988121748765},"GB2-04":{"attempts":1,"playable":41.89524008925337,"score":41.89524008925337},"GB2-05":{"attempts":1,"playable":90.56616011469444,"score":90.56616011469444},"GB2-06":{"attempts":1,"playable":21.061973581924928,"score":21.061973581924928},"GB2-07":{"attempts":1,"playable":71.99637118869325,"score":71.99637118869325},"GB2-08":{"attempts":1,"playable":54.98385404181646,"score":54.98385404181646}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-10-24T18:50:39Z","match_totals_all":{"draws":3194,"losses":4665,"wins":4405},"match_totals_tracks":{"highest":{"draws":930,"losses":1500,"wins":1658},"medium":{"draws":1096,"losses":1572,"wins":1420},"none":{"draws":1168,"losses":1593,"wins":1327}},"model_slug":"qwen-qwen3-8-max","official_rank_by_reasoning":{"highest":42,"medium":37,"none":25},"overall":{"max":90.56616011469444,"mean":50.00072628886439,"min":21.061973581924928},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.601582303855444,"GB2-02":51.85979739005609,"GB2-03":57.69171155645705,"GB2-04":66.54800849483952,"GB2-05":47.42038827962544,"GB2-06":52.12075316960467,"GB2-07":78.0679586400933,"GB2-08":48.28378519292282},"per_game_all":{"GB2-01":33.90684832789466,"GB2-02":45.052416039759585,"GB2-03":51.0174050826634,"GB2-04":48.782398718546425,"GB2-05":68.7045973149584,"GB2-06":40.86961953556672,"GB2-07":63.34169748124227,"GB2-08":56.97412737529302},"per_game_match_totals_all":{"GB2-01":{"draws":380,"losses":861,"wins":307},"GB2-02":{"draws":1073,"losses":279,"wins":88},"GB2-03":{"draws":304,"losses":631,"wins":547},"GB2-04":{"draws":841,"losses":369,"wins":284},"GB2-05":{"draws":0,"losses":517,"wins":1073},"GB2-06":{"draws":106,"losses":897,"wins":503},"GB2-07":{"draws":0,"losses":607,"wins":983},"GB2-08":{"draws":490,"losses":504,"wins":620}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":96,"losses":309,"wins":111},"GB2-02":{"draws":343,"losses":68,"wins":69},"GB2-03":{"draws":37,"losses":210,"wins":247},"GB2-04":{"draws":202,"losses":74,"wins":222},"GB2-05":{"draws":0,"losses":287,"wins":243},"GB2-06":{"draws":40,"losses":242,"wins":220},"GB2-07":{"draws":0,"losses":120,"wins":410},"GB2-08":{"draws":212,"losses":190,"wins":136}},"medium":{"GB2-01":{"draws":166,"losses":225,"wins":125},"GB2-02":{"draws":380,"losses":92,"wins":8},"GB2-03":{"draws":102,"losses":184,"wins":208},"GB2-04":{"draws":326,"losses":154,"wins":18},"GB2-05":{"draws":0,"losses":178,"wins":352},"GB2-06":{"draws":40,"losses":256,"wins":206},"GB2-07":{"draws":0,"losses":332,"wins":198},"GB2-08":{"draws":82,"losses":151,"wins":305}},"none":{"GB2-01":{"draws":118,"losses":327,"wins":71},"GB2-02":{"draws":350,"losses":119,"wins":11},"GB2-03":{"draws":165,"losses":237,"wins":92},"GB2-04":{"draws":313,"losses":141,"wins":44},"GB2-05":{"draws":0,"losses":52,"wins":478},"GB2-06":{"draws":26,"losses":399,"wins":77},"GB2-07":{"draws":0,"losses":155,"wins":375},"GB2-08":{"draws":196,"losses":163,"wins":179}}},"per_game_raw_elo_all":{"GB2-01":1310.36518078514,"GB2-02":1433.5545419424814,"GB2-03":1437.8577268142974,"GB2-04":1468.0762948920117,"GB2-05":1786.9910599961588,"GB2-06":1280.446229964833,"GB2-07":1641.8058909607007,"GB2-08":1488.927686662498},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1299.1689888050341,"GB2-02":1486.2283371207197,"GB2-03":1497.1823645949403,"GB2-04":1611.1073231594137,"GB2-05":1405.301104006592,"GB2-06":1452.6816949221445,"GB2-07":1854.337208797008,"GB2-08":1374.7170951519902},"medium":{"GB2-01":1395.6340263103898,"GB2-02":1417.117036832385,"GB2-03":1485.0140584263813,"GB2-04":1380.8308866066252,"GB2-05":1682.3667095812361,"GB2-06":1410.7171506491256,"GB2-07":1322.3214123559987,"GB2-08":1637.957678828332},"none":{"GB2-01":1236.2925272399957,"GB2-02":1397.3182518743386,"GB2-03":1331.3767574215708,"GB2-04":1412.290674909996,"GB2-05":2273.3053664006484,"GB2-06":977.9398443232292,"GB2-07":1748.7590517290957,"GB2-08":1454.1082860071722}},"per_game_tracks":{"highest":{"GB2-01":32.601582303855444,"GB2-02":51.85979739005609,"GB2-03":57.69171155645705,"GB2-04":66.54800849483952,"GB2-05":47.42038827962544,"GB2-06":52.12075316960467,"GB2-07":78.0679586400933,"GB2-08":48.28378519292282},"medium":{"GB2-01":42.302736781598085,"GB2-02":42.91901284955672,"GB2-03":56.38851556978438,"GB2-04":37.90394757154637,"GB2-05":68.12724355055535,"GB2-06":49.42613185517056,"GB2-07":39.96076261494025,"GB2-08":67.65474289113979},"none":{"GB2-01":26.816225898230446,"GB2-02":40.378437879665945,"GB2-03":38.971988121748765,"GB2-04":41.89524008925337,"GB2-05":90.56616011469444,"GB2-06":21.061973581924928,"GB2-07":71.99637118869325,"GB2-08":54.98385404181646}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:36:59Z","reasoning":{"highest":51.08301079155329,"medium":50.58538671053644,"none":48.33378136450345},"reasoning_agg":{"highest":{"max":78.0679586400933,"mean":51.08301079155329,"min":25.929898695028044},"medium":{"max":68.12724355055535,"mean":50.58538671053644,"min":37.90394757154637},"none":{"max":90.56616011469444,"mean":48.33378136450345,"min":21.061973581924928}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":2.7492294270498405},"working_program_strength":{"all":51.08113873449056,"highest":54.3242481284318,"medium":50.58538671053644,"none":48.33378136450345}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:ba1f2575d1f25f36","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":0.0306889},"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":0.02545105},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.00625249375,"median":0.0043227375,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16,"boardgame-list-prices-2026-10-09":11},"run_count":24,"token_priced_attempt_count":27,"total":0.15005985},"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":48.994290350361894,"highest":57.64302571706299,"medium":44.21229452751426,"none":45.12755080650842},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":39.052289421840854,"score":39.052289421840854},"GB2-02":{"attempts":3,"playable":50.62250558352071,"score":50.62250558352071},"GB2-03":{"attempts":3,"playable":49.339626184851056,"score":49.339626184851056},"GB2-04":{"attempts":3,"playable":52.95324546993124,"score":52.95324546993124},"GB2-05":{"attempts":3,"playable":46.95435293032139,"score":46.95435293032139},"GB2-06":{"attempts":3,"playable":64.51367076736135,"score":64.51367076736135},"GB2-07":{"attempts":3,"playable":41.99605536217903,"score":41.99605536217903},"GB2-08":{"attempts":3,"playable":46.52257708288948,"score":46.52257708288948}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":29.812964037202867,"score":29.812964037202867},"GB2-02":{"attempts":1,"playable":62.7551539228021,"score":62.7551539228021},"GB2-03":{"attempts":1,"playable":50.20191407031732,"score":50.20191407031732},"GB2-04":{"attempts":1,"playable":63.97515553735944,"score":63.97515553735944},"GB2-05":{"attempts":1,"playable":53.932046299693056,"score":53.932046299693056},"GB2-06":{"attempts":1,"playable":86.27591989580623,"score":86.27591989580623},"GB2-07":{"attempts":1,"playable":38.63926149130983,"score":38.63926149130983},"GB2-08":{"attempts":1,"playable":75.55179048201308,"score":75.55179048201308}},"medium":{"GB2-01":{"attempts":1,"playable":39.04587631358342,"score":39.04587631358342},"GB2-02":{"attempts":1,"playable":44.92555622688671,"score":44.92555622688671},"GB2-03":{"attempts":1,"playable":51.73396848497532,"score":51.73396848497532},"GB2-04":{"attempts":1,"playable":50.43861708565576,"score":50.43861708565576},"GB2-05":{"attempts":1,"playable":50.87230621817269,"score":50.87230621817269},"GB2-06":{"attempts":1,"playable":35.077297094579734,"score":35.077297094579734},"GB2-07":{"attempts":1,"playable":53.848229784430316,"score":53.848229784430316},"GB2-08":{"attempts":1,"playable":27.75650501183013,"score":27.75650501183013}},"none":{"GB2-01":{"attempts":1,"playable":48.29802791473627,"score":48.29802791473627},"GB2-02":{"attempts":1,"playable":44.18680660087333,"score":44.18680660087333},"GB2-03":{"attempts":1,"playable":46.08299599926055,"score":46.08299599926055},"GB2-04":{"attempts":1,"playable":44.44596378677852,"score":44.44596378677852},"GB2-05":{"attempts":1,"playable":36.05870627309844,"score":36.05870627309844},"GB2-06":{"attempts":1,"playable":72.1877953116981,"score":72.1877953116981},"GB2-07":{"attempts":1,"playable":33.50067481079693,"score":33.50067481079693},"GB2-08":{"attempts":1,"playable":36.259435754825226,"score":36.259435754825226}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-10-24T18:53:50Z","match_totals_all":{"draws":3131,"losses":4993,"wins":4140},"match_totals_tracks":{"highest":{"draws":597,"losses":1528,"wins":1963},"medium":{"draws":1221,"losses":1774,"wins":1093},"none":{"draws":1313,"losses":1691,"wins":1084}},"model_slug":"gpt-6-luna","official_rank_by_reasoning":{"highest":36,"medium":47,"none":30},"overall":{"max":86.27591989580623,"mean":48.994290350361894,"min":27.75650501183013},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.812964037202867,"GB2-02":62.7551539228021,"GB2-03":50.20191407031732,"GB2-04":63.97515553735944,"GB2-05":53.932046299693056,"GB2-06":86.27591989580623,"GB2-07":38.63926149130983,"GB2-08":75.55179048201308},"per_game_all":{"GB2-01":39.052289421840854,"GB2-02":50.62250558352071,"GB2-03":49.339626184851056,"GB2-04":52.95324546993124,"GB2-05":46.95435293032139,"GB2-06":64.51367076736135,"GB2-07":41.99605536217903,"GB2-08":46.52257708288948},"per_game_match_totals_all":{"GB2-01":{"draws":470,"losses":738,"wins":340},"GB2-02":{"draws":1059,"losses":206,"wins":175},"GB2-03":{"draws":208,"losses":705,"wins":569},"GB2-04":{"draws":839,"losses":309,"wins":346},"GB2-05":{"draws":0,"losses":868,"wins":722},"GB2-06":{"draws":74,"losses":541,"wins":891},"GB2-07":{"draws":0,"losses":962,"wins":628},"GB2-08":{"draws":481,"losses":664,"wins":469}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":370,"wins":144},"GB2-02":{"draws":278,"losses":48,"wins":154},"GB2-03":{"draws":25,"losses":253,"wins":216},"GB2-04":{"draws":234,"losses":71,"wins":193},"GB2-05":{"draws":0,"losses":253,"wins":277},"GB2-06":{"draws":31,"losses":61,"wins":410},"GB2-07":{"draws":0,"losses":339,"wins":191},"GB2-08":{"draws":27,"losses":133,"wins":378}},"medium":{"GB2-01":{"draws":191,"losses":229,"wins":96},"GB2-02":{"draws":395,"losses":75,"wins":10},"GB2-03":{"draws":98,"losses":209,"wins":187},"GB2-04":{"draws":285,"losses":113,"wins":100},"GB2-05":{"draws":0,"losses":269,"wins":261},"GB2-06":{"draws":21,"losses":337,"wins":144},"GB2-07":{"draws":0,"losses":257,"wins":273},"GB2-08":{"draws":231,"losses":285,"wins":22}},"none":{"GB2-01":{"draws":277,"losses":139,"wins":100},"GB2-02":{"draws":386,"losses":83,"wins":11},"GB2-03":{"draws":85,"losses":243,"wins":166},"GB2-04":{"draws":320,"losses":125,"wins":53},"GB2-05":{"draws":0,"losses":346,"wins":184},"GB2-06":{"draws":22,"losses":143,"wins":337},"GB2-07":{"draws":0,"losses":366,"wins":164},"GB2-08":{"draws":223,"losses":246,"wins":69}}},"per_game_raw_elo_all":{"GB2-01":1362.1578480811309,"GB2-02":1478.0803033775926,"GB2-03":1421.769278432259,"GB2-04":1499.5748080034593,"GB2-05":1398.0147123795807,"GB2-06":1689.3866690868438,"GB2-07":1347.0902349743128,"GB2-08":1395.4173490504702},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1269.579244244873,"GB2-02":1574.6780300106493,"GB2-03":1429.2484111646452,"GB2-04":1588.2461401674234,"GB2-05":1486.49182184943,"GB2-06":2080.5620671295083,"GB2-07":1305.6834403858668,"GB2-08":1784.791923092505},"medium":{"GB2-01":1364.0429541315825,"GB2-02":1432.6336855054699,"GB2-03":1442.8140827080117,"GB2-04":1478.3886247970268,"GB2-05":1448.1988610644678,"GB2-06":1192.9826646702027,"GB2-07":1495.922115289023,"GB2-08":1155.4684998856433},"none":{"GB2-01":1452.8513458669372,"GB2-02":1426.929194616659,"GB2-03":1393.2453414241197,"GB2-04":1432.089659045928,"GB2-05":1259.353454224844,"GB2-06":1794.6152754608206,"GB2-07":1239.665149248049,"GB2-08":1245.9916241732624}},"per_game_tracks":{"highest":{"GB2-01":29.812964037202867,"GB2-02":62.7551539228021,"GB2-03":50.20191407031732,"GB2-04":63.97515553735944,"GB2-05":53.932046299693056,"GB2-06":86.27591989580623,"GB2-07":38.63926149130983,"GB2-08":75.55179048201308},"medium":{"GB2-01":39.04587631358342,"GB2-02":44.92555622688671,"GB2-03":51.73396848497532,"GB2-04":50.43861708565576,"GB2-05":50.87230621817269,"GB2-06":35.077297094579734,"GB2-07":53.848229784430316,"GB2-08":27.75650501183013},"none":{"GB2-01":48.29802791473627,"GB2-02":44.18680660087333,"GB2-03":46.08299599926055,"GB2-04":44.44596378677852,"GB2-05":36.05870627309844,"GB2-06":72.1877953116981,"GB2-07":33.50067481079693,"GB2-08":36.259435754825226}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:56:42Z","reasoning":{"highest":57.64302571706299,"medium":44.21229452751426,"none":45.12755080650842},"reasoning_agg":{"highest":{"max":86.27591989580623,"mean":57.64302571706299,"min":29.812964037202867},"medium":{"max":53.848229784430316,"mean":44.21229452751426,"min":27.75650501183013},"none":{"max":72.1877953116981,"mean":45.12755080650842,"min":33.50067481079693}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.43073118954873},"working_program_strength":{"all":48.994290350361894,"highest":57.64302571706299,"medium":44.21229452751426,"none":45.12755080650842}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:8d36d587ce37f8e1","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":3.7157459999999998},"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":2.3233296},"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":0.6080262},"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":48.757409782753086,"highest":45.116203085834265,"medium":49.48016082040562,"none":51.67586544201936},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[262144],"finish_reason_observations":35,"finish_reasons":["length","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":10,"provider_post_attempts":13,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[262144],"total_output_tokens":396310,"total_reasoning_output_tokens":285325,"total_visible_output_tokens":110985,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":42.45949910026455,"score":42.45949910026455},"GB2-02":{"attempts":3,"playable":42.28431847382029,"score":42.28431847382029},"GB2-03":{"attempts":3,"playable":64.52761717499378,"score":64.52761717499378},"GB2-04":{"attempts":3,"playable":48.6430765952987,"score":48.6430765952987},"GB2-05":{"attempts":3,"playable":56.39998335524547,"score":56.39998335524547},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":51.89607374181699,"score":34.59738249454466},"GB2-07":{"attempts":3,"playable":48.918731554739786,"score":48.918731554739786},"GB2-08":{"attempts":3,"playable":52.22866951311744,"score":52.22866951311744}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":6.581541146400312,"score":6.581541146400312},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":77.81487415782914,"score":77.81487415782914},"GB2-04":{"attempts":1,"playable":52.763384258081715,"score":52.763384258081715},"GB2-05":{"attempts":1,"playable":62.29409871818348,"score":62.29409871818348},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":93.67556809558342,"score":93.67556809558342},"GB2-08":{"attempts":1,"playable":24.881145461039345,"score":24.881145461039345}},"medium":{"GB2-01":{"attempts":1,"playable":69.07322901089478,"score":69.07322901089478},"GB2-02":{"attempts":1,"playable":41.54367583083084,"score":41.54367583083084},"GB2-03":{"attempts":1,"playable":65.97577600045163,"score":65.97577600045163},"GB2-04":{"attempts":1,"playable":47.59963020320179,"score":47.59963020320179},"GB2-05":{"attempts":1,"playable":51.638057358625986,"score":51.638057358625986},"GB2-06":{"attempts":1,"playable":56.017189711756345,"score":56.017189711756345},"GB2-07":{"attempts":1,"playable":25.174894088175293,"score":25.174894088175293},"GB2-08":{"attempts":1,"playable":38.81883435930839,"score":38.81883435930839}},"none":{"GB2-01":{"attempts":1,"playable":51.723727143498564,"score":51.723727143498564},"GB2-02":{"attempts":1,"playable":42.390266741073305,"score":42.390266741073305},"GB2-03":{"attempts":1,"playable":49.79220136670058,"score":49.79220136670058},"GB2-04":{"attempts":1,"playable":45.56621532461259,"score":45.56621532461259},"GB2-05":{"attempts":1,"playable":55.26779398892694,"score":55.26779398892694},"GB2-06":{"attempts":1,"playable":47.77495777187764,"score":47.77495777187764},"GB2-07":{"attempts":1,"playable":27.90573248046065,"score":27.90573248046065},"GB2-08":{"attempts":1,"playable":92.98602871900458,"score":92.98602871900458}}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-10-24T19:14:14Z","match_totals_all":{"draws":2910,"losses":4568,"wins":4284},"match_totals_tracks":{"highest":{"draws":806,"losses":1387,"wins":1393},"medium":{"draws":1124,"losses":1613,"wins":1351},"none":{"draws":980,"losses":1568,"wins":1540}},"model_slug":"moonshotai-kimi-k3","official_rank_by_reasoning":{"highest":46,"medium":39,"none":18},"overall":{"max":93.67556809558342,"mean":48.757409782753086,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":6.581541146400312,"GB2-02":42.91901284955672,"GB2-03":77.81487415782914,"GB2-04":52.763384258081715,"GB2-05":62.29409871818348,"GB2-07":93.67556809558342,"GB2-08":24.881145461039345},"per_game_all":{"GB2-01":42.45949910026455,"GB2-02":42.28431847382029,"GB2-03":64.52761717499378,"GB2-04":48.6430765952987,"GB2-05":56.39998335524547,"GB2-07":48.918731554739786,"GB2-08":52.22866951311744},"per_game_match_totals_all":{"GB2-01":{"draws":359,"losses":737,"wins":452},"GB2-02":{"draws":1070,"losses":320,"wins":50},"GB2-03":{"draws":200,"losses":478,"wins":804},"GB2-04":{"draws":812,"losses":387,"wins":295},"GB2-05":{"draws":0,"losses":720,"wins":870},"GB2-06":{"draws":46,"losses":503,"wins":455},"GB2-07":{"draws":0,"losses":834,"wins":756},"GB2-08":{"draws":423,"losses":589,"wins":602}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":482,"wins":26},"GB2-02":{"draws":338,"losses":113,"wins":29},"GB2-03":{"draws":32,"losses":108,"wins":354},"GB2-04":{"draws":248,"losses":120,"wins":130},"GB2-05":{"draws":0,"losses":209,"wins":321},"GB2-07":{"draws":0,"losses":30,"wins":500},"GB2-08":{"draws":180,"losses":325,"wins":33}},"medium":{"GB2-01":{"draws":89,"losses":126,"wins":301},"GB2-02":{"draws":355,"losses":111,"wins":14},"GB2-03":{"draws":73,"losses":150,"wins":271},"GB2-04":{"draws":337,"losses":101,"wins":60},"GB2-05":{"draws":0,"losses":265,"wins":265},"GB2-06":{"draws":27,"losses":228,"wins":247},"GB2-07":{"draws":0,"losses":409,"wins":121},"GB2-08":{"draws":243,"losses":223,"wins":72}},"none":{"GB2-01":{"draws":262,"losses":129,"wins":125},"GB2-02":{"draws":377,"losses":96,"wins":7},"GB2-03":{"draws":95,"losses":220,"wins":179},"GB2-04":{"draws":227,"losses":166,"wins":105},"GB2-05":{"draws":0,"losses":246,"wins":284},"GB2-06":{"draws":19,"losses":275,"wins":208},"GB2-07":{"draws":0,"losses":395,"wins":135},"GB2-08":{"draws":0,"losses":41,"wins":497}}},"per_game_raw_elo_all":{"GB2-01":1346.0897730372683,"GB2-02":1412.1857160258708,"GB2-03":1578.8935214601486,"GB2-04":1464.558548623031,"GB2-05":1519.1461975626323,"GB2-07":1548.3567137464652,"GB2-08":1549.982768083096},"per_game_raw_elo_tracks":{"highest":{"GB2-01":891.6732746798467,"GB2-02":1417.117036832385,"GB2-03":1730.8410652687267,"GB2-04":1496.4916680217996,"GB2-05":1596.2932789415092,"GB2-07":2357.124000619623,"GB2-08":1123.0978410916748},"medium":{"GB2-01":1661.1269142412038,"GB2-02":1406.4264502199794,"GB2-03":1580.1990251438083,"GB2-04":1456.4378398316364,"GB2-05":1457.7402774396653,"GB2-06":1514.557603225621,"GB2-07":1124.2173637561662,"GB2-08":1272.7462133620618},"none":{"GB2-01":1485.4691301907546,"GB2-02":1413.0136610252475,"GB2-03":1425.6404739679108,"GB2-04":1440.746138015656,"GB2-05":1503.4050363067217,"GB2-06":1385.2577921297036,"GB2-07":1163.7287768636058,"GB2-08":2254.1042497955514}},"per_game_tracks":{"highest":{"GB2-01":6.581541146400312,"GB2-02":42.91901284955672,"GB2-03":77.81487415782914,"GB2-04":52.763384258081715,"GB2-05":62.29409871818348,"GB2-07":93.67556809558342,"GB2-08":24.881145461039345},"medium":{"GB2-01":69.07322901089478,"GB2-02":41.54367583083084,"GB2-03":65.97577600045163,"GB2-04":47.59963020320179,"GB2-05":51.638057358625986,"GB2-06":56.017189711756345,"GB2-07":25.174894088175293,"GB2-08":38.81883435930839},"none":{"GB2-01":51.723727143498564,"GB2-02":42.390266741073305,"GB2-03":49.79220136670058,"GB2-04":45.56621532461259,"GB2-05":55.26779398892694,"GB2-06":47.77495777187764,"GB2-07":27.90573248046065,"GB2-08":92.98602871900458}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:58:54Z","reasoning":{"highest":45.116203085834265,"medium":49.48016082040562,"none":51.67586544201936},"reasoning_agg":{"highest":{"max":93.67556809558342,"mean":45.116203085834265,"min":0.0},"medium":{"max":69.07322901089478,"mean":49.48016082040562,"min":25.174894088175293},"none":{"max":92.98602871900458,"mean":51.67586544201936,"min":27.90573248046065}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.559662356185093},"working_program_strength":{"all":50.905800405888044,"highest":51.56137495523916,"medium":49.48016082040562,"none":51.67586544201936}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:7310f3d9c843d84d","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":6.887695},"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":1.4245199999999998},"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":4.709264999999999},"historical-thinking-budget-setting":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":17},"run_count":16,"token_priced_attempt_count":17,"total":4.09607}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-10-09":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203784999999998},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333333,"min_ms":22230,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319301,"mean_ms":209645.0,"min_ms":137590,"run_count":8},"medium":{"attempt_count":8,"max_ms":81353,"mean_ms":54764.0,"min_ms":30922,"run_count":8},"none":{"attempt_count":8,"max_ms":40585,"mean_ms":32235.375,"min_ms":22230,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27669,"output_mean":9998.125,"output_min":2138,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27669,"output_mean":21703.125,"output_min":14720,"run_count":8},"medium":{"attempt_count":8,"output_max":8008,"output_mean":5259.0,"output_min":2375,"run_count":8},"none":{"attempt_count":8,"output_max":4031,"output_mean":3032.25,"output_min":2138,"run_count":8}},"display_name":"Claude Opus 4.5","economics":{"all":48.698344589559504,"highest":49.60736547082898,"medium":48.72650003258975,"none":47.76116826525979},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":47.28669390604811,"score":47.28669390604811},"GB2-02":{"attempts":5,"playable":44.028354785688485,"score":44.028354785688485},"GB2-03":{"attempts":4,"playable":47.21704982301177,"score":47.21704982301177},"GB2-04":{"attempts":5,"playable":43.571992125540326,"score":43.571992125540326},"GB2-05":{"attempts":5,"playable":46.61773284515727,"score":46.61773284515727},"GB2-06":{"attempts":5,"playable":47.65146605168064,"score":47.65146605168064},"GB2-07":{"attempts":5,"playable":45.717273335385705,"score":45.717273335385705},"GB2-08":{"attempts":5,"playable":67.49619384396374,"score":67.49619384396374}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":49.8769837274564,"score":49.8769837274564},"GB2-02":{"attempts":2,"playable":43.60590924238241,"score":43.60590924238241},"GB2-03":{"attempts":1,"playable":50.30426587263482,"score":50.30426587263482},"GB2-04":{"attempts":2,"playable":40.822013275138005,"score":40.822013275138005},"GB2-05":{"attempts":2,"playable":47.41518799040359,"score":47.41518799040359},"GB2-06":{"attempts":2,"playable":50.83515562422053,"score":50.83515562422053},"GB2-07":{"attempts":2,"playable":55.44678146640126,"score":55.44678146640126},"GB2-08":{"attempts":2,"playable":58.55262656799482,"score":58.55262656799482}},"medium":{"GB2-01":{"attempts":2,"playable":47.41609406677081,"score":47.41609406677081},"GB2-02":{"attempts":2,"playable":44.081216558887135,"score":44.081216558887135},"GB2-03":{"attempts":2,"playable":49.22103059474965,"score":49.22103059474965},"GB2-04":{"attempts":2,"playable":41.279336461872035,"score":41.279336461872035},"GB2-05":{"attempts":2,"playable":45.20966144445233,"score":45.20966144445233},"GB2-06":{"attempts":2,"playable":47.48735485052968,"score":47.48735485052968},"GB2-07":{"attempts":2,"playable":49.35535413017583,"score":49.35535413017583},"GB2-08":{"attempts":2,"playable":65.76195215328049,"score":65.76195215328049}},"none":{"GB2-01":{"attempts":1,"playable":44.56700392391712,"score":44.56700392391712},"GB2-02":{"attempts":1,"playable":44.39793855579591,"score":44.39793855579591},"GB2-03":{"attempts":1,"playable":42.12585300165085,"score":42.12585300165085},"GB2-04":{"attempts":1,"playable":48.61462663961093,"score":48.61462663961093},"GB2-05":{"attempts":1,"playable":47.228349100615894,"score":47.228349100615894},"GB2-06":{"attempts":1,"playable":44.63188768029172,"score":44.63188768029172},"GB2-07":{"attempts":1,"playable":32.349684409580014,"score":32.349684409580014},"GB2-08":{"attempts":1,"playable":78.1740028106159,"score":78.1740028106159}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:17:57Z","match_totals_all":{"draws":3212,"losses":4822,"wins":4230},"match_totals_tracks":{"highest":{"draws":1049,"losses":1607,"wins":1432},"medium":{"draws":1005,"losses":1562,"wins":1521},"none":{"draws":1158,"losses":1653,"wins":1277}},"model_slug":"claude-opus-4-5","official_rank_by_reasoning":{"highest":43,"medium":40,"none":27},"overall":{"max":78.1740028106159,"mean":48.698344589559504,"min":32.349684409580014},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.8769837274564,"GB2-02":43.60590924238241,"GB2-03":50.30426587263482,"GB2-04":40.822013275138005,"GB2-05":47.41518799040359,"GB2-06":50.83515562422053,"GB2-07":55.44678146640126,"GB2-08":58.55262656799482},"per_game_all":{"GB2-01":47.28669390604811,"GB2-02":44.028354785688485,"GB2-03":47.21704982301177,"GB2-04":43.571992125540326,"GB2-05":46.61773284515727,"GB2-06":47.65146605168064,"GB2-07":45.717273335385705,"GB2-08":67.49619384396374},"per_game_match_totals_all":{"GB2-01":{"draws":421,"losses":469,"wins":658},"GB2-02":{"draws":1123,"losses":268,"wins":49},"GB2-03":{"draws":391,"losses":655,"wins":436},"GB2-04":{"draws":944,"losses":382,"wins":168},"GB2-05":{"draws":0,"losses":845,"wins":745},"GB2-06":{"draws":68,"losses":776,"wins":662},"GB2-07":{"draws":0,"losses":946,"wins":644},"GB2-08":{"draws":265,"losses":481,"wins":868}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":57,"losses":126,"wins":333},"GB2-02":{"draws":383,"losses":86,"wins":11},"GB2-03":{"draws":74,"losses":228,"wins":192},"GB2-04":{"draws":280,"losses":161,"wins":57},"GB2-05":{"draws":0,"losses":267,"wins":263},"GB2-06":{"draws":32,"losses":230,"wins":240},"GB2-07":{"draws":0,"losses":277,"wins":253},"GB2-08":{"draws":223,"losses":232,"wins":83}},"medium":{"GB2-01":{"draws":129,"losses":164,"wins":223},"GB2-02":{"draws":370,"losses":92,"wins":18},"GB2-03":{"draws":146,"losses":208,"wins":140},"GB2-04":{"draws":339,"losses":119,"wins":40},"GB2-05":{"draws":0,"losses":290,"wins":240},"GB2-06":{"draws":19,"losses":254,"wins":229},"GB2-07":{"draws":0,"losses":297,"wins":233},"GB2-08":{"draws":2,"losses":138,"wins":398}},"none":{"GB2-01":{"draws":235,"losses":179,"wins":102},"GB2-02":{"draws":370,"losses":90,"wins":20},"GB2-03":{"draws":171,"losses":219,"wins":104},"GB2-04":{"draws":325,"losses":102,"wins":71},"GB2-05":{"draws":0,"losses":288,"wins":242},"GB2-06":{"draws":17,"losses":292,"wins":193},"GB2-07":{"draws":0,"losses":372,"wins":158},"GB2-08":{"draws":40,"losses":111,"wins":387}}},"per_game_raw_elo_all":{"GB2-01":1552.79750160021,"GB2-02":1426.1125658931517,"GB2-03":1396.7981494144472,"GB2-04":1432.5148823100283,"GB2-05":1418.0042750157565,"GB2-06":1428.7624905115638,"GB2-07":1359.375460119323,"GB2-08":1641.8826316550485},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1696.2601951826134,"GB2-02":1424.4804152842908,"GB2-03":1430.1509325937732,"GB2-04":1406.7045198838086,"GB2-05":1452.9678673729168,"GB2-06":1500.9065197646191,"GB2-07":1449.825618843749,"GB2-08":1274.8052645245757},"medium":{"GB2-01":1544.8016024384049,"GB2-02":1425.296964632244,"GB2-03":1401.3412949839758,"GB2-04":1426.5660710198995,"GB2-05":1398.132256679762,"GB2-06":1448.1789908543237,"GB2-07":1403.8286202121055,"GB2-08":1811.0675930486063},"none":{"GB2-01":1417.3307071796116,"GB2-02":1428.5603177629207,"GB2-03":1358.9022206655932,"GB2-04":1464.274056026377,"GB2-05":1402.912700994591,"GB2-06":1337.2019609157483,"GB2-07":1224.4721413021148,"GB2-08":1839.7750373919635}},"per_game_tracks":{"highest":{"GB2-01":49.8769837274564,"GB2-02":43.60590924238241,"GB2-03":50.30426587263482,"GB2-04":40.822013275138005,"GB2-05":47.41518799040359,"GB2-06":50.83515562422053,"GB2-07":55.44678146640126,"GB2-08":58.55262656799482},"medium":{"GB2-01":47.41609406677081,"GB2-02":44.081216558887135,"GB2-03":49.22103059474965,"GB2-04":41.279336461872035,"GB2-05":45.20966144445233,"GB2-06":47.48735485052968,"GB2-07":49.35535413017583,"GB2-08":65.76195215328049},"none":{"GB2-01":44.56700392391712,"GB2-02":44.39793855579591,"GB2-03":42.12585300165085,"GB2-04":48.61462663961093,"GB2-05":47.228349100615894,"GB2-06":44.63188768029172,"GB2-07":32.349684409580014,"GB2-08":78.1740028106159}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:06:40Z","reasoning":{"highest":49.60736547082898,"medium":48.72650003258975,"none":47.76116826525979},"reasoning_agg":{"highest":{"max":58.55262656799482,"mean":49.60736547082898,"min":40.822013275138005},"medium":{"max":65.76195215328049,"mean":48.72650003258975,"min":41.279336461872035},"none":{"max":78.1740028106159,"mean":47.76116826525979,"min":32.349684409580014}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"reasoning_settings":{"balanced":"medium","intensive":"high"},"score_diagnostics":{"reasoning_variance":1.8461972055691902},"working_program_strength":{"all":48.698344589559504,"highest":49.60736547082898,"medium":48.72650003258975,"none":47.76116826525979}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:1d3023549259b74f","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":0.49337}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.52499},"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":0.49337000000000003},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.8079499999999995}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.8263099999999994},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":48.10374198413181,"highest":56.53545250964784,"medium":43.98759509702539,"none":43.78817834572219},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":53.09690670744377,"score":53.09690670744377},"GB2-02":{"attempts":3,"playable":42.9188223473494,"score":42.9188223473494},"GB2-03":{"attempts":3,"playable":52.8970508761271,"score":52.8970508761271},"GB2-04":{"attempts":3,"playable":47.21686750903317,"score":47.21686750903317},"GB2-05":{"attempts":3,"playable":40.410537671486956,"score":40.410537671486956},"GB2-06":{"attempts":3,"playable":38.92082520556628,"score":38.92082520556628},"GB2-07":{"attempts":3,"playable":51.43324186613366,"score":51.43324186613366},"GB2-08":{"attempts":3,"playable":57.93568368991409,"score":57.93568368991409}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.77576665856935,"score":63.77576665856935},"GB2-02":{"attempts":1,"playable":42.178687497765914,"score":42.178687497765914},"GB2-03":{"attempts":1,"playable":60.28149194112786,"score":60.28149194112786},"GB2-04":{"attempts":1,"playable":53.16698918839465,"score":53.16698918839465},"GB2-05":{"attempts":1,"playable":54.6955577416025,"score":54.6955577416025},"GB2-06":{"attempts":1,"playable":28.686422763595655,"score":28.686422763595655},"GB2-07":{"attempts":1,"playable":68.14461971211765,"score":68.14461971211765},"GB2-08":{"attempts":1,"playable":81.35408457400912,"score":81.35408457400912}},"medium":{"GB2-01":{"attempts":1,"playable":46.041243168384455,"score":46.041243168384455},"GB2-02":{"attempts":1,"playable":43.65876669472558,"score":43.65876669472558},"GB2-03":{"attempts":1,"playable":42.021145117469075,"score":42.021145117469075},"GB2-04":{"attempts":1,"playable":45.05717114428411,"score":45.05717114428411},"GB2-05":{"attempts":1,"playable":42.997622913837446,"score":42.997622913837446},"GB2-06":{"attempts":1,"playable":39.71694016385535,"score":39.71694016385535},"GB2-07":{"attempts":1,"playable":50.74351938754062,"score":50.74351938754062},"GB2-08":{"attempts":1,"playable":41.66435218610649,"score":41.66435218610649}},"none":{"GB2-01":{"attempts":1,"playable":49.47371029537753,"score":49.47371029537753},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":56.38851556978438,"score":56.38851556978438},"GB2-04":{"attempts":1,"playable":43.42644219442075,"score":43.42644219442075},"GB2-05":{"attempts":1,"playable":23.538432359020923,"score":23.538432359020923},"GB2-06":{"attempts":1,"playable":48.35911268924785,"score":48.35911268924785},"GB2-07":{"attempts":1,"playable":35.41158649874269,"score":35.41158649874269},"GB2-08":{"attempts":1,"playable":50.78861430962667,"score":50.78861430962667}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:18:32Z","match_totals_all":{"draws":3088,"losses":5116,"wins":4060},"match_totals_tracks":{"highest":{"draws":835,"losses":1439,"wins":1814},"medium":{"draws":1179,"losses":1804,"wins":1105},"none":{"draws":1074,"losses":1873,"wins":1141}},"model_slug":"claude-sonnet-5","official_rank_by_reasoning":{"highest":37,"medium":48,"none":32},"overall":{"max":81.35408457400912,"mean":48.10374198413181,"min":23.538432359020923},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.77576665856935,"GB2-02":42.178687497765914,"GB2-03":60.28149194112786,"GB2-04":53.16698918839465,"GB2-05":54.6955577416025,"GB2-06":28.686422763595655,"GB2-07":68.14461971211765,"GB2-08":81.35408457400912},"per_game_all":{"GB2-01":53.09690670744377,"GB2-02":42.9188223473494,"GB2-03":52.8970508761271,"GB2-04":47.21686750903317,"GB2-05":40.410537671486956,"GB2-06":38.92082520556628,"GB2-07":51.43324186613366,"GB2-08":57.93568368991409},"per_game_match_totals_all":{"GB2-01":{"draws":249,"losses":634,"wins":665},"GB2-02":{"draws":1132,"losses":280,"wins":28},"GB2-03":{"draws":327,"losses":592,"wins":563},"GB2-04":{"draws":922,"losses":353,"wins":219},"GB2-05":{"draws":0,"losses":970,"wins":620},"GB2-06":{"draws":36,"losses":966,"wins":504},"GB2-07":{"draws":0,"losses":807,"wins":783},"GB2-08":{"draws":422,"losses":514,"wins":678}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":54,"losses":171,"wins":291},"GB2-02":{"draws":373,"losses":99,"wins":8},"GB2-03":{"draws":107,"losses":162,"wins":225},"GB2-04":{"draws":290,"losses":97,"wins":111},"GB2-05":{"draws":0,"losses":249,"wins":281},"GB2-06":{"draws":7,"losses":374,"wins":121},"GB2-07":{"draws":0,"losses":177,"wins":353},"GB2-08":{"draws":4,"losses":110,"wins":424}},"medium":{"GB2-01":{"draws":106,"losses":236,"wins":174},"GB2-02":{"draws":385,"losses":86,"wins":9},"GB2-03":{"draws":120,"losses":245,"wins":129},"GB2-04":{"draws":314,"losses":125,"wins":59},"GB2-05":{"draws":0,"losses":310,"wins":220},"GB2-06":{"draws":18,"losses":316,"wins":168},"GB2-07":{"draws":0,"losses":274,"wins":256},"GB2-08":{"draws":236,"losses":212,"wins":90}},"none":{"GB2-01":{"draws":89,"losses":227,"wins":200},"GB2-02":{"draws":374,"losses":95,"wins":11},"GB2-03":{"draws":100,"losses":185,"wins":209},"GB2-04":{"draws":318,"losses":131,"wins":49},"GB2-05":{"draws":0,"losses":411,"wins":119},"GB2-06":{"draws":11,"losses":276,"wins":215},"GB2-07":{"draws":0,"losses":356,"wins":174},"GB2-08":{"draws":182,"losses":192,"wins":164}}},"per_game_raw_elo_all":{"GB2-01":1499.9059324348402,"GB2-02":1417.110978417734,"GB2-03":1454.990843928582,"GB2-04":1453.5539663037125,"GB2-05":1305.9207383918974,"GB2-06":1251.2343277773691,"GB2-07":1470.2872277892172,"GB2-08":1539.0476007770524},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1604.300585955315,"GB2-02":1411.3694893247707,"GB2-03":1521.9661872328322,"GB2-04":1499.652857958223,"GB2-05":1496.1403116985903,"GB2-06":1096.6710217714358,"GB2-07":1689.6190691972947,"GB2-08":1911.0373971512035},"medium":{"GB2-01":1431.3861900484414,"GB2-02":1422.8464090960465,"GB2-03":1357.9922861265334,"GB2-04":1436.814489304842,"GB2-05":1349.903537487965,"GB2-06":1262.7864227512746,"GB2-07":1456.7242370388433,"GB2-08":1302.6925168166633},"none":{"GB2-01":1464.0310213007645,"GB2-02":1417.117036832385,"GB2-03":1485.0140584263813,"GB2-04":1424.1945516480725,"GB2-05":1071.7183659891373,"GB2-06":1394.245538809397,"GB2-07":1264.5183771315137,"GB2-08":1403.4128883632904}},"per_game_tracks":{"highest":{"GB2-01":63.77576665856935,"GB2-02":42.178687497765914,"GB2-03":60.28149194112786,"GB2-04":53.16698918839465,"GB2-05":54.6955577416025,"GB2-06":28.686422763595655,"GB2-07":68.14461971211765,"GB2-08":81.35408457400912},"medium":{"GB2-01":46.041243168384455,"GB2-02":43.65876669472558,"GB2-03":42.021145117469075,"GB2-04":45.05717114428411,"GB2-05":42.997622913837446,"GB2-06":39.71694016385535,"GB2-07":50.74351938754062,"GB2-08":41.66435218610649},"none":{"GB2-01":49.47371029537753,"GB2-02":42.91901284955672,"GB2-03":56.38851556978438,"GB2-04":43.42644219442075,"GB2-05":23.538432359020923,"GB2-06":48.35911268924785,"GB2-07":35.41158649874269,"GB2-08":50.78861430962667}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:20:19Z","reasoning":{"highest":56.53545250964784,"medium":43.98759509702539,"none":43.78817834572219},"reasoning_agg":{"highest":{"max":81.35408457400912,"mean":56.53545250964784,"min":28.686422763595655},"medium":{"max":50.74351938754062,"mean":43.98759509702539,"min":39.71694016385535},"none":{"max":56.38851556978438,"mean":43.78817834572219,"min":23.538432359020923}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.747274163925653},"working_program_strength":{"all":48.10374198413181,"highest":56.53545250964784,"medium":43.98759509702539,"none":43.78817834572219}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-3:6a2a7db9e6b297ec","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04598051,"mean":0.037044270000000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":11,"run_count":8,"total":0.29635416000000003},"medium":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.046827143749999994,"median":0.045572185,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":11,"run_count":8,"total":0.37461715000000007},"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":3,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.046827143749999994,"median":0.045572185,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":11,"run_count":8,"total":0.37461715},"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":5,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04598051,"mean":0.037044270000000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":11,"run_count":8,"total":0.29635416000000003}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.028891608750000006,"median":0.03513247,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":31,"run_count":24,"total":0.69339861},"codegen_latency_ms":{"attempt_count":24,"max_ms":377102,"mean_ms":133492.94444444444,"min_ms":3791,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319339,"mean_ms":217388.6,"min_ms":142770,"run_count":5},"medium":{"attempt_count":7,"max_ms":377102,"mean_ms":248372.6,"min_ms":146739,"run_count":5},"none":{"attempt_count":9,"max_ms":30086,"mean_ms":9258.375,"min_ms":3791,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":230653,"output_mean":79571.75,"output_min":2342,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":129270,"output_mean":102689.5,"output_min":67386,"run_count":8},"medium":{"attempt_count":11,"output_max":230653,"output_mean":130579.0,"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":47.81095782628282,"highest":59.550517988399214,"medium":44.96190310132918,"none":38.92045238912005},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":31,"effective_max_output_tokens":[131072],"finish_reason_observations":24,"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,"requested_max_output_token_observations":31,"requested_max_output_tokens":[131072],"total_output_tokens":1909722,"total_reasoning_output_tokens":1808452,"total_visible_output_tokens":101270,"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":"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":3,"evaluated_cells":4,"failed_game_aliases":["GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"admitted":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":{"admitted":1}},"infra_excluded_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"infra_failures_excluded":4,"model_code_failure_rate":0.25,"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":1,"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":5,"evaluated_cells":5,"first_pass_admitted":2,"first_pass_rate":0.4,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"infra_failures_excluded":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":["GB2-04","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":3,"repaired_rate":0.6}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.47377110535652,"score":42.47377110535652},"GB2-02":{"attempts":3,"playable":44.43186628562709,"score":44.43186628562709},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":47.90893045172146,"score":31.939286967814308},"GB2-04":{"attempts":1,"playable":40.66867526681418,"score":40.66867526681418},"GB2-05":{"attempts":1,"playable":25.268629736614283,"score":25.268629736614283},"GB2-06":{"attempts":2,"playable":73.26367228050186,"score":73.26367228050186},"GB2-07":{"attempts":2,"playable":55.69799500240772,"score":55.69799500240772},"GB2-08":{"attempts":3,"playable":50.347393306662774,"score":50.347393306662774}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":50.06109836292545,"score":50.06109836292545},"GB2-02":{"attempts":1,"playable":44.18680660087333,"score":44.18680660087333},"GB2-03":{"attempts":1,"playable":62.1597106042574,"score":62.1597106042574},"GB2-06":{"attempts":1,"playable":79.6464770396741,"score":79.6464770396741},"GB2-08":{"attempts":1,"playable":61.69849733426575,"score":61.69849733426575}},"medium":{"GB2-02":{"attempts":1,"playable":46.40124307156255,"score":46.40124307156255},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":77.89531519401852,"score":77.89531519401852},"GB2-08":{"attempts":1,"playable":55.55105413973563,"score":55.55105413973563}},"none":{"GB2-01":{"attempts":1,"playable":34.88644384778758,"score":34.88644384778758},"GB2-02":{"attempts":1,"playable":42.707549184445384,"score":42.707549184445384},"GB2-03":{"attempts":1,"playable":33.65815029918553,"score":33.65815029918553},"GB2-04":{"attempts":1,"playable":40.66867526681418,"score":40.66867526681418},"GB2-05":{"attempts":1,"playable":25.268629736614283,"score":25.268629736614283},"GB2-06":{"attempts":1,"playable":66.88086752132963,"score":66.88086752132963},"GB2-07":{"attempts":1,"playable":33.50067481079693,"score":33.50067481079693},"GB2-08":{"attempts":1,"playable":33.79262844598693,"score":33.79262844598693}}},"id":"inception/mercury-3","is_recent_addition":false,"last_measured_at":"2026-10-24T16:37:40Z","match_totals_all":{"draws":2052,"losses":3304,"wins":2809},"match_totals_tracks":{"highest":{"draws":727,"losses":725,"wins":1078},"medium":{"draws":335,"losses":477,"wins":736},"none":{"draws":990,"losses":2102,"wins":995}},"model_slug":"inception-mercury-3","official_rank_by_reasoning":{"none":47},"overall":{"max":79.6464770396741,"mean":47.81095782628282,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":41,"overall_ranking_status":"partial","per_game":{"GB2-01":50.06109836292545,"GB2-02":44.18680660087333,"GB2-03":62.1597106042574,"GB2-06":79.6464770396741,"GB2-08":61.69849733426575},"per_game_all":{"GB2-02":44.43186628562709,"GB2-08":50.347393306662774},"per_game_match_totals_all":{"GB2-01":{"draws":438,"losses":395,"wins":199},"GB2-02":{"draws":1053,"losses":298,"wins":89},"GB2-03":{"draws":227,"losses":437,"wins":324},"GB2-04":{"draws":323,"losses":142,"wins":33},"GB2-05":{"draws":0,"losses":402,"wins":128},"GB2-06":{"draws":11,"losses":290,"wins":702},"GB2-07":{"draws":0,"losses":487,"wins":573},"GB2-08":{"draws":0,"losses":853,"wins":761}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":259,"losses":139,"wins":118},"GB2-02":{"draws":348,"losses":102,"wins":30},"GB2-03":{"draws":114,"losses":149,"wins":231},"GB2-06":{"draws":6,"losses":110,"wins":386},"GB2-08":{"draws":0,"losses":225,"wins":313}},"medium":{"GB2-02":{"draws":335,"losses":98,"wins":47},"GB2-07":{"draws":0,"losses":121,"wins":409},"GB2-08":{"draws":0,"losses":258,"wins":280}},"none":{"GB2-01":{"draws":179,"losses":256,"wins":81},"GB2-02":{"draws":370,"losses":98,"wins":12},"GB2-03":{"draws":113,"losses":288,"wins":93},"GB2-04":{"draws":323,"losses":142,"wins":33},"GB2-05":{"draws":0,"losses":402,"wins":128},"GB2-06":{"draws":5,"losses":180,"wins":316},"GB2-07":{"draws":0,"losses":366,"wins":164},"GB2-08":{"draws":0,"losses":370,"wins":168}}},"per_game_raw_elo_all":{"GB2-02":1428.806150036394,"GB2-08":1408.6892386698937},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1469.620390069883,"GB2-02":1426.929194616659,"GB2-03":1540.5344078150044,"GB2-06":1938.321442118005,"GB2-08":1544.6406279391642},"medium":{"GB2-02":1444.0124003029546,"GB2-07":1851.0403728166154,"GB2-08":1461.2645512748502},"none":{"GB2-01":1322.6395416174478,"GB2-02":1415.4768551895686,"GB2-03":1283.9053226921492,"GB2-04":1402.7003284231976,"GB2-05":1100.2601270932003,"GB2-06":1698.0665232061851,"GB2-07":1239.665149248049,"GB2-08":1220.1625367956667}},"per_game_tracks":{"highest":{"GB2-01":50.06109836292545,"GB2-02":44.18680660087333,"GB2-03":62.1597106042574,"GB2-06":79.6464770396741,"GB2-08":61.69849733426575},"medium":{"GB2-02":46.40124307156255,"GB2-07":77.89531519401852,"GB2-08":55.55105413973563},"none":{"GB2-01":34.88644384778758,"GB2-02":42.707549184445384,"GB2-03":33.65815029918553,"GB2-04":40.66867526681418,"GB2-05":25.268629736614283,"GB2-06":66.88086752132963,"GB2-07":33.50067481079693,"GB2-08":33.79262844598693}},"program_outcomes":{"all":{"counted_attempts":17,"failed":1,"infra_excluded":7,"success_rate":0.9411764705882353,"too_slow":0,"worked_after_repair":5,"worked_first_time":11,"working":16},"highest":{"counted_attempts":5,"failed":0,"infra_excluded":3,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":2,"working":5},"medium":{"counted_attempts":4,"failed":1,"infra_excluded":4,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":2,"working":3},"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":59.550517988399214,"medium":44.96190310132918,"none":38.92045238912005},"reasoning_agg":{"highest":{"max":79.6464770396741,"mean":59.550517988399214,"min":44.18680660087333},"medium":{"max":77.89531519401852,"mean":44.96190310132918,"min":0.0},"none":{"max":66.88086752132963,"mean":38.92045238912005,"min":25.268629736614283}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":20.630065599279163},"working_program_strength":{"all":52.806724837541616,"highest":59.550517988399214,"medium":59.94920413510557,"none":38.92045238912005}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:44bc2ca1b1081818","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":0.6137425000000001}},"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":3.06723375}},"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":47.144778983659016,"highest":54.460231382754415,"medium":50.79453483299465,"none":36.17957073522796},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"total_output_tokens":252016,"total_reasoning_output_tokens":152800,"total_visible_output_tokens":99216,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":67.98721901961532,"score":67.98721901961532},"GB2-02":{"attempts":3,"playable":50.084779854115006,"score":50.084779854115006},"GB2-03":{"attempts":3,"playable":34.580715918898456,"score":34.580715918898456},"GB2-04":{"attempts":3,"playable":43.46010017998433,"score":43.46010017998433},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.981358948929014,"score":37.98757263261934},"GB2-06":{"attempts":3,"playable":52.782116977677255,"score":52.782116977677255},"GB2-07":{"attempts":3,"playable":44.934084442514006,"score":44.934084442514006},"GB2-08":{"attempts":3,"playable":45.341642843848355,"score":45.341642843848355}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":72.1376849541376,"score":72.1376849541376},"GB2-02":{"attempts":1,"playable":59.45473635208101,"score":59.45473635208101},"GB2-03":{"attempts":1,"playable":36.323969341588956,"score":36.323969341588956},"GB2-04":{"attempts":1,"playable":42.30378157783618,"score":42.30378157783618},"GB2-05":{"attempts":1,"playable":55.64909123787278,"score":55.64909123787278},"GB2-06":{"attempts":1,"playable":80.55559591622435,"score":80.55559591622435},"GB2-07":{"attempts":1,"playable":44.272181169146435,"score":44.272181169146435},"GB2-08":{"attempts":1,"playable":44.98481051314801,"score":44.98481051314801}},"medium":{"GB2-01":{"attempts":1,"playable":77.26959062604402,"score":77.26959062604402},"GB2-02":{"attempts":1,"playable":46.19058107971835,"score":46.19058107971835},"GB2-03":{"attempts":1,"playable":33.97405749019911,"score":33.97405749019911},"GB2-04":{"attempts":1,"playable":43.834375844994916,"score":43.834375844994916},"GB2-05":{"attempts":1,"playable":58.31362665998524,"score":58.31362665998524},"GB2-06":{"attempts":1,"playable":40.32607454715853,"score":40.32607454715853},"GB2-07":{"attempts":1,"playable":60.87928038334839,"score":60.87928038334839},"GB2-08":{"attempts":1,"playable":45.56869203250862,"score":45.56869203250862}},"none":{"GB2-01":{"attempts":1,"playable":54.55438147866437,"score":54.55438147866437},"GB2-02":{"attempts":1,"playable":44.60902213054566,"score":44.60902213054566},"GB2-03":{"attempts":1,"playable":33.444120924907295,"score":33.444120924907295},"GB2-04":{"attempts":1,"playable":44.242143117121884,"score":44.242143117121884},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":37.464680469648904,"score":37.464680469648904},"GB2-07":{"attempts":1,"playable":29.650791775047207,"score":29.650791775047207},"GB2-08":{"attempts":1,"playable":45.471425985888416,"score":45.471425985888416}}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-10-24T19:15:32Z","match_totals_all":{"draws":3337,"losses":4580,"wins":3818},"match_totals_tracks":{"highest":{"draws":1014,"losses":1452,"wins":1622},"medium":{"draws":1046,"losses":1583,"wins":1460},"none":{"draws":1277,"losses":1545,"wins":736}},"model_slug":"gpt-5-6-terra","official_rank_by_reasoning":{"highest":41,"medium":36,"none":51},"overall":{"max":80.55559591622435,"mean":47.144778983659016,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":42,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.1376849541376,"GB2-02":59.45473635208101,"GB2-03":36.323969341588956,"GB2-04":42.30378157783618,"GB2-05":55.64909123787278,"GB2-06":80.55559591622435,"GB2-07":44.272181169146435,"GB2-08":44.98481051314801},"per_game_all":{"GB2-01":67.98721901961532,"GB2-02":50.084779854115006,"GB2-03":34.580715918898456,"GB2-04":43.46010017998433,"GB2-06":52.782116977677255,"GB2-07":44.934084442514006,"GB2-08":45.341642843848355},"per_game_match_totals_all":{"GB2-01":{"draws":243,"losses":406,"wins":899},"GB2-02":{"draws":1041,"losses":223,"wins":176},"GB2-03":{"draws":547,"losses":748,"wins":188},"GB2-04":{"draws":907,"losses":416,"wins":171},"GB2-05":{"draws":0,"losses":474,"wins":586},"GB2-06":{"draws":84,"losses":724,"wins":698},"GB2-07":{"draws":0,"losses":913,"wins":677},"GB2-08":{"draws":515,"losses":676,"wins":423}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":71,"losses":119,"wins":326},"GB2-02":{"draws":266,"losses":70,"wins":144},"GB2-03":{"draws":152,"losses":256,"wins":86},"GB2-04":{"draws":325,"losses":133,"wins":40},"GB2-05":{"draws":0,"losses":244,"wins":286},"GB2-06":{"draws":34,"losses":91,"wins":377},"GB2-07":{"draws":0,"losses":309,"wins":221},"GB2-08":{"draws":166,"losses":230,"wins":142}},"medium":{"GB2-01":{"draws":3,"losses":126,"wins":387},"GB2-02":{"draws":383,"losses":75,"wins":22},"GB2-03":{"draws":224,"losses":232,"wins":39},"GB2-04":{"draws":252,"losses":162,"wins":84},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":48,"losses":298,"wins":156},"GB2-07":{"draws":0,"losses":218,"wins":312},"GB2-08":{"draws":136,"losses":242,"wins":160}},"none":{"GB2-01":{"draws":169,"losses":161,"wins":186},"GB2-02":{"draws":392,"losses":78,"wins":10},"GB2-03":{"draws":171,"losses":260,"wins":63},"GB2-04":{"draws":330,"losses":121,"wins":47},"GB2-06":{"draws":2,"losses":335,"wins":165},"GB2-07":{"draws":0,"losses":386,"wins":144},"GB2-08":{"draws":213,"losses":204,"wins":121}}},"per_game_raw_elo_all":{"GB2-01":1656.4758132426668,"GB2-02":1473.1575053240304,"GB2-03":1292.2297267753631,"GB2-04":1424.44737263395,"GB2-06":1485.846724695325,"GB2-07":1383.9074028264015,"GB2-08":1342.1535943041663},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1696.2601951826134,"GB2-02":1546.893348274868,"GB2-03":1307.9548063016402,"GB2-04":1415.473315122039,"GB2-05":1508.263354586718,"GB2-06":1956.694861311571,"GB2-07":1376.1109729535456,"GB2-08":1338.2689128345967},"medium":{"GB2-01":1760.5501600748603,"GB2-02":1442.3887721988478,"GB2-03":1286.786109386789,"GB2-04":1427.3559809232622,"GB2-05":1542.6934198919057,"GB2-06":1271.974564533439,"GB2-07":1587.580183835012,"GB2-08":1344.6267418921407},"none":{"GB2-01":1512.6170844705266,"GB2-02":1430.1903954983752,"GB2-03":1281.9482646376605,"GB2-04":1430.5128218565485,"GB2-06":1228.8707482409654,"GB2-07":1188.031051690647,"GB2-08":1343.565128185762}},"per_game_tracks":{"highest":{"GB2-01":72.1376849541376,"GB2-02":59.45473635208101,"GB2-03":36.323969341588956,"GB2-04":42.30378157783618,"GB2-05":55.64909123787278,"GB2-06":80.55559591622435,"GB2-07":44.272181169146435,"GB2-08":44.98481051314801},"medium":{"GB2-01":77.26959062604402,"GB2-02":46.19058107971835,"GB2-03":33.97405749019911,"GB2-04":43.834375844994916,"GB2-05":58.31362665998524,"GB2-06":40.32607454715853,"GB2-07":60.87928038334839,"GB2-08":45.56869203250862},"none":{"GB2-01":54.55438147866437,"GB2-02":44.60902213054566,"GB2-03":33.444120924907295,"GB2-04":44.242143117121884,"GB2-06":37.464680469648904,"GB2-07":29.650791775047207,"GB2-08":45.471425985888416}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:58:28Z","reasoning":{"highest":54.460231382754415,"medium":50.79453483299465,"none":36.17957073522796},"reasoning_agg":{"highest":{"max":80.55559591622435,"mean":54.460231382754415,"min":36.323969341588956},"medium":{"max":77.26959062604402,"mean":50.79453483299465,"min":33.97405749019911},"none":{"max":54.55438147866437,"mean":36.17957073522796,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":18.280660647526453},"working_program_strength":{"all":48.86761568533654,"highest":54.460231382754415,"medium":50.79453483299465,"none":41.34808084026053}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:4c28af42c705817c","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":0.36704000000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.6420659999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704},"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":3.6014780000000006},"codegen_latency_ms":{"attempt_count":28,"max_ms":255692,"mean_ms":76920.70833333333,"min_ms":12384,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":255692,"mean_ms":175619.75,"min_ms":52003,"run_count":8},"medium":{"attempt_count":8,"max_ms":58005,"mean_ms":37933.625,"min_ms":21700,"run_count":8},"none":{"attempt_count":9,"max_ms":20748,"mean_ms":17208.75,"min_ms":12384,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":36035,"output_mean":10826.541666666666,"output_min":1554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":36035,"output_mean":24993.125,"output_min":6631,"run_count":8},"medium":{"attempt_count":8,"output_max":7812,"output_mean":5238.375,"output_min":2903,"run_count":8},"none":{"attempt_count":9,"output_max":3115,"output_mean":2248.125,"output_min":1554,"run_count":8}},"display_name":"Gemini 3.1 Pro Preview","economics":{"all":46.51939072067213,"highest":66.18372637072477,"medium":43.01469424876617,"none":30.359751542525416},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.14418617492404,"score":50.14418617492404},"GB2-02":{"attempts":3,"playable":43.3414330629059,"score":43.3414330629059},"GB2-03":{"attempts":3,"playable":53.662643081283996,"score":53.662643081283996},"GB2-04":{"attempts":3,"playable":56.89233659082797,"score":56.89233659082797},"GB2-05":{"attempts":3,"playable":39.60546905584511,"score":39.60546905584511},"GB2-06":{"attempts":3,"playable":21.21138621867965,"score":21.21138621867965},"GB2-07":{"attempts":3,"playable":56.881178094320376,"score":56.881178094320376},"GB2-08":{"attempts":3,"playable":50.41649348658992,"score":50.41649348658992}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.42544953482206,"score":74.42544953482206},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":65.5868732104754,"score":65.5868732104754},"GB2-04":{"attempts":1,"playable":81.58472848139647,"score":81.58472848139647},"GB2-05":{"attempts":1,"playable":85.17658235933942,"score":85.17658235933942},"GB2-06":{"attempts":1,"playable":19.25812533312175,"score":19.25812533312175},"GB2-07":{"attempts":1,"playable":74.77978494231873,"score":74.77978494231873},"GB2-08":{"attempts":1,"playable":85.73925425476754,"score":85.73925425476754}},"medium":{"GB2-01":{"attempts":1,"playable":35.084886689291196,"score":35.084886689291196},"GB2-02":{"attempts":1,"playable":44.50348640644493,"score":44.50348640644493},"GB2-03":{"attempts":1,"playable":67.23567934220044,"score":67.23567934220044},"GB2-04":{"attempts":1,"playable":46.380117862876105,"score":46.380117862876105},"GB2-05":{"attempts":1,"playable":17.587256918481028,"score":17.587256918481028},"GB2-06":{"attempts":1,"playable":29.44409257277556,"score":29.44409257277556},"GB2-07":{"attempts":1,"playable":71.47287025796041,"score":71.47287025796041},"GB2-08":{"attempts":1,"playable":32.4091639400997,"score":32.4091639400997}},"none":{"GB2-01":{"attempts":1,"playable":40.92222230065885,"score":40.92222230065885},"GB2-02":{"attempts":1,"playable":42.601799932716034,"score":42.601799932716034},"GB2-03":{"attempts":1,"playable":28.165376691176125,"score":28.165376691176125},"GB2-04":{"attempts":1,"playable":42.71216342821136,"score":42.71216342821136},"GB2-05":{"attempts":1,"playable":16.05256788971489,"score":16.05256788971489},"GB2-06":{"attempts":1,"playable":14.931940750141631,"score":14.931940750141631},"GB2-07":{"attempts":1,"playable":24.390879082681977,"score":24.390879082681977},"GB2-08":{"attempts":1,"playable":33.101062264902495,"score":33.101062264902495}}},"id":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-10-24T18:46:30Z","match_totals_all":{"draws":2942,"losses":5331,"wins":3991},"match_totals_tracks":{"highest":{"draws":540,"losses":1169,"wins":2379},"medium":{"draws":1203,"losses":1824,"wins":1061},"none":{"draws":1199,"losses":2338,"wins":551}},"model_slug":"gemini-3-1-pro-preview","official_rank_by_reasoning":{"highest":22,"medium":50,"none":61},"overall":{"max":85.73925425476754,"mean":46.51939072067213,"min":14.931940750141631},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.42544953482206,"GB2-02":42.91901284955672,"GB2-03":65.5868732104754,"GB2-04":81.58472848139647,"GB2-05":85.17658235933942,"GB2-06":19.25812533312175,"GB2-07":74.77978494231873,"GB2-08":85.73925425476754},"per_game_all":{"GB2-01":50.14418617492404,"GB2-02":43.3414330629059,"GB2-03":53.662643081283996,"GB2-04":56.89233659082797,"GB2-05":39.60546905584511,"GB2-06":21.21138621867965,"GB2-07":56.881178094320376,"GB2-08":50.41649348658992},"per_game_match_totals_all":{"GB2-01":{"draws":280,"losses":662,"wins":606},"GB2-02":{"draws":1150,"losses":265,"wins":25},"GB2-03":{"draws":285,"losses":596,"wins":601},"GB2-04":{"draws":691,"losses":321,"wins":482},"GB2-05":{"draws":0,"losses":976,"wins":614},"GB2-06":{"draws":20,"losses":1223,"wins":263},"GB2-07":{"draws":0,"losses":710,"wins":880},"GB2-08":{"draws":516,"losses":578,"wins":520}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":132,"wins":363},"GB2-02":{"draws":378,"losses":93,"wins":9},"GB2-03":{"draws":31,"losses":173,"wins":290},"GB2-04":{"draws":107,"losses":44,"wins":347},"GB2-05":{"draws":0,"losses":84,"wins":446},"GB2-06":{"draws":2,"losses":419,"wins":81},"GB2-07":{"draws":0,"losses":139,"wins":391},"GB2-08":{"draws":1,"losses":85,"wins":452}},"medium":{"GB2-01":{"draws":173,"losses":258,"wins":85},"GB2-02":{"draws":383,"losses":83,"wins":14},"GB2-03":{"draws":98,"losses":131,"wins":265},"GB2-04":{"draws":275,"losses":138,"wins":85},"GB2-05":{"draws":0,"losses":442,"wins":88},"GB2-06":{"draws":16,"losses":366,"wins":120},"GB2-07":{"draws":0,"losses":158,"wins":372},"GB2-08":{"draws":258,"losses":248,"wins":32}},"none":{"GB2-01":{"draws":86,"losses":272,"wins":158},"GB2-02":{"draws":389,"losses":89,"wins":2},"GB2-03":{"draws":156,"losses":292,"wins":46},"GB2-04":{"draws":309,"losses":139,"wins":50},"GB2-05":{"draws":0,"losses":450,"wins":80},"GB2-06":{"draws":2,"losses":438,"wins":62},"GB2-07":{"draws":0,"losses":413,"wins":117},"GB2-08":{"draws":257,"losses":245,"wins":36}}},"per_game_raw_elo_all":{"GB2-01":1476.9666537138773,"GB2-02":1420.3829028028783,"GB2-03":1467.3255563432779,"GB2-04":1547.0557725317422,"GB2-05":1321.2386010173382,"GB2-06":976.097160905931,"GB2-07":1549.2458586181467,"GB2-08":1479.4138211023683},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1723.9393697575117,"GB2-02":1417.117036832385,"GB2-03":1576.0197939895063,"GB2-04":1775.4894851926963,"GB2-05":2065.2814874107644,"GB2-06":948.2519393304783,"GB2-07":1794.8170946790685,"GB2-08":2019.7717886785351},"medium":{"GB2-01":1324.6503061787125,"GB2-02":1429.3754834810786,"GB2-03":1593.9822441438298,"GB2-04":1447.02816205333,"GB2-05":964.4981906708801,"GB2-06":1108.1526847647285,"GB2-07":1740.4424662923977,"GB2-08":1205.5831672859035},"none":{"GB2-01":1382.3102852054083,"GB2-02":1414.656188095171,"GB2-03":1231.9746308964977,"GB2-04":1418.6496703492,"GB2-05":933.9361249703701,"GB2-06":871.8868586225864,"GB2-07":1112.478014882974,"GB2-08":1212.8865073426657}},"per_game_tracks":{"highest":{"GB2-01":74.42544953482206,"GB2-02":42.91901284955672,"GB2-03":65.5868732104754,"GB2-04":81.58472848139647,"GB2-05":85.17658235933942,"GB2-06":19.25812533312175,"GB2-07":74.77978494231873,"GB2-08":85.73925425476754},"medium":{"GB2-01":35.084886689291196,"GB2-02":44.50348640644493,"GB2-03":67.23567934220044,"GB2-04":46.380117862876105,"GB2-05":17.587256918481028,"GB2-06":29.44409257277556,"GB2-07":71.47287025796041,"GB2-08":32.4091639400997},"none":{"GB2-01":40.92222230065885,"GB2-02":42.601799932716034,"GB2-03":28.165376691176125,"GB2-04":42.71216342821136,"GB2-05":16.05256788971489,"GB2-06":14.931940750141631,"GB2-07":24.390879082681977,"GB2-08":33.101062264902495}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:58:47Z","reasoning":{"highest":66.18372637072477,"medium":43.01469424876617,"none":30.359751542525416},"reasoning_agg":{"highest":{"max":85.73925425476754,"mean":66.18372637072477,"min":19.25812533312175},"medium":{"max":71.47287025796041,"mean":43.01469424876617,"min":17.587256918481028},"none":{"max":42.71216342821136,"mean":30.359751542525416,"min":14.931940750141631}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":35.823974828199354},"working_program_strength":{"all":46.51939072067213,"highest":66.18372637072477,"medium":43.01469424876617,"none":30.359751542525416}},{"canonical_public_row_identity":"publication-row.v1:overall:reflection-beam-1-0-501b-a23b:b81a4fc36a279e88","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":0.06745949999999999}},"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":0.08568975000000001},"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":0.06745949999999999},"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":0.227669}},"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":0.38081825},"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":44.71859097101523,"highest":55.60360825605751,"medium":37.69682205591414,"none":40.85534260107404},"first_seen_at":null,"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":33.95283552793654,"score":22.635223685291027},"GB2-02":{"attempts":3,"playable":43.21202884324965,"score":43.21202884324965},"GB2-03":{"attempts":3,"playable":53.93970550555312,"score":53.93970550555312},"GB2-04":{"attempts":3,"playable":46.964627617808,"score":46.964627617808},"GB2-05":{"attempts":3,"playable":52.05180173342195,"score":52.05180173342195},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":65.1948492785539,"score":43.463232852369266},"GB2-07":{"attempts":3,"playable":26.9138727677679,"score":26.9138727677679},"GB2-08":{"attempts":3,"playable":68.56823476266094,"score":68.56823476266094}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":24.913322814235563,"score":24.913322814235563},"GB2-02":{"attempts":1,"playable":50.18419939656429,"score":50.18419939656429},"GB2-03":{"attempts":1,"playable":78.73336941364502,"score":78.73336941364502},"GB2-04":{"attempts":1,"playable":61.09116118624868,"score":61.09116118624868},"GB2-05":{"attempts":1,"playable":53.167946528048695,"score":53.167946528048695},"GB2-06":{"attempts":1,"playable":74.73633860755832,"score":74.73633860755832},"GB2-07":{"attempts":1,"playable":39.20615473939442,"score":39.20615473939442},"GB2-08":{"attempts":1,"playable":62.79637336276514,"score":62.79637336276514}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":33.89359442873875,"score":33.89359442873875},"GB2-03":{"attempts":1,"playable":39.288545647452736,"score":39.288545647452736},"GB2-04":{"attempts":1,"playable":40.05487454955535,"score":40.05487454955535},"GB2-05":{"attempts":1,"playable":41.07153719131046,"score":41.07153719131046},"GB2-06":{"attempts":1,"playable":55.653359949549476,"score":55.653359949549476},"GB2-07":{"attempts":1,"playable":31.38794279525779,"score":31.38794279525779},"GB2-08":{"attempts":1,"playable":60.22472188544856,"score":60.22472188544856}},"none":{"GB2-01":{"attempts":1,"playable":42.99234824163752,"score":42.99234824163752},"GB2-02":{"attempts":1,"playable":45.55829270444591,"score":45.55829270444591},"GB2-03":{"attempts":1,"playable":43.797201455561606,"score":43.797201455561606},"GB2-04":{"attempts":1,"playable":39.74784711761999,"score":39.74784711761999},"GB2-05":{"attempts":1,"playable":61.9159214809067,"score":61.9159214809067},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":10.14752076865149,"score":10.14752076865149},"GB2-08":{"attempts":1,"playable":82.6836090397691,"score":82.6836090397691}}},"id":"reflection/beam-1.0-501b-a23b","is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","match_totals_all":{"draws":2497,"losses":4767,"wins":3981},"match_totals_tracks":{"highest":{"draws":725,"losses":1554,"wins":1809},"medium":{"draws":779,"losses":1732,"wins":1060},"none":{"draws":993,"losses":1481,"wins":1112}},"model_slug":"reflection-beam-1-0-501b-a23b","official_rank_by_reasoning":{"highest":40,"medium":58,"none":42},"overall":{"max":82.6836090397691,"mean":44.71859097101523,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":24.913322814235563,"GB2-02":50.18419939656429,"GB2-03":78.73336941364502,"GB2-04":61.09116118624868,"GB2-05":53.167946528048695,"GB2-06":74.73633860755832,"GB2-07":39.20615473939442,"GB2-08":62.79637336276514},"per_game_all":{"GB2-02":43.21202884324965,"GB2-03":53.93970550555312,"GB2-04":46.964627617808,"GB2-05":52.05180173342195,"GB2-07":26.9138727677679,"GB2-08":68.56823476266094},"per_game_match_totals_all":{"GB2-01":{"draws":344,"losses":528,"wins":160},"GB2-02":{"draws":963,"losses":360,"wins":117},"GB2-03":{"draws":325,"losses":571,"wins":586},"GB2-04":{"draws":826,"losses":404,"wins":264},"GB2-05":{"draws":0,"losses":788,"wins":802},"GB2-06":{"draws":39,"losses":363,"wins":601},"GB2-07":{"draws":0,"losses":1197,"wins":393},"GB2-08":{"draws":0,"losses":556,"wins":1058}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":328,"wins":53},"GB2-02":{"draws":325,"losses":85,"wins":70},"GB2-03":{"draws":38,"losses":100,"wins":356},"GB2-04":{"draws":199,"losses":103,"wins":196},"GB2-05":{"draws":0,"losses":257,"wins":273},"GB2-06":{"draws":28,"losses":126,"wins":348},"GB2-07":{"draws":0,"losses":336,"wins":194},"GB2-08":{"draws":0,"losses":219,"wins":319}},"medium":{"GB2-02":{"draws":281,"losses":184,"wins":15},"GB2-03":{"draws":178,"losses":229,"wins":87},"GB2-04":{"draws":309,"losses":152,"wins":37},"GB2-05":{"draws":0,"losses":320,"wins":210},"GB2-06":{"draws":11,"losses":237,"wins":253},"GB2-07":{"draws":0,"losses":377,"wins":153},"GB2-08":{"draws":0,"losses":233,"wins":305}},"none":{"GB2-01":{"draws":209,"losses":200,"wins":107},"GB2-02":{"draws":357,"losses":91,"wins":32},"GB2-03":{"draws":109,"losses":242,"wins":143},"GB2-04":{"draws":318,"losses":149,"wins":31},"GB2-05":{"draws":0,"losses":211,"wins":319},"GB2-07":{"draws":0,"losses":484,"wins":46},"GB2-08":{"draws":0,"losses":104,"wins":434}}},"per_game_raw_elo_all":{"GB2-02":1418.642885181743,"GB2-03":1484.2866767699788,"GB2-04":1452.3189903054608,"GB2-05":1464.430328025897,"GB2-07":1120.6920808319676,"GB2-08":1675.6459051200966},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1214.1443268233738,"GB2-02":1473.2123521834014,"GB2-03":1745.2967047545142,"GB2-04":1563.6188485414643,"GB2-05":1476.8801647664543,"GB2-06":1842.5637509898422,"GB2-07":1312.8330781371656,"GB2-08":1560.818572183788},"medium":{"GB2-02":1345.2018643819458,"GB2-03":1334.1538891103035,"GB2-04":1397.8782945200899,"GB2-05":1325.351893100165,"GB2-06":1508.708907191009,"GB2-07":1211.6276270765711,"GB2-08":1523.58416647196},"none":{"GB2-01":1402.259882372131,"GB2-02":1437.5144389798816,"GB2-03":1373.409436445119,"GB2-04":1395.459827854828,"GB2-05":1591.0589262110714,"GB2-07":837.6155372821662,"GB2-08":1942.5349767045416}},"per_game_tracks":{"highest":{"GB2-01":24.913322814235563,"GB2-02":50.18419939656429,"GB2-03":78.73336941364502,"GB2-04":61.09116118624868,"GB2-05":53.167946528048695,"GB2-06":74.73633860755832,"GB2-07":39.20615473939442,"GB2-08":62.79637336276514},"medium":{"GB2-02":33.89359442873875,"GB2-03":39.288545647452736,"GB2-04":40.05487454955535,"GB2-05":41.07153719131046,"GB2-06":55.653359949549476,"GB2-07":31.38794279525779,"GB2-08":60.22472188544856},"none":{"GB2-01":42.99234824163752,"GB2-02":45.55829270444591,"GB2-03":43.797201455561606,"GB2-04":39.74784711761999,"GB2-05":61.9159214809067,"GB2-07":10.14752076865149,"GB2-08":82.6836090397691}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:56:58Z","reasoning":{"highest":55.60360825605751,"medium":37.69682205591414,"none":40.85534260107404},"reasoning_agg":{"highest":{"max":78.73336941364502,"mean":55.60360825605751,"min":24.913322814235563},"medium":{"max":60.22472188544856,"mean":37.69682205591414,"min":0.0},"none":{"max":82.6836090397691,"mean":40.85534260107404,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.906786200143372},"working_program_strength":{"all":48.45917024039562,"highest":55.60360825605751,"medium":43.08208234961616,"none":46.69182011551319}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:6d2033982d88524b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14635563000000001,"mean":0.0939111476625,"median":0.10304704349999999,"min":0.032703412,"recorded_attempt_count":26,"run_count":16,"total":1.5025783626},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666666,"min":0.013816857666666668,"recorded_attempt_count":37,"run_count":24,"total":0.5651094239}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23894740000000003,"mean":0.121926546075,"median":0.109979,"min":0.0289264146,"recorded_attempt_count":10,"run_count":8,"total":0.9754123686},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804},"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":0.2059380435},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.09944282164861112,"median":0.056673037849999996,"min":0.013816857666666668,"recorded_attempt_count":72,"run_count":48,"total":3.5146565168},"codegen_latency_ms":{"attempt_count":32,"max_ms":882507,"mean_ms":240683.0,"min_ms":16088,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":882507,"mean_ms":333475.125,"min_ms":88401,"run_count":8},"medium":{"attempt_count":10,"max_ms":677392,"mean_ms":353638.875,"min_ms":112475,"run_count":8},"none":{"attempt_count":13,"max_ms":79329,"mean_ms":34935.0,"min_ms":16088,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":130069,"output_mean":34536.041666666664,"output_min":1442,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":130069,"output_mean":52728.5,"output_min":20107,"run_count":8},"medium":{"attempt_count":10,"output_max":83540,"output_mean":46751.875,"output_min":17329,"run_count":8},"none":{"attempt_count":13,"output_max":8574,"output_mean":4127.75,"output_min":1442,"run_count":8}},"display_name":"GLM-5.2","economics":{"all":44.67498477605153,"highest":44.41001046528548,"medium":48.08241994436648,"none":41.53252391850264},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":6,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":10,"repaired_rate":0.625},"baseline":{"admitted_plugins":24,"evaluated_cells":24,"first_pass_admitted":13,"first_pass_rate":0.5416666666666666,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":3},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":11,"repaired_rate":0.4583333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":40.56611469026394,"score":40.56611469026394},"GB2-02":{"attempts":6,"playable":50.68639602563177,"score":50.68639602563177},"GB2-03":{"attempts":6,"playable":35.96984134815576,"score":35.96984134815576},"GB2-04":{"attempts":6,"playable":50.062331329389316,"score":50.062331329389316},"GB2-05":{"attempts":6,"playable":49.44159946924933,"score":49.44159946924933},"GB2-06":{"attempts":6,"playable":56.01003881092176,"score":56.01003881092176},"GB2-07":{"attempts":6,"playable":39.02121699555412,"score":39.02121699555412},"GB2-08":{"attempts":6,"playable":35.64233953924623,"score":35.64233953924623}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":54.06684288668242,"score":54.06684288668242},"GB2-02":{"attempts":1,"playable":62.240733133465106,"score":62.240733133465106},"GB2-03":{"attempts":1,"playable":37.279315913493164,"score":37.279315913493164},"GB2-04":{"attempts":1,"playable":58.79387562268599,"score":58.79387562268599},"GB2-05":{"attempts":1,"playable":58.88351499425165,"score":58.88351499425165},"GB2-06":{"attempts":1,"playable":42.341405809170936,"score":42.341405809170936},"GB2-07":{"attempts":1,"playable":10.353118751410053,"score":10.353118751410053},"GB2-08":{"attempts":1,"playable":31.321276611124492,"score":31.321276611124492}},"medium":{"GB2-01":{"attempts":2,"playable":39.12246563574213,"score":39.12246563574213},"GB2-02":{"attempts":2,"playable":48.80519488089579,"score":48.80519488089579},"GB2-03":{"attempts":2,"playable":30.533545765774868,"score":30.533545765774868},"GB2-04":{"attempts":2,"playable":48.374869541811535,"score":48.374869541811535},"GB2-05":{"attempts":2,"playable":53.93114544727588,"score":53.93114544727588},"GB2-06":{"attempts":2,"playable":78.73204386116812,"score":78.73204386116812},"GB2-07":{"attempts":2,"playable":58.8416773767531,"score":58.8416773767531},"GB2-08":{"attempts":2,"playable":26.318417045510365,"score":26.318417045510365}},"none":{"GB2-01":{"attempts":3,"playable":28.509035548367248,"score":28.509035548367248},"GB2-02":{"attempts":3,"playable":41.01326006253442,"score":41.01326006253442},"GB2-03":{"attempts":3,"playable":40.09666236519924,"score":40.09666236519924},"GB2-04":{"attempts":3,"playable":43.01824882367044,"score":43.01824882367044},"GB2-05":{"attempts":3,"playable":35.51013796622047,"score":35.51013796622047},"GB2-06":{"attempts":3,"playable":46.95666676242623,"score":46.95666676242623},"GB2-07":{"attempts":3,"playable":47.86885485849922,"score":47.86885485849922},"GB2-08":{"attempts":3,"playable":49.28732496110384,"score":49.28732496110384}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-10-24T19:20:20Z","match_totals_all":{"draws":6898,"losses":10805,"wins":6825},"match_totals_tracks":{"highest":{"draws":1135,"losses":1816,"wins":1137},"medium":{"draws":2407,"losses":3217,"wins":2552},"none":{"draws":3356,"losses":5772,"wins":3136}},"model_slug":"z-ai-glm-5-2","official_rank_by_reasoning":{"highest":48,"medium":43,"none":38},"overall":{"max":78.73204386116812,"mean":44.67498477605153,"min":10.353118751410053},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.06684288668242,"GB2-02":62.240733133465106,"GB2-03":37.279315913493164,"GB2-04":58.79387562268599,"GB2-05":58.88351499425165,"GB2-06":42.341405809170936,"GB2-07":10.353118751410053,"GB2-08":31.321276611124492},"per_game_all":{"GB2-01":40.56611469026394,"GB2-02":50.68639602563177,"GB2-03":35.96984134815576,"GB2-04":50.062331329389316,"GB2-05":49.44159946924933,"GB2-06":56.01003881092176,"GB2-07":39.02121699555412,"GB2-08":35.64233953924623},"per_game_match_totals_all":{"GB2-01":{"draws":765,"losses":1646,"wins":685},"GB2-02":{"draws":2067,"losses":537,"wins":276},"GB2-03":{"draws":1093,"losses":1441,"wins":430},"GB2-04":{"draws":1688,"losses":777,"wins":523},"GB2-05":{"draws":0,"losses":1779,"wins":1401},"GB2-06":{"draws":130,"losses":1340,"wins":1542},"GB2-07":{"draws":0,"losses":1808,"wins":1372},"GB2-08":{"draws":1155,"losses":1477,"wins":596}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":184,"losses":156,"wins":176},"GB2-02":{"draws":237,"losses":71,"wins":172},"GB2-03":{"draws":175,"losses":240,"wins":79},"GB2-04":{"draws":238,"losses":95,"wins":165},"GB2-05":{"draws":0,"losses":227,"wins":303},"GB2-06":{"draws":28,"losses":298,"wins":176},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":273,"losses":246,"wins":19}},"medium":{"GB2-01":{"draws":280,"losses":508,"wins":244},"GB2-02":{"draws":718,"losses":149,"wins":93},"GB2-03":{"draws":416,"losses":510,"wins":62},"GB2-04":{"draws":570,"losses":246,"wins":180},"GB2-05":{"draws":0,"losses":506,"wins":554},"GB2-06":{"draws":40,"losses":216,"wins":748},"GB2-07":{"draws":0,"losses":458,"wins":602},"GB2-08":{"draws":383,"losses":624,"wins":69}},"none":{"GB2-01":{"draws":301,"losses":982,"wins":265},"GB2-02":{"draws":1112,"losses":317,"wins":11},"GB2-03":{"draws":502,"losses":691,"wins":289},"GB2-04":{"draws":880,"losses":436,"wins":178},"GB2-05":{"draws":0,"losses":1046,"wins":544},"GB2-06":{"draws":62,"losses":826,"wins":618},"GB2-07":{"draws":0,"losses":867,"wins":723},"GB2-08":{"draws":499,"losses":607,"wins":508}}},"per_game_raw_elo_all":{"GB2-01":1376.7967411820712,"GB2-02":1479.2397443169673,"GB2-03":1300.417617642937,"GB2-04":1475.8538863867227,"GB2-05":1403.857027969294,"GB2-06":1517.0129951178872,"GB2-07":1271.1905550903682,"GB2-08":1241.008082856027},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1507.9213344466186,"GB2-02":1570.269402684729,"GB2-03":1316.4491853336442,"GB2-04":1544.6073922895616,"GB2-05":1550.1868441900288,"GB2-06":1302.4357484447955,"GB2-07":843.0918174390963,"GB2-08":1194.0401131059741},"medium":{"GB2-01":1363.2010341845883,"GB2-02":1462.7154176358479,"GB2-03":1254.2788085819582,"GB2-04":1462.721519463414,"GB2-05":1486.5482653733543,"GB2-06":1927.2446362888775,"GB2-07":1563.6614640215864,"GB2-08":1139.0670242134288},"none":{"GB2-01":1259.2678549150073,"GB2-02":1404.7344126303246,"GB2-03":1330.524859013209,"GB2-04":1420.2327474071922,"GB2-05":1174.8359743444985,"GB2-06":1321.358600619989,"GB2-07":1406.8183838104214,"GB2-08":1389.917111248678}},"per_game_tracks":{"highest":{"GB2-01":54.06684288668242,"GB2-02":62.240733133465106,"GB2-03":37.279315913493164,"GB2-04":58.79387562268599,"GB2-05":58.88351499425165,"GB2-06":42.341405809170936,"GB2-07":10.353118751410053,"GB2-08":31.321276611124492},"medium":{"GB2-01":39.12246563574213,"GB2-02":48.80519488089579,"GB2-03":30.533545765774868,"GB2-04":48.374869541811535,"GB2-05":53.93114544727588,"GB2-06":78.73204386116812,"GB2-07":58.8416773767531,"GB2-08":26.318417045510365},"none":{"GB2-01":28.509035548367248,"GB2-02":41.01326006253442,"GB2-03":40.09666236519924,"GB2-04":43.01824882367044,"GB2-05":35.51013796622047,"GB2-06":46.95666676242623,"GB2-07":47.86885485849922,"GB2-08":49.28732496110384}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:14:35Z","reasoning":{"highest":44.41001046528548,"medium":48.08241994436648,"none":41.53252391850264},"reasoning_agg":{"highest":{"max":62.240733133465106,"mean":44.41001046528548,"min":10.353118751410053},"medium":{"max":78.73204386116812,"mean":48.08241994436648,"min":26.318417045510365},"none":{"max":49.28732496110384,"mean":41.53252391850264,"min":28.509035548367248}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.549896025863838},"working_program_strength":{"all":44.67498477605153,"highest":44.41001046528548,"medium":48.08241994436648,"none":41.53252391850264}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:9ff71329b8b2ecbf","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":1.17256164828},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.9884523218400001},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784}},"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":0.98845232184},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.37737643796},"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":43.84582677804016,"highest":56.01749933018919,"medium":46.97521686538756,"none":28.544764138543744},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":31,"finish_reasons":["stop"],"indexed_attempts":31,"output_token_observations":31,"provider_post_attempt_observations":31,"provider_post_attempts":31,"reasoning_token_observations":31,"reconciliation_get_attempt_observations":31,"reconciliation_get_attempts":150,"total_output_tokens":797920,"total_reasoning_output_tokens":686933,"total_visible_output_tokens":110987,"visible_token_observations":31},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.56406024463873,"score":43.56406024463873},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.969650657753384,"score":28.64643377183559},"GB2-03":{"attempts":3,"playable":47.838084015982055,"score":47.838084015982055},"GB2-04":{"attempts":3,"playable":40.658734256108495,"score":40.658734256108495},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.67479329757121,"score":39.78319553171414},"GB2-06":{"attempts":3,"playable":55.93294319066064,"score":55.93294319066064},"GB2-07":{"attempts":3,"playable":58.98855582934945,"score":58.98855582934945},"GB2-08":{"attempts":3,"playable":35.35460738403222,"score":35.35460738403222}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":43.583103896001965,"score":43.583103896001965},"GB2-02":{"attempts":1,"playable":45.03104312765546,"score":45.03104312765546},"GB2-03":{"attempts":1,"playable":64.12337333382338,"score":64.12337333382338},"GB2-04":{"attempts":1,"playable":43.32443299908194,"score":43.32443299908194},"GB2-05":{"attempts":1,"playable":74.81232450086726,"score":74.81232450086726},"GB2-06":{"attempts":1,"playable":67.16387383525279,"score":67.16387383525279},"GB2-07":{"attempts":1,"playable":79.27529195288614,"score":79.27529195288614},"GB2-08":{"attempts":1,"playable":30.826550995944636,"score":30.826550995944636}},"medium":{"GB2-01":{"attempts":1,"playable":51.52824935385446,"score":51.52824935385446},"GB2-02":{"attempts":1,"playable":40.90825818785131,"score":40.90825818785131},"GB2-03":{"attempts":1,"playable":43.06690937253382,"score":43.06690937253382},"GB2-04":{"attempts":1,"playable":34.00202759915607,"score":34.00202759915607},"GB2-05":{"attempts":1,"playable":44.53726209427517,"score":44.53726209427517},"GB2-06":{"attempts":1,"playable":39.00354734914658,"score":39.00354734914658},"GB2-07":{"attempts":1,"playable":74.08524346236605,"score":74.08524346236605},"GB2-08":{"attempts":1,"playable":48.67023750391703,"score":48.67023750391703}},"none":{"GB2-01":{"attempts":1,"playable":35.580827484059775,"score":35.580827484059775},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.323969341588956,"score":36.323969341588956},"GB2-04":{"attempts":1,"playable":44.64974217008748,"score":44.64974217008748},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":61.63140838758254,"score":61.63140838758254},"GB2-07":{"attempts":1,"playable":23.605132072796174,"score":23.605132072796174},"GB2-08":{"attempts":1,"playable":26.567033652235,"score":26.567033652235}}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-10-24T19:18:37Z","match_totals_all":{"draws":2571,"losses":4845,"wins":3838},"match_totals_tracks":{"highest":{"draws":777,"losses":1493,"wins":1818},"medium":{"draws":998,"losses":1757,"wins":1333},"none":{"draws":796,"losses":1595,"wins":687}},"model_slug":"deepseek-deepseek-v4-pro-0813","official_rank_by_reasoning":{"highest":38,"medium":45,"none":69},"overall":{"max":79.27529195288614,"mean":43.84582677804016,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":46,"overall_ranking_status":"ranked","per_game":{"GB2-01":43.583103896001965,"GB2-02":45.03104312765546,"GB2-03":64.12337333382338,"GB2-04":43.32443299908194,"GB2-05":74.81232450086726,"GB2-06":67.16387383525279,"GB2-07":79.27529195288614,"GB2-08":30.826550995944636},"per_game_all":{"GB2-01":43.56406024463873,"GB2-03":47.838084015982055,"GB2-04":40.658734256108495,"GB2-06":55.93294319066064,"GB2-07":58.98855582934945,"GB2-08":35.35460738403222},"per_game_match_totals_all":{"GB2-01":{"draws":401,"losses":704,"wins":443},"GB2-02":{"draws":713,"losses":207,"wins":40},"GB2-03":{"draws":284,"losses":686,"wins":512},"GB2-04":{"draws":803,"losses":509,"wins":182},"GB2-05":{"draws":0,"losses":444,"wins":616},"GB2-06":{"draws":31,"losses":706,"wins":769},"GB2-07":{"draws":0,"losses":673,"wins":917},"GB2-08":{"draws":339,"losses":916,"wins":359}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":294,"wins":207},"GB2-02":{"draws":372,"losses":86,"wins":22},"GB2-03":{"draws":26,"losses":183,"wins":285},"GB2-04":{"draws":245,"losses":168,"wins":85},"GB2-05":{"draws":0,"losses":142,"wins":388},"GB2-06":{"draws":11,"losses":176,"wins":315},"GB2-07":{"draws":0,"losses":113,"wins":417},"GB2-08":{"draws":108,"losses":331,"wins":99}},"medium":{"GB2-01":{"draws":284,"losses":119,"wins":113},"GB2-02":{"draws":341,"losses":121,"wins":18},"GB2-03":{"draws":40,"losses":280,"wins":174},"GB2-04":{"draws":192,"losses":240,"wins":66},"GB2-05":{"draws":0,"losses":302,"wins":228},"GB2-06":{"draws":15,"losses":321,"wins":166},"GB2-07":{"draws":0,"losses":143,"wins":387},"GB2-08":{"draws":126,"losses":231,"wins":181}},"none":{"GB2-01":{"draws":102,"losses":291,"wins":123},"GB2-03":{"draws":218,"losses":223,"wins":53},"GB2-04":{"draws":366,"losses":101,"wins":31},"GB2-06":{"draws":5,"losses":209,"wins":288},"GB2-07":{"draws":0,"losses":417,"wins":113},"GB2-08":{"draws":105,"losses":354,"wins":79}}},"per_game_raw_elo_all":{"GB2-01":1407.061216272291,"GB2-03":1411.8713824536064,"GB2-04":1402.0550469026746,"GB2-06":1520.7412665513593,"GB2-07":1587.1821637720902,"GB2-08":1236.6960766701122},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1407.9226012410127,"GB2-02":1433.4476587809247,"GB2-03":1560.5857671716635,"GB2-04":1423.4034254659787,"GB2-05":1800.0044357867923,"GB2-06":1703.1009814914137,"GB2-07":1878.0303314246626,"GB2-08":1188.762105957729},"medium":{"GB2-01":1483.6029994385956,"GB2-02":1401.4662251958114,"GB2-03":1367.0735738875157,"GB2-04":1349.09620190423,"GB2-05":1369.308403886705,"GB2-06":1252.0348843219128,"GB2-07":1783.0067176496561,"GB2-08":1379.0800400940886},"none":{"GB2-01":1329.6580481372648,"GB2-03":1307.9548063016402,"GB2-04":1433.6655133378151,"GB2-06":1607.0879338407515,"GB2-07":1100.5094422419518,"GB2-08":1142.246083958519}},"per_game_tracks":{"highest":{"GB2-01":43.583103896001965,"GB2-02":45.03104312765546,"GB2-03":64.12337333382338,"GB2-04":43.32443299908194,"GB2-05":74.81232450086726,"GB2-06":67.16387383525279,"GB2-07":79.27529195288614,"GB2-08":30.826550995944636},"medium":{"GB2-01":51.52824935385446,"GB2-02":40.90825818785131,"GB2-03":43.06690937253382,"GB2-04":34.00202759915607,"GB2-05":44.53726209427517,"GB2-06":39.00354734914658,"GB2-07":74.08524346236605,"GB2-08":48.67023750391703},"none":{"GB2-01":35.580827484059775,"GB2-03":36.323969341588956,"GB2-04":44.64974217008748,"GB2-06":61.63140838758254,"GB2-07":23.605132072796174,"GB2-08":26.567033652235}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:17:38Z","reasoning":{"highest":56.01749933018919,"medium":46.97521686538756,"none":28.544764138543744},"reasoning_agg":{"highest":{"max":79.27529195288614,"mean":56.01749933018919,"min":30.826550995944636},"medium":{"max":74.08524346236605,"mean":46.97521686538756,"min":34.00202759915607},"none":{"max":61.63140838758254,"mean":28.544764138543744,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.472735191645445},"working_program_strength":{"all":47.01746723787836,"highest":56.01749933018919,"medium":46.97521686538756,"none":38.05968551805832}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:b44807291d543f40","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":0.37262013029400004},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.202372454421}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.372620130294},"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":0.202372454421},"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":43.82186358988201,"highest":48.80266747104267,"medium":53.573876566324486,"none":29.089046732278856},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":514138,"total_reasoning_output_tokens":410486,"total_visible_output_tokens":103652,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":39.652067501696855,"score":39.652067501696855},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.49048962806751,"score":28.326993085378337},"GB2-03":{"attempts":3,"playable":39.848009393116556,"score":39.848009393116556},"GB2-04":{"attempts":3,"playable":45.12440514422454,"score":45.12440514422454},"GB2-05":{"attempts":3,"playable":42.925860452503116,"score":42.925860452503116},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":63.68145064869374,"score":42.454300432462496},"GB2-07":{"attempts":3,"playable":66.99772091494033,"score":66.99772091494033},"GB2-08":{"attempts":3,"playable":45.24555179473378,"score":45.24555179473378}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.516312704953545,"score":27.516312704953545},"GB2-02":{"attempts":1,"playable":45.76910563280643,"score":45.76910563280643},"GB2-03":{"attempts":1,"playable":47.11723944009296,"score":47.11723944009296},"GB2-04":{"attempts":1,"playable":46.481805880558724,"score":46.481805880558724},"GB2-05":{"attempts":1,"playable":45.11429831799664,"score":45.11429831799664},"GB2-06":{"attempts":1,"playable":78.71228582846311,"score":78.71228582846311},"GB2-07":{"attempts":1,"playable":75.12674168151578,"score":75.12674168151578},"GB2-08":{"attempts":1,"playable":24.583550281954086,"score":24.583550281954086}},"medium":{"GB2-01":{"attempts":1,"playable":62.32532361994524,"score":62.32532361994524},"GB2-02":{"attempts":1,"playable":39.21187362332859,"score":39.21187362332859},"GB2-03":{"attempts":1,"playable":29.46432415694756,"score":29.46432415694756},"GB2-04":{"attempts":1,"playable":43.73240795883822,"score":43.73240795883822},"GB2-05":{"attempts":1,"playable":49.14752599463924,"score":49.14752599463924},"GB2-06":{"attempts":1,"playable":48.650615468924364,"score":48.650615468924364},"GB2-07":{"attempts":1,"playable":71.47287025796041,"score":71.47287025796041},"GB2-08":{"attempts":1,"playable":84.58607145001224,"score":84.58607145001224}},"none":{"GB2-01":{"attempts":1,"playable":29.11456618019178,"score":29.11456618019178},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.96246458230915,"score":42.96246458230915},"GB2-04":{"attempts":1,"playable":45.15900159327666,"score":45.15900159327666},"GB2-05":{"attempts":1,"playable":34.51575704487346,"score":34.51575704487346},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":54.393550805344795,"score":54.393550805344795},"GB2-08":{"attempts":1,"playable":26.567033652235,"score":26.567033652235}}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-10-24T18:45:04Z","match_totals_all":{"draws":2663,"losses":4782,"wins":3836},"match_totals_tracks":{"highest":{"draws":999,"losses":1677,"wins":1411},"medium":{"draws":804,"losses":1564,"wins":1720},"none":{"draws":860,"losses":1541,"wins":705}},"model_slug":"deepseek-deepseek-v4-pro","official_rank_by_reasoning":{"highest":45,"medium":30,"none":68},"overall":{"max":84.58607145001224,"mean":43.82186358988201,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":47,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.516312704953545,"GB2-02":45.76910563280643,"GB2-03":47.11723944009296,"GB2-04":46.481805880558724,"GB2-05":45.11429831799664,"GB2-06":78.71228582846311,"GB2-07":75.12674168151578,"GB2-08":24.583550281954086},"per_game_all":{"GB2-01":39.652067501696855,"GB2-03":39.848009393116556,"GB2-04":45.12440514422454,"GB2-05":42.925860452503116,"GB2-07":66.99772091494033,"GB2-08":45.24555179473378},"per_game_match_totals_all":{"GB2-01":{"draws":213,"losses":856,"wins":479},"GB2-02":{"draws":698,"losses":219,"wins":43},"GB2-03":{"draws":444,"losses":723,"wins":315},"GB2-04":{"draws":942,"losses":374,"wins":178},"GB2-05":{"draws":0,"losses":931,"wins":659},"GB2-06":{"draws":19,"losses":388,"wins":596},"GB2-07":{"draws":0,"losses":549,"wins":1041},"GB2-08":{"draws":347,"losses":742,"wins":525}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":43,"losses":361,"wins":112},"GB2-02":{"draws":353,"losses":92,"wins":35},"GB2-03":{"draws":177,"losses":192,"wins":125},"GB2-04":{"draws":296,"losses":127,"wins":75},"GB2-05":{"draws":0,"losses":299,"wins":231},"GB2-06":{"draws":13,"losses":111,"wins":377},"GB2-07":{"draws":0,"losses":137,"wins":393},"GB2-08":{"draws":117,"losses":358,"wins":63}},"medium":{"GB2-01":{"draws":37,"losses":187,"wins":292},"GB2-02":{"draws":345,"losses":127,"wins":8},"GB2-03":{"draws":104,"losses":312,"wins":78},"GB2-04":{"draws":311,"losses":133,"wins":54},"GB2-05":{"draws":0,"losses":278,"wins":252},"GB2-06":{"draws":6,"losses":277,"wins":219},"GB2-07":{"draws":0,"losses":158,"wins":372},"GB2-08":{"draws":1,"losses":92,"wins":445}},"none":{"GB2-01":{"draws":133,"losses":308,"wins":75},"GB2-03":{"draws":163,"losses":219,"wins":112},"GB2-04":{"draws":335,"losses":114,"wins":49},"GB2-05":{"draws":0,"losses":354,"wins":176},"GB2-07":{"draws":0,"losses":254,"wins":276},"GB2-08":{"draws":229,"losses":292,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1365.1994206394018,"GB2-03":1337.6774654031103,"GB2-04":1437.3266938172649,"GB2-05":1347.1791659807088,"GB2-07":1681.3723228355318,"GB2-08":1417.2103858694365},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1244.2294621804222,"GB2-02":1439.1398506663688,"GB2-03":1402.2406128223877,"GB2-04":1447.8128072735615,"GB2-05":1376.541671029408,"GB2-06":1919.6867294858755,"GB2-07":1800.8054202106578,"GB2-08":1119.6608330850854},"medium":{"GB2-01":1589.39439940257,"GB2-02":1388.1408049463282,"GB2-03":1244.624640547696,"GB2-04":1426.5660710198995,"GB2-05":1426.7591891781572,"GB2-06":1398.7382480533117,"GB2-07":1740.4424662923977,"GB2-08":1989.7242405647055},"none":{"GB2-01":1261.9744003352132,"GB2-03":1366.1671428392474,"GB2-04":1437.6012031583343,"GB2-05":1238.2366377345616,"GB2-07":1502.8690820035401,"GB2-08":1142.246083958519}},"per_game_tracks":{"highest":{"GB2-01":27.516312704953545,"GB2-02":45.76910563280643,"GB2-03":47.11723944009296,"GB2-04":46.481805880558724,"GB2-05":45.11429831799664,"GB2-06":78.71228582846311,"GB2-07":75.12674168151578,"GB2-08":24.583550281954086},"medium":{"GB2-01":62.32532361994524,"GB2-02":39.21187362332859,"GB2-03":29.46432415694756,"GB2-04":43.73240795883822,"GB2-05":49.14752599463924,"GB2-06":48.650615468924364,"GB2-07":71.47287025796041,"GB2-08":84.58607145001224},"none":{"GB2-01":29.11456618019178,"GB2-03":42.96246458230915,"GB2-04":45.15900159327666,"GB2-05":34.51575704487346,"GB2-07":54.393550805344795,"GB2-08":26.567033652235}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:14:58Z","reasoning":{"highest":48.80266747104267,"medium":53.573876566324486,"none":29.089046732278856},"reasoning_agg":{"highest":{"max":78.71228582846311,"mean":48.80266747104267,"min":24.583550281954086},"medium":{"max":84.58607145001224,"mean":53.573876566324486,"min":29.46432415694756},"none":{"max":54.393550805344795,"mean":29.089046732278856,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.48482983404563},"working_program_strength":{"all":47.053979893468544,"highest":48.80266747104267,"medium":53.573876566324486,"none":38.78539564303848}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:9c328f26eed06df1","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":0.779305},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-10-09":19},"run_count":24,"token_priced_attempt_count":31,"total":4.45591875},"codegen_latency_ms":{"attempt_count":19,"max_ms":452838,"mean_ms":201000.75,"min_ms":115295,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":452838,"mean_ms":260996.125,"min_ms":140461,"run_count":8},"medium":{"attempt_count":9,"max_ms":181508,"mean_ms":141005.375,"min_ms":115295,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43637,"output_mean":21815.875,"output_min":13286,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43637,"output_mean":26965.5,"output_min":16148,"run_count":8},"medium":{"attempt_count":9,"output_max":19618,"output_mean":16666.25,"output_min":13286,"run_count":8}},"display_name":"GPT-5","economics":{"all":42.95639358433334,"highest":49.533565678267486,"medium":37.80163803394288,"none":41.53397704078967},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"total_output_tokens":349054},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"first_pass_admitted":4,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"performance_rejections":1},"GB2-05":{"admitted":1},"GB2-06":{"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-04","GB2-06"],"performance_rejections":2,"repaired_admitted":2,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.8134275957895,"score":43.8134275957895},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.48283583199873,"score":26.988557221332485},"GB2-03":{"attempts":3,"playable":28.25042920678062,"score":28.25042920678062},"GB2-04":{"attempts":2,"playable":41.43455414475561,"score":41.43455414475561},"GB2-05":{"attempts":3,"playable":61.751747469737005,"score":61.751747469737005},"GB2-06":{"attempts":2,"playable":59.327916665798966,"score":59.327916665798966},"GB2-07":{"attempts":3,"playable":52.41462665363975,"score":52.41462665363975},"GB2-08":{"attempts":3,"playable":35.56806195982459,"score":35.56806195982459}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":39.73753887865891,"score":39.73753887865891},"GB2-02":{"attempts":1,"playable":42.28448286097538,"score":42.28448286097538},"GB2-03":{"attempts":1,"playable":37.59725073191899,"score":37.59725073191899},"GB2-04":{"attempts":1,"playable":40.05487454955535,"score":40.05487454955535},"GB2-05":{"attempts":1,"playable":75.9133113173181,"score":75.9133113173181},"GB2-06":{"attempts":1,"playable":69.90813409585171,"score":69.90813409585171},"GB2-07":{"attempts":1,"playable":52.937657951489925,"score":52.937657951489925},"GB2-08":{"attempts":1,"playable":37.83527504037146,"score":37.83527504037146}},"medium":{"GB2-01":{"attempts":1,"playable":21.09544087678615,"score":21.09544087678615},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.190020315272175,"score":31.190020315272175},"GB2-04":{"attempts":1,"playable":42.81423373995587,"score":42.81423373995587},"GB2-05":{"attempts":1,"playable":61.537543054055796,"score":61.537543054055796},"GB2-06":{"attempts":1,"playable":48.74769923574623,"score":48.74769923574623},"GB2-07":{"attempts":1,"playable":62.840515884841,"score":62.840515884841},"GB2-08":{"attempts":1,"playable":34.18765116488585,"score":34.18765116488585}},"none":{"GB2-01":{"attempts":1,"playable":70.60730303192342,"score":70.60730303192342},"GB2-02":{"attempts":1,"playable":38.681188803022074,"score":38.681188803022074},"GB2-03":{"attempts":1,"playable":15.964016573150685,"score":15.964016573150685},"GB2-05":{"attempts":1,"playable":47.8043880378371,"score":47.8043880378371},"GB2-07":{"attempts":1,"playable":41.46570612458834,"score":41.46570612458834},"GB2-08":{"attempts":1,"playable":34.68125967421646,"score":34.68125967421646}}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-10-24T18:45:41Z","match_totals_all":{"draws":2518,"losses":4889,"wins":3377},"match_totals_tracks":{"highest":{"draws":1165,"losses":1570,"wins":1353},"medium":{"draws":756,"losses":1753,"wins":1099},"none":{"draws":597,"losses":1566,"wins":925}},"model_slug":"gpt-5","official_rank_by_reasoning":{"highest":44,"medium":57,"none":37},"overall":{"max":75.9133113173181,"mean":42.95639358433334,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":48,"overall_ranking_status":"partial","per_game":{"GB2-01":39.73753887865891,"GB2-02":42.28448286097538,"GB2-03":37.59725073191899,"GB2-04":40.05487454955535,"GB2-05":75.9133113173181,"GB2-06":69.90813409585171,"GB2-07":52.937657951489925,"GB2-08":37.83527504037146},"per_game_all":{"GB2-01":43.8134275957895,"GB2-03":28.25042920678062,"GB2-05":61.751747469737005,"GB2-07":52.41462665363975,"GB2-08":35.56806195982459},"per_game_match_totals_all":{"GB2-01":{"draws":208,"losses":794,"wins":546},"GB2-02":{"draws":706,"losses":234,"wins":20},"GB2-03":{"draws":415,"losses":900,"wins":167},"GB2-04":{"draws":599,"losses":300,"wins":97},"GB2-05":{"draws":0,"losses":634,"wins":956},"GB2-06":{"draws":28,"losses":432,"wins":544},"GB2-07":{"draws":0,"losses":793,"wins":797},"GB2-08":{"draws":562,"losses":802,"wins":250}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":86,"losses":278,"wins":152},"GB2-02":{"draws":360,"losses":105,"wins":15},"GB2-03":{"draws":154,"losses":249,"wins":91},"GB2-04":{"draws":331,"losses":141,"wins":26},"GB2-05":{"draws":0,"losses":136,"wins":394},"GB2-06":{"draws":7,"losses":163,"wins":332},"GB2-07":{"draws":0,"losses":262,"wins":268},"GB2-08":{"draws":227,"losses":236,"wins":75}},"medium":{"GB2-01":{"draws":65,"losses":382,"wins":69},"GB2-03":{"draws":190,"losses":261,"wins":43},"GB2-04":{"draws":268,"losses":159,"wins":71},"GB2-05":{"draws":0,"losses":213,"wins":317},"GB2-06":{"draws":21,"losses":269,"wins":212},"GB2-07":{"draws":0,"losses":207,"wins":323},"GB2-08":{"draws":212,"losses":262,"wins":64}},"none":{"GB2-01":{"draws":57,"losses":134,"wins":325},"GB2-02":{"draws":346,"losses":129,"wins":5},"GB2-03":{"draws":71,"losses":390,"wins":33},"GB2-05":{"draws":0,"losses":285,"wins":245},"GB2-07":{"draws":0,"losses":324,"wins":206},"GB2-08":{"draws":123,"losses":304,"wins":111}}},"per_game_raw_elo_all":{"GB2-01":1405.2850351070217,"GB2-03":1223.9766118967482,"GB2-05":1606.0796330246133,"GB2-07":1479.909406944387,"GB2-08":1238.7502597139407},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1370.800666616799,"GB2-02":1412.191784827982,"GB2-03":1319.2641427324645,"GB2-04":1397.8782945200899,"GB2-05":1822.3089543156973,"GB2-06":1752.593690627017,"GB2-07":1484.3674779527653,"GB2-08":1262.456585956901},"medium":{"GB2-01":1166.5883261224612,"GB2-03":1261.0464939161639,"GB2-04":1419.4428312937089,"GB2-05":1585.8552016310275,"GB2-06":1400.2357022926174,"GB2-07":1614.1976839302538,"GB2-08":1224.3097292723855},"none":{"GB2-01":1678.466112581805,"GB2-02":1383.943109542519,"GB2-03":1091.6191990416162,"GB2-05":1410.0747431271152,"GB2-07":1341.1630589501417,"GB2-08":1229.4844639125356}},"per_game_tracks":{"highest":{"GB2-01":39.73753887865891,"GB2-02":42.28448286097538,"GB2-03":37.59725073191899,"GB2-04":40.05487454955535,"GB2-05":75.9133113173181,"GB2-06":69.90813409585171,"GB2-07":52.937657951489925,"GB2-08":37.83527504037146},"medium":{"GB2-01":21.09544087678615,"GB2-03":31.190020315272175,"GB2-04":42.81423373995587,"GB2-05":61.537543054055796,"GB2-06":48.74769923574623,"GB2-07":62.840515884841,"GB2-08":34.18765116488585},"none":{"GB2-01":70.60730303192342,"GB2-02":38.681188803022074,"GB2-03":15.964016573150685,"GB2-05":47.8043880378371,"GB2-07":41.46570612458834,"GB2-08":34.68125967421646}},"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":49.533565678267486,"medium":37.80163803394288,"none":41.53397704078967},"reasoning_agg":{"highest":{"max":75.9133113173181,"mean":49.533565678267486,"min":37.59725073191899},"medium":{"max":62.840515884841,"mean":37.80163803394288,"min":0.0},"none":{"max":70.60730303192342,"mean":41.53397704078967,"min":15.964016573150685}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":11.731927644324607},"working_program_strength":{"all":44.75647158594967,"highest":49.533565678267486,"medium":43.20187203879186,"none":41.53397704078967}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:bdb834bbe44b790a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0367878}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"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":0.0367878},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.33399884999999996},"codegen_output_tokens":{"attempt_count":25,"output_max":29793,"output_mean":9924.083333333334,"output_min":1845,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":29793,"output_mean":24080.5,"output_min":19109,"run_count":8},"medium":{"attempt_count":9,"output_max":6277,"output_mean":3473.625,"output_min":2113,"run_count":8},"none":{"attempt_count":8,"output_max":2721,"output_mean":2218.125,"output_min":1845,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":41.578822752165735,"highest":55.836332420887274,"medium":42.92410347242674,"none":25.976032363183194},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":51.349436602126296,"score":51.349436602126296},"GB2-02":{"attempts":3,"playable":43.65808395372832,"score":43.65808395372832},"GB2-03":{"attempts":3,"playable":38.460794073668374,"score":38.460794073668374},"GB2-04":{"attempts":3,"playable":41.989345527655544,"score":41.989345527655544},"GB2-05":{"attempts":3,"playable":40.09733316739957,"score":40.09733316739957},"GB2-06":{"attempts":3,"playable":52.60878570549263,"score":52.60878570549263},"GB2-07":{"attempts":3,"playable":38.804848735466976,"score":38.804848735466976},"GB2-08":{"attempts":3,"playable":25.66195425178816,"score":25.66195425178816}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.40046698521593,"score":81.40046698521593},"GB2-02":{"attempts":1,"playable":45.136517742837526,"score":45.136517742837526},"GB2-03":{"attempts":1,"playable":41.916408073516,"score":41.916408073516},"GB2-04":{"attempts":1,"playable":38.621368430069445,"score":38.621368430069445},"GB2-05":{"attempts":1,"playable":51.25524698114122,"score":51.25524698114122},"GB2-06":{"attempts":1,"playable":83.55455059557512,"score":83.55455059557512},"GB2-07":{"attempts":1,"playable":72.69356066223246,"score":72.69356066223246},"GB2-08":{"attempts":1,"playable":32.11253989651049,"score":32.11253989651049}},"medium":{"GB2-01":{"attempts":1,"playable":46.532229662825465,"score":46.532229662825465},"GB2-02":{"attempts":1,"playable":43.44746737727414,"score":43.44746737727414},"GB2-03":{"attempts":1,"playable":44.10974286654087,"score":44.10974286654087},"GB2-04":{"attempts":1,"playable":47.701182163897485,"score":47.701182163897485},"GB2-05":{"attempts":1,"playable":44.53726209427517,"score":44.53726209427517},"GB2-06":{"attempts":1,"playable":54.78756514869444,"score":54.78756514869444},"GB2-07":{"attempts":1,"playable":28.68230514083877,"score":28.68230514083877},"GB2-08":{"attempts":1,"playable":33.595073325067546,"score":33.595073325067546}},"none":{"GB2-01":{"attempts":1,"playable":26.115613158337485,"score":26.115613158337485},"GB2-02":{"attempts":1,"playable":42.390266741073305,"score":42.390266741073305},"GB2-03":{"attempts":1,"playable":29.356231280948254,"score":29.356231280948254},"GB2-04":{"attempts":1,"playable":39.64548598899971,"score":39.64548598899971},"GB2-05":{"attempts":1,"playable":24.499490426782323,"score":24.499490426782323},"GB2-06":{"attempts":1,"playable":19.48424137220833,"score":19.48424137220833},"GB2-07":{"attempts":1,"playable":15.038680403329685,"score":15.038680403329685},"GB2-08":{"attempts":1,"playable":11.27824953378643,"score":11.27824953378643}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-10-24T19:07:02Z","match_totals_all":{"draws":3543,"losses":5670,"wins":3051},"match_totals_tracks":{"highest":{"draws":1208,"losses":1280,"wins":1600},"medium":{"draws":1230,"losses":1827,"wins":1031},"none":{"draws":1105,"losses":2563,"wins":420}},"model_slug":"gpt-5-6-luna","official_rank_by_reasoning":{"highest":39,"medium":51,"none":75},"overall":{"max":83.55455059557512,"mean":41.578822752165735,"min":11.27824953378643},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.40046698521593,"GB2-02":45.136517742837526,"GB2-03":41.916408073516,"GB2-04":38.621368430069445,"GB2-05":51.25524698114122,"GB2-06":83.55455059557512,"GB2-07":72.69356066223246,"GB2-08":32.11253989651049},"per_game_all":{"GB2-01":51.349436602126296,"GB2-02":43.65808395372832,"GB2-03":38.460794073668374,"GB2-04":41.989345527655544,"GB2-05":40.09733316739957,"GB2-06":52.60878570549263,"GB2-07":38.804848735466976,"GB2-08":25.66195425178816},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":697,"wins":682},"GB2-02":{"draws":1127,"losses":272,"wins":41},"GB2-03":{"draws":578,"losses":676,"wins":228},"GB2-04":{"draws":952,"losses":415,"wins":127},"GB2-05":{"draws":0,"losses":975,"wins":615},"GB2-06":{"draws":83,"losses":717,"wins":706},"GB2-07":{"draws":0,"losses":1002,"wins":588},"GB2-08":{"draws":634,"losses":916,"wins":64}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":105,"wins":410},"GB2-02":{"draws":359,"losses":92,"wins":29},"GB2-03":{"draws":211,"losses":200,"wins":83},"GB2-04":{"draws":293,"losses":167,"wins":38},"GB2-05":{"draws":0,"losses":267,"wins":263},"GB2-06":{"draws":43,"losses":70,"wins":389},"GB2-07":{"draws":0,"losses":151,"wins":379},"GB2-08":{"draws":301,"losses":228,"wins":9}},"medium":{"GB2-01":{"draws":67,"losses":253,"wins":196},"GB2-02":{"draws":385,"losses":87,"wins":8},"GB2-03":{"draws":156,"losses":217,"wins":121},"GB2-04":{"draws":346,"losses":96,"wins":56},"GB2-05":{"draws":0,"losses":302,"wins":228},"GB2-06":{"draws":18,"losses":239,"wins":245},"GB2-07":{"draws":0,"losses":391,"wins":139},"GB2-08":{"draws":258,"losses":242,"wins":38}},"none":{"GB2-01":{"draws":101,"losses":339,"wins":76},"GB2-02":{"draws":383,"losses":93,"wins":4},"GB2-03":{"draws":211,"losses":259,"wins":24},"GB2-04":{"draws":313,"losses":152,"wins":33},"GB2-05":{"draws":0,"losses":406,"wins":124},"GB2-06":{"draws":22,"losses":408,"wins":72},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":75,"losses":446,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1494.6256926209962,"GB2-02":1422.82873941696,"GB2-03":1325.5947788735455,"GB2-04":1412.8065163974036,"GB2-05":1303.3245968379354,"GB2-06":1488.7787146028804,"GB2-07":1295.182071583253,"GB2-08":1116.7515846212402},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1819.5775541161893,"GB2-02":1434.2614162890784,"GB2-03":1357.0819169938684,"GB2-04":1386.5454844648805,"GB2-05":1452.9678673729168,"GB2-06":2019.4556194046304,"GB2-07":1759.992673352323,"GB2-08":1202.4436632101492},"medium":{"GB2-01":1436.0595261466096,"GB2-02":1421.2111409365534,"GB2-03":1376.1203822209875,"GB2-04":1457.221549219465,"GB2-05":1369.308403886705,"GB2-06":1494.8537979399707,"GB2-07":1174.6245110331324,"GB2-08":1218.0861949364878},"none":{"GB2-01":1228.2399976001898,"GB2-02":1413.0136610252475,"GB2-03":1243.5820374057807,"GB2-04":1394.6525155078648,"GB2-05":1087.6975192541845,"GB2-06":952.0267264640406,"GB2-07":950.9290303643036,"GB2-08":929.7248957170838}},"per_game_tracks":{"highest":{"GB2-01":81.40046698521593,"GB2-02":45.136517742837526,"GB2-03":41.916408073516,"GB2-04":38.621368430069445,"GB2-05":51.25524698114122,"GB2-06":83.55455059557512,"GB2-07":72.69356066223246,"GB2-08":32.11253989651049},"medium":{"GB2-01":46.532229662825465,"GB2-02":43.44746737727414,"GB2-03":44.10974286654087,"GB2-04":47.701182163897485,"GB2-05":44.53726209427517,"GB2-06":54.78756514869444,"GB2-07":28.68230514083877,"GB2-08":33.595073325067546},"none":{"GB2-01":26.115613158337485,"GB2-02":42.390266741073305,"GB2-03":29.356231280948254,"GB2-04":39.64548598899971,"GB2-05":24.499490426782323,"GB2-06":19.48424137220833,"GB2-07":15.038680403329685,"GB2-08":11.27824953378643}},"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":"2026-10-22T10:41:55Z","reasoning":{"highest":55.836332420887274,"medium":42.92410347242674,"none":25.976032363183194},"reasoning_agg":{"highest":{"max":83.55455059557512,"mean":55.836332420887274,"min":32.11253989651049},"medium":{"max":54.78756514869444,"mean":42.92410347242674,"min":28.68230514083877},"none":{"max":42.390266741073305,"mean":25.976032363183194,"min":11.27824953378643}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.86030005770408},"working_program_strength":{"all":41.578822752165735,"highest":55.836332420887274,"medium":42.92410347242674,"none":25.976032363183194}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3-1-flash:02aee399a5efb5d8","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":38.06764751902421,"highest":40.000243435601064,"medium":42.66501655403108,"none":31.53768256744049},"economics_best_value":{"per_model":{"all":true,"highest":true}},"first_seen_at":null,"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":37.984526611686285,"score":37.984526611686285},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.437750297924254,"score":27.625166865282836},"GB2-03":{"attempts":3,"playable":34.81424799111,"score":34.81424799111},"GB2-04":{"attempts":3,"playable":39.67932749297111,"score":39.67932749297111},"GB2-05":{"attempts":3,"playable":48.93678146726333,"score":48.93678146726333},"GB2-06":{"attempts":3,"playable":51.170318933375164,"score":51.170318933375164},"GB2-07":{"attempts":3,"playable":54.64931967722796,"score":54.64931967722796},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":29.044473339831068,"score":9.681491113277023}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":14.931440464969151,"score":14.931440464969151},"GB2-02":{"attempts":1,"playable":41.120108789207535,"score":41.120108789207535},"GB2-03":{"attempts":1,"playable":49.129228508756306,"score":49.129228508756306},"GB2-04":{"attempts":1,"playable":39.64548598899971,"score":39.64548598899971},"GB2-05":{"attempts":1,"playable":72.7826745082981,"score":72.7826745082981},"GB2-06":{"attempts":1,"playable":32.143727831090544,"score":32.143727831090544},"GB2-07":{"attempts":1,"playable":70.24928139348721,"score":70.24928139348721},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":68.11270615327604,"score":68.11270615327604},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.835312098700676,"score":31.835312098700676},"GB2-04":{"attempts":1,"playable":38.72382122309945,"score":38.72382122309945},"GB2-05":{"attempts":1,"playable":50.489237534470966,"score":50.489237534470966},"GB2-06":{"attempts":1,"playable":51.64171182491002,"score":51.64171182491002},"GB2-07":{"attempts":1,"playable":71.47287025796041,"score":71.47287025796041},"GB2-08":{"attempts":1,"playable":29.044473339831068,"score":29.044473339831068}},"none":{"GB2-01":{"attempts":1,"playable":30.909433216813675,"score":30.909433216813675},"GB2-02":{"attempts":1,"playable":41.755391806640965,"score":41.755391806640965},"GB2-03":{"attempts":1,"playable":23.478203365873036,"score":23.478203365873036},"GB2-04":{"attempts":1,"playable":40.66867526681418,"score":40.66867526681418},"GB2-05":{"attempts":1,"playable":23.538432359020923,"score":23.538432359020923},"GB2-06":{"attempts":1,"playable":69.72551714412494,"score":69.72551714412494},"GB2-07":{"attempts":1,"playable":22.22580738023624,"score":22.22580738023624},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"minimax/minimax-m3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:17Z","match_totals_all":{"draws":2213,"losses":5166,"wins":3327},"match_totals_tracks":{"highest":{"draws":790,"losses":1598,"wins":1160},"medium":{"draws":500,"losses":1679,"wins":1429},"none":{"draws":923,"losses":1889,"wins":738}},"model_slug":"minimax-minimax-m3-1-flash","official_rank_by_reasoning":{"highest":50,"medium":52,"none":57},"overall":{"max":72.7826745082981,"mean":38.06764751902421,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["unknown_capability_evidence"],"overall_official_rank":50,"overall_ranking_status":"partial","per_game":{"GB2-01":14.931440464969151,"GB2-02":41.120108789207535,"GB2-03":49.129228508756306,"GB2-04":39.64548598899971,"GB2-05":72.7826745082981,"GB2-06":32.143727831090544,"GB2-07":70.24928139348721},"per_game_all":{"GB2-01":37.984526611686285,"GB2-03":34.81424799111,"GB2-04":39.67932749297111,"GB2-05":48.93678146726333,"GB2-06":51.170318933375164,"GB2-07":54.64931967722796},"per_game_match_totals_all":{"GB2-01":{"draws":136,"losses":918,"wins":494},"GB2-02":{"draws":726,"losses":215,"wins":19},"GB2-03":{"draws":387,"losses":821,"wins":273},"GB2-04":{"draws":946,"losses":452,"wins":96},"GB2-05":{"draws":0,"losses":835,"wins":755},"GB2-06":{"draws":18,"losses":784,"wins":703},"GB2-07":{"draws":0,"losses":747,"wins":843},"GB2-08":{"draws":0,"losses":394,"wins":144}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":26,"losses":432,"wins":58},"GB2-02":{"draws":349,"losses":116,"wins":15},"GB2-03":{"draws":94,"losses":223,"wins":176},"GB2-04":{"draws":315,"losses":151,"wins":32},"GB2-05":{"draws":0,"losses":153,"wins":377},"GB2-06":{"draws":6,"losses":358,"wins":137},"GB2-07":{"draws":0,"losses":165,"wins":365}},"medium":{"GB2-01":{"draws":81,"losses":135,"wins":300},"GB2-03":{"draws":112,"losses":297,"wins":85},"GB2-04":{"draws":296,"losses":165,"wins":37},"GB2-05":{"draws":0,"losses":271,"wins":259},"GB2-06":{"draws":11,"losses":259,"wins":232},"GB2-07":{"draws":0,"losses":158,"wins":372},"GB2-08":{"draws":0,"losses":394,"wins":144}},"none":{"GB2-01":{"draws":29,"losses":351,"wins":136},"GB2-02":{"draws":377,"losses":99,"wins":4},"GB2-03":{"draws":181,"losses":301,"wins":12},"GB2-04":{"draws":335,"losses":136,"wins":27},"GB2-05":{"draws":0,"losses":411,"wins":119},"GB2-06":{"draws":1,"losses":167,"wins":334},"GB2-07":{"draws":0,"losses":424,"wins":106}}},"per_game_raw_elo_all":{"GB2-01":1336.085193971507,"GB2-03":1290.1772165738557,"GB2-04":1394.9039767507877,"GB2-05":1425.5070998216725,"GB2-06":1447.7738236149864,"GB2-07":1513.5895166982434},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1076.4050620176076,"GB2-02":1403.1216555505632,"GB2-03":1419.8176306425219,"GB2-04":1394.6525155078648,"GB2-05":1761.370473304597,"GB2-06":1148.880336594409,"GB2-07":1721.3690750091407},"medium":{"GB2-01":1650.4968799789253,"GB2-03":1267.0882051708843,"GB2-04":1387.3590863213005,"GB2-05":1443.4324601712833,"GB2-06":1445.178395556533,"GB2-07":1740.4424662923977,"GB2-08":1169.5645471079335},"none":{"GB2-01":1281.353639917988,"GB2-02":1408.0759500504598,"GB2-03":1183.6258139081613,"GB2-04":1402.7003284231976,"GB2-05":1071.7183659891373,"GB2-06":1749.2627386940176,"GB2-07":1078.9570087931918}},"per_game_tracks":{"highest":{"GB2-01":14.931440464969151,"GB2-02":41.120108789207535,"GB2-03":49.129228508756306,"GB2-04":39.64548598899971,"GB2-05":72.7826745082981,"GB2-06":32.143727831090544,"GB2-07":70.24928139348721},"medium":{"GB2-01":68.11270615327604,"GB2-03":31.835312098700676,"GB2-04":38.72382122309945,"GB2-05":50.489237534470966,"GB2-06":51.64171182491002,"GB2-07":71.47287025796041,"GB2-08":29.044473339831068},"none":{"GB2-01":30.909433216813675,"GB2-02":41.755391806640965,"GB2-03":23.478203365873036,"GB2-04":40.66867526681418,"GB2-05":23.538432359020923,"GB2-06":69.72551714412494,"GB2-07":22.22580738023624}},"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":40.000243435601064,"medium":42.66501655403108,"none":31.53768256744049},"reasoning_agg":{"highest":{"max":72.7826745082981,"mean":40.000243435601064,"min":0.0},"medium":{"max":71.47287025796041,"mean":42.66501655403108,"min":0.0},"none":{"max":69.72551714412494,"mean":31.53768256744049,"min":0.0}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":11.127333986590585},"working_program_strength":{"all":43.50588287888481,"highest":45.71456392640122,"medium":48.76001891889266,"none":36.04306579136056}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:6e7cd0e8fff13a95","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":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.39097600000000005},"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":0.345102}},"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":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.9275520000000004}},"codegen_cost_usd":{"admitted_cell_count":33,"cell_count":24,"cost_basis_counts":{"estimated":32,"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":15,"max":0.1097735,"mean":0.06116525,"median":0.054719000000000004,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":58},"recorded_attempt_count":32,"run_count":48,"token_priced_attempt_count":26,"total":3.66363},"codegen_latency_ms":{"attempt_count":26,"max_ms":79649,"mean_ms":37254.041666666664,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":10,"max_ms":74310,"mean_ms":41174.25,"min_ms":21597,"run_count":8}},"codegen_output_tokens":{"attempt_count":58,"output_max":15813,"output_mean":7191.916666666667,"output_min":1943,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":10,"output_max":6022,"output_mean":2920.75,"output_min":1943,"run_count":8}},"display_name":"o3","economics":{"all":36.19631575933074,"highest":31.951782231189434,"medium":34.294007737060184,"none":42.343157309742594},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[100000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":82,"output_token_observations":58,"provider_post_attempt_observations":10,"provider_post_attempts":10,"reasoning_token_observations":10,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[100000],"total_output_tokens":345212,"total_reasoning_output_tokens":5824,"total_visible_output_tokens":17542,"visible_token_observations":10},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6785714285714286,"game_attempts":{"GB2-01":{"admitted":3,"model_code_failures":1},"GB2-02":{"performance_rejections":4},"GB2-03":{"admitted":1,"model_code_failures":3},"GB2-04":{"model_code_failures":4},"GB2-05":{"admitted":4},"GB2-06":{"admitted":4},"GB2-07":{"admitted":4},"GB2-08":{"admitted":3,"model_code_failures":1}},"model_code_failure_rate":0.32142857142857145,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-02"],"performance_rejections":4}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":45.37934257520976,"score":40.31137302521068},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.496039108275625,"score":21.248019554137812},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":39.0670426272568,"score":16.990275789588473},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":42.91482789802922,"score":28.609885265352816},"GB2-05":{"attempts":6,"playable":48.39987938503035,"score":48.39987938503035},"GB2-06":{"attempts":6,"playable":44.74622624010947,"score":44.74622624010947},"GB2-07":{"attempts":6,"playable":47.08535967338929,"score":47.08535967338929},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":42.557229024239525,"score":38.611586249476446}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":60.81563459998895,"score":45.61172594999171},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":36.217677180997555,"score":9.054419295249389},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":49.02334095058866,"score":49.02334095058866},"GB2-06":{"attempts":4,"playable":41.141329002950044,"score":41.141329002950044},"GB2-07":{"attempts":4,"playable":43.32087544667849,"score":43.32087544667849},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":47.347713297156986,"score":35.51078497286774}},"medium":{"GB2-01":{"attempts":1,"playable":37.4632595130504,"score":37.4632595130504},"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":41.17991362597097,"score":41.17991362597097},"GB2-05":{"attempts":1,"playable":44.72962858336614,"score":44.72962858336614},"GB2-06":{"attempts":1,"playable":45.224925047187334,"score":45.224925047187334},"GB2-07":{"attempts":1,"playable":58.729048834094975,"score":58.729048834094975},"GB2-08":{"attempts":1,"playable":47.025286292811614,"score":47.025286292811614}},"none":{"GB2-01":{"attempts":1,"playable":37.85913361258993,"score":37.85913361258993},"GB2-02":{"attempts":1,"playable":42.496039108275625,"score":42.496039108275625},"GB2-03":{"attempts":1,"playable":41.91640807351603,"score":41.91640807351603},"GB2-04":{"attempts":1,"playable":44.64974217008748,"score":44.64974217008748},"GB2-05":{"attempts":1,"playable":51.44666862113627,"score":51.44666862113627},"GB2-06":{"attempts":1,"playable":47.87242467019103,"score":47.87242467019103},"GB2-07":{"attempts":1,"playable":39.20615473939442,"score":39.20615473939442},"GB2-08":{"attempts":1,"playable":33.29868748274998,"score":33.29868748274998}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-10-24T18:09:41Z","match_totals_all":{"draws":2316,"losses":8565,"wins":6225},"match_totals_tracks":{"highest":{"draws":654,"losses":5169,"wins":4081},"medium":{"draws":555,"losses":1487,"wins":1072},"none":{"draws":1107,"losses":1909,"wins":1072}},"model_slug":"o3","official_rank_by_reasoning":{"highest":59,"medium":62,"none":35},"overall":{"max":58.729048834094975,"mean":36.19631575933074,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.81563459998895,"GB2-03":36.217677180997555,"GB2-05":49.02334095058866,"GB2-06":41.14132900295004,"GB2-07":43.32087544667849,"GB2-08":47.347713297156986},"per_game_all":{"GB2-01":45.37934257520976,"GB2-05":48.39987938503035,"GB2-06":44.74622624010947,"GB2-07":47.08535967338929,"GB2-08":42.557229024239525},"per_game_match_totals_all":{"GB2-01":{"draws":299,"losses":1153,"wins":1128},"GB2-02":{"draws":378,"losses":95,"wins":7},"GB2-03":{"draws":260,"losses":508,"wins":220},"GB2-04":{"draws":600,"losses":285,"wins":111},"GB2-05":{"draws":0,"losses":1681,"wins":1499},"GB2-06":{"draws":60,"losses":1815,"wins":1137},"GB2-07":{"draws":0,"losses":1820,"wins":1360},"GB2-08":{"draws":719,"losses":1208,"wins":763}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":157,"losses":561,"wins":830},"GB2-03":{"draws":127,"losses":269,"wins":98},"GB2-05":{"draws":0,"losses":1114,"wins":1006},"GB2-06":{"draws":23,"losses":1252,"wins":733},"GB2-07":{"draws":0,"losses":1254,"wins":866},"GB2-08":{"draws":347,"losses":719,"wins":548}},"medium":{"GB2-01":{"draws":99,"losses":283,"wins":134},"GB2-04":{"draws":334,"losses":134,"wins":30},"GB2-05":{"draws":0,"losses":301,"wins":229},"GB2-06":{"draws":29,"losses":283,"wins":190},"GB2-07":{"draws":0,"losses":230,"wins":300},"GB2-08":{"draws":93,"losses":256,"wins":189}},"none":{"GB2-01":{"draws":43,"losses":309,"wins":164},"GB2-02":{"draws":378,"losses":95,"wins":7},"GB2-03":{"draws":133,"losses":239,"wins":122},"GB2-04":{"draws":266,"losses":151,"wins":81},"GB2-05":{"draws":0,"losses":266,"wins":264},"GB2-06":{"draws":8,"losses":280,"wins":214},"GB2-07":{"draws":0,"losses":336,"wins":194},"GB2-08":{"draws":279,"losses":233,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1425.646887284606,"GB2-05":1417.3800256628874,"GB2-06":1339.0155797148936,"GB2-07":1411.6145677211214,"GB2-08":1325.8720871001435},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1576.1092457188468,"GB2-03":1307.0061471342517,"GB2-05":1425.0646244433553,"GB2-06":1284.056068376961,"GB2-07":1363.011921558929,"GB2-08":1401.9944205605832},"medium":{"GB2-01":1348.4578565997933,"GB2-04":1406.7045198838086,"GB2-05":1371.7218557596518,"GB2-06":1346.2346486652227,"GB2-07":1558.9987034672686,"GB2-08":1360.6538791357407},"none":{"GB2-01":1352.3735595351773,"GB2-02":1413.8351260724141,"GB2-03":1357.0819169938686,"GB2-04":1433.6655133378151,"GB2-05":1455.353596785655,"GB2-06":1386.7560221024967,"GB2-07":1312.8330781371656,"GB2-08":1214.9679616041067}},"per_game_tracks":{"highest":{"GB2-01":60.81563459998895,"GB2-03":36.217677180997555,"GB2-05":49.02334095058866,"GB2-06":41.14132900295004,"GB2-07":43.32087544667849,"GB2-08":47.347713297156986},"medium":{"GB2-01":37.4632595130504,"GB2-04":41.17991362597097,"GB2-05":44.72962858336614,"GB2-06":45.224925047187334,"GB2-07":58.729048834094975,"GB2-08":47.025286292811614},"none":{"GB2-01":37.85913361258993,"GB2-02":42.496039108275625,"GB2-03":41.91640807351603,"GB2-04":44.64974217008748,"GB2-05":51.44666862113627,"GB2-06":47.87242467019103,"GB2-07":39.20615473939442,"GB2-08":33.29868748274998}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:48:59Z","reasoning":{"highest":31.951782231189434,"medium":34.294007737060184,"none":42.343157309742594},"reasoning_agg":{"highest":{"max":49.02334095058866,"mean":31.951782231189434,"min":0.0},"medium":{"max":58.729048834094975,"mean":34.294007737060184,"min":0.0},"none":{"max":51.44666862113627,"mean":42.343157309742594,"min":33.29868748274998}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.39137507855316},"working_program_strength":{"all":44.79319867962766,"highest":46.31109507972678,"medium":45.72534364941358,"none":42.343157309742594}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:a3960c506262e9f0","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40577},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.42810400000000004},"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":0.167609}},"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":0.42810400000000004},"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":0.40577}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"codegen_latency_ms":{"attempt_count":34,"max_ms":395404,"mean_ms":199903.16666666666,"min_ms":55601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":395404,"mean_ms":251379.375,"min_ms":180439,"run_count":8},"medium":{"attempt_count":14,"max_ms":353826,"mean_ms":258198.75,"min_ms":158866,"run_count":8},"none":{"attempt_count":9,"max_ms":131809,"mean_ms":90131.375,"min_ms":55601,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22808,"output_mean":12018.333333333334,"output_min":2752,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":22808,"output_mean":15068.125,"output_min":11085,"run_count":8},"medium":{"attempt_count":14,"output_max":21381,"output_mean":15556.75,"output_min":10057,"run_count":8},"none":{"attempt_count":9,"output_max":8609,"output_mean":5430.125,"output_min":2752,"run_count":8}},"display_name":"Seed 2.0 Code","economics":{"all":36.18433981694693,"highest":42.29595889271515,"medium":40.11001375655116,"none":26.14704680157448},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":157,"total_output_tokens":288440,"total_reasoning_output_tokens":204471,"total_visible_output_tokens":83969,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":38.689424385989675,"score":38.689424385989675},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.16616568105054,"score":26.77744378736703},"GB2-03":{"attempts":3,"playable":42.67730246365725,"score":42.67730246365725},"GB2-04":{"attempts":3,"playable":40.497234933261126,"score":40.497234933261126},"GB2-05":{"attempts":3,"playable":38.37149841517748,"score":38.37149841517748},"GB2-06":{"attempts":3,"playable":17.283776903999023,"score":17.283776903999023},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":37.043605049999115,"score":24.69573669999941},"GB2-08":{"attempts":3,"playable":60.48230094612443,"score":60.48230094612443}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.31683167132644,"score":41.31683167132644},"GB2-02":{"attempts":1,"playable":40.90825818785131,"score":40.90825818785131},"GB2-03":{"attempts":1,"playable":41.916408073516,"score":41.916408073516},"GB2-04":{"attempts":1,"playable":38.621368430069445,"score":38.621368430069445},"GB2-05":{"attempts":1,"playable":49.91440011487013,"score":49.91440011487013},"GB2-06":{"attempts":1,"playable":19.710180870890056,"score":19.710180870890056},"GB2-07":{"attempts":1,"playable":45.01721505136273,"score":45.01721505136273},"GB2-08":{"attempts":1,"playable":60.96300874183507,"score":60.96300874183507}},"medium":{"GB2-01":{"attempts":1,"playable":50.94161502132821,"score":50.94161502132821},"GB2-02":{"attempts":1,"playable":39.424073174249784,"score":39.424073174249784},"GB2-03":{"attempts":1,"playable":40.44703556143217,"score":40.44703556143217},"GB2-04":{"attempts":1,"playable":40.66867526681418,"score":40.66867526681418},"GB2-05":{"attempts":1,"playable":48.38018601111506,"score":48.38018601111506},"GB2-06":{"attempts":1,"playable":14.129704245999184,"score":14.129704245999184},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":86.88882077147068,"score":86.88882077147068}},"none":{"GB2-01":{"attempts":1,"playable":23.809826465314384,"score":23.809826465314384},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.66846375602359,"score":45.66846375602359},"GB2-04":{"attempts":1,"playable":42.20166110289975,"score":42.20166110289975},"GB2-05":{"attempts":1,"playable":16.819909119547248,"score":16.819909119547248},"GB2-06":{"attempts":1,"playable":18.011445595107823,"score":18.011445595107823},"GB2-07":{"attempts":1,"playable":29.069995048635498,"score":29.069995048635498},"GB2-08":{"attempts":1,"playable":33.595073325067546,"score":33.595073325067546}}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-10-24T19:21:15Z","match_totals_all":{"draws":2910,"losses":5592,"wins":2752},"match_totals_tracks":{"highest":{"draws":1227,"losses":1836,"wins":1025},"medium":{"draws":829,"losses":1567,"wins":1162},"none":{"draws":854,"losses":2189,"wins":565}},"model_slug":"bytedance-seed-seed-2-0-code","official_rank_by_reasoning":{"highest":49,"medium":54,"none":73},"overall":{"max":86.88882077147068,"mean":36.18433981694693,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.31683167132644,"GB2-02":40.90825818785131,"GB2-03":41.916408073516,"GB2-04":38.621368430069445,"GB2-05":49.91440011487013,"GB2-06":19.710180870890056,"GB2-07":45.01721505136273,"GB2-08":60.96300874183507},"per_game_all":{"GB2-01":38.689424385989675,"GB2-03":42.67730246365725,"GB2-04":40.497234933261126,"GB2-05":38.37149841517748,"GB2-06":17.283776903999023,"GB2-08":60.48230094612443},"per_game_match_totals_all":{"GB2-01":{"draws":392,"losses":782,"wins":374},"GB2-02":{"draws":706,"losses":237,"wins":17},"GB2-03":{"draws":337,"losses":737,"wins":408},"GB2-04":{"draws":984,"losses":421,"wins":89},"GB2-05":{"draws":0,"losses":1002,"wins":588},"GB2-06":{"draws":6,"losses":1283,"wins":217},"GB2-07":{"draws":0,"losses":694,"wins":366},"GB2-08":{"draws":485,"losses":436,"wins":693}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":208,"losses":209,"wins":99},"GB2-02":{"draws":361,"losses":111,"wins":8},"GB2-03":{"draws":133,"losses":239,"wins":122},"GB2-04":{"draws":317,"losses":155,"wins":26},"GB2-05":{"draws":0,"losses":274,"wins":256},"GB2-06":{"draws":2,"losses":417,"wins":83},"GB2-07":{"draws":0,"losses":305,"wins":225},"GB2-08":{"draws":206,"losses":126,"wins":206}},"medium":{"GB2-01":{"draws":68,"losses":230,"wins":218},"GB2-02":{"draws":345,"losses":126,"wins":9},"GB2-03":{"draws":101,"losses":262,"wins":131},"GB2-04":{"draws":313,"losses":147,"wins":38},"GB2-05":{"draws":0,"losses":282,"wins":248},"GB2-06":{"draws":1,"losses":442,"wins":59},"GB2-08":{"draws":1,"losses":78,"wins":459}},"none":{"GB2-01":{"draws":116,"losses":343,"wins":57},"GB2-03":{"draws":103,"losses":236,"wins":155},"GB2-04":{"draws":354,"losses":119,"wins":25},"GB2-05":{"draws":0,"losses":446,"wins":84},"GB2-06":{"draws":3,"losses":424,"wins":75},"GB2-07":{"draws":0,"losses":389,"wins":141},"GB2-08":{"draws":278,"losses":232,"wins":28}}},"per_game_raw_elo_all":{"GB2-01":1355.001184186602,"GB2-03":1363.6709203035484,"GB2-04":1401.3080251098743,"GB2-05":1267.638616210538,"GB2-06":913.1552409018786,"GB2-08":1601.0550643945792},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1386.127701355551,"GB2-02":1401.4662251958114,"GB2-03":1357.0819169938684,"GB2-04":1386.5454844648805,"GB2-05":1436.286012770563,"GB2-06":955.7821720986218,"GB2-07":1385.3680903533505,"GB2-08":1534.040305366625},"medium":{"GB2-01":1478.0075609035503,"GB2-02":1389.8151171454763,"GB2-03":1344.285903415982,"GB2-04":1402.7003284231976,"GB2-05":1417.2287044375887,"GB2-06":856.5668878099593,"GB2-08":2051.0386928806247},"none":{"GB2-01":1200.8682903007048,"GB2-03":1389.6449405007947,"GB2-04":1414.6782624415446,"GB2-05":949.4011314234622,"GB2-06":927.1166627970548,"GB2-07":1180.0145139284828,"GB2-08":1218.0861949364878}},"per_game_tracks":{"highest":{"GB2-01":41.31683167132644,"GB2-02":40.90825818785131,"GB2-03":41.916408073516,"GB2-04":38.621368430069445,"GB2-05":49.91440011487013,"GB2-06":19.710180870890056,"GB2-07":45.01721505136273,"GB2-08":60.96300874183507},"medium":{"GB2-01":50.94161502132821,"GB2-02":39.424073174249784,"GB2-03":40.44703556143217,"GB2-04":40.66867526681418,"GB2-05":48.38018601111506,"GB2-06":14.129704245999184,"GB2-08":86.88882077147068},"none":{"GB2-01":23.809826465314384,"GB2-03":45.66846375602359,"GB2-04":42.20166110289975,"GB2-05":16.819909119547248,"GB2-06":18.011445595107823,"GB2-07":29.069995048635498,"GB2-08":33.595073325067546}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:37:00Z","reasoning":{"highest":42.29595889271515,"medium":40.11001375655116,"none":26.14704680157448},"reasoning_agg":{"highest":{"max":60.96300874183507,"mean":42.29595889271515,"min":19.710180870890056},"medium":{"max":86.88882077147068,"mean":40.11001375655116,"min":0.0},"none":{"max":45.66846375602359,"mean":26.14704680157448,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":16.14891209114067},"working_program_strength":{"all":39.33943793876244,"highest":42.29595889271515,"medium":45.84001572177276,"none":29.882339201799404}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:cd2b67dff13967b7","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":0.35846965},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.16881450499999998}},"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":0.35846965},"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":0.16881450499999998},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.3521656,"mean":0.08720021666666666,"median":0.0402421875,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":38,"run_count":24,"total":2.0928052000000004},"codegen_latency_ms":{"attempt_count":38,"max_ms":2128037,"mean_ms":537328.375,"min_ms":33625,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":2128037,"mean_ms":1259891.875,"min_ms":809012,"run_count":8},"medium":{"attempt_count":13,"max_ms":394009,"mean_ms":249918.25,"min_ms":106640,"run_count":8},"none":{"attempt_count":14,"max_ms":139550,"mean_ms":102175.0,"min_ms":33625,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":142524,"output_mean":33293.458333333336,"output_min":2177,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":142524,"output_mean":77872.0,"output_min":45409,"run_count":8},"medium":{"attempt_count":13,"output_max":24263,"output_mean":15845.5,"output_min":6781,"run_count":8},"none":{"attempt_count":14,"output_max":9194,"output_mean":6162.875,"output_min":2177,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"all":34.447661891146936,"highest":45.02381544628297,"medium":40.82629929482779,"none":17.492870932330053},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[131072],"finish_reason_observations":38,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":41,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"reconciliation_get_attempts":53,"requested_max_output_token_observations":27,"requested_max_output_tokens":[131072],"total_output_tokens":799043,"total_reasoning_output_tokens":636129,"total_visible_output_tokens":162914,"visible_token_observations":38},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-27b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.5,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.90504974507882,"score":50.90504974507882},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.072874969252936,"score":28.04858331283529},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":45.81013430034032,"score":30.540089533560216},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":55.61238582447603,"score":37.07492388298402},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.263218229506606,"score":39.508812153004406},"GB2-06":{"attempts":3,"playable":40.44496969022467,"score":40.44496969022467},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":49.63982042951684,"score":33.09321361967789},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":47.89695957543058,"score":15.965653191810192}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.71069355976981,"score":74.71069355976981},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":71.06757336032884,"score":71.06757336032884},"GB2-05":{"attempts":1,"playable":59.263218229506606,"score":59.263218229506606},"GB2-06":{"attempts":1,"playable":29.011519781158363,"score":29.011519781158363},"GB2-07":{"attempts":1,"playable":78.24055906406954,"score":78.24055906406954},"GB2-08":{"attempts":1,"playable":47.89695957543058,"score":47.89695957543058}},"medium":{"GB2-01":{"attempts":1,"playable":53.091132861231074,"score":53.091132861231074},"GB2-02":{"attempts":1,"playable":42.178687497765914,"score":42.178687497765914},"GB2-03":{"attempts":1,"playable":48.971314080510886,"score":48.971314080510886},"GB2-04":{"attempts":1,"playable":40.15719828862322,"score":40.15719828862322},"GB2-05":{"attempts":1,"playable":59.263218229506606,"score":59.263218229506606},"GB2-06":{"attempts":1,"playable":61.909761606020474,"score":61.909761606020474},"GB2-07":{"attempts":1,"playable":21.039081794964133,"score":21.039081794964133},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"playable":24.913322814235563,"score":24.913322814235563},"GB2-02":{"attempts":1,"playable":41.96706244073995,"score":41.96706244073995},"GB2-03":{"attempts":1,"playable":42.64895452016975,"score":42.64895452016975},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":30.413627683495157,"score":30.413627683495157},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.8-27b","is_recent_addition":false,"last_measured_at":"2026-10-24T16:27:38Z","match_totals_all":{"draws":1939,"losses":3676,"wins":3041},"match_totals_tracks":{"highest":{"draws":302,"losses":1160,"wins":1652},"medium":{"draws":1006,"losses":1478,"wins":1066},"none":{"draws":631,"losses":1038,"wins":323}},"model_slug":"qwen-qwen3-8-27b","official_rank_by_reasoning":{"highest":47,"medium":53},"overall":{"max":78.24055906406954,"mean":34.447661891146936,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":53,"overall_ranking_status":"partial","per_game":{"GB2-01":74.71069355976981,"GB2-04":71.06757336032884,"GB2-05":59.263218229506606,"GB2-06":29.011519781158363,"GB2-07":78.24055906406954,"GB2-08":47.89695957543058},"per_game_all":{"GB2-01":50.90504974507882,"GB2-06":40.44496969022467},"per_game_match_totals_all":{"GB2-01":{"draws":265,"losses":657,"wins":626},"GB2-02":{"draws":758,"losses":193,"wins":9},"GB2-03":{"draws":273,"losses":437,"wins":278},"GB2-04":{"draws":466,"losses":225,"wins":305},"GB2-05":{"draws":0,"losses":450,"wins":610},"GB2-06":{"draws":51,"losses":930,"wins":525},"GB2-07":{"draws":0,"losses":549,"wins":511},"GB2-08":{"draws":126,"losses":235,"wins":177}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":136,"wins":370},"GB2-04":{"draws":152,"losses":76,"wins":270},"GB2-05":{"draws":0,"losses":225,"wins":305},"GB2-06":{"draws":14,"losses":369,"wins":119},"GB2-07":{"draws":0,"losses":119,"wins":411},"GB2-08":{"draws":126,"losses":235,"wins":177}},"medium":{"GB2-01":{"draws":114,"losses":196,"wins":206},"GB2-02":{"draws":381,"losses":95,"wins":4},"GB2-03":{"draws":173,"losses":185,"wins":136},"GB2-04":{"draws":314,"losses":149,"wins":35},"GB2-05":{"draws":0,"losses":225,"wins":305},"GB2-06":{"draws":24,"losses":198,"wins":280},"GB2-07":{"draws":0,"losses":430,"wins":100}},"none":{"GB2-01":{"draws":141,"losses":325,"wins":50},"GB2-02":{"draws":377,"losses":98,"wins":5},"GB2-03":{"draws":100,"losses":252,"wins":142},"GB2-06":{"draws":13,"losses":363,"wins":126}}},"per_game_raw_elo_all":{"GB2-01":1480.062564442095,"GB2-06":1278.735440423414},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1727.4925489433351,"GB2-04":1653.934035956083,"GB2-05":1555.2091171003772,"GB2-06":1101.6011406633643,"GB2-07":1857.655038387862,"GB2-08":1370.3714573284306},"medium":{"GB2-01":1498.5508175595755,"GB2-02":1411.3694893247707,"GB2-03":1418.4332596390548,"GB2-04":1398.683320004907,"GB2-05":1555.2091171003772,"GB2-06":1611.7984468057127,"GB2-07":1059.7955405915052},"none":{"GB2-01":1214.1443268233738,"GB2-02":1409.723607623177,"GB2-03":1363.4456936102683,"GB2-06":1122.806733801165}},"per_game_tracks":{"highest":{"GB2-01":74.71069355976981,"GB2-04":71.06757336032884,"GB2-05":59.263218229506606,"GB2-06":29.011519781158363,"GB2-07":78.24055906406954,"GB2-08":47.89695957543058},"medium":{"GB2-01":53.091132861231074,"GB2-02":42.178687497765914,"GB2-03":48.971314080510886,"GB2-04":40.15719828862322,"GB2-05":59.263218229506606,"GB2-06":61.909761606020474,"GB2-07":21.039081794964133},"none":{"GB2-01":24.913322814235563,"GB2-02":41.96706244073995,"GB2-03":42.64895452016975,"GB2-06":30.413627683495157}},"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":45.02381544628296,"medium":40.82629929482779,"none":17.492870932330053},"reasoning_agg":{"highest":{"max":78.24055906406954,"mean":45.02381544628296,"min":0.0},"medium":{"max":61.909761606020474,"mean":40.82629929482779,"min":0.0},"none":{"max":42.64895452016975,"mean":17.492870932330053,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":27.530944513952907},"working_program_strength":{"all":47.22537451951829,"highest":60.03175392837729,"medium":46.65862776551747,"none":34.985741864660106}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:f53ed4c014b59525","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.0584754711},"medium":{"admitted_cell_count":22,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.008042989573333334,"mean":0.0037891845841666666,"median":0.0032265161666666666,"min":0.002126702,"recorded_attempt_count":36,"run_count":24,"total":0.09094043001999999},"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":0.010671596920000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01663094,"mean":0.00499588742,"median":0.0034890575,"min":0.00258188,"recorded_attempt_count":12,"run_count":8,"total":0.039967099359999994},"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":34.118043351048705,"highest":36.51207388819027,"medium":34.74427251306486,"none":31.09778365189098},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":339820,"total_reasoning_output_tokens":258096,"total_visible_output_tokens":81724,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":22,"evaluated_cells":22,"first_pass_admitted":15,"first_pass_rate":0.6818181818181818,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2,"infra_failures_excluded":1},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"infra_excluded_game_aliases":["GB2-03","GB2-04"],"infra_failures_excluded":2,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.3181818181818182},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-05"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":24.833077066746085,"score":24.833077066746085},"GB2-02":{"attempts":5,"playable":41.61179859740832,"score":41.61179859740832},"GB2-03":{"attempts":4,"playable":37.940164242271926,"score":37.940164242271926},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.53727571365582,"score":27.691517142437217},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":35.331206851408766,"score":23.55413790093918},"GB2-06":{"attempts":5,"playable":54.88143307129613,"score":54.88143307129613},"GB2-07":{"attempts":5,"playable":27.977725571276228,"score":27.977725571276228},"GB2-08":{"attempts":5,"playable":34.454493216014534,"score":34.454493216014534}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":15.641036940477292,"score":15.641036940477292},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":34.939953974889406,"score":34.939953974889406},"GB2-04":{"attempts":1,"playable":42.30378157783618,"score":42.30378157783618},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":82.10085504770582,"score":82.10085504770582},"GB2-07":{"attempts":1,"playable":39.01727969631933,"score":39.01727969631933},"GB2-08":{"attempts":1,"playable":35.1746710187374,"score":35.1746710187374}},"medium":{"GB2-01":{"attempts":3,"playable":38.16559937148221,"score":38.16559937148221},"GB2-02":{"attempts":3,"playable":40.055150136583684,"score":40.055150136583684},"GB2-03":{"attempts":2,"playable":43.83395173689165,"score":43.83395173689165},"GB2-04":{"attempts":2,"playable":40.770769849475464,"score":40.770769849475464},"GB2-05":{"attempts":3,"playable":25.740439583444836,"score":25.740439583444836},"GB2-06":{"attempts":3,"playable":25.866243322330977,"score":25.866243322330977},"GB2-07":{"attempts":3,"playable":25.664908314951024,"score":25.664908314951024},"GB2-08":{"attempts":3,"playable":37.857117789359016,"score":37.857117789359016}},"none":{"GB2-01":{"attempts":1,"playable":20.692594888278762,"score":20.692594888278762},"GB2-02":{"attempts":1,"playable":41.861232806084544,"score":41.861232806084544},"GB2-03":{"attempts":1,"playable":35.04658701503474,"score":35.04658701503474},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.92197411937269,"score":44.92197411937269},"GB2-06":{"attempts":1,"playable":56.677200843851594,"score":56.677200843851594},"GB2-07":{"attempts":1,"playable":19.250988702558328,"score":19.250988702558328},"GB2-08":{"attempts":1,"playable":30.33169083994718,"score":30.33169083994718}}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T19:06:59Z","match_totals_all":{"draws":4719,"losses":9898,"wins":3804},"match_totals_tracks":{"highest":{"draws":1172,"losses":1571,"wins":815},"medium":{"draws":2725,"losses":6332,"wins":2216},"none":{"draws":822,"losses":1995,"wins":773}},"model_slug":"deepseek-deepseek-v4-flash","official_rank_by_reasoning":{"highest":51,"medium":61,"none":58},"overall":{"max":82.10085504770582,"mean":34.118043351048705,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":15.641036940477292,"GB2-02":42.91901284955672,"GB2-03":34.939953974889406,"GB2-04":42.30378157783618,"GB2-06":82.10085504770582,"GB2-07":39.01727969631933,"GB2-08":35.1746710187374},"per_game_all":{"GB2-01":24.833077066746085,"GB2-02":41.61179859740832,"GB2-03":37.940164242271926,"GB2-06":54.88143307129613,"GB2-07":27.977725571276228,"GB2-08":34.454493216014534},"per_game_match_totals_all":{"GB2-01":{"draws":400,"losses":1642,"wins":538},"GB2-02":{"draws":1791,"losses":560,"wins":49},"GB2-03":{"draws":560,"losses":990,"wins":427},"GB2-04":{"draws":979,"losses":412,"wins":103},"GB2-05":{"draws":0,"losses":1499,"wins":621},"GB2-06":{"draws":63,"losses":1468,"wins":979},"GB2-07":{"draws":0,"losses":1993,"wins":657},"GB2-08":{"draws":926,"losses":1334,"wins":430}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":103,"losses":390,"wins":23},"GB2-02":{"draws":348,"losses":108,"wins":24},"GB2-03":{"draws":145,"losses":266,"wins":83},"GB2-04":{"draws":293,"losses":149,"wins":56},"GB2-06":{"draws":37,"losses":81,"wins":384},"GB2-07":{"draws":0,"losses":337,"wins":193},"GB2-08":{"draws":246,"losses":240,"wins":52}},"medium":{"GB2-01":{"draws":188,"losses":890,"wins":470},"GB2-02":{"draws":1061,"losses":356,"wins":23},"GB2-03":{"draws":277,"losses":455,"wins":257},"GB2-04":{"draws":686,"losses":263,"wins":47},"GB2-05":{"draws":0,"losses":1199,"wins":391},"GB2-06":{"draws":14,"losses":1155,"wins":337},"GB2-07":{"draws":0,"losses":1217,"wins":373},"GB2-08":{"draws":499,"losses":797,"wins":318}},"none":{"GB2-01":{"draws":109,"losses":362,"wins":45},"GB2-02":{"draws":382,"losses":96,"wins":2},"GB2-03":{"draws":138,"losses":269,"wins":87},"GB2-05":{"draws":0,"losses":300,"wins":230},"GB2-06":{"draws":12,"losses":232,"wins":258},"GB2-07":{"draws":0,"losses":439,"wins":91},"GB2-08":{"draws":181,"losses":297,"wins":60}}},"per_game_raw_elo_all":{"GB2-01":1193.7375776055326,"GB2-02":1408.0377669443787,"GB2-03":1321.91960449934,"GB2-06":1547.0546923028035,"GB2-07":1164.3735905985905,"GB2-08":1243.6346528519632},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1087.9637584411137,"GB2-02":1417.117036832385,"GB2-03":1295.5397210109682,"GB2-04":1415.473315122039,"GB2-06":1988.565713970154,"GB2-07":1310.4531721616627,"GB2-08":1234.650357966912},"medium":{"GB2-01":1331.974209615346,"GB2-02":1398.0962590431895,"GB2-03":1373.7177375831734,"GB2-04":1403.4930714590778,"GB2-05":1159.9616434042096,"GB2-06":1127.3891678349344,"GB2-07":1152.9967218946113,"GB2-08":1312.7915674668523},"none":{"GB2-01":1161.274764760138,"GB2-02":1408.9000049575616,"GB2-03":1296.5013549038786,"GB2-05":1374.1329139559875,"GB2-06":1525.209195103322,"GB2-07":1029.6708777394972,"GB2-08":1183.462033122125}},"per_game_tracks":{"highest":{"GB2-01":15.641036940477292,"GB2-02":42.91901284955672,"GB2-03":34.939953974889406,"GB2-04":42.30378157783618,"GB2-06":82.10085504770582,"GB2-07":39.01727969631933,"GB2-08":35.1746710187374},"medium":{"GB2-01":38.16559937148221,"GB2-02":40.055150136583684,"GB2-03":43.83395173689165,"GB2-04":40.770769849475464,"GB2-05":25.740439583444836,"GB2-06":25.866243322330977,"GB2-07":25.664908314951024,"GB2-08":37.857117789359016},"none":{"GB2-01":20.692594888278762,"GB2-02":41.861232806084544,"GB2-03":35.04658701503474,"GB2-05":44.92197411937269,"GB2-06":56.677200843851594,"GB2-07":19.250988702558328,"GB2-08":30.33169083994718}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:17:35Z","reasoning":{"highest":36.51207388819027,"medium":34.74427251306486,"none":31.09778365189098},"reasoning_agg":{"highest":{"max":82.10085504770582,"mean":36.51207388819027,"min":0.0},"medium":{"max":43.83395173689165,"mean":34.74427251306486,"min":25.664908314951024},"none":{"max":56.677200843851594,"mean":31.09778365189098,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.414290236299294},"working_program_strength":{"all":37.33756037676685,"highest":41.728084443646026,"medium":34.74427251306486,"none":35.54032417358969}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:67ba69ad004706a8","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":33.3249425762493,"highest":35.977157707107054,"medium":35.834549060915236,"none":28.16312096072561},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":42,"effective_max_output_tokens":[262144],"finish_reason_observations":42,"finish_reasons":["stop"],"indexed_attempts":42,"output_token_observations":42,"provider_post_attempt_observations":42,"provider_post_attempts":42,"reasoning_token_observations":42,"reconciliation_get_attempt_observations":42,"requested_max_output_token_observations":42,"requested_max_output_tokens":[262144],"total_output_tokens":341271,"total_visible_output_tokens":341271,"visible_token_observations":42},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":56.5757747998829,"score":37.717183199921934},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.913908647932054,"score":27.942605765288036},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":41.154304821762935,"score":27.436203214508623},"GB2-04":{"attempts":3,"playable":41.31447877900317,"score":41.31447877900317},"GB2-05":{"attempts":3,"playable":34.14685693816042,"score":34.14685693816042},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":48.8978843584095,"score":32.598589572273},"GB2-07":{"attempts":3,"playable":45.522739569663905,"score":45.522739569663905},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":29.88132535676297,"score":19.920883571175313}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.77576665856935,"score":63.77576665856935},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.82626496490585,"score":38.82626496490585},"GB2-05":{"attempts":1,"playable":45.691139088496946,"score":45.691139088496946},"GB2-06":{"attempts":1,"playable":39.61520849357933,"score":39.61520849357933},"GB2-07":{"attempts":1,"playable":74.43261994221649,"score":74.43261994221649},"GB2-08":{"attempts":1,"playable":25.47626250908845,"score":25.47626250908845}},"medium":{"GB2-01":{"attempts":1,"playable":49.37578294119645,"score":49.37578294119645},"GB2-02":{"attempts":1,"playable":42.601799932716034,"score":42.601799932716034},"GB2-03":{"attempts":1,"playable":45.77214142661275,"score":45.77214142661275},"GB2-04":{"attempts":1,"playable":41.58873026702318,"score":41.58873026702318},"GB2-05":{"attempts":1,"playable":13.174302726318334,"score":13.174302726318334},"GB2-06":{"attempts":1,"playable":58.18056022323967,"score":58.18056022323967},"GB2-07":{"attempts":1,"playable":35.98307497021546,"score":35.98307497021546},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.226017363148074,"score":41.226017363148074},"GB2-03":{"attempts":1,"playable":36.53646821691313,"score":36.53646821691313},"GB2-04":{"attempts":1,"playable":43.52844110508048,"score":43.52844110508048},"GB2-05":{"attempts":1,"playable":43.57512899966596,"score":43.57512899966596},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.152523796559755,"score":26.152523796559755},"GB2-08":{"attempts":1,"playable":34.28638820443749,"score":34.28638820443749}}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-10-24T19:02:40Z","match_totals_all":{"draws":2651,"losses":4538,"wins":2545},"match_totals_tracks":{"highest":{"draws":656,"losses":1357,"wins":1101},"medium":{"draws":915,"losses":1732,"wins":903},"none":{"draws":1080,"losses":1449,"wins":541}},"model_slug":"stealth-space-bunny-alpha","official_rank_by_reasoning":{"highest":53,"medium":59,"none":70},"overall":{"max":74.43261994221649,"mean":33.3249425762493,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.77576665856935,"GB2-04":38.82626496490585,"GB2-05":45.691139088496946,"GB2-06":39.61520849357933,"GB2-07":74.43261994221649,"GB2-08":25.47626250908845},"per_game_all":{"GB2-04":41.31447877900317,"GB2-05":34.14685693816042,"GB2-07":45.522739569663905},"per_game_match_totals_all":{"GB2-01":{"draws":248,"losses":346,"wins":438},"GB2-02":{"draws":751,"losses":198,"wins":11},"GB2-03":{"draws":220,"losses":508,"wins":260},"GB2-04":{"draws":958,"losses":422,"wins":114},"GB2-05":{"draws":0,"losses":1068,"wins":522},"GB2-06":{"draws":13,"losses":549,"wins":442},"GB2-07":{"draws":0,"losses":898,"wins":692},"GB2-08":{"draws":461,"losses":549,"wins":66}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":154,"losses":121,"wins":241},"GB2-04":{"draws":295,"losses":165,"wins":38},"GB2-05":{"draws":0,"losses":296,"wins":234},"GB2-06":{"draws":7,"losses":322,"wins":173},"GB2-07":{"draws":0,"losses":141,"wins":389},"GB2-08":{"draws":200,"losses":312,"wins":26}},"medium":{"GB2-01":{"draws":94,"losses":225,"wins":197},"GB2-02":{"draws":379,"losses":94,"wins":7},"GB2-03":{"draws":102,"losses":236,"wins":156},"GB2-04":{"draws":334,"losses":132,"wins":32},"GB2-05":{"draws":0,"losses":465,"wins":65},"GB2-06":{"draws":6,"losses":227,"wins":269},"GB2-07":{"draws":0,"losses":353,"wins":177}},"none":{"GB2-02":{"draws":372,"losses":104,"wins":4},"GB2-03":{"draws":118,"losses":272,"wins":104},"GB2-04":{"draws":329,"losses":125,"wins":44},"GB2-05":{"draws":0,"losses":307,"wins":223},"GB2-07":{"draws":0,"losses":404,"wins":126},"GB2-08":{"draws":261,"losses":237,"wins":40}}},"per_game_raw_elo_all":{"GB2-04":1407.685557996422,"GB2-05":1204.3073780177835,"GB2-07":1399.7842804579934},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1604.300585955315,"GB2-04":1388.17202162157,"GB2-05":1383.7550624958876,"GB2-06":1261.252642169859,"GB2-07":1788.8849317227414,"GB2-08":1129.917383911085},"medium":{"GB2-01":1463.099507899785,"GB2-02":1414.656188095171,"GB2-03":1390.5452168466832,"GB2-04":1409.8992890450377,"GB2-05":871.96506557487,"GB2-06":1549.6827689782228,"GB2-07":1271.873425257387},"none":{"GB2-02":1403.9485997012819,"GB2-03":1309.8491372604415,"GB2-04":1424.9853633226578,"GB2-05":1357.202005982593,"GB2-07":1138.5944843938526,"GB2-08":1225.345457274866}},"per_game_tracks":{"highest":{"GB2-01":63.77576665856935,"GB2-04":38.82626496490585,"GB2-05":45.691139088496946,"GB2-06":39.61520849357933,"GB2-07":74.43261994221649,"GB2-08":25.47626250908845},"medium":{"GB2-01":49.37578294119645,"GB2-02":42.601799932716034,"GB2-03":45.77214142661275,"GB2-04":41.58873026702318,"GB2-05":13.174302726318334,"GB2-06":58.18056022323967,"GB2-07":35.98307497021546},"none":{"GB2-02":41.226017363148074,"GB2-03":36.53646821691313,"GB2-04":43.52844110508048,"GB2-05":43.57512899966596,"GB2-07":26.152523796559755,"GB2-08":34.28638820443749}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:59:02Z","reasoning":{"highest":35.977157707107054,"medium":35.834549060915236,"none":28.16312096072561},"reasoning_agg":{"highest":{"max":74.43261994221649,"mean":35.977157707107054,"min":0.0},"medium":{"max":58.18056022323967,"mean":35.834549060915236,"min":0.0},"none":{"max":43.57512899966596,"mean":28.16312096072561,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":7.8140367463814435},"working_program_strength":{"all":42.1580473041473,"highest":47.96954360947607,"medium":40.9537703553317,"none":37.55082794763415}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:12939bf008fc0164","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":0.6081093000000001},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.27157109999999995}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000001}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519748999999999},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":33.282282969599805,"highest":33.3773978710674,"medium":27.295617576292983,"none":39.17383346143903},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0625,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.375},"intensive":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":13,"first_pass_rate":0.8125,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.0625}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":37.70508991454657,"score":31.84107427617184},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":43.020529498065095,"score":28.29164409953124},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":48.34588588276108,"score":39.149096569164044},"GB2-04":{"attempts":6,"playable":43.114930272056334,"score":43.114930272056334},"GB2-05":{"attempts":6,"playable":15.380081080372983,"score":15.380081080372983},"GB2-06":{"attempts":6,"playable":37.696549001316974,"score":37.696549001316974},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":42.52584855213404,"score":39.085420196278335},"GB2-08":{"attempts":6,"playable":31.699468261906688,"score":31.699468261906688}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":35.18409383024837,"score":17.592046915124186},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.71454569647757,"score":22.357272848238786},"GB2-03":{"attempts":2,"playable":47.94122776431646,"score":47.94122776431646},"GB2-04":{"attempts":2,"playable":39.84928408125912,"score":39.84928408125912},"GB2-05":{"attempts":2,"playable":18.06691775327741,"score":18.06691775327741},"GB2-06":{"attempts":2,"playable":43.09237381053626,"score":43.09237381053626},"GB2-07":{"attempts":2,"playable":44.92018150069604,"score":44.92018150069604},"GB2-08":{"attempts":2,"playable":33.199878295090954,"score":33.199878295090954}},"medium":{"GB2-01":{"attempts":2,"playable":41.02088794892465,"score":41.02088794892465},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.65876669472558,"score":21.82938334736279},"GB2-03":{"attempts":2,"playable":41.915694002384534,"score":41.915694002384534},"GB2-04":{"attempts":2,"playable":42.456160792404596,"score":42.456160792404596},"GB2-05":{"attempts":2,"playable":16.24440415458963,"score":16.24440415458963},"GB2-06":{"attempts":2,"playable":13.899926997469107,"score":13.899926997469107},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.642570135134267,"score":10.321285067567134},"GB2-08":{"attempts":2,"playable":30.67719829964141,"score":30.67719829964141}},"none":{"GB2-01":{"attempts":2,"playable":36.91028796446669,"score":36.91028796446669},"GB2-02":{"attempts":2,"playable":40.68827610299215,"score":40.68827610299215},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":55.180735881582265,"score":27.590367940791133},"GB2-04":{"attempts":2,"playable":47.039345942505285,"score":47.039345942505285},"GB2-05":{"attempts":2,"playable":11.828921333251913,"score":11.828921333251913},"GB2-06":{"attempts":2,"playable":56.09734619594556,"score":56.09734619594556},"GB2-07":{"attempts":2,"playable":62.01479402057183,"score":62.01479402057183},"GB2-08":{"attempts":2,"playable":31.2213281909877,"score":31.2213281909877}}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-24T19:12:16Z","match_totals_all":{"draws":5409,"losses":11298,"wins":4782},"match_totals_tracks":{"highest":{"draws":1487,"losses":3508,"wins":1647},"medium":{"draws":1913,"losses":4140,"wins":1113},"none":{"draws":2009,"losses":3650,"wins":2022}},"model_slug":"google-gemini-3-5-flash-lite","official_rank_by_reasoning":{"highest":56,"medium":69,"none":46},"overall":{"max":62.01479402057183,"mean":33.282282969599805,"min":10.321285067567134},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":56,"overall_ranking_status":"ranked","per_game":{"GB2-01":35.18409383024837,"GB2-02":44.71454569647757,"GB2-03":47.94122776431646,"GB2-04":39.84928408125912,"GB2-05":18.06691775327741,"GB2-06":43.09237381053626,"GB2-07":44.92018150069604,"GB2-08":33.199878295090954},"per_game_all":{"GB2-01":37.70508991454657,"GB2-02":43.020529498065095,"GB2-03":48.34588588276108,"GB2-04":43.114930272056334,"GB2-05":15.380081080372983,"GB2-06":37.696549001316974,"GB2-07":42.52584855213404,"GB2-08":31.699468261906688},"per_game_match_totals_all":{"GB2-01":{"draws":465,"losses":1411,"wins":704},"GB2-02":{"draws":1497,"losses":388,"wins":34},"GB2-03":{"draws":539,"losses":1134,"wins":797},"GB2-04":{"draws":1840,"losses":829,"wins":319},"GB2-05":{"draws":0,"losses":2721,"wins":459},"GB2-06":{"draws":39,"losses":1954,"wins":1019},"GB2-07":{"draws":0,"losses":1465,"wins":1185},"GB2-08":{"draws":1029,"losses":1396,"wins":265}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":100,"losses":294,"wins":122},"GB2-02":{"draws":357,"losses":95,"wins":28},"GB2-03":{"draws":145,"losses":479,"wins":364},"GB2-04":{"draws":590,"losses":320,"wins":86},"GB2-05":{"draws":0,"losses":879,"wins":181},"GB2-06":{"draws":27,"losses":591,"wins":386},"GB2-07":{"draws":0,"losses":611,"wins":449},"GB2-08":{"draws":268,"losses":239,"wins":31}},"medium":{"GB2-01":{"draws":170,"losses":544,"wins":318},"GB2-02":{"draws":397,"losses":80,"wins":3},"GB2-03":{"draws":306,"losses":458,"wins":224},"GB2-04":{"draws":663,"losses":258,"wins":75},"GB2-05":{"draws":0,"losses":898,"wins":162},"GB2-06":{"draws":4,"losses":885,"wins":115},"GB2-07":{"draws":0,"losses":432,"wins":98},"GB2-08":{"draws":373,"losses":585,"wins":118}},"none":{"GB2-01":{"draws":195,"losses":573,"wins":264},"GB2-02":{"draws":743,"losses":213,"wins":3},"GB2-03":{"draws":88,"losses":197,"wins":209},"GB2-04":{"draws":587,"losses":251,"wins":158},"GB2-05":{"draws":0,"losses":944,"wins":116},"GB2-06":{"draws":8,"losses":478,"wins":518},"GB2-07":{"draws":0,"losses":422,"wins":638},"GB2-08":{"draws":388,"losses":572,"wins":116}}},"per_game_raw_elo_all":{"GB2-01":1350.3771461708204,"GB2-02":1417.8562195121497,"GB2-03":1414.007154173972,"GB2-04":1421.6537450682943,"GB2-05":916.2454468788513,"GB2-06":1230.3058852301576,"GB2-07":1349.322853520663,"GB2-08":1197.9279298905742},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1325.6540242075687,"GB2-02":1431.0050614408563,"GB2-03":1411.0594239379789,"GB2-04":1396.2100758703843,"GB2-05":973.5581772789716,"GB2-06":1322.5848424565743,"GB2-07":1384.1568624596625,"GB2-08":1213.9275064113824},"medium":{"GB2-01":1383.265485482544,"GB2-02":1422.8464090960465,"GB2-03":1357.0710408256837,"GB2-04":1416.635295451854,"GB2-05":937.8264352782412,"GB2-06":851.9581531480305,"GB2-07":1053.252491808305,"GB2-08":1187.019073802766},"none":{"GB2-01":1342.2119288223485,"GB2-02":1399.7171879995467,"GB2-03":1473.8909977582537,"GB2-04":1452.1158638826437,"GB2-05":837.3517280793415,"GB2-06":1516.3746600858685,"GB2-07":1610.5592062940218,"GB2-08":1192.837209457574}},"per_game_tracks":{"highest":{"GB2-01":35.18409383024837,"GB2-02":44.71454569647757,"GB2-03":47.94122776431646,"GB2-04":39.84928408125912,"GB2-05":18.06691775327741,"GB2-06":43.09237381053626,"GB2-07":44.92018150069604,"GB2-08":33.199878295090954},"medium":{"GB2-01":41.02088794892465,"GB2-02":43.65876669472558,"GB2-03":41.915694002384534,"GB2-04":42.456160792404596,"GB2-05":16.24440415458963,"GB2-06":13.899926997469107,"GB2-07":20.642570135134267,"GB2-08":30.67719829964141},"none":{"GB2-01":36.91028796446669,"GB2-02":40.68827610299215,"GB2-03":55.180735881582265,"GB2-04":47.039345942505285,"GB2-05":11.828921333251913,"GB2-06":56.09734619594556,"GB2-07":62.01479402057183,"GB2-08":31.2213281909877}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:33:29Z","reasoning":{"highest":33.3773978710674,"medium":27.295617576292983,"none":39.17383346143903},"reasoning_agg":{"highest":{"max":47.94122776431646,"mean":33.3773978710674,"min":17.592046915124186},"medium":{"max":42.456160792404596,"mean":27.295617576292983,"min":10.321285067567134},"none":{"max":62.01479402057183,"mean":39.17383346143903,"min":11.828921333251913}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.878215885146048},"working_program_strength":{"all":37.43604780789497,"highest":38.37106284148778,"medium":31.31445112815922,"none":42.62262945403793}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:8b9ac06aa7e2af6c","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":0.07763975},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.07206399999999999}},"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":0.07206399999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761485}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373185999999999},"codegen_latency_ms":{"attempt_count":43,"max_ms":599272,"mean_ms":125847.07142857143,"min_ms":18961,"run_count":28},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":599272,"mean_ms":283663.1,"min_ms":69866,"run_count":10},"medium":{"attempt_count":15,"max_ms":68712,"mean_ms":42566.11111111111,"min_ms":22862,"run_count":9},"none":{"attempt_count":14,"max_ms":63236,"mean_ms":33776.88888888889,"min_ms":18961,"run_count":9}},"codegen_output_tokens":{"attempt_count":43,"output_max":49133,"output_mean":11683.67857142857,"output_min":894,"run_count":28},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":49133,"output_mean":28182.1,"output_min":11882,"run_count":10},"medium":{"attempt_count":15,"output_max":4066,"output_mean":2679.6666666666665,"output_min":1736,"run_count":9},"none":{"attempt_count":14,"output_max":5147,"output_mean":2356.1111111111113,"output_min":894,"run_count":9}},"display_name":"Inkling Small","economics":{"all":32.03224674745757,"highest":36.36967290064566,"medium":30.26070391415827,"none":29.46636342756878},"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.4444444444444444},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":21.47904206995452,"score":21.47904206995452},"GB2-02":{"attempts":3,"playable":41.68471072546111,"score":41.68471072546111},"GB2-03":{"attempts":3,"playable":47.66429238094728,"score":47.66429238094728},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":43.76576201823652,"score":36.715131755263826},"GB2-05":{"attempts":3,"playable":19.13853808445575,"score":19.13853808445575},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":29.83410375252444,"score":24.09568257656335},"GB2-07":{"attempts":3,"playable":35.48110451151361,"score":35.48110451151361},"GB2-08":{"attempts":3,"playable":29.999471875501115,"score":29.999471875501115}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":33.198128543801985,"score":33.198128543801985},"GB2-02":{"attempts":1,"playable":41.96706244073995,"score":41.96706244073995},"GB2-03":{"attempts":1,"playable":45.87578936897378,"score":45.87578936897378},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.30378157783618,"score":21.15189078891809},"GB2-05":{"attempts":1,"playable":41.8421530642193,"score":41.8421530642193},"GB2-06":{"attempts":1,"playable":55.07178420180679,"score":55.07178420180679},"GB2-07":{"attempts":1,"playable":18.453085035148472,"score":18.453085035148472},"GB2-08":{"attempts":1,"playable":33.39748976155693,"score":33.39748976155693}},"medium":{"GB2-01":{"attempts":1,"playable":9.439023937646569,"score":9.439023937646569},"GB2-02":{"attempts":1,"playable":42.072880681147076,"score":42.072880681147076},"GB2-03":{"attempts":1,"playable":40.026170921598634,"score":40.026170921598634},"GB2-04":{"attempts":1,"playable":45.05717114428411,"score":45.05717114428411},"GB2-05":{"attempts":1,"playable":10.10048403312083,"score":10.10048403312083},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.670585553711437,"score":8.835292776855718},"GB2-07":{"attempts":1,"playable":56.024957216207405,"score":56.024957216207405},"GB2-08":{"attempts":1,"playable":30.529650602405795,"score":30.529650602405795}},"none":{"GB2-01":{"attempts":1,"playable":21.799973728415015,"score":21.799973728415015},"GB2-02":{"attempts":1,"playable":41.01418905449628,"score":41.01418905449628},"GB2-03":{"attempts":1,"playable":57.09091685226942,"score":57.09091685226942},"GB2-04":{"attempts":1,"playable":43.936333332589264,"score":43.936333332589264},"GB2-05":{"attempts":1,"playable":5.472977156027121,"score":5.472977156027121},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.759941502055096,"score":8.379970751027548},"GB2-07":{"attempts":1,"playable":31.965271283184947,"score":31.965271283184947},"GB2-08":{"attempts":1,"playable":26.07127526254062,"score":26.07127526254062}}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-10-24T19:01:26Z","match_totals_all":{"draws":3434,"losses":6717,"wins":2113},"match_totals_tracks":{"highest":{"draws":1222,"losses":1989,"wins":877},"medium":{"draws":1110,"losses":2339,"wins":639},"none":{"draws":1102,"losses":2389,"wins":597}},"model_slug":"thinkingmachines-inkling-small","official_rank_by_reasoning":{"highest":52,"medium":68,"none":67},"overall":{"max":57.09091685226942,"mean":32.03224674745757,"min":5.472977156027121},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":57,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.198128543801985,"GB2-02":41.96706244073995,"GB2-03":45.87578936897378,"GB2-04":42.30378157783618,"GB2-05":41.8421530642193,"GB2-06":55.07178420180679,"GB2-07":18.453085035148472,"GB2-08":33.39748976155693},"per_game_all":{"GB2-01":21.47904206995452,"GB2-02":41.68471072546111,"GB2-03":47.66429238094728,"GB2-04":43.76576201823652,"GB2-05":19.13853808445575,"GB2-06":29.83410375252444,"GB2-07":35.48110451151361,"GB2-08":29.999471875501115},"per_game_match_totals_all":{"GB2-01":{"draws":262,"losses":1106,"wins":180},"GB2-02":{"draws":1147,"losses":290,"wins":3},"GB2-03":{"draws":441,"losses":612,"wins":429},"GB2-04":{"draws":952,"losses":389,"wins":153},"GB2-05":{"draws":0,"losses":1302,"wins":288},"GB2-06":{"draws":19,"losses":1095,"wins":392},"GB2-07":{"draws":0,"losses":1062,"wins":528},"GB2-08":{"draws":613,"losses":861,"wins":140}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":140,"losses":284,"wins":92},"GB2-02":{"draws":387,"losses":93,"wins":0},"GB2-03":{"draws":93,"losses":240,"wins":161},"GB2-04":{"draws":311,"losses":140,"wins":47},"GB2-05":{"draws":0,"losses":316,"wins":214},"GB2-06":{"draws":15,"losses":239,"wins":248},"GB2-07":{"draws":0,"losses":443,"wins":87},"GB2-08":{"draws":276,"losses":234,"wins":28}},"medium":{"GB2-01":{"draws":60,"losses":442,"wins":14},"GB2-02":{"draws":386,"losses":93,"wins":1},"GB2-03":{"draws":129,"losses":250,"wins":115},"GB2-04":{"draws":302,"losses":131,"wins":65},"GB2-05":{"draws":0,"losses":481,"wins":49},"GB2-06":{"draws":2,"losses":426,"wins":74},"GB2-07":{"draws":0,"losses":245,"wins":285},"GB2-08":{"draws":231,"losses":271,"wins":36}},"none":{"GB2-01":{"draws":62,"losses":380,"wins":74},"GB2-02":{"draws":374,"losses":104,"wins":2},"GB2-03":{"draws":219,"losses":122,"wins":153},"GB2-04":{"draws":339,"losses":118,"wins":41},"GB2-05":{"draws":0,"losses":505,"wins":25},"GB2-06":{"draws":2,"losses":430,"wins":70},"GB2-07":{"draws":0,"losses":374,"wins":156},"GB2-08":{"draws":106,"losses":356,"wins":76}}},"per_game_raw_elo_all":{"GB2-01":1150.0966661959258,"GB2-02":1407.5215247292374,"GB2-03":1407.8684763723857,"GB2-04":1426.8111361693948,"GB2-05":924.5959236181088,"GB2-06":1108.6291078895847,"GB2-07":1252.9392924519577,"GB2-08":1179.420450723275},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1305.35698556915,"GB2-02":1409.723607623177,"GB2-03":1391.4453702850296,"GB2-04":1415.473315122039,"GB2-05":1335.217098058588,"GB2-06":1499.3925480984915,"GB2-07":1015.6737809841143,"GB2-08":1216.0078860556325},"medium":{"GB2-01":969.2018122132674,"GB2-02":1410.5467663290833,"GB2-03":1340.6102990047448,"GB2-04":1436.814489304842,"GB2-05":796.0275233246325,"GB2-06":921.2330254726182,"GB2-07":1523.7887150382696,"GB2-08":1185.5848320788277},"none":{"GB2-01":1175.7312008053602,"GB2-02":1402.2942002354519,"GB2-03":1491.5497598273819,"GB2-04":1428.1456040813032,"GB2-05":642.5431494711063,"GB2-06":905.2617500976444,"GB2-07":1219.3553813334893,"GB2-08":1136.6686340353642}},"per_game_tracks":{"highest":{"GB2-01":33.198128543801985,"GB2-02":41.96706244073995,"GB2-03":45.87578936897378,"GB2-04":42.30378157783618,"GB2-05":41.8421530642193,"GB2-06":55.07178420180679,"GB2-07":18.453085035148472,"GB2-08":33.39748976155693},"medium":{"GB2-01":9.439023937646569,"GB2-02":42.072880681147076,"GB2-03":40.026170921598634,"GB2-04":45.05717114428411,"GB2-05":10.10048403312083,"GB2-06":17.670585553711437,"GB2-07":56.024957216207405,"GB2-08":30.529650602405795},"none":{"GB2-01":21.799973728415015,"GB2-02":41.01418905449628,"GB2-03":57.09091685226942,"GB2-04":43.936333332589264,"GB2-05":5.472977156027121,"GB2-06":16.759941502055096,"GB2-07":31.965271283184947,"GB2-08":26.07127526254062}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:56:26Z","reasoning":{"highest":36.36967290064566,"medium":30.26070391415827,"none":29.46636342756878},"reasoning_agg":{"highest":{"max":55.07178420180679,"mean":36.36967290064566,"min":18.453085035148472},"medium":{"max":56.024957216207405,"mean":30.26070391415827,"min":8.835292776855718},"none":{"max":57.09091685226942,"mean":29.46636342756878,"min":5.472977156027121}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.903309473076881},"working_program_strength":{"all":33.63087817732429,"highest":39.01365924926043,"medium":31.365115511265238,"none":30.513859771447223}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:97778464fdf4bc27","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":0.15725572000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.058501660000000004},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539000000004},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":30.529894456197127,"highest":35.941433131983615,"medium":31.677448032764598,"none":23.970802203843157},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":164,"total_output_tokens":154154,"total_reasoning_output_tokens":105962,"total_visible_output_tokens":48432,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-glimmer-30b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":29.995530176386723,"score":29.995530176386723},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.13040641486156,"score":28.753604276574375},"GB2-03":{"attempts":3,"playable":40.645640656707236,"score":40.645640656707236},"GB2-04":{"attempts":3,"playable":46.038304164668624,"score":46.038304164668624},"GB2-05":{"attempts":3,"playable":23.05021606277954,"score":23.05021606277954},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":17.215563096589744,"score":5.738521032196581},"GB2-07":{"attempts":3,"playable":37.47638049903903,"score":37.47638049903903},"GB2-08":{"attempts":3,"playable":32.54095878122488,"score":32.54095878122488}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":31.710677941544184,"score":31.710677941544184},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":37.491301059150196,"score":37.491301059150196},"GB2-04":{"attempts":1,"playable":49.121683269699886,"score":49.121683269699886},"GB2-05":{"attempts":1,"playable":45.88337415040265,"score":45.88337415040265},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":47.79853401951436,"score":47.79853401951436},"GB2-08":{"attempts":1,"playable":32.606881766000896,"score":32.606881766000896}},"medium":{"GB2-01":{"attempts":1,"playable":22.00116473957175,"score":22.00116473957175},"GB2-02":{"attempts":1,"playable":43.3417999801664,"score":43.3417999801664},"GB2-03":{"attempts":1,"playable":39.815565149295026,"score":39.815565149295026},"GB2-04":{"attempts":1,"playable":45.26082126546774,"score":45.26082126546774},"GB2-05":{"attempts":1,"playable":15.477039442891922,"score":15.477039442891922},"GB2-06":{"attempts":1,"playable":17.215563096589744,"score":17.215563096589744},"GB2-07":{"attempts":1,"playable":37.50305681246873,"score":37.50305681246873},"GB2-08":{"attempts":1,"playable":32.80457377566549,"score":32.80457377566549}},"none":{"GB2-01":{"attempts":1,"playable":36.274747848044235,"score":36.274747848044235},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.63005576167648,"score":44.63005576167648},"GB2-04":{"attempts":1,"playable":43.73240795883822,"score":43.73240795883822},"GB2-05":{"attempts":1,"playable":7.790234595044046,"score":7.790234595044046},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":27.127550665134,"score":27.127550665134},"GB2-08":{"attempts":1,"playable":32.211420802008256,"score":32.211420802008256}}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-10-24T18:34:55Z","match_totals_all":{"draws":3252,"losses":5644,"wins":1883},"match_totals_tracks":{"highest":{"draws":1204,"losses":1590,"wins":791},"medium":{"draws":1209,"losses":2284,"wins":595},"none":{"draws":839,"losses":1770,"wins":497}},"model_slug":"meta-muse-glimmer-30b","official_rank_by_reasoning":{"highest":54,"medium":65,"none":78},"overall":{"max":49.121683269699886,"mean":30.529894456197127,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.710677941544184,"GB2-02":42.91901284955672,"GB2-03":37.491301059150196,"GB2-04":49.121683269699886,"GB2-05":45.88337415040265,"GB2-07":47.79853401951436,"GB2-08":32.606881766000896},"per_game_all":{"GB2-01":29.995530176386723,"GB2-03":40.645640656707236,"GB2-04":46.038304164668624,"GB2-05":23.05021606277954,"GB2-07":37.47638049903903,"GB2-08":32.54095878122488},"per_game_match_totals_all":{"GB2-01":{"draws":320,"losses":949,"wins":278},"GB2-02":{"draws":784,"losses":170,"wins":6},"GB2-03":{"draws":451,"losses":709,"wins":322},"GB2-04":{"draws":985,"losses":339,"wins":170},"GB2-05":{"draws":0,"losses":1241,"wins":349},"GB2-06":{"draws":2,"losses":428,"wins":72},"GB2-07":{"draws":0,"losses":1034,"wins":556},"GB2-08":{"draws":710,"losses":774,"wins":130}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":293,"wins":87},"GB2-02":{"draws":386,"losses":89,"wins":5},"GB2-03":{"draws":157,"losses":248,"wins":89},"GB2-04":{"draws":288,"losses":118,"wins":92},"GB2-05":{"draws":0,"losses":295,"wins":235},"GB2-07":{"draws":0,"losses":290,"wins":240},"GB2-08":{"draws":238,"losses":257,"wins":43}},"medium":{"GB2-01":{"draws":90,"losses":365,"wins":61},"GB2-02":{"draws":398,"losses":81,"wins":1},"GB2-03":{"draws":129,"losses":251,"wins":114},"GB2-04":{"draws":342,"losses":110,"wins":46},"GB2-05":{"draws":0,"losses":453,"wins":77},"GB2-06":{"draws":2,"losses":428,"wins":72},"GB2-07":{"draws":0,"losses":345,"wins":185},"GB2-08":{"draws":248,"losses":251,"wins":39}},"none":{"GB2-01":{"draws":95,"losses":291,"wins":130},"GB2-03":{"draws":165,"losses":210,"wins":119},"GB2-04":{"draws":355,"losses":111,"wins":32},"GB2-05":{"draws":0,"losses":493,"wins":37},"GB2-07":{"draws":0,"losses":399,"wins":131},"GB2-08":{"draws":224,"losses":266,"wins":48}}},"per_game_raw_elo_all":{"GB2-01":1268.2578517958455,"GB2-03":1345.90970953271,"GB2-04":1444.3821093223862,"GB2-05":1012.0768715943306,"GB2-07":1287.966359238862,"GB2-08":1206.97461429759},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1289.8400293352486,"GB2-02":1417.117036832385,"GB2-03":1318.3266979991868,"GB2-04":1468.1925386333587,"GB2-05":1386.155542582243,"GB2-07":1419.940886413642,"GB2-08":1207.6728892636213},"medium":{"GB2-01":1178.308609783032,"GB2-02":1420.3930140337618,"GB2-03":1338.7688408115014,"GB2-04":1438.3877183139014,"GB2-05":922.0743621097271,"GB2-06":913.3005579808784,"GB2-07":1291.28918589015,"GB2-08":1209.7601144938835},"none":{"GB2-01":1336.624916269256,"GB2-03":1380.6335897874417,"GB2-04":1426.5660710198995,"GB2-05":728.0007100910215,"GB2-07":1152.669005412794,"GB2-08":1203.4908391352656}},"per_game_tracks":{"highest":{"GB2-01":31.710677941544184,"GB2-02":42.91901284955672,"GB2-03":37.491301059150196,"GB2-04":49.121683269699886,"GB2-05":45.88337415040265,"GB2-07":47.79853401951436,"GB2-08":32.606881766000896},"medium":{"GB2-01":22.00116473957175,"GB2-02":43.3417999801664,"GB2-03":39.815565149295026,"GB2-04":45.26082126546774,"GB2-05":15.477039442891922,"GB2-06":17.215563096589744,"GB2-07":37.50305681246873,"GB2-08":32.80457377566549},"none":{"GB2-01":36.274747848044235,"GB2-03":44.63005576167648,"GB2-04":43.73240795883822,"GB2-05":7.790234595044046,"GB2-07":27.127550665134,"GB2-08":32.211420802008256}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:20:51Z","reasoning":{"highest":35.941433131983615,"medium":31.677448032764598,"none":23.970802203843153},"reasoning_agg":{"highest":{"max":49.121683269699886,"mean":35.941433131983615,"min":0.0},"medium":{"max":45.26082126546774,"mean":31.677448032764598,"min":15.477039442891922},"none":{"max":44.63005576167648,"mean":23.970802203843153,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":11.970630928140462},"working_program_strength":{"all":34.90481373909955,"highest":41.075923579409846,"medium":31.677448032764598,"none":31.96106960512421}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:f7b7ca6843818cf7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855891}},"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":0.05953976200000001}},"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":30.221032038040136,"highest":34.97943004334445,"medium":31.27543720753043,"none":24.40822886324552},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":33,"finish_reasons":["stop"],"indexed_attempts":33,"output_token_observations":33,"provider_post_attempt_observations":33,"provider_post_attempts":33,"reasoning_token_observations":33,"reconciliation_get_attempt_observations":33,"reconciliation_get_attempts":158,"total_output_tokens":223323,"total_reasoning_output_tokens":139050,"total_visible_output_tokens":87482,"visible_token_observations":33},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":38.49914890839152,"score":25.66609927226101},"GB2-02":{"attempts":3,"playable":43.27117499671606,"score":43.27117499671606},"GB2-03":{"attempts":3,"playable":39.363340475670405,"score":39.363340475670405},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":40.820431529122175,"score":27.213621019414784},"GB2-05":{"attempts":3,"playable":29.883799452722062,"score":29.883799452722062},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":24.342860185565456,"score":16.228573457043638},"GB2-07":{"attempts":3,"playable":28.062758255994936,"score":28.062758255994936},"GB2-08":{"attempts":3,"playable":32.07888937449818,"score":32.07888937449818}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.87001850459841,"score":43.87001850459841},"GB2-03":{"attempts":1,"playable":46.18655465207163,"score":46.18655465207163},"GB2-04":{"attempts":1,"playable":42.71216342821136,"score":42.71216342821136},"GB2-05":{"attempts":1,"playable":58.31362665998524,"score":58.31362665998524},"GB2-06":{"attempts":1,"playable":22.071280542068205,"score":22.071280542068205},"GB2-07":{"attempts":1,"playable":34.07491479381986,"score":34.07491479381986},"GB2-08":{"attempts":1,"playable":32.606881766000896,"score":32.606881766000896}},"medium":{"GB2-01":{"attempts":1,"playable":35.977409867858384,"score":35.977409867858384},"GB2-02":{"attempts":1,"playable":42.496039108275625,"score":42.496039108275625},"GB2-03":{"attempts":1,"playable":35.685789593942026,"score":35.685789593942026},"GB2-04":{"attempts":1,"playable":38.928699630032995,"score":38.928699630032995},"GB2-05":{"attempts":1,"playable":15.668885849090477,"score":15.668885849090477},"GB2-06":{"attempts":1,"playable":26.614439829062704,"score":26.614439829062704},"GB2-07":{"attempts":1,"playable":21.2371604569137,"score":21.2371604569137},"GB2-08":{"attempts":1,"playable":33.595073325067546,"score":33.595073325067546}},"none":{"GB2-01":{"attempts":1,"playable":41.02088794892465,"score":41.02088794892465},"GB2-02":{"attempts":1,"playable":43.44746737727414,"score":43.44746737727414},"GB2-03":{"attempts":1,"playable":36.217677180997555,"score":36.217677180997555},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":15.668885849090476,"score":15.668885849090476},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":28.876199517251244,"score":28.876199517251244},"GB2-08":{"attempts":1,"playable":30.034713032426097,"score":30.034713032426097}}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-10-24T19:06:59Z","match_totals_all":{"draws":2970,"losses":5815,"wins":1963},"match_totals_tracks":{"highest":{"draws":947,"losses":1759,"wins":866},"medium":{"draws":1190,"losses":2315,"wins":583},"none":{"draws":833,"losses":1741,"wins":514}},"model_slug":"openai-gpt-oss-120b","official_rank_by_reasoning":{"highest":55,"medium":67,"none":76},"overall":{"max":58.31362665998524,"mean":30.221032038040136,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":59,"overall_ranking_status":"ranked","per_game":{"GB2-02":43.87001850459841,"GB2-03":46.18655465207163,"GB2-04":42.71216342821136,"GB2-05":58.31362665998524,"GB2-06":22.071280542068205,"GB2-07":34.07491479381986,"GB2-08":32.606881766000896},"per_game_all":{"GB2-02":43.27117499671606,"GB2-03":39.363340475670405,"GB2-05":29.883799452722062,"GB2-07":28.062758255994936,"GB2-08":32.07888937449818},"per_game_match_totals_all":{"GB2-01":{"draws":179,"losses":565,"wins":288},"GB2-02":{"draws":1160,"losses":261,"wins":19},"GB2-03":{"draws":359,"losses":773,"wins":350},"GB2-04":{"draws":653,"losses":279,"wins":64},"GB2-05":{"draws":0,"losses":1134,"wins":456},"GB2-06":{"draws":9,"losses":790,"wins":205},"GB2-07":{"draws":0,"losses":1182,"wins":408},"GB2-08":{"draws":610,"losses":831,"wins":173}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":381,"losses":87,"wins":12},"GB2-03":{"draws":120,"losses":225,"wins":149},"GB2-04":{"draws":325,"losses":131,"wins":42},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":3,"losses":406,"wins":93},"GB2-07":{"draws":0,"losses":363,"wins":167},"GB2-08":{"draws":118,"losses":317,"wins":103}},"medium":{"GB2-01":{"draws":94,"losses":293,"wins":129},"GB2-02":{"draws":382,"losses":93,"wins":5},"GB2-03":{"draws":122,"losses":274,"wins":98},"GB2-04":{"draws":328,"losses":148,"wins":22},"GB2-05":{"draws":0,"losses":452,"wins":78},"GB2-06":{"draws":6,"losses":384,"wins":112},"GB2-07":{"draws":0,"losses":429,"wins":101},"GB2-08":{"draws":258,"losses":242,"wins":38}},"none":{"GB2-01":{"draws":85,"losses":272,"wins":159},"GB2-02":{"draws":397,"losses":81,"wins":2},"GB2-03":{"draws":117,"losses":274,"wins":103},"GB2-05":{"draws":0,"losses":452,"wins":78},"GB2-07":{"draws":0,"losses":390,"wins":140},"GB2-08":{"draws":234,"losses":272,"wins":32}}},"per_game_raw_elo_all":{"GB2-02":1419.842227431086,"GB2-03":1334.4662487437752,"GB2-05":1131.6008527445847,"GB2-07":1162.5133739034372,"GB2-08":1202.0098942668699},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1424.4804152842908,"GB2-03":1394.1451755780754,"GB2-04":1418.6496703492,"GB2-05":1542.6934198919057,"GB2-06":994.1812595705389,"GB2-07":1247.1790929370632,"GB2-08":1207.6728892636213},"medium":{"GB2-01":1333.645213527798,"GB2-02":1413.8351260724141,"GB2-03":1302.247423518998,"GB2-04":1388.9842988380162,"GB2-05":926.0545691709242,"GB2-06":1065.0868311406512,"GB2-07":1063.0368400058499,"GB2-08":1218.0861949364878},"none":{"GB2-01":1383.265485482544,"GB2-02":1421.2111409365534,"GB2-03":1307.0061471342517,"GB2-05":926.0545691709241,"GB2-07":1177.3241887673983,"GB2-08":1180.2705986005008}},"per_game_tracks":{"highest":{"GB2-02":43.87001850459841,"GB2-03":46.18655465207163,"GB2-04":42.71216342821136,"GB2-05":58.31362665998524,"GB2-06":22.071280542068205,"GB2-07":34.07491479381986,"GB2-08":32.606881766000896},"medium":{"GB2-01":35.977409867858384,"GB2-02":42.496039108275625,"GB2-03":35.685789593942026,"GB2-04":38.928699630032995,"GB2-05":15.668885849090477,"GB2-06":26.614439829062704,"GB2-07":21.2371604569137,"GB2-08":33.595073325067546},"none":{"GB2-01":41.02088794892465,"GB2-02":43.44746737727414,"GB2-03":36.217677180997555,"GB2-05":15.668885849090476,"GB2-07":28.876199517251244,"GB2-08":30.034713032426097}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:35:23Z","reasoning":{"highest":34.97943004334445,"medium":31.27543720753043,"none":24.408228863245522},"reasoning_agg":{"highest":{"max":58.31362665998524,"mean":34.97943004334445,"min":0.0},"medium":{"max":42.496039108275625,"mean":31.27543720753043,"min":15.668885849090477},"none":{"max":43.44746737727414,"mean":24.408228863245522,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.571201180098928},"working_program_strength":{"all":34.5987446122108,"highest":39.976491478107945,"medium":31.27543720753043,"none":32.54430515099403}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:9c0592db82206e94","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":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"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":0.5047206500000001}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.2116408499999998},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":27.542924799939424,"highest":24.022845402436776,"medium":28.090345277590522,"none":30.51558371979097},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":56,"finish_reasons":["error","length","stop"],"indexed_attempts":56,"output_token_observations":56,"total_output_tokens":194565},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":7,"failed_game_aliases":["GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":2,"model_code_failure_rate":0.2857142857142857,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.7142857142857143},"baseline":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222},"intensive":{"admitted_plugins":9,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-03","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.35714285714285715,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.5}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":46.01161246264795,"score":41.74247073763353},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.9607544678317,"score":27.307169645221133},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":30.759266119518013,"score":10.253088706506004},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.63961435353267,"score":27.759742902355114},"GB2-05":{"attempts":3,"playable":46.09978085644994,"score":46.09978085644994},"GB2-06":{"attempts":3,"playable":35.45036437787409,"score":35.45036437787409},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":7.448148734053278,"score":4.139676070859166},"GB2-08":{"attempts":4,"playable":33.594250295569545,"score":33.594250295569545}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":25.614850350086492,"score":12.807425175043246},"GB2-02":{"attempts":2,"playable":40.90731988116712,"score":40.90731988116712},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":40.97544712922916,"score":40.97544712922916},"GB2-05":{"attempts":2,"playable":30.28364023199318,"score":30.28364023199318},"GB2-06":{"attempts":1,"playable":33.71265982325492,"score":33.71265982325492},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":33.49627097880659,"score":33.49627097880659}},"medium":{"GB2-01":{"attempts":1,"playable":57.183407516855624,"score":57.183407516855624},"GB2-02":{"attempts":1,"playable":41.01418905449628,"score":41.01418905449628},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":56.677200843851594,"score":56.677200843851594},"GB2-07":{"attempts":1,"playable":9.941758957048439,"score":9.941758957048439},"GB2-08":{"attempts":1,"playable":31.81586057088171,"score":31.81586057088171}},"none":{"GB2-01":{"attempts":1,"playable":55.23657952100173,"score":55.23657952100173},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":30.759266119518013,"score":30.759266119518013},"GB2-04":{"attempts":1,"playable":42.30378157783618,"score":42.30378157783618},"GB2-05":{"attempts":1,"playable":61.9159214809067,"score":61.9159214809067},"GB2-06":{"attempts":1,"playable":15.961232466515742,"score":15.961232466515742},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":4.954538511058117,"score":2.4772692555290585},"GB2-08":{"attempts":1,"playable":35.47061933702033,"score":35.47061933702033}}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-10-24T17:47:50Z","match_totals_all":{"draws":3249,"losses":5539,"wins":1998},"match_totals_tracks":{"highest":{"draws":1692,"losses":2280,"wins":640},"medium":{"draws":704,"losses":1274,"wins":588},"none":{"draws":853,"losses":1985,"wins":770}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","official_rank_by_reasoning":{"highest":61,"none":60},"overall":{"max":61.9159214809067,"mean":27.542924799939424,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":60,"overall_ranking_status":"partial","per_game":{"GB2-01":25.614850350086492,"GB2-02":40.90731988116712,"GB2-04":40.97544712922916,"GB2-05":30.28364023199318,"GB2-06":33.71265982325492,"GB2-08":33.49627097880659},"per_game_all":{"GB2-01":46.01161246264795,"GB2-06":35.45036437787409,"GB2-08":33.594250295569545},"per_game_match_totals_all":{"GB2-01":{"draws":286,"losses":723,"wins":539},"GB2-02":{"draws":1102,"losses":323,"wins":15},"GB2-03":{"draws":182,"losses":267,"wins":45},"GB2-04":{"draws":691,"losses":252,"wins":53},"GB2-05":{"draws":0,"losses":963,"wins":627},"GB2-06":{"draws":41,"losses":1006,"wins":459},"GB2-07":{"draws":0,"losses":994,"wins":66},"GB2-08":{"draws":947,"losses":1011,"wins":194}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":106,"losses":339,"wins":71},"GB2-02":{"draws":726,"losses":220,"wins":14},"GB2-04":{"draws":350,"losses":127,"wins":21},"GB2-05":{"draws":0,"losses":752,"wins":308},"GB2-06":{"draws":26,"losses":341,"wins":135},"GB2-08":{"draws":484,"losses":501,"wins":91}},"medium":{"GB2-01":{"draws":102,"losses":181,"wins":233},"GB2-02":{"draws":376,"losses":103,"wins":1},"GB2-06":{"draws":10,"losses":233,"wins":259},"GB2-07":{"draws":0,"losses":485,"wins":45},"GB2-08":{"draws":216,"losses":272,"wins":50}},"none":{"GB2-01":{"draws":78,"losses":203,"wins":235},"GB2-03":{"draws":182,"losses":267,"wins":45},"GB2-04":{"draws":341,"losses":125,"wins":32},"GB2-05":{"draws":0,"losses":211,"wins":319},"GB2-06":{"draws":5,"losses":432,"wins":65},"GB2-07":{"draws":0,"losses":509,"wins":21},"GB2-08":{"draws":247,"losses":238,"wins":53}}},"per_game_raw_elo_all":{"GB2-01":1426.5835989692393,"GB2-06":1196.2000244825156,"GB2-08":1218.030162057259},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1222.41319247331,"GB2-02":1401.4215370094985,"GB2-04":1405.1043195835468,"GB2-05":1169.1370853715007,"GB2-06":1172.4752734826227,"GB2-08":1217.046283452422},"medium":{"GB2-01":1538.1328095367096,"GB2-02":1402.2942002354519,"GB2-06":1525.209195103322,"GB2-07":832.0525148083517,"GB2-08":1199.2979203475327},"none":{"GB2-01":1519.2047948976983,"GB2-03":1256.9848584875642,"GB2-04":1415.473315122039,"GB2-05":1591.0589262110714,"GB2-06":890.9156048616018,"GB2-07":657.8852226033678,"GB2-08":1237.7462823718224}},"per_game_tracks":{"highest":{"GB2-01":25.614850350086492,"GB2-02":40.90731988116712,"GB2-04":40.97544712922916,"GB2-05":30.28364023199318,"GB2-06":33.71265982325492,"GB2-08":33.49627097880659},"medium":{"GB2-01":57.183407516855624,"GB2-02":41.01418905449628,"GB2-06":56.677200843851594,"GB2-07":9.941758957048439,"GB2-08":31.81586057088171},"none":{"GB2-01":55.23657952100173,"GB2-03":30.759266119518013,"GB2-04":42.30378157783618,"GB2-05":61.9159214809067,"GB2-06":15.961232466515742,"GB2-07":4.954538511058117,"GB2-08":35.47061933702033}},"program_outcomes":{"all":{"counted_attempts":30,"failed":9,"infra_excluded":4,"success_rate":0.7,"too_slow":0,"worked_after_repair":14,"worked_first_time":7,"working":21},"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":7,"failed":2,"infra_excluded":2,"success_rate":0.7142857142857143,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"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":24.022845402436776,"medium":28.090345277590522,"none":30.51558371979097},"reasoning_agg":{"highest":{"max":40.97544712922916,"mean":24.022845402436776,"min":0.0},"medium":{"max":57.183407516855624,"mean":28.090345277590522,"min":0.0},"none":{"max":61.9159214809067,"mean":30.51558371979097,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.4927383173541955},"working_program_strength":{"all":36.24012107275576,"highest":34.16503139908958,"medium":39.32648338862673,"none":35.228848430550975}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:ccc5a8a54a03baa4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":60},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.261503015,"mean":0.224623670625,"median":0.22750746833333335,"min":0.17735088333333335,"recorded_attempt_count":60,"run_count":22,"total":4.90638056},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164000000002},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.5884539500000001},"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":4.90638056}},"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.261503015,"mean":0.09751241583333332,"median":0.042993304999999996,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":112,"run_count":46,"total":5.7439161499999996},"codegen_latency_ms":{"attempt_count":112,"max_ms":712912,"mean_ms":234938.63043478262,"min_ms":16322,"run_count":46},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":60,"max_ms":712912,"mean_ms":442344.0909090909,"min_ms":125659,"run_count":22},"medium":{"attempt_count":13,"max_ms":52676,"mean_ms":32623.625,"min_ms":16322,"run_count":8},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":112,"output_max":80000,"output_mean":26608.978260869564,"output_min":1372,"run_count":46},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":60,"output_max":80000,"output_mean":50498.318181818184,"output_min":12059,"run_count":22},"medium":{"attempt_count":13,"output_max":9117,"output_mean":4863.875,"output_min":2632,"run_count":8},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":26.714516046639478,"highest":33.318196038795726,"medium":19.210425064147287,"none":27.61492703697543},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":20,"effective_max_output_tokens":[262144],"finish_reason_observations":112,"finish_reasons":["length","stop"],"indexed_attempts":112,"output_token_observations":112,"provider_post_attempt_observations":20,"provider_post_attempts":23,"reasoning_token_observations":85,"reconciliation_get_attempt_observations":20,"reconciliation_get_attempts":33,"requested_max_output_token_observations":20,"requested_max_output_tokens":[262144],"total_output_tokens":1224013,"total_reasoning_output_tokens":793927,"total_visible_output_tokens":126602,"visible_token_observations":82},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1,"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125},"intensive":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"admitted":2,"infra_failures_excluded":1},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":2,"infra_failures_excluded":1},"GB2-08":{"admitted":2,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":25.9804558853878,"score":25.9804558853878},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":42.94488707015661,"score":21.300653627287577},"GB2-03":{"attempts":5,"playable":44.745934102194475,"score":44.745934102194475},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":42.20033425038937,"score":34.86062085156103},"GB2-05":{"attempts":5,"playable":19.256188521989657,"score":19.256188521989657},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":35.1553346813512,"score":21.590560605307687},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":23.745524460672897,"score":19.811335781873535},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":57.37238807148722,"score":26.170378997514092}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":40.090199639793596,"score":40.090199639793596},"GB2-02":{"attempts":2,"playable":41.91414762341225,"score":41.91414762341225},"GB2-03":{"attempts":2,"playable":48.30281971478934,"score":48.30281971478934},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.03828039297004,"score":22.01914019648502},"GB2-05":{"attempts":2,"playable":16.148480374319213,"score":16.148480374319213},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":54.028259201057125,"score":27.014129600528562},"GB2-07":{"attempts":2,"playable":28.779153318927733,"score":28.779153318927733},"GB2-08":{"attempts":2,"playable":42.277497842110115,"score":42.277497842110115}},"medium":{"GB2-01":{"attempts":1,"playable":17.86739349889354,"score":17.86739349889354},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":37.06150597304973,"score":37.06150597304973},"GB2-04":{"attempts":1,"playable":41.69091002994343,"score":41.69091002994343},"GB2-05":{"attempts":1,"playable":14.133943433204301,"score":14.133943433204301},"GB2-06":{"attempts":1,"playable":24.077359587792532,"score":24.077359587792532},"GB2-07":{"attempts":1,"playable":18.85228799029478,"score":18.85228799029478},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":2,"playable":19.983774517476277,"score":19.983774517476277},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.975626516900974,"score":21.987813258450487},"GB2-03":{"attempts":2,"playable":48.87347661874438,"score":48.87347661874438},"GB2-04":{"attempts":2,"playable":40.87181232825463,"score":40.87181232825463},"GB2-05":{"attempts":2,"playable":27.486141758445452,"score":27.486141758445452},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":27.36038525520393,"score":13.680192627601965},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":23.605132072796174,"score":11.802566036398087},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":72.46727830086432,"score":36.23363915043216}}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-10-24T19:04:18Z","match_totals_all":{"draws":4219,"losses":8889,"wins":3264},"match_totals_tracks":{"highest":{"draws":1931,"losses":3666,"wins":1579},"medium":{"draws":692,"losses":2012,"wins":367},"none":{"draws":1596,"losses":3211,"wins":1318}},"model_slug":"thinkingmachines-inkling","official_rank_by_reasoning":{"highest":57,"medium":77,"none":71},"overall":{"max":48.87347661874438,"mean":26.714516046639478,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":61,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.090199639793596,"GB2-02":41.91414762341225,"GB2-03":48.30281971478934,"GB2-04":44.03828039297004,"GB2-05":16.148480374319213,"GB2-06":54.028259201057125,"GB2-07":28.779153318927733,"GB2-08":42.277497842110115},"per_game_all":{"GB2-01":25.9804558853878,"GB2-03":44.745934102194475,"GB2-04":42.20033425038937,"GB2-05":19.256188521989657,"GB2-06":35.1553346813512,"GB2-07":23.745524460672897},"per_game_match_totals_all":{"GB2-01":{"draws":629,"losses":1594,"wins":357},"GB2-02":{"draws":1149,"losses":276,"wins":15},"GB2-03":{"draws":773,"losses":1034,"wins":664},"GB2-04":{"draws":1263,"losses":559,"wins":170},"GB2-05":{"draws":0,"losses":2140,"wins":510},"GB2-06":{"draws":27,"losses":1020,"wins":458},"GB2-07":{"draws":0,"losses":1639,"wins":481},"GB2-08":{"draws":378,"losses":627,"wins":609}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":282,"losses":497,"wins":253},"GB2-02":{"draws":753,"losses":197,"wins":10},"GB2-03":{"draws":213,"losses":443,"wins":332},"GB2-04":{"draws":316,"losses":129,"wins":53},"GB2-05":{"draws":0,"losses":899,"wins":161},"GB2-06":{"draws":10,"losses":247,"wins":245},"GB2-07":{"draws":0,"losses":781,"wins":279},"GB2-08":{"draws":357,"losses":473,"wins":246}},"medium":{"GB2-01":{"draws":61,"losses":400,"wins":55},"GB2-03":{"draws":299,"losses":180,"wins":16},"GB2-04":{"draws":329,"losses":134,"wins":35},"GB2-05":{"draws":0,"losses":460,"wins":70},"GB2-06":{"draws":3,"losses":397,"wins":102},"GB2-07":{"draws":0,"losses":441,"wins":89}},"none":{"GB2-01":{"draws":286,"losses":697,"wins":49},"GB2-02":{"draws":396,"losses":79,"wins":5},"GB2-03":{"draws":261,"losses":411,"wins":316},"GB2-04":{"draws":618,"losses":296,"wins":82},"GB2-05":{"draws":0,"losses":781,"wins":279},"GB2-06":{"draws":14,"losses":376,"wins":111},"GB2-07":{"draws":0,"losses":417,"wins":113},"GB2-08":{"draws":21,"losses":154,"wins":363}}},"per_game_raw_elo_all":{"GB2-01":1214.6539603932545,"GB2-03":1382.6660111050294,"GB2-04":1414.6211094827406,"GB2-05":987.0500311619153,"GB2-06":1195.0418616077307,"GB2-07":1099.7324260115377},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1371.4949882548399,"GB2-02":1409.3118062903693,"GB2-03":1412.5838255066287,"GB2-04":1428.9349473815187,"GB2-05":935.8126290190567,"GB2-06":1482.7721980810506,"GB2-07":1175.9649111112287,"GB2-08":1317.7135631852507},"medium":{"GB2-01":1121.9902627334736,"GB2-03":1314.5174170448188,"GB2-04":1410.6968520050061,"GB2-05":893.409929601957,"GB2-06":1025.8591190537509,"GB2-07":1022.7229246814325},"none":{"GB2-01":1150.4766301914503,"GB2-02":1425.2969646322442,"GB2-03":1420.8967907636404,"GB2-04":1404.231529061697,"GB2-05":1131.9275348647325,"GB2-06":1076.4942676883907,"GB2-07":1100.5094422419518,"GB2-08":1724.1466295002108}},"per_game_tracks":{"highest":{"GB2-01":40.090199639793596,"GB2-02":41.91414762341225,"GB2-03":48.30281971478934,"GB2-04":44.03828039297004,"GB2-05":16.148480374319213,"GB2-06":54.028259201057125,"GB2-07":28.779153318927733,"GB2-08":42.277497842110115},"medium":{"GB2-01":17.86739349889354,"GB2-03":37.06150597304973,"GB2-04":41.69091002994343,"GB2-05":14.133943433204301,"GB2-06":24.077359587792532,"GB2-07":18.85228799029478},"none":{"GB2-01":19.983774517476277,"GB2-02":43.975626516900974,"GB2-03":48.87347661874438,"GB2-04":40.87181232825463,"GB2-05":27.486141758445452,"GB2-06":27.36038525520393,"GB2-07":23.605132072796174,"GB2-08":72.46727830086432}},"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":0,"rank_movement_baseline_at":"2026-10-22T10:42:34Z","reasoning":{"highest":33.318196038795726,"medium":19.210425064147287,"none":27.61492703697543},"reasoning_agg":{"highest":{"max":48.30281971478934,"mean":33.318196038795726,"min":16.148480374319213},"medium":{"max":41.69091002994343,"mean":19.210425064147287,"min":0.0},"none":{"max":48.87347661874438,"mean":27.61492703697543,"min":11.802566036398087}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":14.107770974648439},"working_program_strength":{"all":34.379736090012635,"highest":39.44735476342242,"medium":25.613900085529718,"none":38.077953421085766}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:eb076fe7c5397a32","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":0.1134224}},"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":0.13713908000000002},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1134224},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005}},"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":24.179888437287335,"highest":15.53477421363608,"medium":26.429221069834213,"none":30.575670028391713},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[230400],"finish_reason_observations":46,"finish_reasons":["stop"],"indexed_attempts":46,"output_token_observations":46,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[230400],"total_output_tokens":577622,"total_visible_output_tokens":183088,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-05","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":17.700236341110152,"score":17.700236341110152},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":43.55312295903319,"score":14.517707653011064},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":36.10930769050144,"score":24.072871793667627},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.15719828862322,"score":13.385732762874406},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":45.008857382090035,"score":30.005904921393356},"GB2-06":{"attempts":3,"playable":42.54505440853109,"score":42.54505440853109},"GB2-07":{"attempts":3,"playable":35.09140994013867,"score":35.09140994013867},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":24.18028451635849,"score":16.120189677572327}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":9.744915935712314,"score":9.744915935712314},"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":39.336927052825246,"score":39.336927052825246},"GB2-06":{"attempts":1,"playable":33.07907327861639,"score":33.07907327861639},"GB2-07":{"attempts":1,"playable":24.9790509984145,"score":24.9790509984145},"GB2-08":{"attempts":1,"playable":17.13822644352018,"score":17.13822644352018}},"medium":{"GB2-01":{"attempts":1,"playable":10.356474095985108,"score":10.356474095985108},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":34.83329259854874,"score":34.83329259854874},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":50.680787711354824,"score":50.680787711354824},"GB2-06":{"attempts":1,"playable":45.32359186726892,"score":45.32359186726892},"GB2-07":{"attempts":1,"playable":39.01727969631933,"score":39.01727969631933},"GB2-08":{"attempts":1,"playable":31.2223425891968,"score":31.2223425891968}},"none":{"GB2-01":{"attempts":1,"playable":32.99931899163304,"score":32.99931899163304},"GB2-02":{"attempts":1,"playable":43.55312295903319,"score":43.55312295903319},"GB2-03":{"attempts":1,"playable":37.38532278245414,"score":37.38532278245414},"GB2-04":{"attempts":1,"playable":40.15719828862322,"score":40.15719828862322},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":49.232498079707945,"score":49.232498079707945},"GB2-07":{"attempts":1,"playable":41.277899125682175,"score":41.277899125682175},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T16:58:20Z","match_totals_all":{"draws":1620,"losses":5173,"wins":1953},"match_totals_tracks":{"highest":{"draws":155,"losses":1943,"wins":518},"medium":{"draws":489,"losses":1849,"wins":772},"none":{"draws":976,"losses":1381,"wins":663}},"model_slug":"stepfun-step-3-7-flash","official_rank_by_reasoning":{"highest":64,"medium":71,"none":59},"overall":{"max":50.680787711354824,"mean":24.179888437287335,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":62,"overall_ranking_status":"ranked","per_game":{"GB2-01":9.744915935712314,"GB2-05":39.336927052825246,"GB2-06":33.07907327861639,"GB2-07":24.9790509984145,"GB2-08":17.13822644352018},"per_game_all":{"GB2-01":17.700236341110152,"GB2-06":42.54505440853109,"GB2-07":35.09140994013867},"per_game_match_totals_all":{"GB2-01":{"draws":192,"losses":1197,"wins":159},"GB2-02":{"draws":382,"losses":88,"wins":10},"GB2-03":{"draws":286,"losses":523,"wins":179},"GB2-04":{"draws":320,"losses":146,"wins":32},"GB2-05":{"draws":0,"losses":599,"wins":461},"GB2-06":{"draws":52,"losses":905,"wins":549},"GB2-07":{"draws":0,"losses":1072,"wins":518},"GB2-08":{"draws":388,"losses":643,"wins":45}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":27,"losses":457,"wins":32},"GB2-05":{"draws":0,"losses":329,"wins":201},"GB2-06":{"draws":10,"losses":352,"wins":140},"GB2-07":{"draws":0,"losses":410,"wins":120},"GB2-08":{"draws":118,"losses":395,"wins":25}},"medium":{"GB2-01":{"draws":69,"losses":433,"wins":14},"GB2-03":{"draws":138,"losses":270,"wins":86},"GB2-05":{"draws":0,"losses":270,"wins":260},"GB2-06":{"draws":12,"losses":291,"wins":199},"GB2-07":{"draws":0,"losses":337,"wins":193},"GB2-08":{"draws":270,"losses":248,"wins":20}},"none":{"GB2-01":{"draws":96,"losses":307,"wins":113},"GB2-02":{"draws":382,"losses":88,"wins":10},"GB2-03":{"draws":148,"losses":253,"wins":93},"GB2-04":{"draws":320,"losses":146,"wins":32},"GB2-06":{"draws":30,"losses":262,"wins":210},"GB2-07":{"draws":0,"losses":325,"wins":205}}},"per_game_raw_elo_all":{"GB2-01":1089.8678290840783,"GB2-06":1306.1372656230049,"GB2-07":1256.8576816045095},"per_game_raw_elo_tracks":{"highest":{"GB2-01":976.3074281637312,"GB2-05":1302.9041395141408,"GB2-06":1162.9504289674178,"GB2-07":1121.3030791230212,"GB2-08":1025.2529760085818},"medium":{"GB2-01":989.9963178964458,"GB2-03":1294.5769218063936,"GB2-05":1445.8153845899706,"GB2-06":1347.7388728803694,"GB2-07":1310.4531721616627,"GB2-08":1192.9861865166235},"none":{"GB2-01":1303.2997411920578,"GB2-02":1422.0289366733252,"GB2-03":1317.388382660603,"GB2-04":1398.683320004907,"GB2-06":1407.7224950212271,"GB2-07":1338.8167935288445}},"per_game_tracks":{"highest":{"GB2-01":9.744915935712314,"GB2-05":39.336927052825246,"GB2-06":33.07907327861639,"GB2-07":24.9790509984145,"GB2-08":17.13822644352018},"medium":{"GB2-01":10.356474095985108,"GB2-03":34.83329259854874,"GB2-05":50.680787711354824,"GB2-06":45.32359186726892,"GB2-07":39.01727969631933,"GB2-08":31.2223425891968},"none":{"GB2-01":32.99931899163304,"GB2-02":43.55312295903319,"GB2-03":37.38532278245414,"GB2-04":40.15719828862322,"GB2-06":49.232498079707945,"GB2-07":41.277899125682175}},"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":0,"rank_movement_baseline_at":"2026-10-22T09:45:32Z","reasoning":{"highest":15.53477421363608,"medium":26.429221069834213,"none":30.575670028391713},"reasoning_agg":{"highest":{"max":39.336927052825246,"mean":15.53477421363608,"min":0.0},"medium":{"max":50.680787711354824,"mean":26.429221069834213,"min":0.0},"none":{"max":49.232498079707945,"mean":30.575670028391713,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":15.040895814755633},"working_program_strength":{"all":33.620720068706326,"highest":24.855638741817728,"medium":35.23896142644562,"none":40.76756003785562}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:734104767af6fe82","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":0.01057822},"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":0.01012224},"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":0.00761251},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.01057822}},"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":0.028312969999999993},"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":21.924754461026634,"highest":21.15324044693237,"medium":20.389149794901787,"none":24.23187314124574},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"provider_post_attempt_observations":37,"provider_post_attempts":37,"reasoning_token_observations":37,"reconciliation_get_attempt_observations":37,"reconciliation_get_attempts":176,"total_output_tokens":116503,"total_reasoning_output_tokens":61584,"total_visible_output_tokens":54919,"visible_token_observations":37},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-2.5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":27.416332290501842,"score":9.13877743016728},"GB2-02":{"attempts":3,"playable":42.60172648812952,"score":42.60172648812952},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":46.18655465207163,"score":15.395518217357209},"GB2-04":{"attempts":3,"playable":41.211934813522625,"score":41.211934813522625},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":28.271190186459485,"score":18.847460124306323},"GB2-06":{"attempts":3,"playable":18.569288886589675,"score":18.569288886589675},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.189985663034076,"score":8.126657108689384},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.26000892917654,"score":21.506672619451027}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.416332290501842,"score":27.416332290501842},"GB2-02":{"attempts":1,"playable":42.390266741073305,"score":42.390266741073305},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.031125192970194,"score":39.031125192970194},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":15.732724087743625,"score":15.732724087743625},"GB2-07":{"attempts":1,"playable":14.026852574658097,"score":14.026852574658097},"GB2-08":{"attempts":1,"playable":30.628622688511875,"score":30.628622688511875}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.13042986233988,"score":43.13042986233988},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.56639885462764,"score":40.56639885462764},"GB2-05":{"attempts":1,"playable":16.819909119547248,"score":16.819909119547248},"GB2-06":{"attempts":1,"playable":18.351946601448255,"score":18.351946601448255},"GB2-07":{"attempts":1,"playable":10.353118751410053,"score":10.353118751410053},"GB2-08":{"attempts":1,"playable":33.89139516984121,"score":33.89139516984121}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.28448286097538,"score":42.28448286097538},"GB2-03":{"attempts":1,"playable":46.18655465207163,"score":46.18655465207163},"GB2-04":{"attempts":1,"playable":44.03828039297004,"score":44.03828039297004},"GB2-05":{"attempts":1,"playable":39.72247125337172,"score":39.72247125337172},"GB2-06":{"attempts":1,"playable":21.623195970577143,"score":21.623195970577143},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"inception/mercury-2.5-preview","is_recent_addition":false,"last_measured_at":"2026-10-24T19:02:08Z","match_totals_all":{"draws":2969,"losses":4682,"wins":995},"match_totals_tracks":{"highest":{"draws":1057,"losses":1737,"wins":270},"medium":{"draws":1031,"losses":1792,"wins":255},"none":{"draws":881,"losses":1153,"wins":470}},"model_slug":"inception-mercury-2-5-preview","official_rank_by_reasoning":{"highest":62,"medium":75,"none":77},"overall":{"max":46.18655465207163,"mean":21.924754461026634,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":63,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.416332290501842,"GB2-02":42.390266741073305,"GB2-04":39.031125192970194,"GB2-06":15.732724087743625,"GB2-07":14.026852574658097,"GB2-08":30.628622688511875},"per_game_all":{"GB2-02":42.60172648812952,"GB2-04":41.211934813522625,"GB2-06":18.569288886589675},"per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":324,"wins":74},"GB2-02":{"draws":1173,"losses":264,"wins":3},"GB2-03":{"draws":116,"losses":227,"wins":151},"GB2-04":{"draws":1057,"losses":374,"wins":63},"GB2-05":{"draws":0,"losses":773,"wins":287},"GB2-06":{"draws":10,"losses":1264,"wins":232},"GB2-07":{"draws":0,"losses":948,"wins":112},"GB2-08":{"draws":495,"losses":508,"wins":73}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":118,"losses":324,"wins":74},"GB2-02":{"draws":387,"losses":91,"wins":2},"GB2-04":{"draws":349,"losses":137,"wins":12},"GB2-06":{"draws":3,"losses":434,"wins":65},"GB2-07":{"draws":0,"losses":465,"wins":65},"GB2-08":{"draws":200,"losses":286,"wins":52}},"medium":{"GB2-02":{"draws":396,"losses":83,"wins":1},"GB2-04":{"draws":336,"losses":136,"wins":26},"GB2-05":{"draws":0,"losses":446,"wins":84},"GB2-06":{"draws":4,"losses":422,"wins":76},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":295,"losses":222,"wins":21}},"none":{"GB2-02":{"draws":390,"losses":90,"wins":0},"GB2-03":{"draws":116,"losses":227,"wins":151},"GB2-04":{"draws":372,"losses":101,"wins":25},"GB2-05":{"draws":0,"losses":327,"wins":203},"GB2-06":{"draws":3,"losses":408,"wins":91}}},"per_game_raw_elo_all":{"GB2-02":1414.653727016402,"GB2-04":1406.876285629481,"GB2-06":935.5643819471644},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1243.1024157071952,"GB2-02":1413.0136610252475,"GB2-04":1389.7959263985558,"GB2-06":886.7467145144922,"GB2-07":929.8812449548834,"GB2-08":1186.644831226881},"medium":{"GB2-02":1418.7557351959765,"GB2-04":1401.8979831083686,"GB2-05":949.4011314234622,"GB2-06":932.9469318159873,"GB2-07":843.0918174390963,"GB2-08":1221.200002227521},"none":{"GB2-02":1412.191784827982,"GB2-03":1394.1451755780754,"GB2-04":1428.9349473815187,"GB2-05":1307.9249098777013,"GB2-06":986.9994995110138}},"per_game_tracks":{"highest":{"GB2-01":27.416332290501842,"GB2-02":42.390266741073305,"GB2-04":39.031125192970194,"GB2-06":15.732724087743625,"GB2-07":14.026852574658097,"GB2-08":30.628622688511875},"medium":{"GB2-02":43.13042986233988,"GB2-04":40.56639885462764,"GB2-05":16.819909119547248,"GB2-06":18.351946601448255,"GB2-07":10.353118751410053,"GB2-08":33.89139516984121},"none":{"GB2-02":42.28448286097538,"GB2-03":46.18655465207163,"GB2-04":44.03828039297004,"GB2-05":39.72247125337172,"GB2-06":21.623195970577143}},"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":0,"rank_movement_baseline_at":"2026-10-22T09:50:59Z","reasoning":{"highest":21.15324044693237,"medium":20.389149794901787,"none":24.23187314124574},"reasoning_agg":{"highest":{"max":42.390266741073305,"mean":21.15324044693237,"min":0.0},"medium":{"max":43.13042986233988,"mean":20.389149794901787,"min":0.0},"none":{"max":46.18655465207163,"mean":24.23187314124574,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":3.842723346343952},"working_program_strength":{"all":31.386950227257348,"highest":28.204320595909824,"medium":27.185533059869048,"none":38.77099702599318}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:1403a2cbf671e1ab","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":0.21994025},"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":0.04706874999999999}},"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":0.08108399999999999},"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":0.04706875},"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":16.297728324352807,"highest":17.48502669984836,"medium":20.248599965560867,"none":11.159558307649203},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":150003},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":23.296770828869416,"score":15.531180552579611},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.81328683343108,"score":14.271095611143693},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":44.14002826833128,"score":29.426685512220853},"GB2-05":{"attempts":3,"playable":11.247392636833304,"score":11.247392636833304},"GB2-06":{"attempts":3,"playable":22.169005576367653,"score":22.169005576367653},"GB2-07":{"attempts":3,"playable":14.188886098428327,"score":14.188886098428327},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":35.321370910873554,"score":23.547580607249035}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.52844110508048,"score":43.52844110508048},"GB2-05":{"attempts":1,"playable":10.677281053543194,"score":10.677281053543194},"GB2-06":{"attempts":1,"playable":18.578743304298715,"score":18.578743304298715},"GB2-07":{"attempts":1,"playable":33.50067481079693,"score":33.50067481079693},"GB2-08":{"attempts":1,"playable":33.595073325067546,"score":33.595073325067546}},"medium":{"GB2-01":{"attempts":1,"playable":33.794323334695044,"score":33.794323334695044},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":44.75161543158207,"score":44.75161543158207},"GB2-05":{"attempts":1,"playable":17.01174376362402,"score":17.01174376362402},"GB2-06":{"attempts":1,"playable":22.964993690888004,"score":22.964993690888004},"GB2-07":{"attempts":1,"playable":6.418455007018242,"score":6.418455007018242},"GB2-08":{"attempts":1,"playable":37.047668496679556,"score":37.047668496679556}},"none":{"GB2-01":{"attempts":1,"playable":12.799218323043787,"score":12.799218323043787},"GB2-02":{"attempts":1,"playable":42.81328683343108,"score":42.81328683343108},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":6.053153093332702,"score":6.053153093332702},"GB2-06":{"attempts":1,"playable":24.963279733916245,"score":24.963279733916245},"GB2-07":{"attempts":1,"playable":2.6475284774698085,"score":2.6475284774698085},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-24T18:55:15Z","match_totals_all":{"draws":1825,"losses":5508,"wins":937},"match_totals_tracks":{"highest":{"draws":625,"losses":1615,"wins":358},"medium":{"draws":725,"losses":1976,"wins":413},"none":{"draws":475,"losses":1917,"wins":166}},"model_slug":"google-gemini-3-1-flash-lite","official_rank_by_reasoning":{"highest":63,"medium":76,"none":84},"overall":{"max":44.75161543158207,"mean":16.297728324352807,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":64,"overall_ranking_status":"partial","per_game":{"GB2-04":43.52844110508048,"GB2-05":10.677281053543194,"GB2-06":18.578743304298715,"GB2-07":33.50067481079693,"GB2-08":33.595073325067546},"per_game_all":{"GB2-05":11.247392636833304,"GB2-06":22.169005576367653,"GB2-07":14.188886098428327},"per_game_match_totals_all":{"GB2-01":{"draws":331,"losses":641,"wins":60},"GB2-02":{"draws":379,"losses":93,"wins":8},"GB2-04":{"draws":680,"losses":233,"wins":83},"GB2-05":{"draws":0,"losses":1425,"wins":165},"GB2-06":{"draws":10,"losses":1216,"wins":280},"GB2-07":{"draws":0,"losses":1388,"wins":202},"GB2-08":{"draws":425,"losses":512,"wins":139}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":355,"losses":112,"wins":31},"GB2-05":{"draws":0,"losses":478,"wins":52},"GB2-06":{"draws":0,"losses":423,"wins":79},"GB2-07":{"draws":0,"losses":366,"wins":164},"GB2-08":{"draws":270,"losses":236,"wins":32}},"medium":{"GB2-01":{"draws":242,"losses":230,"wins":44},"GB2-04":{"draws":325,"losses":121,"wins":52},"GB2-05":{"draws":0,"losses":445,"wins":85},"GB2-06":{"draws":3,"losses":402,"wins":97},"GB2-07":{"draws":0,"losses":502,"wins":28},"GB2-08":{"draws":155,"losses":276,"wins":107}},"none":{"GB2-01":{"draws":89,"losses":411,"wins":16},"GB2-02":{"draws":379,"losses":93,"wins":8},"GB2-05":{"draws":0,"losses":502,"wins":28},"GB2-06":{"draws":7,"losses":391,"wins":104},"GB2-07":{"draws":0,"losses":520,"wins":10}}},"per_game_raw_elo_all":{"GB2-05":810.255847760834,"GB2-06":994.9442449766517,"GB2-07":826.150851428241},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1424.9853633226578,"GB2-05":811.3032987243216,"GB2-06":936.8053671768521,"GB2-07":1239.665149248049,"GB2-08":1218.0861949364878},"medium":{"GB2-01":1311.497366933092,"GB2-04":1434.4530888117813,"GB2-05":953.2086035181738,"GB2-06":1008.3824924338235,"GB2-07":719.6126806932724,"GB2-08":1254.226459415052},"none":{"GB2-01":1039.0709210584932,"GB2-02":1416.2971354225347,"GB2-05":666.2556410400061,"GB2-06":1039.6448753192794,"GB2-07":519.174724343402}},"per_game_tracks":{"highest":{"GB2-04":43.52844110508048,"GB2-05":10.677281053543194,"GB2-06":18.578743304298715,"GB2-07":33.50067481079693,"GB2-08":33.595073325067546},"medium":{"GB2-01":33.794323334695044,"GB2-04":44.75161543158207,"GB2-05":17.01174376362402,"GB2-06":22.964993690888004,"GB2-07":6.418455007018242,"GB2-08":37.047668496679556},"none":{"GB2-01":12.799218323043787,"GB2-02":42.81328683343108,"GB2-05":6.053153093332702,"GB2-06":24.963279733916245,"GB2-07":2.6475284774698085}},"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":17.48502669984836,"medium":20.248599965560867,"none":11.159558307649203},"reasoning_agg":{"highest":{"max":43.52844110508048,"mean":17.48502669984836,"min":0.0},"medium":{"max":44.75161543158207,"mean":20.248599965560867,"min":0.0},"none":{"max":42.81328683343108,"mean":11.159558307649203,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":9.089041657911665},"working_program_strength":{"all":24.276489766470196,"highest":27.976042719757373,"medium":26.99813328741449,"none":17.855293292238724}},{"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:08b83f586d8fd4ed","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":0.01215665},"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":8.17652354572111,"highest":13.807999868641833,"medium":5.650770911693044,"none":5.070799856828455},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":49,"effective_max_output_tokens":[131072],"finish_reason_observations":48,"finish_reasons":["stop"],"indexed_attempts":49,"output_token_observations":49,"provider_post_attempt_observations":49,"provider_post_attempts":51,"reasoning_token_observations":49,"reconciliation_get_attempt_observations":49,"requested_max_output_token_observations":49,"requested_max_output_tokens":[131072],"total_output_tokens":913760,"total_reasoning_output_tokens":808441,"total_visible_output_tokens":105319,"visible_token_observations":49},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":2,"evaluated_cells":7,"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.7142857142857143,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.14285714285714285},"baseline":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.875,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":19.281155354512265,"score":6.427051784837421},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.56639885462764,"score":13.522132951542547},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":46.0755859951699,"score":15.358528665056633},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.772634725484043,"score":17.181756483656027},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":33.117384530335706,"score":11.039128176778569},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":46.0755859951699,"score":46.0755859951699},"GB2-06":{"attempts":1,"playable":31.271028423629044,"score":31.271028423629044},"GB2-07":{"attempts":1,"playable":33.117384530335706,"score":33.117384530335706},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":19.281155354512265,"score":19.281155354512265},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":20.27424102733904,"score":20.27424102733904},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.56639885462764,"score":40.56639885462764},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"upstage/solar-mini4","is_recent_addition":false,"last_measured_at":"2026-10-24T16:19:36Z","match_totals_all":{"draws":437,"losses":1952,"wins":689},"match_totals_tracks":{"highest":{"draws":7,"losses":1024,"wins":531},"medium":{"draws":84,"losses":797,"wins":137},"none":{"draws":346,"losses":131,"wins":21}},"model_slug":"upstage-solar-mini4","overall":{"max":46.0755859951699,"mean":8.17652354572111,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":65,"overall_ranking_status":"partial","per_game":{"GB2-05":46.0755859951699,"GB2-06":31.271028423629044,"GB2-07":33.117384530335706},"per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":384,"wins":53},"GB2-04":{"draws":346,"losses":131,"wins":21},"GB2-05":{"draws":0,"losses":294,"wins":236},"GB2-06":{"draws":12,"losses":775,"wins":217},"GB2-07":{"draws":0,"losses":368,"wins":162}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":294,"wins":236},"GB2-06":{"draws":7,"losses":362,"wins":133},"GB2-07":{"draws":0,"losses":368,"wins":162}},"medium":{"GB2-01":{"draws":79,"losses":384,"wins":53},"GB2-06":{"draws":5,"losses":413,"wins":84}},"none":{"GB2-04":{"draws":346,"losses":131,"wins":21}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1388.554185839504,"GB2-06":1135.7380952246162,"GB2-07":1234.6260523517194},"medium":{"GB2-01":1142.1200692949292,"GB2-06":965.0899362075756},"none":{"GB2-04":1401.8979831083686}},"per_game_tracks":{"highest":{"GB2-05":46.0755859951699,"GB2-06":31.271028423629044,"GB2-07":33.117384530335706},"medium":{"GB2-01":19.281155354512265,"GB2-06":20.27424102733904},"none":{"GB2-04":40.56639885462764}},"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":13.807999868641835,"medium":5.650770911693044,"none":5.070799856828455},"reasoning_agg":{"highest":{"max":46.0755859951699,"mean":13.807999868641835,"min":0.0},"medium":{"max":20.27424102733904,"mean":5.650770911693044,"min":0.0},"none":{"max":40.56639885462764,"mean":5.070799856828455,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.737200011813378},"working_program_strength":{"all":32.388476676199396,"highest":36.82133298304489,"medium":19.777698190925655,"none":40.56639885462764}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:dd8d48484dfe30a5","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":0.018105180000000002},"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":0.06705538000000001}},"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":0.10770048000000002},"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":1.6177610402044105,"highest":0.0,"medium":4.853283120613232,"none":0.0},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":37,"effective_max_output_tokens":[117964],"finish_reason_observations":56,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":56,"provider_post_attempt_observations":56,"provider_post_attempts":56,"reasoning_token_observations":56,"reconciliation_get_attempt_observations":56,"reconciliation_get_attempts":88,"requested_max_output_token_observations":37,"requested_max_output_tokens":[117964],"total_output_tokens":331648,"total_reasoning_output_tokens":194609,"total_visible_output_tokens":137039,"visible_token_observations":56},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"ibm","provider_model":"ibm-granite/granite-4.2-8b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.875,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-02":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":38.82626496490585,"score":12.942088321635284},"GB2-05":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-06":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-07":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.82626496490585,"score":38.82626496490585},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"ibm-granite/granite-4.2-8b","is_recent_addition":false,"last_measured_at":"2026-10-24T14:40:36Z","match_totals_all":{"draws":317,"losses":154,"wins":27},"match_totals_tracks":{"medium":{"draws":317,"losses":154,"wins":27}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":38.82626496490585,"mean":1.6177610402044105,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","grouped_stability_incomplete"],"overall_official_rank":66,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-04":{"draws":317,"losses":154,"wins":27}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":317,"losses":154,"wins":27}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1388.17202162157}},"per_game_tracks":{"medium":{"GB2-04":38.82626496490585}},"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":4.853283120613232,"none":0.0},"reasoning_agg":{"highest":{"max":0.0,"mean":0.0,"min":0.0},"medium":{"max":38.82626496490585,"mean":4.853283120613232,"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":4.853283120613232},"working_program_strength":{"all":38.82626496490585,"medium":38.82626496490585}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10:597e25e7df4b3ed3","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":90.61242654284027,"none":90.61242654284027},"first_seen_at":null,"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":91.44388755261483,"score":91.44388755261483},"GB2-02":{"attempts":1,"playable":79.51471945910833,"score":79.51471945910833},"GB2-03":{"attempts":1,"playable":96.42711516699417,"score":96.42711516699417},"GB2-04":{"attempts":1,"playable":85.64833786482147,"score":85.64833786482147},"GB2-05":{"attempts":1,"playable":91.90020194921873,"score":91.90020194921873},"GB2-06":{"attempts":1,"playable":93.60935442733972,"score":93.60935442733972},"GB2-07":{"attempts":1,"playable":95.14793315420775,"score":95.14793315420775},"GB2-08":{"attempts":1,"playable":91.20786276841703,"score":91.20786276841703}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":91.44388755261483,"score":91.44388755261483},"GB2-02":{"attempts":1,"playable":79.51471945910833,"score":79.51471945910833},"GB2-03":{"attempts":1,"playable":96.42711516699417,"score":96.42711516699417},"GB2-04":{"attempts":1,"playable":85.64833786482147,"score":85.64833786482147},"GB2-05":{"attempts":1,"playable":91.90020194921873,"score":91.90020194921873},"GB2-06":{"attempts":1,"playable":93.60935442733972,"score":93.60935442733972},"GB2-07":{"attempts":1,"playable":95.14793315420775,"score":95.14793315420775},"GB2-08":{"attempts":1,"playable":91.20786276841703,"score":91.20786276841703}}},"id":"unbiased/pareto-26.10","is_recent_addition":false,"last_measured_at":"2026-10-24T16:27:19Z","match_totals_all":{"draws":263,"losses":270,"wins":3555},"match_totals_tracks":{"none":{"draws":263,"losses":270,"wins":3555}},"model_slug":"unbiased-pareto-26-10","official_rank_by_reasoning":{"none":1},"overall":{"max":96.42711516699417,"mean":90.61242654284027,"min":79.51471945910833},"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":466},"GB2-02":{"draws":182,"losses":13,"wins":285},"GB2-03":{"draws":2,"losses":17,"wins":475},"GB2-04":{"draws":62,"losses":45,"wins":391},"GB2-05":{"draws":0,"losses":44,"wins":486},"GB2-06":{"draws":17,"losses":27,"wins":458},"GB2-07":{"draws":0,"losses":22,"wins":508},"GB2-08":{"draws":0,"losses":52,"wins":486}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":0,"losses":50,"wins":466},"GB2-02":{"draws":182,"losses":13,"wins":285},"GB2-03":{"draws":2,"losses":17,"wins":475},"GB2-04":{"draws":62,"losses":45,"wins":391},"GB2-05":{"draws":0,"losses":44,"wins":486},"GB2-06":{"draws":17,"losses":27,"wins":458},"GB2-07":{"draws":0,"losses":22,"wins":508},"GB2-08":{"draws":0,"losses":52,"wins":486}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":2022.7221644382153,"GB2-02":1747.580886440394,"GB2-03":2301.178751810179,"GB2-04":1837.1838496043765,"GB2-05":2335.368092010557,"GB2-06":2293.925183041517,"GB2-07":2445.2579871475996,"GB2-08":2185.7519580026674}},"per_game_tracks":{"none":{"GB2-01":91.44388755261483,"GB2-02":79.51471945910833,"GB2-03":96.42711516699417,"GB2-04":85.64833786482147,"GB2-05":91.90020194921873,"GB2-06":93.60935442733972,"GB2-07":95.14793315420775,"GB2-08":91.20786276841703}},"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":90.61242654284027},"reasoning_agg":{"none":{"max":96.42711516699417,"mean":90.61242654284027,"min":79.51471945910833}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":90.61242654284027,"none":90.61242654284027}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:5bc5f373fda4e7ae","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.2454376}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998},"codegen_latency_ms":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8}},"codegen_output_tokens":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8}},"display_name":"Pareto 26.10 Preview","economics":{"all":89.68302090781248,"none":89.68302090781248},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[131072],"finish_reason_observations":9,"finish_reasons":["stop"],"indexed_attempts":9,"output_token_observations":9,"provider_post_attempt_observations":9,"provider_post_attempts":9,"reasoning_token_observations":9,"reconciliation_get_attempt_observations":9,"requested_max_output_token_observations":9,"requested_max_output_tokens":[131072],"total_output_tokens":57710,"total_visible_output_tokens":57710,"visible_token_observations":9},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":73.75922694814803,"score":73.75922694814803},"GB2-02":{"attempts":1,"playable":91.56205872585954,"score":91.56205872585954},"GB2-03":{"attempts":1,"playable":93.76798748209035,"score":93.76798748209035},"GB2-04":{"attempts":1,"playable":86.39858455820529,"score":86.39858455820529},"GB2-05":{"attempts":1,"playable":94.26077753004762,"score":94.26077753004762},"GB2-06":{"attempts":1,"playable":87.54230197502969,"score":87.54230197502969},"GB2-07":{"attempts":1,"playable":95.89866297570543,"score":95.89866297570543},"GB2-08":{"attempts":1,"playable":94.2745670674139,"score":94.2745670674139}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":73.75922694814803,"score":73.75922694814803},"GB2-02":{"attempts":1,"playable":91.56205872585954,"score":91.56205872585954},"GB2-03":{"attempts":1,"playable":93.76798748209035,"score":93.76798748209035},"GB2-04":{"attempts":1,"playable":86.39858455820529,"score":86.39858455820529},"GB2-05":{"attempts":1,"playable":94.26077753004762,"score":94.26077753004762},"GB2-06":{"attempts":1,"playable":87.54230197502969,"score":87.54230197502969},"GB2-07":{"attempts":1,"playable":95.89866297570543,"score":95.89866297570543},"GB2-08":{"attempts":1,"playable":94.2745670674139,"score":94.2745670674139}}},"id":"unbiased/pareto-26.10-preview","is_recent_addition":false,"last_measured_at":"2026-10-24T15:40:41Z","match_totals_all":{"draws":142,"losses":373,"wins":3573},"match_totals_tracks":{"none":{"draws":142,"losses":373,"wins":3573}},"model_slug":"unbiased-pareto-26-10-preview","official_rank_by_reasoning":{"none":2},"overall":{"max":95.89866297570543,"mean":89.68302090781248,"min":73.75922694814803},"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":16,"losses":138,"wins":362},"GB2-02":{"draws":38,"losses":23,"wins":419},"GB2-03":{"draws":5,"losses":31,"wins":458},"GB2-04":{"draws":44,"losses":50,"wins":404},"GB2-05":{"draws":0,"losses":30,"wins":500},"GB2-06":{"draws":39,"losses":50,"wins":413},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":33,"wins":505}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":16,"losses":138,"wins":362},"GB2-02":{"draws":38,"losses":23,"wins":419},"GB2-03":{"draws":5,"losses":31,"wins":458},"GB2-04":{"draws":44,"losses":50,"wins":404},"GB2-05":{"draws":0,"losses":30,"wins":500},"GB2-06":{"draws":39,"losses":50,"wins":413},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":33,"wins":505}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1715.7328710117636,"GB2-02":1970.403573127545,"GB2-03":2145.4742630394157,"GB2-04":1850.0765603403815,"GB2-05":2461.8660942974966,"GB2-06":2111.008343739167,"GB2-07":2495.831868214045,"GB2-08":2311.968880990643}},"per_game_tracks":{"none":{"GB2-01":73.75922694814803,"GB2-02":91.56205872585954,"GB2-03":93.76798748209035,"GB2-04":86.39858455820529,"GB2-05":94.26077753004762,"GB2-06":87.54230197502969,"GB2-07":95.89866297570543,"GB2-08":94.2745670674139}},"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":89.68302090781248},"reasoning_agg":{"none":{"max":95.89866297570543,"mean":89.68302090781248,"min":73.75922694814803}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":89.68302090781248,"none":89.68302090781248}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:ebb0e62acb9965d6","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":0.05751309}},"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":0.45532711500000006},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.032052512812499996,"median":0.0201057,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":19,"run_count":16,"total":0.512840205},"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":62.0624365326147,"medium":73.15875071771754,"none":50.966122347511856},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":19,"effective_max_output_tokens":[131072],"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"provider_post_attempt_observations":19,"provider_post_attempts":20,"reasoning_token_observations":19,"reconciliation_get_attempt_observations":19,"requested_max_output_token_observations":19,"requested_max_output_tokens":[131072],"total_output_tokens":513762,"total_reasoning_output_tokens":447944,"total_visible_output_tokens":65818,"visible_token_observations":19},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":46.803404509298716,"score":46.803404509298716},"GB2-02":{"attempts":2,"playable":60.48180184731841,"score":60.48180184731841},"GB2-03":{"attempts":2,"playable":65.47855358182966,"score":65.47855358182966},"GB2-04":{"attempts":2,"playable":50.42306027253833,"score":50.42306027253833},"GB2-05":{"attempts":2,"playable":65.34786040455442,"score":65.34786040455442},"GB2-06":{"attempts":2,"playable":56.58263924559819,"score":56.58263924559819},"GB2-07":{"attempts":2,"playable":66.55706685714472,"score":66.55706685714472},"GB2-08":{"attempts":2,"playable":84.82510554263519,"score":84.82510554263519}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":54.06684288668242,"score":54.06684288668242},"GB2-02":{"attempts":1,"playable":80.79717086084281,"score":80.79717086084281},"GB2-03":{"attempts":1,"playable":85.9113327606461,"score":85.9113327606461},"GB2-04":{"attempts":1,"playable":45.362630131234,"score":45.362630131234},"GB2-05":{"attempts":1,"playable":85.00458172061191,"score":85.00458172061191},"GB2-06":{"attempts":1,"playable":57.05371345737677,"score":57.05371345737677},"GB2-07":{"attempts":1,"playable":89.77523221591522,"score":89.77523221591522},"GB2-08":{"attempts":1,"playable":87.29850170843115,"score":87.29850170843115}},"none":{"GB2-01":{"attempts":1,"playable":39.539966131915016,"score":39.539966131915016},"GB2-02":{"attempts":1,"playable":40.166432833794005,"score":40.166432833794005},"GB2-03":{"attempts":1,"playable":45.045774403013226,"score":45.045774403013226},"GB2-04":{"attempts":1,"playable":55.48349041384266,"score":55.48349041384266},"GB2-05":{"attempts":1,"playable":45.691139088496946,"score":45.691139088496946},"GB2-06":{"attempts":1,"playable":56.1115650338196,"score":56.1115650338196},"GB2-07":{"attempts":1,"playable":43.338901498374206,"score":43.338901498374206},"GB2-08":{"attempts":1,"playable":82.35170937683921,"score":82.35170937683921}}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-24T19:04:26Z","match_totals_all":{"draws":1402,"losses":2548,"wins":4226},"match_totals_tracks":{"medium":{"draws":386,"losses":961,"wins":2741},"none":{"draws":1016,"losses":1587,"wins":1485}},"model_slug":"xiaomi-mimo-v2-6-pro","official_rank_by_reasoning":{"medium":9,"none":21},"overall":{"max":89.77523221591522,"mean":62.0624365326147,"min":39.539966131915016},"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":304,"losses":418,"wins":310},"GB2-02":{"draws":443,"losses":171,"wins":346},"GB2-03":{"draws":97,"losses":321,"wins":570},"GB2-04":{"draws":506,"losses":258,"wins":232},"GB2-05":{"draws":0,"losses":381,"wins":679},"GB2-06":{"draws":52,"losses":451,"wins":501},"GB2-07":{"draws":0,"losses":366,"wins":694},"GB2-08":{"draws":0,"losses":182,"wins":894}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":80,"losses":208,"wins":228},"GB2-02":{"draws":89,"losses":53,"wins":338},"GB2-03":{"draws":2,"losses":78,"wins":414},"GB2-04":{"draws":185,"losses":188,"wins":125},"GB2-05":{"draws":0,"losses":85,"wins":445},"GB2-06":{"draws":30,"losses":221,"wins":251},"GB2-07":{"draws":0,"losses":52,"wins":478},"GB2-08":{"draws":0,"losses":76,"wins":462}},"none":{"GB2-01":{"draws":224,"losses":210,"wins":82},"GB2-02":{"draws":354,"losses":118,"wins":8},"GB2-03":{"draws":95,"losses":243,"wins":156},"GB2-04":{"draws":321,"losses":70,"wins":107},"GB2-05":{"draws":0,"losses":296,"wins":234},"GB2-06":{"draws":22,"losses":230,"wins":250},"GB2-07":{"draws":0,"losses":314,"wins":216},"GB2-08":{"draws":0,"losses":106,"wins":432}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1507.9213344466186,"GB2-02":1764.7941561740347,"GB2-03":1884.184461681059,"GB2-04":1439.1740414216567,"GB2-05":2059.5954080734778,"GB2-06":1531.3103564554667,"GB2-07":2170.814537089538,"GB2-08":2062.544963637708},"none":{"GB2-01":1368.8733707624715,"GB2-02":1395.65512057755,"GB2-03":1384.2402372354097,"GB2-04":1517.9363045936238,"GB2-05":1383.7550624958876,"GB2-06":1516.0773540494586,"GB2-07":1364.5071729759707,"GB2-08":1934.566799443285}},"per_game_tracks":{"medium":{"GB2-01":54.06684288668242,"GB2-02":80.79717086084281,"GB2-03":85.9113327606461,"GB2-04":45.362630131234,"GB2-05":85.00458172061191,"GB2-06":57.05371345737677,"GB2-07":89.77523221591522,"GB2-08":87.29850170843115},"none":{"GB2-01":39.539966131915016,"GB2-02":40.166432833794005,"GB2-03":45.045774403013226,"GB2-04":55.48349041384266,"GB2-05":45.691139088496946,"GB2-06":56.1115650338196,"GB2-07":43.338901498374206,"GB2-08":82.35170937683921}},"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":73.15875071771754,"none":50.966122347511856},"reasoning_agg":{"medium":{"max":89.77523221591522,"mean":73.15875071771754,"min":45.362630131234},"none":{"max":82.35170937683921,"mean":50.966122347511856,"min":39.539966131915016}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":22.192628370205682},"working_program_strength":{"all":62.0624365326147,"medium":73.15875071771754,"none":50.966122347511856}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:b267f0076fff90c1","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419},"medium":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419}},"codegen_cost_usd":{"admitted_cell_count":2,"cell_count":3,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1851245,"median":0.183419,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":5,"run_count":3,"total":0.5553735},"codegen_latency_ms":{"attempt_count":4,"max_ms":724394,"mean_ms":700552.5,"min_ms":676711,"run_count":2},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":2,"max_ms":724394,"mean_ms":724394.0,"min_ms":724394,"run_count":1},"none":{"attempt_count":2,"max_ms":676711,"mean_ms":676711.0,"min_ms":676711,"run_count":1}},"codegen_output_tokens":{"attempt_count":5,"output_max":64000,"output_mean":62025.0,"output_min":59586,"run_count":3},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":1,"output_max":64000,"output_mean":64000.0,"output_min":64000,"run_count":1},"medium":{"attempt_count":2,"output_max":59586,"output_mean":59586.0,"output_min":59586,"run_count":1},"none":{"attempt_count":2,"output_max":62489,"output_mean":62489.0,"output_min":62489,"run_count":1}},"display_name":"Step 5 Preview","economics":{"all":58.65079208603305,"medium":83.01519596762861,"none":34.28638820443749},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":5,"effective_max_output_tokens":[64000],"finish_reason_observations":4,"finish_reasons":["stop"],"indexed_attempts":5,"output_token_observations":5,"provider_post_attempt_observations":5,"provider_post_attempts":5,"reasoning_token_observations":5,"reconciliation_get_attempt_observations":5,"requested_max_output_token_observations":5,"requested_max_output_tokens":[64000],"total_output_tokens":186075,"total_reasoning_output_tokens":53683,"total_visible_output_tokens":132392,"visible_token_observations":5},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":64000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-08":{"attempts":2,"playable":58.65079208603305,"score":58.65079208603305}},"headline_games_tracks":{"medium":{"GB2-08":{"attempts":1,"playable":83.01519596762861,"score":83.01519596762861}},"none":{"GB2-08":{"attempts":1,"playable":34.28638820443749,"score":34.28638820443749}}},"id":"stepfun/step-5-preview","is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:32Z","match_totals_all":{"draws":277,"losses":331,"wins":468},"match_totals_tracks":{"medium":{"draws":2,"losses":101,"wins":435},"none":{"draws":275,"losses":230,"wins":33}},"model_slug":"stepfun-step-5-preview","overall":{"max":83.01519596762861,"mean":58.65079208603305,"min":34.28638820443749},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":277,"losses":331,"wins":468}},"per_game_match_totals_tracks":{"medium":{"GB2-08":{"draws":2,"losses":101,"wins":435}},"none":{"GB2-08":{"draws":275,"losses":230,"wins":33}}},"per_game_raw_elo_tracks":{"medium":{"GB2-08":1950.5694940891003},"none":{"GB2-08":1225.345457274866}},"per_game_tracks":{"medium":{"GB2-08":83.01519596762861},"none":{"GB2-08":34.28638820443749}},"program_outcomes":{"all":{"counted_attempts":2,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":2,"working":2},"medium":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1},"none":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":83.01519596762861,"none":34.28638820443749},"reasoning_agg":{"medium":{"max":83.01519596762861,"mean":83.01519596762861,"min":83.01519596762861},"none":{"max":34.28638820443749,"mean":34.28638820443749,"min":34.28638820443749}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":48.72880776319112},"working_program_strength":{"all":58.65079208603305,"medium":83.01519596762861,"none":34.28638820443749}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:93146796c36c7ec4","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":0.14258062},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.0234374}},"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":50.219067744212786,"medium":60.03443585784811,"none":40.403699630577464},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[131072],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":23,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[131072],"total_output_tokens":500838,"total_reasoning_output_tokens":411817,"total_visible_output_tokens":89021,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":61.03882830147279,"score":61.03882830147279},"GB2-02":{"attempts":2,"playable":54.776229723645145,"score":54.776229723645145},"GB2-03":{"attempts":2,"playable":51.28291719232132,"score":51.28291719232132},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":58.69380279708807,"score":29.346901398544034},"GB2-05":{"attempts":2,"playable":56.403880615487566,"score":56.403880615487566},"GB2-06":{"attempts":2,"playable":58.382436320652445,"score":58.382436320652445},"GB2-07":{"attempts":2,"playable":61.972267333351056,"score":61.972267333351056},"GB2-08":{"attempts":2,"playable":28.549081068227927,"score":28.549081068227927}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":53.67665997060996,"score":53.67665997060996},"GB2-02":{"attempts":1,"playable":67.05642033901466,"score":67.05642033901466},"GB2-03":{"attempts":1,"playable":62.75026923534761,"score":62.75026923534761},"GB2-04":{"attempts":1,"playable":58.69380279708807,"score":58.69380279708807},"GB2-05":{"attempts":1,"playable":60.02207934671342,"score":60.02207934671342},"GB2-06":{"attempts":1,"playable":65.60310754548404,"score":65.60310754548404},"GB2-07":{"attempts":1,"playable":83.23058925067261,"score":83.23058925067261},"GB2-08":{"attempts":1,"playable":29.242558377854483,"score":29.242558377854483}},"none":{"GB2-01":{"attempts":1,"playable":68.40099663233562,"score":68.40099663233562},"GB2-02":{"attempts":1,"playable":42.496039108275625,"score":42.496039108275625},"GB2-03":{"attempts":1,"playable":39.815565149295026,"score":39.815565149295026},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":52.78568188426171,"score":52.78568188426171},"GB2-06":{"attempts":1,"playable":51.161765095820854,"score":51.161765095820854},"GB2-07":{"attempts":1,"playable":40.7139454160295,"score":40.7139454160295},"GB2-08":{"attempts":1,"playable":27.855603758601376,"score":27.855603758601376}}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T19:01:54Z","match_totals_all":{"draws":1444,"losses":3033,"wins":3201},"match_totals_tracks":{"medium":{"draws":557,"losses":1449,"wins":2082},"none":{"draws":887,"losses":1584,"wins":1119}},"model_slug":"xiaomi-mimo-v2-6-flash","official_rank_by_reasoning":{"medium":22,"none":44},"overall":{"max":83.23058925067261,"mean":50.219067744212786,"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":184,"losses":332,"wins":516},"GB2-02":{"draws":566,"losses":167,"wins":227},"GB2-03":{"draws":179,"losses":429,"wins":380},"GB2-04":{"draws":55,"losses":187,"wins":256},"GB2-05":{"draws":0,"losses":480,"wins":580},"GB2-06":{"draws":36,"losses":439,"wins":529},"GB2-07":{"draws":0,"losses":418,"wins":642},"GB2-08":{"draws":424,"losses":581,"wins":71}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":20,"losses":240,"wins":256},"GB2-02":{"draws":208,"losses":62,"wins":210},"GB2-03":{"draws":30,"losses":188,"wins":276},"GB2-04":{"draws":55,"losses":187,"wins":256},"GB2-05":{"draws":0,"losses":221,"wins":309},"GB2-06":{"draws":16,"losses":182,"wins":304},"GB2-07":{"draws":0,"losses":90,"wins":440},"GB2-08":{"draws":228,"losses":279,"wins":31}},"none":{"GB2-01":{"draws":164,"losses":92,"wins":260},"GB2-02":{"draws":358,"losses":105,"wins":17},"GB2-03":{"draws":149,"losses":241,"wins":104},"GB2-05":{"draws":0,"losses":259,"wins":271},"GB2-06":{"draws":20,"losses":257,"wins":225},"GB2-07":{"draws":0,"losses":328,"wins":202},"GB2-08":{"draws":196,"losses":302,"wins":40}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1504.1699924296918,"GB2-02":1612.9438658611796,"GB2-03":1546.4914208881007,"GB2-04":1543.789599897591,"GB2-05":1565.3224286607353,"GB2-06":1675.5009864329081,"GB2-07":1965.635302390168,"GB2-08":1171.7146013227702},"none":{"GB2-01":1653.6701606352826,"GB2-02":1413.8351260724141,"GB2-03":1338.7688408115014,"GB2-05":1472.0860161700643,"GB2-06":1437.68061504168,"GB2-07":1331.763222623801,"GB2-08":1156.5607431652625}},"per_game_tracks":{"medium":{"GB2-01":53.67665997060996,"GB2-02":67.05642033901466,"GB2-03":62.75026923534761,"GB2-04":58.69380279708807,"GB2-05":60.02207934671342,"GB2-06":65.60310754548404,"GB2-07":83.23058925067261,"GB2-08":29.242558377854483},"none":{"GB2-01":68.40099663233562,"GB2-02":42.496039108275625,"GB2-03":39.815565149295026,"GB2-05":52.78568188426171,"GB2-06":51.161765095820854,"GB2-07":40.7139454160295,"GB2-08":27.855603758601376}},"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":60.03443585784811,"none":40.403699630577464},"reasoning_agg":{"medium":{"max":83.23058925067261,"mean":60.03443585784811,"min":29.242558377854483},"none":{"max":68.40099663233562,"mean":40.403699630577464,"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":19.630736227270646},"working_program_strength":{"all":53.105046289254034,"medium":60.03443585784811,"none":46.17565672065996}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:96faf37e1712a459","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":0.30150960000000004},"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":0.02748863}},"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":0.027488630000000003}},"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":0.32899823000000006},"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":48.569123826317224,"medium":62.98508725331715,"none":34.15316039931731},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":22,"finish_reasons":["stop"],"indexed_attempts":22,"output_token_observations":22,"provider_post_attempt_observations":22,"provider_post_attempts":22,"reasoning_token_observations":22,"reconciliation_get_attempt_observations":22,"reconciliation_get_attempts":100,"total_output_tokens":640481,"total_reasoning_output_tokens":544948,"total_visible_output_tokens":95533,"visible_token_observations":22},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":43.107350217513726,"score":43.107350217513726},"GB2-02":{"attempts":2,"playable":50.931419369583004,"score":50.931419369583004},"GB2-03":{"attempts":2,"playable":55.770266187488545,"score":55.770266187488545},"GB2-04":{"attempts":2,"playable":44.286083763284395,"score":44.286083763284395},"GB2-05":{"attempts":2,"playable":44.43692725262614,"score":44.43692725262614},"GB2-06":{"attempts":2,"playable":68.09386091115343,"score":68.09386091115343},"GB2-07":{"attempts":2,"playable":42.72383187445691,"score":42.72383187445691},"GB2-08":{"attempts":2,"playable":39.20325103443163,"score":39.20325103443163}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":51.62599243619174,"score":51.62599243619174},"GB2-02":{"attempts":1,"playable":58.626717940825515,"score":58.626717940825515},"GB2-03":{"attempts":1,"playable":65.97577600045163,"score":65.97577600045163},"GB2-04":{"attempts":1,"playable":48.00576867194115,"score":48.00576867194115},"GB2-05":{"attempts":1,"playable":71.6702750001142,"score":71.6702750001142},"GB2-06":{"attempts":1,"playable":80.73741138623573,"score":80.73741138623573},"GB2-07":{"attempts":1,"playable":75.30014298026234,"score":75.30014298026234},"GB2-08":{"attempts":1,"playable":51.93861361051483,"score":51.93861361051483}},"none":{"GB2-01":{"attempts":1,"playable":34.58870799883571,"score":34.58870799883571},"GB2-02":{"attempts":1,"playable":43.236120798340494,"score":43.236120798340494},"GB2-03":{"attempts":1,"playable":45.56475637452546,"score":45.56475637452546},"GB2-04":{"attempts":1,"playable":40.56639885462764,"score":40.56639885462764},"GB2-05":{"attempts":1,"playable":17.203579505138084,"score":17.203579505138084},"GB2-06":{"attempts":1,"playable":55.450310436071135,"score":55.450310436071135},"GB2-07":{"attempts":1,"playable":10.14752076865149,"score":10.14752076865149},"GB2-08":{"attempts":1,"playable":26.467888458348437,"score":26.467888458348437}}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T18:55:46Z","match_totals_all":{"draws":2191,"losses":3304,"wins":2681},"match_totals_tracks":{"medium":{"draws":1023,"losses":1089,"wins":1976},"none":{"draws":1168,"losses":2215,"wins":705}},"model_slug":"qwen-qwen3-8-flash","official_rank_by_reasoning":{"medium":19,"none":54},"overall":{"max":80.73741138623573,"mean":48.569123826317224,"min":10.14752076865149},"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":293,"losses":461,"wins":278},"GB2-02":{"draws":637,"losses":169,"wins":154},"GB2-03":{"draws":253,"losses":348,"wins":387},"GB2-04":{"draws":623,"losses":260,"wins":113},"GB2-05":{"draws":0,"losses":603,"wins":457},"GB2-06":{"draws":53,"losses":325,"wins":626},"GB2-07":{"draws":0,"losses":620,"wins":440},"GB2-08":{"draws":332,"losses":518,"wins":226}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":181,"losses":170,"wins":165},"GB2-02":{"draws":264,"losses":75,"wins":141},"GB2-03":{"draws":127,"losses":123,"wins":244},"GB2-04":{"draws":289,"losses":123,"wins":86},"GB2-05":{"draws":0,"losses":159,"wins":371},"GB2-06":{"draws":44,"losses":85,"wins":373},"GB2-07":{"draws":0,"losses":136,"wins":394},"GB2-08":{"draws":118,"losses":218,"wins":202}},"none":{"GB2-01":{"draws":112,"losses":291,"wins":113},"GB2-02":{"draws":373,"losses":94,"wins":13},"GB2-03":{"draws":126,"losses":225,"wins":143},"GB2-04":{"draws":334,"losses":137,"wins":27},"GB2-05":{"draws":0,"losses":444,"wins":86},"GB2-06":{"draws":9,"losses":240,"wins":253},"GB2-07":{"draws":0,"losses":484,"wins":46},"GB2-08":{"draws":214,"losses":300,"wins":24}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1484.535996201038,"GB2-02":1540.0894913263812,"GB2-03":1580.199025143808,"GB2-04":1459.5724843079126,"GB2-05":1741.3936587843807,"GB2-06":1960.4005580448768,"GB2-07":1803.8213664483565,"GB2-08":1416.9500396206936},"none":{"GB2-01":1319.6149121356289,"GB2-02":1419.5745480878245,"GB2-03":1388.7445329807788,"GB2-04":1401.8979831083686,"GB2-05":956.9936144439919,"GB2-06":1505.451715339656,"GB2-07":837.6155372821662,"GB2-08":1141.133980707856}},"per_game_tracks":{"medium":{"GB2-01":51.62599243619174,"GB2-02":58.626717940825515,"GB2-03":65.97577600045163,"GB2-04":48.00576867194115,"GB2-05":71.6702750001142,"GB2-06":80.73741138623573,"GB2-07":75.30014298026234,"GB2-08":51.93861361051483},"none":{"GB2-01":34.58870799883571,"GB2-02":43.236120798340494,"GB2-03":45.56475637452546,"GB2-04":40.56639885462764,"GB2-05":17.203579505138084,"GB2-06":55.450310436071135,"GB2-07":10.14752076865149,"GB2-08":26.467888458348437}},"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":62.98508725331715,"none":34.15316039931731},"reasoning_agg":{"medium":{"max":80.73741138623573,"mean":62.98508725331715,"min":48.00576867194115},"none":{"max":55.450310436071135,"mean":34.15316039931731,"min":10.14752076865149}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":28.83192685399984},"working_program_strength":{"all":48.569123826317224,"medium":62.98508725331715,"none":34.15316039931731}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:384cba7aa09bc4cf","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924832999999997},"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":1.6981897300000002},"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":46.73835548892441,"highest":57.847092961095086,"none":35.62961801675373},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[262144],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[262144],"total_output_tokens":750541,"total_reasoning_output_tokens":655796,"total_visible_output_tokens":94745,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":47.1532799464413,"score":47.1532799464413},"GB2-02":{"attempts":2,"playable":54.27628934652677,"score":54.27628934652677},"GB2-03":{"attempts":2,"playable":37.01230025760826,"score":37.01230025760826},"GB2-04":{"attempts":2,"playable":52.09065394947966,"score":52.09065394947966},"GB2-05":{"attempts":2,"playable":56.66787536627718,"score":56.66787536627718},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":79.64647703967412,"score":39.82323851983706},"GB2-07":{"attempts":2,"playable":44.48867480977443,"score":44.48867480977443},"GB2-08":{"attempts":2,"playable":42.3945317154506,"score":42.3945317154506}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":34.98567003262313,"score":34.98567003262313},"GB2-02":{"attempts":1,"playable":65.42214883071365,"score":65.42214883071365},"GB2-03":{"attempts":1,"playable":43.588693415205206,"score":43.588693415205206},"GB2-04":{"attempts":1,"playable":65.55993946888988,"score":65.55993946888988},"GB2-05":{"attempts":1,"playable":49.53102259124648,"score":49.53102259124648},"GB2-06":{"attempts":1,"playable":79.64647703967412,"score":79.64647703967412},"GB2-07":{"attempts":1,"playable":79.44760849821657,"score":79.44760849821657},"GB2-08":{"attempts":1,"playable":44.59518381219164,"score":44.59518381219164}},"none":{"GB2-01":{"attempts":1,"playable":59.32088986025947,"score":59.32088986025947},"GB2-02":{"attempts":1,"playable":43.13042986233988,"score":43.13042986233988},"GB2-03":{"attempts":1,"playable":30.435907100011317,"score":30.435907100011317},"GB2-04":{"attempts":1,"playable":38.621368430069445,"score":38.621368430069445},"GB2-05":{"attempts":1,"playable":63.804728141307876,"score":63.804728141307876},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.529741121332288,"score":9.529741121332288},"GB2-08":{"attempts":1,"playable":40.19387961870955,"score":40.19387961870955}}},"id":"mistralai/mistral-large-4-0","is_recent_addition":false,"last_measured_at":"2026-10-24T15:45:31Z","match_totals_all":{"draws":2202,"losses":2912,"wins":2560},"match_totals_tracks":{"highest":{"draws":989,"losses":1318,"wins":1781},"none":{"draws":1213,"losses":1594,"wins":779}},"model_slug":"mistralai-mistral-large-4-0","official_rank_by_reasoning":{"highest":35,"none":52},"overall":{"max":79.64647703967412,"mean":46.73835548892441,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":34.98567003262313,"GB2-02":65.42214883071365,"GB2-03":43.588693415205206,"GB2-04":65.55993946888988,"GB2-05":49.53102259124648,"GB2-06":79.64647703967412,"GB2-07":79.44760849821657,"GB2-08":44.59518381219164},"per_game_match_totals_all":{"GB2-01":{"draws":128,"losses":502,"wins":402},"GB2-02":{"draws":652,"losses":129,"wins":179},"GB2-03":{"draws":342,"losses":486,"wins":160},"GB2-04":{"draws":529,"losses":229,"wins":238},"GB2-05":{"draws":0,"losses":477,"wins":583},"GB2-06":{"draws":36,"losses":95,"wins":371},"GB2-07":{"draws":0,"losses":599,"wins":461},"GB2-08":{"draws":515,"losses":395,"wins":166}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":334,"wins":160},"GB2-02":{"draws":264,"losses":42,"wins":174},"GB2-03":{"draws":177,"losses":209,"wins":108},"GB2-04":{"draws":234,"losses":63,"wins":201},"GB2-05":{"draws":0,"losses":276,"wins":254},"GB2-06":{"draws":36,"losses":95,"wins":371},"GB2-07":{"draws":0,"losses":112,"wins":418},"GB2-08":{"draws":256,"losses":187,"wins":95}},"none":{"GB2-01":{"draws":106,"losses":168,"wins":242},"GB2-02":{"draws":388,"losses":87,"wins":5},"GB2-03":{"draws":165,"losses":277,"wins":52},"GB2-04":{"draws":295,"losses":166,"wins":37},"GB2-05":{"draws":0,"losses":201,"wins":329},"GB2-07":{"draws":0,"losses":487,"wins":43},"GB2-08":{"draws":259,"losses":208,"wins":71}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1323.6454822104886,"GB2-02":1598.082505806442,"GB2-03":1371.600737087832,"GB2-04":1602.2159016291432,"GB2-05":1431.522672325341,"GB2-06":1938.3214421180053,"GB2-07":1881.5091387376087,"GB2-08":1334.0455834891352},"none":{"GB2-01":1559.1840090605813,"GB2-02":1418.7557351959765,"GB2-03":1253.920053901863,"GB2-04":1386.5454844648805,"GB2-05":1617.5625259940173,"GB2-07":820.6518927074762,"GB2-08":1287.1745521371154}},"per_game_tracks":{"highest":{"GB2-01":34.98567003262313,"GB2-02":65.42214883071365,"GB2-03":43.588693415205206,"GB2-04":65.55993946888988,"GB2-05":49.53102259124648,"GB2-06":79.64647703967412,"GB2-07":79.44760849821657,"GB2-08":44.59518381219164},"none":{"GB2-01":59.32088986025947,"GB2-02":43.13042986233988,"GB2-03":30.435907100011317,"GB2-04":38.621368430069445,"GB2-05":63.804728141307876,"GB2-07":9.529741121332288,"GB2-08":40.19387961870955}},"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":57.847092961095086,"none":35.62961801675373},"reasoning_agg":{"highest":{"max":79.64647703967412,"mean":57.847092961095086,"min":34.98567003262313},"none":{"max":63.804728141307876,"mean":35.62961801675373,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":22.217474944341355},"working_program_strength":{"all":49.283328204406814,"highest":57.847092961095086,"none":40.71956344771855}},{"canonical_public_row_identity":"publication-row.v1:overall:elorian-glimpse:75e259dbabeebff6","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":0.1844346}},"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":0.18443459999999998}},"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":42.6580359773881,"medium":65.83971175023645,"none":19.476360204539763},"first_seen_at":null,"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":47.884995424092175,"score":47.884995424092175},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.87001850459841,"score":21.935009252299206},"GB2-03":{"attempts":2,"playable":45.5026787664108,"score":45.5026787664108},"GB2-04":{"attempts":2,"playable":48.22688618218727,"score":48.22688618218727},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.69359635890299,"score":29.346798179451493},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":84.64400296364497,"score":42.32200148182248},"GB2-07":{"attempts":2,"playable":45.78802992342058,"score":45.78802992342058},"GB2-08":{"attempts":2,"playable":60.25788860942084,"score":60.25788860942084}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":83.07243212052249,"score":83.07243212052249},"GB2-02":{"attempts":1,"playable":43.87001850459841,"score":43.87001850459841},"GB2-03":{"attempts":1,"playable":36.43023302396182,"score":36.43023302396182},"GB2-04":{"attempts":1,"playable":55.78509709756037,"score":55.78509709756037},"GB2-05":{"attempts":1,"playable":58.69359635890299,"score":58.69359635890299},"GB2-06":{"attempts":1,"playable":84.64400296364497,"score":84.64400296364497},"GB2-07":{"attempts":1,"playable":75.12674168151578,"score":75.12674168151578},"GB2-08":{"attempts":1,"playable":89.09557225118479,"score":89.09557225118479}},"none":{"GB2-01":{"attempts":1,"playable":12.697558727661853,"score":12.697558727661853},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":54.57512450885979,"score":54.57512450885979},"GB2-04":{"attempts":1,"playable":40.66867526681418,"score":40.66867526681418},"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":16.449318165325376,"score":16.449318165325376},"GB2-08":{"attempts":1,"playable":31.420204967656883,"score":31.420204967656883}}},"id":"elorian/glimpse","is_recent_addition":false,"last_measured_at":"2026-10-24T14:24:48Z","match_totals_all":{"draws":1341,"losses":2618,"wins":2705},"match_totals_tracks":{"medium":{"draws":928,"losses":986,"wins":2174},"none":{"draws":413,"losses":1632,"wins":531}},"model_slug":"elorian-glimpse","official_rank_by_reasoning":{"medium":16,"none":81},"overall":{"max":89.09557225118479,"mean":42.6580359773881,"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":53,"losses":526,"wins":453},"GB2-02":{"draws":381,"losses":87,"wins":12},"GB2-03":{"draws":277,"losses":437,"wins":274},"GB2-04":{"draws":611,"losses":227,"wins":158},"GB2-05":{"draws":0,"losses":228,"wins":302},"GB2-06":{"draws":19,"losses":76,"wins":407},"GB2-07":{"draws":0,"losses":590,"wins":470},"GB2-08":{"draws":0,"losses":447,"wins":629}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":21,"losses":86,"wins":409},"GB2-02":{"draws":381,"losses":87,"wins":12},"GB2-03":{"draws":211,"losses":226,"wins":57},"GB2-04":{"draws":296,"losses":81,"wins":121},"GB2-05":{"draws":0,"losses":228,"wins":302},"GB2-06":{"draws":19,"losses":76,"wins":407},"GB2-07":{"draws":0,"losses":137,"wins":393},"GB2-08":{"draws":0,"losses":65,"wins":473}},"none":{"GB2-01":{"draws":32,"losses":440,"wins":44},"GB2-03":{"draws":66,"losses":211,"wins":217},"GB2-04":{"draws":315,"losses":146,"wins":37},"GB2-07":{"draws":0,"losses":453,"wins":77},"GB2-08":{"draws":0,"losses":382,"wins":156}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1846.120946165409,"GB2-02":1424.4804152842908,"GB2-03":1308.9024656338747,"GB2-04":1520.337007946202,"GB2-05":1547.683835586288,"GB2-06":2043.3279727799145,"GB2-07":1800.8054202106578,"GB2-08":2115.7424493751937},"none":{"GB2-01":1037.1786481689942,"GB2-03":1468.3639551706979,"GB2-04":1402.7003284231976,"GB2-07":978.7375559283233,"GB2-08":1195.0932318832167}},"per_game_tracks":{"medium":{"GB2-01":83.07243212052249,"GB2-02":43.87001850459841,"GB2-03":36.43023302396182,"GB2-04":55.78509709756037,"GB2-05":58.69359635890299,"GB2-06":84.64400296364497,"GB2-07":75.12674168151578,"GB2-08":89.09557225118479},"none":{"GB2-01":12.697558727661853,"GB2-03":54.57512450885979,"GB2-04":40.66867526681418,"GB2-07":16.449318165325376,"GB2-08":31.420204967656883}},"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":65.83971175023645,"none":19.476360204539763},"reasoning_agg":{"medium":{"max":89.09557225118479,"mean":65.83971175023645,"min":36.43023302396182},"none":{"max":54.57512450885979,"mean":19.476360204539763,"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":46.36335154569669},"working_program_strength":{"all":48.500944038750035,"medium":65.83971175023645,"none":31.16217632726362}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:a1e2894f4db70ea9","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":42.48497663776318,"none":42.48497663776318},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":11,"finish_reasons":["stop"],"indexed_attempts":11,"output_token_observations":11,"total_output_tokens":35469},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":61.841350424054454,"score":61.841350424054454},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":39.288545647452736,"score":39.288545647452736},"GB2-04":{"attempts":1,"playable":38.621368430069445,"score":38.621368430069445},"GB2-05":{"attempts":1,"playable":13.942038727726402,"score":13.942038727726402},"GB2-06":{"attempts":1,"playable":50.981470929880146,"score":50.981470929880146},"GB2-07":{"attempts":1,"playable":47.98325183276144,"score":47.98325183276144},"GB2-08":{"attempts":1,"playable":44.30277426060413,"score":44.30277426060413}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":61.841350424054454,"score":61.841350424054454},"GB2-02":{"attempts":1,"playable":42.91901284955672,"score":42.91901284955672},"GB2-03":{"attempts":1,"playable":39.288545647452736,"score":39.288545647452736},"GB2-04":{"attempts":1,"playable":38.621368430069445,"score":38.621368430069445},"GB2-05":{"attempts":1,"playable":13.942038727726402,"score":13.942038727726402},"GB2-06":{"attempts":1,"playable":50.981470929880146,"score":50.981470929880146},"GB2-07":{"attempts":1,"playable":47.98325183276144,"score":47.98325183276144},"GB2-08":{"attempts":1,"playable":44.30277426060413,"score":44.30277426060413}}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-10-24T19:21:15Z","match_totals_all":{"draws":1114,"losses":1898,"wins":1075},"match_totals_tracks":{"none":{"draws":1114,"losses":1898,"wins":1075}},"model_slug":"gpt-4-1","official_rank_by_reasoning":{"none":34},"overall":{"max":61.841350424054454,"mean":42.48497663776318,"min":13.942038727726402},"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":34,"losses":191,"wins":291},"GB2-02":{"draws":386,"losses":89,"wins":5},"GB2-03":{"draws":118,"losses":259,"wins":117},"GB2-04":{"draws":321,"losses":153,"wins":24},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":16,"losses":259,"wins":226},"GB2-07":{"draws":0,"losses":289,"wins":241},"GB2-08":{"draws":239,"losses":197,"wins":102}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":34,"losses":191,"wins":291},"GB2-02":{"draws":386,"losses":89,"wins":5},"GB2-03":{"draws":118,"losses":259,"wins":117},"GB2-04":{"draws":321,"losses":153,"wins":24},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":16,"losses":259,"wins":226},"GB2-07":{"draws":0,"losses":289,"wins":241},"GB2-08":{"draws":239,"losses":197,"wins":102}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1584.4708476044434,"GB2-02":1417.117036832385,"GB2-03":1334.1538891103035,"GB2-04":1386.5454844648805,"GB2-05":889.1906093489134,"GB2-06":1434.868951138352,"GB2-07":1422.2406585152985,"GB2-08":1330.885637443778}},"per_game_tracks":{"none":{"GB2-01":61.841350424054454,"GB2-02":42.91901284955672,"GB2-03":39.288545647452736,"GB2-04":38.621368430069445,"GB2-05":13.942038727726402,"GB2-06":50.981470929880146,"GB2-07":47.98325183276144,"GB2-08":44.30277426060413}},"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":42.48497663776318},"reasoning_agg":{"none":{"max":61.841350424054454,"mean":42.48497663776318,"min":13.942038727726402}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"working_program_strength":{"all":42.48497663776318,"none":42.48497663776318}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:889b2709e6e0b012","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"all":40.76251112585612,"medium":40.76251112585612},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":18,"finish_reasons":["length","stop"],"indexed_attempts":18,"output_token_observations":18,"total_output_tokens":308283},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k2.7-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-06"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":6,"repaired_rate":0.8571428571428571}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":38.51463420639908,"score":38.51463420639908},"GB2-02":{"attempts":1,"playable":42.601799932716034,"score":42.601799932716034},"GB2-04":{"attempts":1,"playable":38.82626496490585,"score":38.82626496490585},"GB2-05":{"attempts":1,"playable":52.97683185709665,"score":52.97683185709665},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.52573420732089,"score":43.52573420732089},"GB2-08":{"attempts":1,"playable":68.89231271255434,"score":68.89231271255434}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":38.51463420639908,"score":38.51463420639908},"GB2-02":{"attempts":1,"playable":42.601799932716034,"score":42.601799932716034},"GB2-04":{"attempts":1,"playable":38.82626496490585,"score":38.82626496490585},"GB2-05":{"attempts":1,"playable":52.97683185709665,"score":52.97683185709665},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.52573420732089,"score":43.52573420732089},"GB2-08":{"attempts":1,"playable":68.89231271255434,"score":68.89231271255434}}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-10-24T19:10:18Z","match_totals_all":{"draws":707,"losses":1325,"wins":1059},"match_totals_tracks":{"medium":{"draws":707,"losses":1325,"wins":1059}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":68.89231271255434,"mean":40.76251112585612,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":323,"wins":185},"GB2-02":{"draws":363,"losses":102,"wins":15},"GB2-04":{"draws":293,"losses":166,"wins":39},"GB2-05":{"draws":0,"losses":258,"wins":272},"GB2-07":{"draws":0,"losses":313,"wins":217},"GB2-08":{"draws":44,"losses":163,"wins":331}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":323,"wins":185},"GB2-02":{"draws":363,"losses":102,"wins":15},"GB2-04":{"draws":293,"losses":166,"wins":39},"GB2-05":{"draws":0,"losses":258,"wins":272},"GB2-07":{"draws":0,"losses":313,"wins":217},"GB2-08":{"draws":44,"losses":163,"wins":331}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1358.8314435424713,"GB2-02":1414.656188095171,"GB2-04":1388.17202162157,"GB2-05":1474.4822048555152,"GB2-07":1366.8311255001263,"GB2-08":1659.1580859292674}},"per_game_tracks":{"medium":{"GB2-01":38.51463420639908,"GB2-02":42.601799932716034,"GB2-04":38.82626496490585,"GB2-05":52.97683185709665,"GB2-07":43.52573420732089,"GB2-08":68.89231271255434}},"program_outcomes":{"all":{"counted_attempts":7,"failed":1,"infra_excluded":1,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":6,"worked_first_time":0,"working":6},"medium":{"counted_attempts":7,"failed":1,"infra_excluded":1,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":6,"worked_first_time":0,"working":6}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.76251112585612},"reasoning_agg":{"medium":{"max":68.89231271255434,"mean":40.76251112585612,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":47.55626298016548,"medium":47.55626298016548}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:60daed6b43fd9431","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.0151682500000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":22},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":0.2156185632352941,"median":0.169101,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":22},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.1688104},"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":39.26708049827859,"medium":48.38666833344284,"none":30.147492663114335},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":21,"finish_reasons":["incomplete","stop"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":2,"total_output_tokens":1096010,"total_reasoning_output_tokens":255888,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":51.819236707417375,"score":51.819236707417375},"GB2-02":{"attempts":2,"playable":41.54367583083084,"score":41.54367583083084},"GB2-03":{"attempts":2,"playable":45.30526538876934,"score":45.30526538876934},"GB2-04":{"attempts":2,"playable":43.88529211110118,"score":43.88529211110118},"GB2-05":{"attempts":2,"playable":29.529012348386004,"score":29.529012348386004},"GB2-06":{"attempts":2,"playable":39.342798313298076,"score":39.342798313298076},"GB2-07":{"attempts":2,"playable":26.0896461803,"score":26.0896461803},"GB2-08":{"attempts":2,"playable":36.621717106125914,"score":36.621717106125914}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":69.74481824668709,"score":69.74481824668709},"GB2-02":{"attempts":1,"playable":41.54367583083084,"score":41.54367583083084},"GB2-03":{"attempts":1,"playable":45.045774403013226,"score":45.045774403013226},"GB2-04":{"attempts":1,"playable":44.242143117121884,"score":44.242143117121884},"GB2-05":{"attempts":1,"playable":47.996347925984125,"score":47.996347925984125},"GB2-06":{"attempts":1,"playable":48.16456597813221,"score":48.16456597813221},"GB2-07":{"attempts":1,"playable":45.76083735358176,"score":45.76083735358176},"GB2-08":{"attempts":1,"playable":44.59518381219164,"score":44.59518381219164}},"none":{"GB2-01":{"attempts":1,"playable":33.89365516814766,"score":33.89365516814766},"GB2-02":{"attempts":1,"playable":41.54367583083084,"score":41.54367583083084},"GB2-03":{"attempts":1,"playable":45.56475637452546,"score":45.56475637452546},"GB2-04":{"attempts":1,"playable":43.52844110508048,"score":43.52844110508048},"GB2-05":{"attempts":1,"playable":11.061676770787882,"score":11.061676770787882},"GB2-06":{"attempts":1,"playable":30.521030648463938,"score":30.521030648463938},"GB2-07":{"attempts":1,"playable":6.418455007018236,"score":6.418455007018236},"GB2-08":{"attempts":1,"playable":28.648250400060192,"score":28.648250400060192}}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-10-24T18:55:04Z","match_totals_all":{"draws":2526,"losses":3911,"wins":1739},"match_totals_tracks":{"medium":{"draws":1067,"losses":1681,"wins":1340},"none":{"draws":1459,"losses":2230,"wins":399}},"model_slug":"gpt-5-4-mini","official_rank_by_reasoning":{"medium":41,"none":64},"overall":{"max":69.74481824668709,"mean":39.26708049827859,"min":6.418455007018236},"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":195,"losses":420,"wins":417},"GB2-02":{"draws":746,"losses":204,"wins":10},"GB2-03":{"draws":551,"losses":303,"wins":134},"GB2-04":{"draws":611,"losses":270,"wins":115},"GB2-05":{"draws":0,"losses":760,"wins":300},"GB2-06":{"draws":45,"losses":629,"wins":330},"GB2-07":{"draws":0,"losses":803,"wins":257},"GB2-08":{"draws":378,"losses":522,"wins":176}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":36,"losses":149,"wins":331},"GB2-02":{"draws":365,"losses":106,"wins":9},"GB2-03":{"draws":167,"losses":207,"wins":120},"GB2-04":{"draws":322,"losses":125,"wins":51},"GB2-05":{"draws":0,"losses":284,"wins":246},"GB2-06":{"draws":33,"losses":266,"wins":203},"GB2-07":{"draws":0,"losses":301,"wins":229},"GB2-08":{"draws":144,"losses":243,"wins":151}},"none":{"GB2-01":{"draws":159,"losses":271,"wins":86},"GB2-02":{"draws":381,"losses":98,"wins":1},"GB2-03":{"draws":384,"losses":96,"wins":14},"GB2-04":{"draws":289,"losses":145,"wins":64},"GB2-05":{"draws":0,"losses":476,"wins":54},"GB2-06":{"draws":12,"losses":363,"wins":127},"GB2-07":{"draws":0,"losses":502,"wins":28},"GB2-08":{"draws":234,"losses":279,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1668.6604194363117,"GB2-02":1406.4264502199794,"GB2-03":1384.2402372354097,"GB2-04":1430.5128218565485,"GB2-05":1412.4601683523217,"GB2-06":1391.2500249000013,"GB2-07":1394.6061265012488,"GB2-08":1334.0455834891352},"none":{"GB2-01":1312.5163171726574,"GB2-02":1406.4264502199794,"GB2-03":1388.7445329807788,"GB2-04":1424.9853633226578,"GB2-05":821.1852561784556,"GB2-06":1124.4278642120776,"GB2-07":719.6126806932722,"GB2-08":1165.2502224274206}},"per_game_tracks":{"medium":{"GB2-01":69.74481824668709,"GB2-02":41.54367583083084,"GB2-03":45.045774403013226,"GB2-04":44.242143117121884,"GB2-05":47.996347925984125,"GB2-06":48.16456597813221,"GB2-07":45.76083735358176,"GB2-08":44.59518381219164},"none":{"GB2-01":33.89365516814766,"GB2-02":41.54367583083084,"GB2-03":45.56475637452546,"GB2-04":43.52844110508048,"GB2-05":11.061676770787882,"GB2-06":30.521030648463938,"GB2-07":6.418455007018236,"GB2-08":28.648250400060192}},"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":48.38666833344284,"none":30.147492663114335},"reasoning_agg":{"medium":{"max":69.74481824668709,"mean":48.38666833344284,"min":41.54367583083084},"none":{"max":45.56475637452546,"mean":30.147492663114335,"min":6.418455007018236}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":18.239175670328507},"working_program_strength":{"all":39.26708049827859,"medium":48.38666833344284,"none":30.147492663114335}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:996de790147b6de7","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2996388,"mean":0.08320818615,"median":0.048126608099999996,"min":0.0057139812,"recorded_attempt_count":28,"run_count":16,"total":1.3313309784},"codegen_latency_ms":{"attempt_count":28,"max_ms":2144825,"mean_ms":691475.625,"min_ms":43161,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":11,"max_ms":886851,"mean_ms":223216.625,"min_ms":43161,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":131072,"output_mean":41065.3125,"output_min":2846,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":11,"output_max":42691,"output_mean":10871.125,"output_min":2846,"run_count":8}},"display_name":"MiMo-V2.5-Pro","economics":{"all":38.3674330578864,"medium":46.8853510681486,"none":29.84951504762421},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["error","length","stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":657045},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":6,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":2,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":6,"repaired_rate":1.0},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":54.31912280348946,"score":54.31912280348946},"GB2-02":{"attempts":1,"playable":38.999631461099575,"score":38.999631461099575},"GB2-03":{"attempts":1,"playable":34.939953974889406,"score":34.939953974889406},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":48.107274277511145,"score":24.053637138755573},"GB2-05":{"attempts":2,"playable":22.29132792253099,"score":22.29132792253099},"GB2-06":{"attempts":2,"playable":52.77677792007063,"score":52.77677792007063},"GB2-07":{"attempts":2,"playable":45.55743831839432,"score":45.55743831839432},"GB2-08":{"attempts":2,"playable":24.086016573707184,"score":24.086016573707184}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":71.37297850573391,"score":71.37297850573391},"GB2-04":{"attempts":1,"playable":48.107274277511145,"score":48.107274277511145},"GB2-05":{"attempts":1,"playable":25.268629736614283,"score":25.268629736614283},"GB2-06":{"attempts":1,"playable":67.16387383525279,"score":67.16387383525279},"GB2-07":{"attempts":1,"playable":41.841053983875774,"score":41.841053983875774},"GB2-08":{"attempts":1,"playable":27.558296069903705,"score":27.558296069903705}},"none":{"GB2-01":{"attempts":1,"playable":37.265267101245016,"score":37.265267101245016},"GB2-02":{"attempts":1,"playable":38.999631461099575,"score":38.999631461099575},"GB2-03":{"attempts":1,"playable":34.939953974889406,"score":34.939953974889406},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.314026108447692,"score":19.314026108447692},"GB2-06":{"attempts":1,"playable":38.38968200488848,"score":38.38968200488848},"GB2-07":{"attempts":1,"playable":49.273822652912855,"score":49.273822652912855},"GB2-08":{"attempts":1,"playable":20.61373707751066,"score":20.61373707751066}}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-24T19:02:40Z","match_totals_all":{"draws":1338,"losses":3519,"wins":1847},"match_totals_tracks":{"medium":{"draws":585,"losses":1440,"wins":1089},"none":{"draws":753,"losses":2079,"wins":758}},"model_slug":"xiaomi-mimo-v2-5-pro","official_rank_by_reasoning":{"none":65},"overall":{"max":71.37297850573391,"mean":38.3674330578864,"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":190,"losses":397,"wins":445},"GB2-02":{"draws":317,"losses":142,"wins":21},"GB2-03":{"draws":183,"losses":247,"wins":64},"GB2-04":{"draws":250,"losses":142,"wins":106},"GB2-05":{"draws":0,"losses":835,"wins":225},"GB2-06":{"draws":20,"losses":503,"wins":481},"GB2-07":{"draws":0,"losses":604,"wins":456},"GB2-08":{"draws":378,"losses":649,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":63,"losses":127,"wins":326},"GB2-04":{"draws":250,"losses":142,"wins":106},"GB2-05":{"draws":0,"losses":402,"wins":128},"GB2-06":{"draws":15,"losses":174,"wins":313},"GB2-07":{"draws":0,"losses":322,"wins":208},"GB2-08":{"draws":257,"losses":273,"wins":8}},"none":{"GB2-01":{"draws":127,"losses":270,"wins":119},"GB2-02":{"draws":317,"losses":142,"wins":21},"GB2-03":{"draws":183,"losses":247,"wins":64},"GB2-05":{"draws":0,"losses":433,"wins":97},"GB2-06":{"draws":5,"losses":329,"wins":168},"GB2-07":{"draws":0,"losses":282,"wins":248},"GB2-08":{"draws":121,"losses":376,"wins":41}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1687.3026853182046,"GB2-04":1460.3560861340277,"GB2-05":1100.2601270932003,"GB2-06":1703.1009814914137,"GB2-07":1345.8486054180753,"GB2-08":1153.2797676440346},"none":{"GB2-01":1346.4948265745074,"GB2-02":1386.4638068073464,"GB2-03":1295.5397210109682,"GB2-05":997.2735527176172,"GB2-06":1242.7903803918355,"GB2-07":1438.332324470866,"GB2-08":1071.7054682613602}},"per_game_tracks":{"medium":{"GB2-01":71.37297850573391,"GB2-04":48.107274277511145,"GB2-05":25.268629736614283,"GB2-06":67.16387383525279,"GB2-07":41.841053983875774,"GB2-08":27.558296069903705},"none":{"GB2-01":37.265267101245016,"GB2-02":38.999631461099575,"GB2-03":34.939953974889406,"GB2-05":19.314026108447692,"GB2-06":38.38968200488848,"GB2-07":49.273822652912855,"GB2-08":20.61373707751066}},"program_outcomes":{"all":{"counted_attempts":14,"failed":1,"infra_excluded":2,"success_rate":0.9285714285714286,"too_slow":0,"worked_after_repair":9,"worked_first_time":4,"working":13},"medium":{"counted_attempts":6,"failed":0,"infra_excluded":2,"success_rate":1.0,"too_slow":0,"worked_after_repair":6,"worked_first_time":0,"working":6},"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":46.8853510681486,"none":29.84951504762421},"reasoning_agg":{"medium":{"max":71.37297850573391,"mean":46.8853510681486,"min":25.268629736614283},"none":{"max":49.273822652912855,"mean":29.84951504762421,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":17.035836020524393},"working_program_strength":{"all":40.49954127557385,"medium":46.8853510681486,"none":34.11373148299909}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:8ba956e24bebbf1e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237500000001},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239874999999997}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112225},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"all":37.56379806953068,"medium":39.564029994094895,"none":35.56356614496645},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"total_output_tokens":178317},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.234418844674195,"score":42.234418844674195},"GB2-02":{"attempts":2,"playable":45.24158482856183,"score":45.24158482856183},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":29.460399061775256,"score":14.730199530887628},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.63042970269787,"score":21.815214851348934},"GB2-05":{"attempts":2,"playable":38.08350495269451,"score":38.08350495269451},"GB2-06":{"attempts":2,"playable":38.07776179210181,"score":38.07776179210181},"GB2-07":{"attempts":2,"playable":68.61217627790053,"score":68.61217627790053},"GB2-08":{"attempts":2,"playable":31.71552347807598,"score":31.71552347807598}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.473577347966636,"score":18.473577347966636},"GB2-02":{"attempts":1,"playable":44.39793855579591,"score":44.39793855579591},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.63042970269787,"score":43.63042970269787},"GB2-05":{"attempts":1,"playable":39.52970392915049,"score":39.52970392915049},"GB2-06":{"attempts":1,"playable":60.42279949646,"score":60.42279949646},"GB2-07":{"attempts":1,"playable":76.16639575084709,"score":76.16639575084709},"GB2-08":{"attempts":1,"playable":33.89139516984121,"score":33.89139516984121}},"none":{"GB2-01":{"attempts":1,"playable":65.99526034138175,"score":65.99526034138175},"GB2-02":{"attempts":1,"playable":46.08523110132774,"score":46.08523110132774},"GB2-03":{"attempts":1,"playable":29.460399061775256,"score":29.460399061775256},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":36.63730597623852,"score":36.63730597623852},"GB2-06":{"attempts":1,"playable":15.732724087743625,"score":15.732724087743625},"GB2-07":{"attempts":1,"playable":61.057956804953974,"score":61.057956804953974},"GB2-08":{"attempts":1,"playable":29.539651786310746,"score":29.539651786310746}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-10-24T19:07:15Z","match_totals_all":{"draws":1947,"losses":3270,"wins":1968},"match_totals_tracks":{"medium":{"draws":1022,"losses":1527,"wins":1045},"none":{"draws":925,"losses":1743,"wins":923}},"model_slug":"qwen-qwen3-7-max","official_rank_by_reasoning":{"medium":55,"none":53},"overall":{"max":76.16639575084709,"mean":37.56379806953068,"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":222,"losses":503,"wins":307},"GB2-02":{"draws":690,"losses":197,"wins":73},"GB2-03":{"draws":192,"losses":269,"wins":34},"GB2-04":{"draws":268,"losses":155,"wins":75},"GB2-05":{"draws":0,"losses":671,"wins":389},"GB2-06":{"draws":49,"losses":629,"wins":326},"GB2-07":{"draws":0,"losses":348,"wins":712},"GB2-08":{"draws":526,"losses":498,"wins":52}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":69,"losses":393,"wins":54},"GB2-02":{"draws":362,"losses":94,"wins":24},"GB2-04":{"draws":268,"losses":155,"wins":75},"GB2-05":{"draws":0,"losses":328,"wins":202},"GB2-06":{"draws":46,"losses":195,"wins":261},"GB2-07":{"draws":0,"losses":131,"wins":399},"GB2-08":{"draws":277,"losses":231,"wins":30}},"none":{"GB2-01":{"draws":153,"losses":110,"wins":253},"GB2-02":{"draws":328,"losses":103,"wins":49},"GB2-03":{"draws":192,"losses":269,"wins":34},"GB2-05":{"draws":0,"losses":343,"wins":187},"GB2-06":{"draws":3,"losses":434,"wins":65},"GB2-07":{"draws":0,"losses":217,"wins":313},"GB2-08":{"draws":249,"losses":267,"wins":22}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1130.7467658342625,"GB2-02":1428.5603177629207,"GB2-04":1425.7758674628817,"GB2-05":1305.4169590280248,"GB2-06":1586.7770805972154,"GB2-07":1819.1312485379797,"GB2-08":1221.200002227521},"none":{"GB2-01":1627.6050883284406,"GB2-02":1441.5767610407138,"GB2-03":1244.586811888218,"GB2-05":1267.1626562247923,"GB2-06":886.7467145144922,"GB2-07":1589.9820630916538,"GB2-08":1174.9311828734253}},"per_game_tracks":{"medium":{"GB2-01":18.473577347966636,"GB2-02":44.39793855579591,"GB2-04":43.63042970269787,"GB2-05":39.52970392915049,"GB2-06":60.42279949646,"GB2-07":76.16639575084709,"GB2-08":33.89139516984121},"none":{"GB2-01":65.99526034138175,"GB2-02":46.08523110132774,"GB2-03":29.460399061775256,"GB2-05":36.63730597623852,"GB2-06":15.732724087743625,"GB2-07":61.057956804953974,"GB2-08":29.539651786310746}},"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":39.564029994094895,"none":35.56356614496645},"reasoning_agg":{"medium":{"max":76.16639575084709,"mean":39.564029994094895,"min":0.0},"none":{"max":65.99526034138175,"mean":35.56356614496645,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":4.000463849128444},"working_program_strength":{"all":42.93005493660648,"medium":45.216034278965594,"none":40.644075594247376}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:397ad047775cb684","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":0.48528459999999995}},"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":0.48528459999999995},"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":35.097599699400725,"medium":35.097599699400725},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":17,"finish_reasons":["stop"],"indexed_attempts":17,"output_token_observations":17,"total_output_tokens":179458},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":37.36426792982258,"score":37.36426792982258},"GB2-02":{"attempts":1,"playable":43.55312295903319,"score":43.55312295903319},"GB2-03":{"attempts":1,"playable":29.13996212092226,"score":29.13996212092226},"GB2-04":{"attempts":1,"playable":40.97544712922916,"score":40.97544712922916},"GB2-05":{"attempts":1,"playable":50.29765599977094,"score":50.29765599977094},"GB2-06":{"attempts":1,"playable":31.804779287097062,"score":31.804779287097062},"GB2-07":{"attempts":1,"playable":15.038680403329685,"score":15.038680403329685},"GB2-08":{"attempts":1,"playable":32.606881766000896,"score":32.606881766000896}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":37.36426792982258,"score":37.36426792982258},"GB2-02":{"attempts":1,"playable":43.55312295903319,"score":43.55312295903319},"GB2-03":{"attempts":1,"playable":29.13996212092226,"score":29.13996212092226},"GB2-04":{"attempts":1,"playable":40.97544712922916,"score":40.97544712922916},"GB2-05":{"attempts":1,"playable":50.29765599977094,"score":50.29765599977094},"GB2-06":{"attempts":1,"playable":31.804779287097062,"score":31.804779287097062},"GB2-07":{"attempts":1,"playable":15.038680403329685,"score":15.038680403329685},"GB2-08":{"attempts":1,"playable":32.606881766000896,"score":32.606881766000896}}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-10-24T19:20:25Z","match_totals_all":{"draws":1225,"losses":2138,"wins":725},"match_totals_tracks":{"medium":{"draws":1225,"losses":2138,"wins":725}},"model_slug":"x-ai-grok-build-0-1","official_rank_by_reasoning":{"medium":60},"overall":{"max":50.29765599977094,"mean":35.097599699400725,"min":15.038680403329685},"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":100,"losses":283,"wins":133},"GB2-02":{"draws":382,"losses":88,"wins":10},"GB2-03":{"draws":135,"losses":298,"wins":61},"GB2-04":{"draws":340,"losses":132,"wins":26},"GB2-05":{"draws":0,"losses":272,"wins":258},"GB2-06":{"draws":6,"losses":360,"wins":136},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":262,"losses":245,"wins":31}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":100,"losses":283,"wins":133},"GB2-02":{"draws":382,"losses":88,"wins":10},"GB2-03":{"draws":135,"losses":298,"wins":61},"GB2-04":{"draws":340,"losses":132,"wins":26},"GB2-05":{"draws":0,"losses":272,"wins":258},"GB2-06":{"draws":6,"losses":360,"wins":136},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":262,"losses":245,"wins":31}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1347.4767807545425,"GB2-02":1422.0289366733252,"GB2-03":1241.490717711793,"GB2-04":1405.1043195835468,"GB2-05":1441.0499889813532,"GB2-06":1143.777996160222,"GB2-07":950.9290303643036,"GB2-08":1207.6728892636213}},"per_game_tracks":{"medium":{"GB2-01":37.36426792982258,"GB2-02":43.55312295903319,"GB2-03":29.13996212092226,"GB2-04":40.97544712922916,"GB2-05":50.29765599977094,"GB2-06":31.804779287097062,"GB2-07":15.038680403329685,"GB2-08":32.606881766000896}},"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":35.097599699400725},"reasoning_agg":{"medium":{"max":50.29765599977094,"mean":35.097599699400725,"min":15.038680403329685}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":35.097599699400725,"medium":35.097599699400725}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:527a8fffe808ac75","codegen_cost_by_reasoning":{"medium":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":2,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":3,"run_count":2,"total":0.0},"codegen_latency_ms":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1}},"codegen_output_tokens":{"attempt_count":3,"output_max":32768,"output_mean":19502.5,"output_min":6237,"run_count":2},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":1,"output_max":32768,"output_mean":32768.0,"output_min":32768,"run_count":1},"none":{"attempt_count":2,"output_max":6237,"output_mean":6237.0,"output_min":6237,"run_count":1}},"display_name":"Ling 3.1 Flash","economics":{"all":33.29868748274998,"none":33.29868748274998},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":3,"effective_max_output_tokens":[32768],"finish_reason_observations":2,"finish_reasons":["stop"],"indexed_attempts":3,"output_token_observations":3,"provider_post_attempt_observations":3,"provider_post_attempts":4,"reasoning_token_observations":3,"reconciliation_get_attempt_observations":3,"requested_max_output_token_observations":3,"requested_max_output_tokens":[32768],"total_output_tokens":39005,"total_reasoning_output_tokens":30791,"total_visible_output_tokens":8214,"visible_token_observations":3},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-08":{"attempts":1,"playable":33.29868748274998,"score":33.29868748274998}},"headline_games_tracks":{"none":{"GB2-08":{"attempts":1,"playable":33.29868748274998,"score":33.29868748274998}}},"id":"inclusionai/ling-3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T14:05:01Z","match_totals_all":{"draws":287,"losses":229,"wins":22},"match_totals_tracks":{"none":{"draws":287,"losses":229,"wins":22}},"model_slug":"inclusionai-ling-3-1-flash","overall":{"max":33.29868748274998,"mean":33.29868748274998,"min":33.29868748274998},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":287,"losses":229,"wins":22}},"per_game_match_totals_tracks":{"none":{"GB2-08":{"draws":287,"losses":229,"wins":22}}},"per_game_raw_elo_tracks":{"none":{"GB2-08":1214.9679616041067}},"per_game_tracks":{"none":{"GB2-08":33.29868748274998}},"program_outcomes":{"all":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1},"none":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":33.29868748274998},"reasoning_agg":{"none":{"max":33.29868748274998,"mean":33.29868748274998,"min":33.29868748274998}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"},"working_program_strength":{"all":33.29868748274998,"none":33.29868748274998}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:957df8aae5e922d8","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176385999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917795999999999},"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":31.824107350852238,"medium":31.485081818222778,"none":32.163132883481694},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"poolside","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":13,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.5833333333333334,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"infra_failures_excluded":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.08333333333333333,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-07"],"performance_rejections":1,"repaired_admitted":4,"repaired_rate":0.3333333333333333},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.35714285714285715}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.618931429286626,"score":35.38837585412191},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.96637010925764,"score":31.765791054749073},"GB2-03":{"attempts":4,"playable":39.06120385572966,"score":39.06120385572966},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.361817502287046,"score":20.180908751143523},"GB2-05":{"attempts":4,"playable":38.19633094910294,"score":38.19633094910294},"GB2-06":{"attempts":2,"playable":20.10467879564613,"score":20.10467879564613},"GB2-07":{"attempts":2,"playable":45.22001764347978,"score":45.22001764347978},"GB2-08":{"attempts":4,"playable":31.54301981547339,"score":31.54301981547339}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":40.92222230065885,"score":20.461111150329426},"GB2-02":{"attempts":2,"playable":43.13042400048102,"score":43.13042400048102},"GB2-03":{"attempts":2,"playable":38.43089508479425,"score":38.43089508479425},"GB2-04":{"attempts":1,"playable":40.361817502287046,"score":40.361817502287046},"GB2-05":{"attempts":2,"playable":27.98435192563801,"score":27.98435192563801},"GB2-06":{"attempts":1,"playable":19.597233345122632,"score":19.597233345122632},"GB2-08":{"attempts":2,"playable":30.429739718907065,"score":30.429739718907065}},"none":{"GB2-01":{"attempts":2,"playable":50.3156405579144,"score":50.3156405579144},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.80231621803426,"score":20.40115810901713},"GB2-03":{"attempts":2,"playable":39.69151262666507,"score":39.69151262666507},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":48.40830997256787,"score":48.40830997256787},"GB2-06":{"attempts":1,"playable":20.612124246169632,"score":20.612124246169632},"GB2-07":{"attempts":2,"playable":45.22001764347978,"score":45.22001764347978},"GB2-08":{"attempts":2,"playable":32.656299912039714,"score":32.656299912039714}}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-10-24T19:07:26Z","match_totals_all":{"draws":3164,"losses":6002,"wins":2632},"match_totals_tracks":{"medium":{"draws":1821,"losses":2884,"wins":895},"none":{"draws":1343,"losses":3118,"wins":1737}},"model_slug":"poolside-laguna-s-2-1","official_rank_by_reasoning":{"medium":66,"none":55},"overall":{"max":50.3156405579144,"mean":31.824107350852238,"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":252,"losses":723,"wins":573},"GB2-02":{"draws":1134,"losses":287,"wins":19},"GB2-03":{"draws":652,"losses":950,"wins":374},"GB2-04":{"draws":298,"losses":156,"wins":44},"GB2-05":{"draws":0,"losses":1336,"wins":784},"GB2-06":{"draws":13,"losses":826,"wins":165},"GB2-07":{"draws":0,"losses":606,"wins":454},"GB2-08":{"draws":815,"losses":1118,"wins":219}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":86,"losses":272,"wins":158},"GB2-02":{"draws":792,"losses":166,"wins":2},"GB2-03":{"draws":302,"losses":493,"wins":193},"GB2-04":{"draws":298,"losses":156,"wins":44},"GB2-05":{"draws":0,"losses":776,"wins":284},"GB2-06":{"draws":5,"losses":416,"wins":81},"GB2-08":{"draws":338,"losses":605,"wins":133}},"none":{"GB2-01":{"draws":166,"losses":451,"wins":415},"GB2-02":{"draws":342,"losses":121,"wins":17},"GB2-03":{"draws":350,"losses":457,"wins":181},"GB2-05":{"draws":0,"losses":560,"wins":500},"GB2-06":{"draws":8,"losses":410,"wins":84},"GB2-07":{"draws":0,"losses":606,"wins":454},"GB2-08":{"draws":477,"losses":513,"wins":86}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1382.3102852054083,"GB2-02":1418.7555577585772,"GB2-03":1326.3846448673044,"GB2-04":1400.2917235707478,"GB2-05":1121.4674213477238,"GB2-06":953.9068300685063,"GB2-08":1184.3529567862765},"none":{"GB2-01":1472.676541500483,"GB2-02":1400.6377218341197,"GB2-03":1337.4249944301368,"GB2-05":1428.7680412906325,"GB2-06":970.6218718271314,"GB2-07":1387.6533798785522,"GB2-08":1208.194230836213}},"per_game_tracks":{"medium":{"GB2-01":40.92222230065885,"GB2-02":43.13042400048102,"GB2-03":38.43089508479425,"GB2-04":40.361817502287046,"GB2-05":27.98435192563801,"GB2-06":19.597233345122632,"GB2-08":30.429739718907065},"none":{"GB2-01":50.3156405579144,"GB2-02":40.80231621803426,"GB2-03":39.69151262666507,"GB2-05":48.40830997256787,"GB2-06":20.612124246169632,"GB2-07":45.22001764347978,"GB2-08":32.656299912039714}},"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":31.48508181822278,"none":32.163132883481694},"reasoning_agg":{"medium":{"max":43.13042400048102,"mean":31.48508181822278,"min":19.597233345122632},"none":{"max":50.3156405579144,"mean":32.163132883481694,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.6780510652589129},"working_program_strength":{"all":37.040207503911404,"medium":34.40809769684127,"none":39.67231731098153}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:e70ee5ccebcd089b","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":0.04172561300000001},"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":31.589031673755017,"highest":32.851398928282855,"none":30.32666441922718},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"total_output_tokens":130744},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1,"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":71.81271684810598,"score":71.81271684810598},"GB2-02":{"attempts":2,"playable":38.41552688305904,"score":38.41552688305904},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":32.2649460109786,"score":16.1324730054893},"GB2-04":{"attempts":2,"playable":45.97058808680119,"score":45.97058808680119},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":37.74843375200467,"score":22.69551399005672},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.53191327457305,"score":8.265956637286525},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":25.566261762934516,"score":12.783130881467258},"GB2-08":{"attempts":2,"playable":36.63634705777413,"score":36.63634705777413}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":65.22390644042689,"score":65.22390644042689},"GB2-02":{"attempts":1,"playable":39.10575785483857,"score":39.10575785483857},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.73240795883822,"score":43.73240795883822},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":60.2116790477918,"score":30.1058395238959},"GB2-06":{"attempts":1,"playable":16.53191327457305,"score":16.53191327457305},"GB2-07":{"attempts":1,"playable":25.566261762934516,"score":25.566261762934516},"GB2-08":{"attempts":1,"playable":42.54510461075572,"score":42.54510461075572}},"none":{"GB2-01":{"attempts":1,"playable":78.40152725578507,"score":78.40152725578507},"GB2-02":{"attempts":1,"playable":37.7252959112795,"score":37.7252959112795},"GB2-03":{"attempts":1,"playable":32.2649460109786,"score":32.2649460109786},"GB2-04":{"attempts":1,"playable":48.20876821476416,"score":48.20876821476416},"GB2-05":{"attempts":1,"playable":15.285188456217542,"score":15.285188456217542},"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":30.727589504792537,"score":30.727589504792537}}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-10-24T18:46:30Z","match_totals_all":{"draws":1977,"losses":3060,"wins":1613},"match_totals_tracks":{"highest":{"draws":907,"losses":1710,"wins":977},"none":{"draws":1070,"losses":1350,"wins":636}},"model_slug":"tencent-hy3-preview","official_rank_by_reasoning":{"highest":58,"none":62},"overall":{"max":78.40152725578507,"mean":31.589031673755017,"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":65.22390644042689,"GB2-02":39.10575785483857,"GB2-04":43.73240795883822,"GB2-05":60.2116790477918,"GB2-06":16.53191327457305,"GB2-07":25.566261762934516,"GB2-08":42.54510461075572},"per_game_match_totals_all":{"GB2-01":{"draws":158,"losses":233,"wins":641},"GB2-02":{"draws":691,"losses":261,"wins":8},"GB2-03":{"draws":118,"losses":292,"wins":84},"GB2-04":{"draws":662,"losses":224,"wins":110},"GB2-05":{"draws":0,"losses":674,"wins":386},"GB2-06":{"draws":4,"losses":430,"wins":68},"GB2-07":{"draws":0,"losses":407,"wins":123},"GB2-08":{"draws":344,"losses":539,"wins":193}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":79,"losses":151,"wins":286},"GB2-02":{"draws":344,"losses":128,"wins":8},"GB2-04":{"draws":359,"losses":109,"wins":30},"GB2-05":{"draws":0,"losses":220,"wins":310},"GB2-06":{"draws":4,"losses":430,"wins":68},"GB2-07":{"draws":0,"losses":407,"wins":123},"GB2-08":{"draws":121,"losses":265,"wins":152}},"none":{"GB2-01":{"draws":79,"losses":82,"wins":355},"GB2-02":{"draws":347,"losses":133,"wins":0},"GB2-03":{"draws":118,"losses":292,"wins":84},"GB2-04":{"draws":303,"losses":115,"wins":80},"GB2-05":{"draws":0,"losses":454,"wins":76},"GB2-08":{"draws":223,"losses":274,"wins":41}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1619.4322460888263,"GB2-02":1387.3026462780722,"GB2-04":1426.5660710198995,"GB2-05":1567.8658779123584,"GB2-06":901.2002077746325,"GB2-07":1130.006348169337,"GB2-08":1312.0465173029902},"none":{"GB2-01":1775.9430000361929,"GB2-02":1376.3411652681314,"GB2-03":1271.0837996726095,"GB2-04":1461.1396769174576,"GB2-05":918.0669730455171,"GB2-08":1187.7039174144063}},"per_game_tracks":{"highest":{"GB2-01":65.22390644042689,"GB2-02":39.10575785483857,"GB2-04":43.73240795883822,"GB2-05":60.2116790477918,"GB2-06":16.53191327457305,"GB2-07":25.566261762934516,"GB2-08":42.54510461075572},"none":{"GB2-01":78.40152725578507,"GB2-02":37.7252959112795,"GB2-03":32.2649460109786,"GB2-04":48.20876821476416,"GB2-05":15.285188456217542,"GB2-08":30.727589504792537}},"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":32.851398928282855,"none":30.326664419227182},"reasoning_agg":{"highest":{"max":65.22390644042689,"mean":32.851398928282855,"min":0.0},"none":{"max":78.40152725578507,"mean":30.326664419227182,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":2.5247345090556728},"working_program_strength":{"all":41.14042134735327,"highest":41.84529013573696,"none":40.43555255896957}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:5058ed4f0f6da1c6","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":0.19736108440000003},"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":0.06890521579999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0265755425,"mean":0.018416099712499998,"median":0.017703669999999998,"min":0.0109615788,"recorded_attempt_count":32,"run_count":15,"total":0.2720731754},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.2141143316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.030685472800000002},"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":30.950066382604117,"highest":36.62705174633566,"medium":30.206403148866368,"none":26.016744252610323},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["length","stop"],"indexed_attempts":32,"output_token_observations":32,"total_output_tokens":734523},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":32.04306814418678,"score":32.04306814418678},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":42.61266911623851,"score":33.451331924427826},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.46101929934333,"score":15.153673099781109},"GB2-04":{"attempts":6,"playable":40.076536777500316,"score":40.076536777500316},"GB2-05":{"attempts":5,"playable":26.06447829727289,"score":26.06447829727289},"GB2-06":{"attempts":5,"playable":34.64337920124235,"score":34.64337920124235},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":25.73680946814127,"score":22.281813206641825},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":30.618485139282157,"score":23.40827684831436}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":23.50863802284668,"score":23.50863802284668},"GB2-02":{"attempts":1,"playable":44.08122255938022,"score":44.08122255938022},"GB2-04":{"attempts":1,"playable":39.54311557804636,"score":39.54311557804636},"GB2-06":{"attempts":1,"playable":49.03870177226871,"score":49.03870177226871},"GB2-08":{"attempts":1,"playable":26.963580799136338,"score":26.963580799136338}},"medium":{"GB2-01":{"attempts":2,"playable":29.908960922183027,"score":29.908960922183027},"GB2-02":{"attempts":3,"playable":42.530767426187225,"score":42.530767426187225},"GB2-04":{"attempts":3,"playable":38.689109370732105,"score":38.689109370732105},"GB2-05":{"attempts":2,"playable":24.40579392335669,"score":24.40579392335669},"GB2-06":{"attempts":1,"playable":21.959334945613744,"score":21.959334945613744},"GB2-07":{"attempts":2,"playable":30.743641367285868,"score":30.743641367285868},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":34.81082113005886,"score":23.207214086705907}},"none":{"GB2-01":{"attempts":3,"playable":42.71160548753065,"score":42.71160548753065},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":41.226017363148074,"score":13.742005787716025},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.46101929934333,"score":15.153673099781109},"GB2-04":{"attempts":2,"playable":41.997385383722474,"score":41.997385383722474},"GB2-05":{"attempts":3,"playable":27.723162671189087,"score":27.723162671189087},"GB2-06":{"attempts":3,"playable":32.93210088584459,"score":32.93210088584459},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":20.729977568996674,"score":13.819985045997782},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":30.08105348865127,"score":20.054035659100848}}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:07:23Z","match_totals_all":{"draws":5548,"losses":10093,"wins":3307},"match_totals_tracks":{"highest":{"draws":1155,"losses":1093,"wins":286},"medium":{"draws":2461,"losses":4011,"wins":1192},"none":{"draws":1932,"losses":4989,"wins":1829}},"model_slug":"xiaomi-mimo-v2-5","official_rank_by_reasoning":{"none":74},"overall":{"max":49.03870177226871,"mean":30.950066382604117,"min":13.742005787716025},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":23.50863802284668,"GB2-02":44.08122255938022,"GB2-04":39.54311557804636,"GB2-06":49.03870177226871,"GB2-08":26.963580799136338},"per_game_all":{"GB2-01":32.04306814418678,"GB2-02":42.61266911623851,"GB2-04":40.076536777500316,"GB2-06":34.64337920124235,"GB2-08":30.618485139282157},"per_game_match_totals_all":{"GB2-01":{"draws":639,"losses":1741,"wins":716},"GB2-02":{"draws":1862,"losses":487,"wins":51},"GB2-03":{"draws":181,"losses":198,"wins":115},"GB2-04":{"draws":1845,"losses":920,"wins":223},"GB2-05":{"draws":0,"losses":1981,"wins":669},"GB2-06":{"draws":48,"losses":1720,"wins":742},"GB2-07":{"draws":0,"losses":1622,"wins":498},"GB2-08":{"draws":973,"losses":1424,"wins":293}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":215,"losses":295,"wins":6},"GB2-02":{"draws":385,"losses":84,"wins":11},"GB2-04":{"draws":306,"losses":156,"wins":36},"GB2-06":{"draws":20,"losses":268,"wins":214},"GB2-08":{"draws":229,"losses":290,"wins":19}},"medium":{"GB2-01":{"draws":132,"losses":675,"wins":225},"GB2-02":{"draws":1111,"losses":296,"wins":33},"GB2-04":{"draws":929,"losses":475,"wins":90},"GB2-05":{"draws":0,"losses":813,"wins":247},"GB2-06":{"draws":16,"losses":400,"wins":86},"GB2-07":{"draws":0,"losses":760,"wins":300},"GB2-08":{"draws":273,"losses":592,"wins":211}},"none":{"GB2-01":{"draws":292,"losses":771,"wins":485},"GB2-02":{"draws":366,"losses":107,"wins":7},"GB2-03":{"draws":181,"losses":198,"wins":115},"GB2-04":{"draws":610,"losses":289,"wins":97},"GB2-05":{"draws":0,"losses":1168,"wins":422},"GB2-06":{"draws":12,"losses":1052,"wins":442},"GB2-07":{"draws":0,"losses":862,"wins":198},"GB2-08":{"draws":471,"losses":542,"wins":63}}},"per_game_raw_elo_all":{"GB2-01":1282.7959624867615,"GB2-02":1414.5593549699868,"GB2-04":1399.0296792289344,"GB2-06":1166.5173256538135,"GB2-08":1184.329880324235},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1197.1836109731348,"GB2-02":1426.113221831944,"GB2-04":1393.8446113073871,"GB2-06":1404.7278390167767,"GB2-08":1146.678203033334},"medium":{"GB2-01":1270.005296343773,"GB2-02":1413.6162433767345,"GB2-04":1390.1576840671191,"GB2-05":1084.2202940775514,"GB2-06":992.3911083638818,"GB2-07":1198.3057683178827,"GB2-08":1226.145298491868},"none":{"GB2-01":1381.1989801433763,"GB2-02":1403.9485997012819,"GB2-03":1387.8439860032354,"GB2-04":1413.0867423122968,"GB2-05":1191.4309813844811,"GB2-06":1102.4330295807817,"GB2-07":1035.8312345688144,"GB2-08":1180.1661394475034}},"per_game_tracks":{"highest":{"GB2-01":23.50863802284668,"GB2-02":44.08122255938022,"GB2-04":39.54311557804636,"GB2-06":49.03870177226871,"GB2-08":26.963580799136338},"medium":{"GB2-01":29.908960922183027,"GB2-02":42.530767426187225,"GB2-04":38.689109370732105,"GB2-05":24.40579392335669,"GB2-06":21.959334945613744,"GB2-07":30.743641367285868,"GB2-08":34.81082113005886},"none":{"GB2-01":42.71160548753065,"GB2-02":41.226017363148074,"GB2-03":45.46101929934333,"GB2-04":41.997385383722474,"GB2-05":27.723162671189087,"GB2-06":32.93210088584459,"GB2-07":20.729977568996674,"GB2-08":30.08105348865127}},"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":36.62705174633566,"medium":30.206403148866368,"none":26.016744252610323},"reasoning_agg":{"highest":{"max":49.03870177226871,"mean":36.62705174633566,"min":23.50863802284668},"medium":{"max":42.530767426187225,"mean":30.206403148866368,"min":21.959334945613744},"none":{"max":42.71160548753065,"mean":26.016744252610323,"min":13.742005787716025}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":10.610307493725337},"working_program_strength":{"all":34.616301104268565,"highest":36.62705174633566,"medium":31.864061297916788,"none":35.357790268553266}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-5-super-vl:1cc2f77d42b49a10","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":0.02850254}},"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":0.0934742},"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":0.028502540000000003}},"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":0.12197673999999999},"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":30.93164805973646,"medium":50.16403931767357,"none":11.699256801799352},"first_seen_at":null,"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":66.18798778557334,"score":33.09399389278667},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.82005707252698,"score":22.41002853626349},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":36.217677180997555,"score":18.108838590498777},"GB2-04":{"attempts":2,"playable":42.2010591011576,"score":42.2010591011576},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.31362665998524,"score":29.15681332999262},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":46.79785911579964,"score":23.39892955789982},"GB2-07":{"attempts":2,"playable":40.45527008530516,"score":40.45527008530516},"GB2-08":{"attempts":2,"playable":38.62825138398755,"score":38.62825138398755}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":66.18798778557334,"score":66.18798778557334},"GB2-02":{"attempts":1,"playable":44.82005707252698,"score":44.82005707252698},"GB2-03":{"attempts":1,"playable":36.217677180997555,"score":36.217677180997555},"GB2-04":{"attempts":1,"playable":41.07768520323326,"score":41.07768520323326},"GB2-05":{"attempts":1,"playable":58.31362665998524,"score":58.31362665998524},"GB2-06":{"attempts":1,"playable":46.79785911579964,"score":46.79785911579964},"GB2-07":{"attempts":1,"playable":57.10880721364588,"score":57.10880721364588},"GB2-08":{"attempts":1,"playable":50.78861430962667,"score":50.78861430962667}},"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":43.32443299908194,"score":43.32443299908194},"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":23.801732956964443,"score":23.801732956964443},"GB2-08":{"attempts":1,"playable":26.467888458348437,"score":26.467888458348437}}},"id":"nvidia/nemotron-3.5-super-vl","is_recent_addition":false,"last_measured_at":"2026-10-24T16:50:40Z","match_totals_all":{"draws":1317,"losses":2589,"wins":1748},"match_totals_tracks":{"medium":{"draws":968,"losses":1650,"wins":1470},"none":{"draws":349,"losses":939,"wins":278}},"model_slug":"nvidia-nemotron-3-5-super-vl","official_rank_by_reasoning":{"medium":38},"overall":{"max":66.18798778557334,"mean":30.93164805973646,"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":67,"losses":152,"wins":297},"GB2-02":{"draws":378,"losses":84,"wins":18},"GB2-03":{"draws":183,"losses":241,"wins":70},"GB2-04":{"draws":678,"losses":253,"wins":65},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":11,"losses":284,"wins":207},"GB2-07":{"draws":0,"losses":655,"wins":405},"GB2-08":{"draws":0,"losses":690,"wins":386}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":67,"losses":152,"wins":297},"GB2-02":{"draws":378,"losses":84,"wins":18},"GB2-03":{"draws":183,"losses":241,"wins":70},"GB2-04":{"draws":329,"losses":137,"wins":32},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":11,"losses":284,"wins":207},"GB2-07":{"draws":0,"losses":239,"wins":291},"GB2-08":{"draws":0,"losses":283,"wins":255}},"none":{"GB2-04":{"draws":349,"losses":116,"wins":33},"GB2-07":{"draws":0,"losses":416,"wins":114},"GB2-08":{"draws":0,"losses":407,"wins":131}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1629.6602428478632,"GB2-02":1431.8194889144627,"GB2-03":1307.0061471342517,"GB2-04":1405.9046606856264,"GB2-05":1542.6934198919057,"GB2-06":1370.2670467475596,"GB2-07":1537.8141705203711,"GB2-08":1403.4128883632904},"none":{"GB2-04":1423.4034254659787,"GB2-07":1103.5240441878334,"GB2-08":1141.133980707856}},"per_game_tracks":{"medium":{"GB2-01":66.18798778557334,"GB2-02":44.82005707252698,"GB2-03":36.217677180997555,"GB2-04":41.07768520323326,"GB2-05":58.31362665998524,"GB2-06":46.79785911579964,"GB2-07":57.10880721364588,"GB2-08":50.78861430962667},"none":{"GB2-04":43.32443299908194,"GB2-07":23.801732956964443,"GB2-08":26.467888458348437}},"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":50.16403931767357,"none":11.699256801799352},"reasoning_agg":{"medium":{"max":66.18798778557334,"mean":50.16403931767357,"min":36.217677180997555},"none":{"max":43.32443299908194,"mean":11.699256801799352,"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":38.46478251587422},"working_program_strength":{"all":40.681028727902586,"medium":50.16403931767357,"none":31.198018138131605}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:8886fdcee94228f5","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":0.14744575},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":55},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":8,"max":0.26962149999999996,"mean":0.03182758529411764,"median":0.01676735,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821378999999998},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"all":29.56694583351231,"medium":32.29251156899071,"none":26.84138009803391},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["incomplete","stop"],"indexed_attempts":57,"output_token_observations":57,"reasoning_token_observations":2,"total_output_tokens":752982,"total_reasoning_output_tokens":128000,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.3125,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-03","GB2-04","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.3125,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"model_code_failures":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":31.30989340098394,"score":31.30989340098394},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.192921172895154,"score":30.177817687677564},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":34.83329259854874,"score":8.708323149637184},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":51.5513082769799,"score":12.887827069244976},"GB2-05":{"attempts":4,"playable":29.550664627473544,"score":29.550664627473544},"GB2-06":{"attempts":4,"playable":50.809520116919984,"score":50.809520116919984},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":28.189716256456485,"score":22.88042614222806},"GB2-08":{"attempts":4,"playable":50.211094473933244,"score":50.211094473933244}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"playable":16.249409696957105,"score":16.249409696957105},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.06041394087035,"score":20.030206970435174},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":51.5513082769799,"score":25.77565413848995},"GB2-05":{"attempts":2,"playable":50.732999615186536,"score":50.732999615186536},"GB2-06":{"attempts":2,"playable":60.17265192747166,"score":60.17265192747166},"GB2-07":{"attempts":2,"playable":35.14227205599927,"score":35.14227205599927},"GB2-08":{"attempts":2,"playable":50.23689814738602,"score":50.23689814738602}},"none":{"GB2-01":{"attempts":2,"playable":46.37037710501077,"score":46.37037710501077},"GB2-02":{"attempts":2,"playable":40.325428404919954,"score":40.325428404919954},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":34.83329259854874,"score":17.41664629927437},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":8.36832963976055,"score":8.36832963976055},"GB2-06":{"attempts":2,"playable":41.44638830636831,"score":41.44638830636831},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":21.2371604569137,"score":10.61858022845685},"GB2-08":{"attempts":2,"playable":50.18529080048047,"score":50.18529080048047}}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-10-24T19:20:25Z","match_totals_all":{"draws":2290,"losses":6610,"wins":3466},"match_totals_tracks":{"medium":{"draws":964,"losses":3179,"wins":2067},"none":{"draws":1326,"losses":3431,"wins":1399}},"model_slug":"gpt-5-4-nano","official_rank_by_reasoning":{"medium":64,"none":72},"overall":{"max":60.17265192747166,"mean":29.56694583351231,"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":384,"losses":1259,"wins":421},"GB2-02":{"draws":1086,"losses":341,"wins":13},"GB2-03":{"draws":144,"losses":267,"wins":83},"GB2-04":{"draws":238,"losses":131,"wins":129},"GB2-05":{"draws":0,"losses":1514,"wins":606},"GB2-06":{"draws":37,"losses":1040,"wins":931},"GB2-07":{"draws":0,"losses":1135,"wins":455},"GB2-08":{"draws":401,"losses":923,"wins":828}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":161,"losses":796,"wins":75},"GB2-02":{"draws":365,"losses":113,"wins":2},"GB2-04":{"draws":238,"losses":131,"wins":129},"GB2-05":{"draws":0,"losses":534,"wins":526},"GB2-06":{"draws":35,"losses":421,"wins":548},"GB2-07":{"draws":0,"losses":706,"wins":354},"GB2-08":{"draws":165,"losses":478,"wins":433}},"none":{"GB2-01":{"draws":223,"losses":463,"wins":346},"GB2-02":{"draws":721,"losses":228,"wins":11},"GB2-03":{"draws":144,"losses":267,"wins":83},"GB2-05":{"draws":0,"losses":980,"wins":80},"GB2-06":{"draws":2,"losses":619,"wins":383},"GB2-07":{"draws":0,"losses":429,"wins":101},"GB2-08":{"draws":236,"losses":445,"wins":395}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1059.8201645499362,"GB2-02":1394.8226749637631,"GB2-04":1487.033125919346,"GB2-05":1488.8380516067161,"GB2-06":1583.5271527938753,"GB2-07":1206.2233522914614,"GB2-08":1458.365192804068},"none":{"GB2-01":1434.3221761407715,"GB2-02":1396.9020379228573,"GB2-03":1294.5769218063936,"GB2-05":746.2411838590915,"GB2-06":1294.9080066439487,"GB2-07":1063.0368400058499,"GB2-08":1447.319252236986}},"per_game_tracks":{"medium":{"GB2-01":16.249409696957105,"GB2-02":40.06041394087035,"GB2-04":51.5513082769799,"GB2-05":50.732999615186536,"GB2-06":60.17265192747166,"GB2-07":35.14227205599927,"GB2-08":50.23689814738602},"none":{"GB2-01":46.37037710501077,"GB2-02":40.325428404919954,"GB2-03":34.83329259854874,"GB2-05":8.36832963976055,"GB2-06":41.44638830636831,"GB2-07":21.2371604569137,"GB2-08":50.18529080048047}},"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":32.29251156899071,"none":26.84138009803391},"reasoning_agg":{"medium":{"max":60.17265192747166,"mean":32.29251156899071,"min":0.0},"none":{"max":50.18529080048047,"mean":26.84138009803391,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":5.451131470956803},"working_program_strength":{"all":39.06515864091809,"medium":43.449421951550114,"none":34.68089533028607}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:87daea4d942b603c","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.030739789999999996},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.014924670000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.03073979},"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":0.01492467}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0061656,"mean":0.0028540287500000002,"median":0.00232709,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"recorded_attempt_count":25,"run_count":16,"total":0.045664460000000004},"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":29.20935420931343,"medium":38.08556066323405,"none":20.33314775539282},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[16384],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":26,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[16384],"total_output_tokens":78215,"total_reasoning_output_tokens":27437,"total_visible_output_tokens":50778,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":16384,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":22.403408740786293,"score":11.201704370393147},"GB2-02":{"attempts":2,"playable":41.70092577474455,"score":41.70092577474455},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":43.90141136154609,"score":21.950705680773044},"GB2-04":{"attempts":2,"playable":44.64884386066582,"score":44.64884386066582},"GB2-05":{"attempts":2,"playable":44.43068317547378,"score":44.43068317547378},"GB2-06":{"attempts":2,"playable":22.28833535555473,"score":22.28833535555473},"GB2-07":{"attempts":2,"playable":14.303206036700509,"score":14.303206036700509},"GB2-08":{"attempts":2,"playable":33.15042942020188,"score":33.15042942020188}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":22.403408740786293,"score":22.403408740786293},"GB2-02":{"attempts":1,"playable":43.44746737727414,"score":43.44746737727414},"GB2-03":{"attempts":1,"playable":43.90141136154609,"score":43.90141136154609},"GB2-04":{"attempts":1,"playable":43.32443299908194,"score":43.32443299908194},"GB2-05":{"attempts":1,"playable":72.04145723140032,"score":72.04145723140032},"GB2-06":{"attempts":1,"playable":27.816729209054365,"score":27.816729209054365},"GB2-07":{"attempts":1,"playable":18.253293321990967,"score":18.253293321990967},"GB2-08":{"attempts":1,"playable":33.496285064738274,"score":33.496285064738274}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":39.95438417221496,"score":39.95438417221496},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":45.9732547222497,"score":45.9732547222497},"GB2-05":{"attempts":1,"playable":16.819909119547248,"score":16.819909119547248},"GB2-06":{"attempts":1,"playable":16.759941502055096,"score":16.759941502055096},"GB2-07":{"attempts":1,"playable":10.353118751410053,"score":10.353118751410053},"GB2-08":{"attempts":1,"playable":32.80457377566549,"score":32.80457377566549}}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-10-24T16:59:02Z","match_totals_all":{"draws":2197,"losses":3838,"wins":1131},"match_totals_tracks":{"medium":{"draws":1250,"losses":2003,"wins":835},"none":{"draws":947,"losses":1835,"wins":296}},"model_slug":"google-gemma-4-31b-it","official_rank_by_reasoning":{"medium":56,"none":80},"overall":{"max":72.04145723140032,"mean":29.20935420931343,"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":128,"losses":344,"wins":44},"GB2-02":{"draws":739,"losses":206,"wins":15},"GB2-03":{"draws":114,"losses":239,"wins":141},"GB2-04":{"draws":630,"losses":253,"wins":113},"GB2-05":{"draws":0,"losses":603,"wins":457},"GB2-06":{"draws":37,"losses":794,"wins":173},"GB2-07":{"draws":0,"losses":927,"wins":133},"GB2-08":{"draws":549,"losses":472,"wins":55}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":128,"losses":344,"wins":44},"GB2-02":{"draws":377,"losses":91,"wins":12},"GB2-03":{"draws":114,"losses":239,"wins":141},"GB2-04":{"draws":323,"losses":129,"wins":46},"GB2-05":{"draws":0,"losses":157,"wins":373},"GB2-06":{"draws":35,"losses":364,"wins":103},"GB2-07":{"draws":0,"losses":444,"wins":86},"GB2-08":{"draws":273,"losses":235,"wins":30}},"none":{"GB2-02":{"draws":362,"losses":115,"wins":3},"GB2-04":{"draws":307,"losses":124,"wins":67},"GB2-05":{"draws":0,"losses":446,"wins":84},"GB2-06":{"draws":2,"losses":430,"wins":70},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":276,"losses":237,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1183.4189798925327,"GB2-02":1421.2111409365534,"GB2-03":1374.3133568292085,"GB2-04":1423.4034254659787,"GB2-05":1747.9731360100175,"GB2-06":1083.4513115071045,"GB2-07":1012.1098294098201,"GB2-08":1217.0472928329903},"none":{"GB2-02":1393.9896308290422,"GB2-04":1443.888317525916,"GB2-05":949.4011314234622,"GB2-06":905.2617500976444,"GB2-07":843.0918174390963,"GB2-08":1209.7601144938835}},"per_game_tracks":{"medium":{"GB2-01":22.403408740786293,"GB2-02":43.44746737727414,"GB2-03":43.90141136154609,"GB2-04":43.32443299908194,"GB2-05":72.04145723140032,"GB2-06":27.816729209054365,"GB2-07":18.253293321990967,"GB2-08":33.496285064738274},"none":{"GB2-02":39.95438417221496,"GB2-04":45.9732547222497,"GB2-05":16.819909119547248,"GB2-06":16.759941502055096,"GB2-07":10.353118751410053,"GB2-08":32.80457377566549}},"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":38.08556066323405,"none":20.33314775539282},"reasoning_agg":{"medium":{"max":72.04145723140032,"mean":38.08556066323405,"min":18.253293321990967},"none":{"max":45.9732547222497,"mean":20.33314775539282,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":17.75241290784123},"working_program_strength":{"all":32.59821216854557,"medium":38.08556066323405,"none":27.110863673857093}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:9f72a9701d980346","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":28.17251369544792,"medium":26.866808280302557,"none":29.47821911059328},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meituan","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"model_code_failures":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.1875},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":2,"playable":42.647507554892826,"score":21.323753777446413},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":41.80742691919289,"score":20.903713459596446},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":37.14136375484313,"score":27.18747246751937},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":42.256731640882776,"score":30.68712696394391},"GB2-05":{"attempts":4,"playable":22.741973534316713,"score":22.741973534316713},"GB2-06":{"attempts":4,"playable":31.074622289547207,"score":31.074622289547207},"GB2-07":{"attempts":4,"playable":36.35625119190289,"score":36.35625119190289},"GB2-08":{"attempts":4,"playable":35.10519587931041,"score":35.10519587931041}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.13042986233988,"score":21.56521493116994},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.815565149295026,"score":19.907782574647513},"GB2-04":{"attempts":2,"playable":38.235044574010104,"score":38.235044574010104},"GB2-05":{"attempts":2,"playable":33.36694820961766,"score":33.36694820961766},"GB2-06":{"attempts":2,"playable":24.999952266061957,"score":24.999952266061957},"GB2-07":{"attempts":2,"playable":37.72096537992307,"score":37.72096537992307},"GB2-08":{"attempts":2,"playable":39.13855830699021,"score":39.13855830699021}},"none":{"GB2-01":{"attempts":2,"playable":42.647507554892826,"score":42.647507554892826},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.4844239760459,"score":20.24221198802295},"GB2-03":{"attempts":2,"playable":34.46716236039123,"score":34.46716236039123},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":46.27841870775544,"score":23.13920935387772},"GB2-05":{"attempts":2,"playable":12.116998859015762,"score":12.116998859015762},"GB2-06":{"attempts":2,"playable":37.149292313032454,"score":37.149292313032454},"GB2-07":{"attempts":2,"playable":34.99153700388271,"score":34.99153700388271},"GB2-08":{"attempts":2,"playable":31.071833451630603,"score":31.071833451630603}}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-10-24T19:17:03Z","match_totals_all":{"draws":2911,"losses":7602,"wins":2854},"match_totals_tracks":{"medium":{"draws":1327,"losses":3434,"wins":1408},"none":{"draws":1584,"losses":4168,"wins":1446}},"model_slug":"meituan-longcat-2-0","official_rank_by_reasoning":{"medium":70,"none":66},"overall":{"max":42.647507554892826,"mean":28.17251369544792,"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":247,"losses":489,"wins":296},"GB2-02":{"draws":765,"losses":192,"wins":3},"GB2-03":{"draws":439,"losses":777,"wins":266},"GB2-04":{"draws":834,"losses":489,"wins":170},"GB2-05":{"draws":0,"losses":1661,"wins":459},"GB2-06":{"draws":74,"losses":1424,"wins":510},"GB2-07":{"draws":0,"losses":1396,"wins":724},"GB2-08":{"draws":552,"losses":1174,"wins":426}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":394,"losses":84,"wins":2},"GB2-03":{"draws":149,"losses":241,"wins":104},"GB2-04":{"draws":548,"losses":356,"wins":91},"GB2-05":{"draws":0,"losses":720,"wins":340},"GB2-06":{"draws":33,"losses":772,"wins":199},"GB2-07":{"draws":0,"losses":680,"wins":380},"GB2-08":{"draws":203,"losses":581,"wins":292}},"none":{"GB2-01":{"draws":247,"losses":489,"wins":296},"GB2-02":{"draws":371,"losses":108,"wins":1},"GB2-03":{"draws":290,"losses":536,"wins":162},"GB2-04":{"draws":286,"losses":133,"wins":79},"GB2-05":{"draws":0,"losses":941,"wins":119},"GB2-06":{"draws":41,"losses":652,"wins":311},"GB2-07":{"draws":0,"losses":716,"wins":344},"GB2-08":{"draws":349,"losses":593,"wins":134}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1418.7557351959765,"GB2-03":1338.7688408115014,"GB2-04":1383.234586855719,"GB2-05":1191.3833672837327,"GB2-06":1039.7096396913685,"GB2-07":1262.3386353125575,"GB2-08":1280.7409984433525},"none":{"GB2-01":1398.9451634376796,"GB2-02":1398.1489552681644,"GB2-03":1289.653995307851,"GB2-04":1446.2433969698104,"GB2-05":844.2007383860841,"GB2-06":1224.4480027846525,"GB2-07":1257.3873300275234,"GB2-08":1191.0820122150558}},"per_game_tracks":{"medium":{"GB2-02":43.13042986233988,"GB2-03":39.815565149295026,"GB2-04":38.235044574010104,"GB2-05":33.36694820961766,"GB2-06":24.999952266061957,"GB2-07":37.72096537992307,"GB2-08":39.13855830699021},"none":{"GB2-01":42.647507554892826,"GB2-02":40.4844239760459,"GB2-03":34.46716236039123,"GB2-04":46.27841870775544,"GB2-05":12.116998859015762,"GB2-06":37.149292313032454,"GB2-07":34.99153700388271,"GB2-08":31.071833451630603}},"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":26.866808280302553,"none":29.47821911059328},"reasoning_agg":{"medium":{"max":39.13855830699021,"mean":26.866808280302553,"min":0.0},"none":{"max":42.647507554892826,"mean":29.47821911059328,"min":12.116998859015762}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":2.611410830290726},"working_program_strength":{"all":35.765267228325285,"medium":36.629637678319696,"none":34.90089677833087}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:fdaffbd8b87d25c5","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":0.20304798000000004}},"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":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"all":26.674205086779274,"medium":23.04952020711777,"none":30.298889966440775},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"total_output_tokens":596080},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":38.65646615133419,"score":38.65646615133419},"GB2-02":{"attempts":2,"playable":39.63622451071189,"score":39.63622451071189},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.92088247893277,"score":19.960441239466384},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.361817502287046,"score":20.180908751143523},"GB2-05":{"attempts":2,"playable":15.450454915918773,"score":15.450454915918773},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.873901808935734,"score":8.436950904467867},"GB2-07":{"attempts":2,"playable":33.004271496109055,"score":33.004271496109055},"GB2-08":{"attempts":2,"playable":38.06792272508248,"score":38.06792272508248}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.574566237086078,"score":18.574566237086078},"GB2-02":{"attempts":1,"playable":39.53015690135886,"score":39.53015690135886},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.361817502287046,"score":40.361817502287046},"GB2-05":{"attempts":1,"playable":2.167961594572618,"score":2.167961594572618},"GB2-06":{"attempts":1,"playable":16.873901808935734,"score":16.873901808935734},"GB2-07":{"attempts":1,"playable":42.403410919421944,"score":42.403410919421944},"GB2-08":{"attempts":1,"playable":24.484346693279885,"score":24.484346693279885}},"none":{"GB2-01":{"attempts":1,"playable":58.738366065582305,"score":58.738366065582305},"GB2-02":{"attempts":1,"playable":39.742292120064924,"score":39.742292120064924},"GB2-03":{"attempts":1,"playable":39.92088247893277,"score":39.92088247893277},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":28.732948237264928,"score":28.732948237264928},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.605132072796174,"score":23.605132072796174},"GB2-08":{"attempts":1,"playable":51.651498756885076,"score":51.651498756885076}}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-10-24T18:11:47Z","match_totals_all":{"draws":1374,"losses":3947,"wins":1361},"match_totals_tracks":{"medium":{"draws":807,"losses":2315,"wins":472},"none":{"draws":567,"losses":1632,"wins":889}},"model_slug":"minimax-minimax-m3","official_rank_by_reasoning":{"medium":74,"none":63},"overall":{"max":58.738366065582305,"mean":26.674205086779274,"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":599,"wins":329},"GB2-02":{"draws":722,"losses":234,"wins":4},"GB2-03":{"draws":104,"losses":263,"wins":127},"GB2-04":{"draws":320,"losses":145,"wins":33},"GB2-05":{"draws":0,"losses":906,"wins":154},"GB2-06":{"draws":3,"losses":429,"wins":70},"GB2-07":{"draws":0,"losses":736,"wins":324},"GB2-08":{"draws":121,"losses":635,"wins":320}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":22,"losses":416,"wins":78},"GB2-02":{"draws":362,"losses":117,"wins":1},"GB2-04":{"draws":320,"losses":145,"wins":33},"GB2-05":{"draws":0,"losses":522,"wins":8},"GB2-06":{"draws":3,"losses":429,"wins":70},"GB2-07":{"draws":0,"losses":319,"wins":211},"GB2-08":{"draws":100,"losses":367,"wins":71}},"none":{"GB2-01":{"draws":82,"losses":183,"wins":251},"GB2-02":{"draws":360,"losses":117,"wins":3},"GB2-03":{"draws":104,"losses":263,"wins":127},"GB2-05":{"draws":0,"losses":384,"wins":146},"GB2-07":{"draws":0,"losses":417,"wins":113},"GB2-08":{"draws":21,"losses":268,"wins":249}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1132.1868015924906,"GB2-02":1390.6512891910147,"GB2-04":1400.2917235707478,"GB2-05":441.62025707446764,"GB2-06":907.2818109412686,"GB2-07":1352.8604484767263,"GB2-08":1118.5109614364317},"none":{"GB2-01":1553.4149889714995,"GB2-02":1392.321711106902,"GB2-03":1339.6898828621593,"GB2-05":1154.5727727217238,"GB2-07":1100.5094422419518,"GB2-08":1413.5469148754805}},"per_game_tracks":{"medium":{"GB2-01":18.574566237086078,"GB2-02":39.53015690135886,"GB2-04":40.361817502287046,"GB2-05":2.167961594572618,"GB2-06":16.873901808935734,"GB2-07":42.403410919421944,"GB2-08":24.484346693279885},"none":{"GB2-01":58.738366065582305,"GB2-02":39.742292120064924,"GB2-03":39.92088247893277,"GB2-05":28.732948237264928,"GB2-07":23.605132072796174,"GB2-08":51.651498756885076}},"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":23.04952020711777,"none":30.298889966440772},"reasoning_agg":{"medium":{"max":42.403410919421944,"mean":23.04952020711777,"min":0.0},"none":{"max":58.738366065582305,"mean":30.298889966440772,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":7.249369759323002},"working_program_strength":{"all":33.37041438169448,"medium":26.342308808134593,"none":40.398519955254365}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:4d67cb8dc5f7cc0b","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.81977125},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.81977125},"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":2.5860279999999998}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.40579925},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"all":26.204193432007465,"medium":15.757129931163199,"none":36.65125693285173},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":53,"finish_reasons":["length","stop"],"indexed_attempts":53,"output_token_observations":53,"total_output_tokens":2639964},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":6,"failed_game_aliases":["GB2-04"],"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02"],"infra_failures_excluded":2,"model_code_failure_rate":0.16666666666666666,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":7,"evaluated_cells":7,"game_attempts":{"GB2-01":{"infra_failures_excluded":2},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":1,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":9,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":7,"repaired_rate":1.0}},"headline_games_all":{"GB2-02":{"attempts":1,"playable":36.44948099041644,"score":36.44948099041644},"GB2-03":{"attempts":2,"playable":33.27921064978822,"score":33.27921064978822},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.20166110289975,"score":21.100830551449874},"GB2-05":{"attempts":2,"playable":21.052784275983747,"score":21.052784275983747},"GB2-06":{"attempts":2,"playable":12.975758685951973,"score":12.975758685951973},"GB2-07":{"attempts":2,"playable":44.20867605640553,"score":44.20867605640553},"GB2-08":{"attempts":2,"playable":24.708788343683096,"score":24.708788343683096}},"headline_games_tracks":{"medium":{"GB2-03":{"attempts":1,"playable":31.40522959129578,"score":31.40522959129578},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":11.445973927608172,"score":11.445973927608172},"GB2-06":{"attempts":1,"playable":15.61842087884419,"score":15.61842087884419},"GB2-07":{"attempts":1,"playable":23.801732956964443,"score":23.801732956964443},"GB2-08":{"attempts":1,"playable":12.271422232266604,"score":12.271422232266604}},"none":{"GB2-02":{"attempts":1,"playable":36.44948099041644,"score":36.44948099041644},"GB2-03":{"attempts":1,"playable":35.15319170828066,"score":35.15319170828066},"GB2-04":{"attempts":1,"playable":42.20166110289975,"score":42.20166110289975},"GB2-05":{"attempts":1,"playable":30.659594624359322,"score":30.659594624359322},"GB2-06":{"attempts":1,"playable":10.333096493059756,"score":10.333096493059756},"GB2-07":{"attempts":1,"playable":64.61561915584662,"score":64.61561915584662},"GB2-08":{"attempts":1,"playable":37.14615445509959,"score":37.14615445509959}}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-10-24T18:46:15Z","match_totals_all":{"draws":1379,"losses":3799,"wins":988},"match_totals_tracks":{"medium":{"draws":221,"losses":2049,"wins":324},"none":{"draws":1158,"losses":1750,"wins":664}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":64.61561915584662,"mean":26.204193432007465,"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":323,"losses":151,"wins":6},"GB2-03":{"draws":401,"losses":492,"wins":95},"GB2-04":{"draws":360,"losses":116,"wins":22},"GB2-05":{"draws":0,"losses":848,"wins":212},"GB2-06":{"draws":24,"losses":883,"wins":97},"GB2-07":{"draws":0,"losses":613,"wins":447},"GB2-08":{"draws":271,"losses":696,"wins":109}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":162,"losses":274,"wins":58},"GB2-05":{"draws":0,"losses":474,"wins":56},"GB2-06":{"draws":18,"losses":427,"wins":57},"GB2-07":{"draws":0,"losses":416,"wins":114},"GB2-08":{"draws":41,"losses":458,"wins":39}},"none":{"GB2-02":{"draws":323,"losses":151,"wins":6},"GB2-03":{"draws":239,"losses":218,"wins":37},"GB2-04":{"draws":360,"losses":116,"wins":22},"GB2-05":{"draws":0,"losses":374,"wins":156},"GB2-06":{"draws":6,"losses":456,"wins":40},"GB2-07":{"draws":0,"losses":197,"wins":333},"GB2-08":{"draws":230,"losses":238,"wins":70}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1263.0670223291327,"GB2-05":830.8461080899681,"GB2-06":884.6499202102941,"GB2-07":1103.5240441878334,"GB2-08":948.1510710164554},"none":{"GB2-02":1366.1022378418945,"GB2-03":1297.4618367609612,"GB2-04":1414.6782624415446,"GB2-05":1183.3282047925616,"GB2-06":775.8579207733708,"GB2-07":1638.8206444045527,"GB2-08":1255.2553655614633}},"per_game_tracks":{"medium":{"GB2-03":31.40522959129578,"GB2-05":11.445973927608172,"GB2-06":15.61842087884419,"GB2-07":23.801732956964443,"GB2-08":12.271422232266604},"none":{"GB2-02":36.44948099041644,"GB2-03":35.15319170828066,"GB2-04":42.20166110289975,"GB2-05":30.659594624359322,"GB2-06":10.333096493059756,"GB2-07":64.61561915584662,"GB2-08":37.14615445509959}},"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":15.7571299311632,"none":36.65125693285173},"reasoning_agg":{"medium":{"max":31.40522959129578,"mean":15.7571299311632,"min":0.0},"none":{"max":64.61561915584662,"mean":36.65125693285173,"min":10.333096493059756}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":20.89412700168853},"working_program_strength":{"all":27.779906425123784,"medium":18.908555917395837,"none":36.65125693285173}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:fc6a8f8c064e1320","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":1.3975426639832813},"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":0.5409853360167188}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167187},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.3975426639832813}},"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":26.060170280890354,"highest":29.061807197788475,"none":23.058533363992233},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[209715],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":34,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[209715],"total_output_tokens":220326,"total_visible_output_tokens":220326,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":209715,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":12.087370960602446,"score":6.043685480301223},"GB2-02":{"attempts":2,"playable":42.70624369966712,"score":42.70624369966712},"GB2-03":{"attempts":2,"playable":36.05476786660195,"score":36.05476786660195},"GB2-04":{"attempts":2,"playable":36.82300892052211,"score":36.82300892052211},"GB2-05":{"attempts":2,"playable":25.09910886488914,"score":25.09910886488914},"GB2-06":{"attempts":2,"playable":22.19731433544358,"score":22.19731433544358},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":13.01136678591397,"score":6.505683392956985},"GB2-08":{"attempts":2,"playable":33.05154968674074,"score":33.05154968674074}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.292378610126704,"score":44.292378610126704},"GB2-03":{"attempts":1,"playable":37.70317178904868,"score":37.70317178904868},"GB2-04":{"attempts":1,"playable":39.95254142394899,"score":39.95254142394899},"GB2-05":{"attempts":1,"playable":37.215882531026224,"score":37.215882531026224},"GB2-06":{"attempts":1,"playable":26.724043117175718,"score":26.724043117175718},"GB2-07":{"attempts":1,"playable":13.01136678591397,"score":13.01136678591397},"GB2-08":{"attempts":1,"playable":33.595073325067546,"score":33.595073325067546}},"none":{"GB2-01":{"attempts":1,"playable":12.087370960602446,"score":12.087370960602446},"GB2-02":{"attempts":1,"playable":41.120108789207535,"score":41.120108789207535},"GB2-03":{"attempts":1,"playable":34.40636394415522,"score":34.40636394415522},"GB2-04":{"attempts":1,"playable":33.69347641709523,"score":33.69347641709523},"GB2-05":{"attempts":1,"playable":12.982335198752054,"score":12.982335198752054},"GB2-06":{"attempts":1,"playable":17.670585553711437,"score":17.670585553711437},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":32.50802604841393,"score":32.50802604841393}}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-10-24T19:13:49Z","match_totals_all":{"draws":2094,"losses":4126,"wins":910},"match_totals_tracks":{"highest":{"draws":1107,"losses":1922,"wins":543},"none":{"draws":987,"losses":2204,"wins":367}},"model_slug":"mistralai-mistral-medium-3-5","official_rank_by_reasoning":{"highest":60,"none":79},"overall":{"max":44.292378610126704,"mean":26.060170280890354,"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":44.292378610126704,"GB2-03":37.70317178904868,"GB2-04":39.95254142394899,"GB2-05":37.215882531026224,"GB2-06":26.724043117175718,"GB2-07":13.01136678591397,"GB2-08":33.595073325067546},"per_game_match_totals_all":{"GB2-01":{"draws":46,"losses":436,"wins":34},"GB2-02":{"draws":748,"losses":192,"wins":20},"GB2-03":{"draws":239,"losses":547,"wins":202},"GB2-04":{"draws":557,"losses":366,"wins":73},"GB2-05":{"draws":0,"losses":806,"wins":254},"GB2-06":{"draws":17,"losses":805,"wins":182},"GB2-07":{"draws":0,"losses":470,"wins":60},"GB2-08":{"draws":487,"losses":504,"wins":85}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":371,"losses":90,"wins":19},"GB2-03":{"draws":129,"losses":261,"wins":104},"GB2-04":{"draws":326,"losses":144,"wins":28},"GB2-05":{"draws":0,"losses":340,"wins":190},"GB2-06":{"draws":15,"losses":379,"wins":108},"GB2-07":{"draws":0,"losses":470,"wins":60},"GB2-08":{"draws":266,"losses":238,"wins":34}},"none":{"GB2-01":{"draws":46,"losses":436,"wins":34},"GB2-02":{"draws":377,"losses":102,"wins":1},"GB2-03":{"draws":110,"losses":286,"wins":98},"GB2-04":{"draws":231,"losses":222,"wins":45},"GB2-05":{"draws":0,"losses":466,"wins":64},"GB2-06":{"draws":2,"losses":426,"wins":74},"GB2-08":{"draws":221,"losses":266,"wins":51}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1427.744890697309,"GB2-03":1320.2007281746523,"GB2-04":1397.072709325324,"GB2-05":1274.9158331239694,"GB2-06":1066.7659235755764,"GB2-07":907.6803471673223,"GB2-08":1218.0861949364878},"none":{"GB2-01":1025.5730685378435,"GB2-02":1403.1216555505632,"GB2-03":1290.7138029156201,"GB2-04":1346.529795049037,"GB2-05":867.5662375814271,"GB2-06":921.2330254726182,"GB2-08":1206.6283471785423}},"per_game_tracks":{"highest":{"GB2-02":44.292378610126704,"GB2-03":37.70317178904868,"GB2-04":39.95254142394899,"GB2-05":37.215882531026224,"GB2-06":26.724043117175718,"GB2-07":13.01136678591397,"GB2-08":33.595073325067546},"none":{"GB2-01":12.087370960602446,"GB2-02":41.120108789207535,"GB2-03":34.40636394415522,"GB2-04":33.69347641709523,"GB2-05":12.982335198752054,"GB2-06":17.670585553711437,"GB2-08":32.50802604841393}},"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":29.061807197788475,"none":23.058533363992233},"reasoning_agg":{"highest":{"max":44.292378610126704,"mean":29.061807197788475,"min":0.0},"none":{"max":41.120108789207535,"mean":23.058533363992233,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":6.003273833796243},"working_program_strength":{"all":29.783051749588974,"highest":33.213493940329684,"none":26.352609558848265}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:ea2d2c42e42a55cb","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":0.43500896000000006},"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":0.08145696}},"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":0.43500896000000006},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.5164659199999999},"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":25.70723746440848,"medium":33.24164418362844,"none":18.172830745188516},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"total_output_tokens":343242},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":6,"evaluated_cells":9,"failed_game_aliases":["GB2-01","GB2-03","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.3333333333333333,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":34.960008884026806,"score":30.215408197345457},"GB2-02":{"attempts":2,"playable":40.85248093604908,"score":40.85248093604908},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.44762878899899,"score":21.723814394499495},"GB2-05":{"attempts":2,"playable":38.080876360805526,"score":38.080876360805526},"GB2-06":{"attempts":2,"playable":42.497225014828985,"score":42.497225014828985},"GB2-07":{"attempts":2,"playable":16.132947059816203,"score":16.132947059816203},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":32.310295503846106,"score":16.155147751923053}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":50.94161502132821,"score":50.94161502132821},"GB2-02":{"attempts":1,"playable":43.236120798340494,"score":43.236120798340494},"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":43.96004079359951,"score":43.96004079359951},"GB2-06":{"attempts":1,"playable":71.09420226923116,"score":71.09420226923116},"GB2-07":{"attempts":1,"playable":24.390879082681977,"score":24.390879082681977},"GB2-08":{"attempts":1,"playable":32.310295503846106,"score":32.310295503846106}},"none":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":18.978402746725408,"score":9.489201373362704},"GB2-02":{"attempts":1,"playable":38.46884107375767,"score":38.46884107375767},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.44762878899899,"score":43.44762878899899},"GB2-05":{"attempts":1,"playable":32.20171192801154,"score":32.20171192801154},"GB2-06":{"attempts":1,"playable":13.900247760426804,"score":13.900247760426804},"GB2-07":{"attempts":1,"playable":7.875015036950432,"score":7.875015036950432},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-10-24T19:17:41Z","match_totals_all":{"draws":1549,"losses":3347,"wins":1255},"match_totals_tracks":{"medium":{"draws":754,"losses":1423,"wins":919},"none":{"draws":795,"losses":1924,"wins":336}},"model_slug":"qwen-qwen3-7-plus","official_rank_by_reasoning":{"medium":63,"none":83},"overall":{"max":71.09420226923116,"mean":25.70723746440848,"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":196,"losses":591,"wins":245},"GB2-02":{"draws":739,"losses":214,"wins":7},"GB2-04":{"draws":334,"losses":122,"wins":41},"GB2-05":{"draws":0,"losses":671,"wins":389},"GB2-06":{"draws":27,"losses":590,"wins":387},"GB2-07":{"draws":0,"losses":908,"wins":152},"GB2-08":{"draws":253,"losses":251,"wins":34}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":88,"losses":220,"wins":208},"GB2-02":{"draws":391,"losses":85,"wins":4},"GB2-05":{"draws":0,"losses":305,"wins":225},"GB2-06":{"draws":22,"losses":149,"wins":331},"GB2-07":{"draws":0,"losses":413,"wins":117},"GB2-08":{"draws":253,"losses":251,"wins":34}},"none":{"GB2-01":{"draws":108,"losses":371,"wins":37},"GB2-02":{"draws":348,"losses":129,"wins":3},"GB2-04":{"draws":334,"losses":122,"wins":41},"GB2-05":{"draws":0,"losses":366,"wins":164},"GB2-06":{"draws":5,"losses":441,"wins":56},"GB2-07":{"draws":0,"losses":495,"wins":35}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1478.0075609035503,"GB2-02":1419.5745480878245,"GB2-05":1362.052761981763,"GB2-06":1774.3553814409877,"GB2-07":1112.478014882974,"GB2-08":1204.5373358694924},"none":{"GB2-01":1137.8938596925523,"GB2-02":1382.2590673984803,"GB2-04":1424.3588333274831,"GB2-05":1205.6825892177453,"GB2-06":852.0966644625689,"GB2-07":770.7458022294192}},"per_game_tracks":{"medium":{"GB2-01":50.94161502132821,"GB2-02":43.236120798340494,"GB2-05":43.96004079359951,"GB2-06":71.09420226923116,"GB2-07":24.390879082681977,"GB2-08":32.310295503846106},"none":{"GB2-01":18.978402746725408,"GB2-02":38.46884107375767,"GB2-04":43.44762878899899,"GB2-05":32.20171192801154,"GB2-06":13.900247760426804,"GB2-07":7.875015036950432}},"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":33.24164418362844,"none":18.172830745188516},"reasoning_agg":{"medium":{"max":71.09420226923116,"mean":33.24164418362844,"min":0.0},"none":{"max":43.44762878899899,"mean":18.172830745188516,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":15.068813438439921},"working_program_strength":{"all":35.06708340032486,"medium":44.322192244837915,"none":25.811974555811805}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:27453f470337f222","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":24.45483203401151,"medium":30.368678586750253,"none":18.540985481272763},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[32768],"finish_reason_observations":96,"finish_reasons":["length","stop","unknown"],"indexed_attempts":98,"output_token_observations":97,"provider_post_attempt_observations":4,"provider_post_attempts":5,"reasoning_token_observations":69,"reconciliation_get_attempt_observations":4,"requested_max_output_token_observations":4,"requested_max_output_tokens":[32768],"total_output_tokens":1115800,"total_reasoning_output_tokens":656294,"total_visible_output_tokens":120852,"visible_token_observations":59},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":6,"first_pass_admitted":1,"first_pass_rate":0.16666666666666666,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"infra_failures_excluded":2}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":10,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":11,"evaluated_cells":17,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.4117647058823529,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"model_code_failures":2},"GB2-06":{"admitted":2},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.35294117647058826,"model_code_failures":6,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.23529411764705882}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":27.574818810624784,"score":27.574818810624784},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":38.945599729484684,"score":28.8509902595682},"GB2-03":{"attempts":2,"playable":28.90457849496353,"score":28.90457849496353},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.30114179701823,"score":31.138706254496366},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":14.156679309559589,"score":14.156679309559589},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":35.9765330120497,"score":17.98826650602485},"GB2-08":{"attempts":3,"playable":31.847776008422244,"score":31.847776008422244}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":19.48293114318705,"score":19.48293114318705},"GB2-02":{"attempts":1,"playable":37.51276157930343,"score":37.51276157930343},"GB2-04":{"attempts":1,"playable":39.95254142394899,"score":39.95254142394899},"GB2-06":{"attempts":1,"playable":18.918625775262086,"score":18.918625775262086},"GB2-07":{"attempts":2,"playable":35.9765330120497,"score":35.9765330120497}},"none":{"GB2-01":{"attempts":2,"playable":35.66670647806252,"score":35.66670647806252},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.378437879665945,"score":20.189218939832973},"GB2-03":{"attempts":2,"playable":28.90457849496353,"score":28.90457849496353},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.64974217008748,"score":22.32487108504374},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":9.394732843857092,"score":9.394732843857092},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":3,"playable":31.847776008422244,"score":31.847776008422244}}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T18:55:41Z","match_totals_all":{"draws":2731,"losses":4859,"wins":1082},"match_totals_tracks":{"medium":{"draws":809,"losses":1760,"wins":487},"none":{"draws":1922,"losses":3099,"wins":595}},"model_slug":"inclusionai-ling-3-0-flash","official_rank_by_reasoning":{"none":82},"overall":{"max":39.95254142394899,"mean":24.45483203401151,"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":323,"losses":944,"wins":281},"GB2-02":{"draws":705,"losses":249,"wins":6},"GB2-03":{"draws":306,"losses":580,"wins":102},"GB2-04":{"draws":698,"losses":242,"wins":56},"GB2-06":{"draws":8,"losses":1344,"wins":154},"GB2-07":{"draws":0,"losses":706,"wins":354},"GB2-08":{"draws":691,"losses":794,"wins":129}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":129,"losses":358,"wins":29},"GB2-02":{"draws":337,"losses":139,"wins":4},"GB2-04":{"draws":340,"losses":137,"wins":21},"GB2-06":{"draws":3,"losses":420,"wins":79},"GB2-07":{"draws":0,"losses":706,"wins":354}},"none":{"GB2-01":{"draws":194,"losses":586,"wins":252},"GB2-02":{"draws":368,"losses":110,"wins":2},"GB2-03":{"draws":306,"losses":580,"wins":102},"GB2-04":{"draws":358,"losses":105,"wins":35},"GB2-06":{"draws":5,"losses":924,"wins":75},"GB2-08":{"draws":691,"losses":794,"wins":129}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1144.9126412456255,"GB2-02":1374.6432237877098,"GB2-04":1397.072709325324,"GB2-06":942.552164744418,"GB2-07":1271.537802396807},"none":{"GB2-01":1329.168789362865,"GB2-02":1397.3182518743386,"GB2-03":1237.9246262662796,"GB2-04":1433.6655133378151,"GB2-06":626.8127206423987,"GB2-08":1195.2496496803114}},"per_game_tracks":{"medium":{"GB2-01":19.48293114318705,"GB2-02":37.51276157930343,"GB2-04":39.95254142394899,"GB2-06":18.918625775262086,"GB2-07":35.9765330120497},"none":{"GB2-01":35.66670647806252,"GB2-02":40.378437879665945,"GB2-03":28.90457849496353,"GB2-04":44.64974217008748,"GB2-06":9.394732843857092,"GB2-08":31.847776008422244}},"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":30.368678586750253,"none":18.540985481272763},"reasoning_agg":{"medium":{"max":39.95254142394899,"mean":30.368678586750253,"min":18.918625775262086},"none":{"max":35.66670647806252,"mean":18.540985481272763,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":11.82769310547749},"working_program_strength":{"all":31.087837116296697,"medium":30.368678586750253,"none":31.80699564584314}},{"canonical_public_row_identity":"publication-row.v1:overall:recursive-flint-v1-0:4c67da8b97724824","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":23.61425400614099,"medium":23.61425400614099},"first_seen_at":null,"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":44.7636805125865,"score":44.7636805125865},"GB2-02":{"attempts":1,"playable":35.06573160569595,"score":35.06573160569595},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.74784711761999,"score":39.74784711761999},"GB2-05":{"attempts":1,"playable":13.942038727726402,"score":13.942038727726402},"GB2-06":{"attempts":1,"playable":16.98782575319495,"score":16.98782575319495},"GB2-07":{"attempts":1,"playable":10.353118751410053,"score":10.353118751410053},"GB2-08":{"attempts":1,"playable":28.05378958089407,"score":28.05378958089407}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":44.7636805125865,"score":44.7636805125865},"GB2-02":{"attempts":1,"playable":35.06573160569595,"score":35.06573160569595},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.74784711761999,"score":39.74784711761999},"GB2-05":{"attempts":1,"playable":13.942038727726402,"score":13.942038727726402},"GB2-06":{"attempts":1,"playable":16.98782575319495,"score":16.98782575319495},"GB2-07":{"attempts":1,"playable":10.353118751410053,"score":10.353118751410053},"GB2-08":{"attempts":1,"playable":28.05378958089407,"score":28.05378958089407}}},"id":"recursive/flint-v1.0","is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","match_totals_all":{"draws":733,"losses":2329,"wins":532},"match_totals_tracks":{"medium":{"draws":733,"losses":2329,"wins":532}},"model_slug":"recursive-flint-v1-0","official_rank_by_reasoning":{"medium":72},"overall":{"max":44.7636805125865,"mean":23.61425400614099,"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":75,"losses":258,"wins":183},"GB2-02":{"draws":322,"losses":158,"wins":0},"GB2-04":{"draws":334,"losses":141,"wins":23},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":2,"losses":429,"wins":71},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":0,"losses":399,"wins":139}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":75,"losses":258,"wins":183},"GB2-02":{"draws":322,"losses":158,"wins":0},"GB2-04":{"draws":334,"losses":141,"wins":23},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":2,"losses":429,"wins":71},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":0,"losses":399,"wins":139}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1419.2083549585993,"GB2-02":1354.857872981993,"GB2-04":1395.459827854828,"GB2-05":889.1906093489134,"GB2-06":909.2948893863331,"GB2-07":843.0918174390963,"GB2-08":1158.7410791882703}},"per_game_tracks":{"medium":{"GB2-01":44.7636805125865,"GB2-02":35.06573160569595,"GB2-04":39.74784711761999,"GB2-05":13.942038727726402,"GB2-06":16.98782575319495,"GB2-07":10.353118751410053,"GB2-08":28.05378958089407}},"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":23.61425400614099},"reasoning_agg":{"medium":{"max":44.7636805125865,"mean":23.61425400614099,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":26.98771886416113,"medium":26.98771886416113}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-5-pro:fccb1b6c33bebb4e","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":0.033157215}},"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":0.033157215},"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":19.63537348088722,"highest":20.638949562841088,"none":18.631797398933355},"first_seen_at":null,"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":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","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":37.51276157930343,"score":37.51276157930343},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":45.87578936897378,"score":22.93789468448689},"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":38.05858818646358,"score":38.05858818646358},"GB2-08":{"attempts":1,"playable":30.826550995944636,"score":30.826550995944636}},"headline_games_tracks":{"highest":{"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":41.277899125682175,"score":41.277899125682175}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":37.51276157930343,"score":37.51276157930343},"GB2-03":{"attempts":1,"playable":45.87578936897378,"score":45.87578936897378},"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":34.839277247244986,"score":34.839277247244986},"GB2-08":{"attempts":1,"playable":30.826550995944636,"score":30.826550995944636}}},"id":"nex-agi/nex-n2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-24T14:00:28Z","match_totals_all":{"draws":498,"losses":1414,"wins":660},"match_totals_tracks":{"highest":{"draws":0,"losses":325,"wins":205},"none":{"draws":498,"losses":1089,"wins":455}},"model_slug":"nex-agi-nex-n2-5-pro","overall":{"max":45.87578936897378,"mean":19.63537348088722,"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":41.277899125682175},"per_game_match_totals_all":{"GB2-02":{"draws":341,"losses":137,"wins":2},"GB2-03":{"draws":157,"losses":208,"wins":129},"GB2-07":{"draws":0,"losses":684,"wins":376},"GB2-08":{"draws":0,"losses":385,"wins":153}},"per_game_match_totals_tracks":{"highest":{"GB2-07":{"draws":0,"losses":325,"wins":205}},"none":{"GB2-02":{"draws":341,"losses":137,"wins":2},"GB2-03":{"draws":157,"losses":208,"wins":129},"GB2-07":{"draws":0,"losses":359,"wins":171},"GB2-08":{"draws":0,"losses":385,"wins":153}}},"per_game_raw_elo_tracks":{"highest":{"GB2-07":1338.8167935288445},"none":{"GB2-02":1374.6432237877098,"GB2-03":1391.4453702850296,"GB2-07":1257.1188990691503,"GB2-08":1188.762105957729}},"per_game_tracks":{"highest":{"GB2-07":41.277899125682175},"none":{"GB2-02":37.51276157930343,"GB2-03":45.87578936897378,"GB2-07":34.839277247244986,"GB2-08":30.826550995944636}},"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":20.638949562841088,"none":18.631797398933355},"reasoning_agg":{"highest":{"max":41.277899125682175,"mean":20.638949562841088,"min":0.0},"none":{"max":45.87578936897378,"mean":18.631797398933355,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":2.007152163907733},"working_program_strength":{"all":39.27074696177444,"highest":41.277899125682175,"none":37.26359479786671}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:6e98d5379eb035a9","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":15.084876593448286,"medium":23.466221320985,"none":6.70353186591157},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[64000],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":15,"provider_post_attempts":15,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[64000],"total_output_tokens":270044,"total_visible_output_tokens":29197,"visible_token_observations":15},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":21.941252683309312,"score":10.970626341654656},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.17991362597097,"score":20.589956812985484},"GB2-05":{"attempts":2,"playable":33.17484144151828,"score":33.17484144151828},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.784244890458616,"score":8.892122445229308},"GB2-07":{"attempts":2,"playable":16.126132649508516,"score":16.126132649508516},"GB2-08":{"attempts":2,"playable":30.925333056690018,"score":30.925333056690018}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":21.941252683309312,"score":21.941252683309312},"GB2-04":{"attempts":1,"playable":41.17991362597097,"score":41.17991362597097},"GB2-05":{"attempts":1,"playable":46.459938565179655,"score":46.459938565179655},"GB2-06":{"attempts":1,"playable":17.784244890458616,"score":17.784244890458616},"GB2-07":{"attempts":1,"playable":30.23071015102376,"score":30.23071015102376},"GB2-08":{"attempts":1,"playable":30.13371065193765,"score":30.13371065193765}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.889744317856906,"score":19.889744317856906},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":2.0215551479932716,"score":2.0215551479932716},"GB2-08":{"attempts":1,"playable":31.716955461442385,"score":31.716955461442385}}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":816,"losses":3115,"wins":759},"match_totals_tracks":{"medium":{"draws":533,"losses":1923,"wins":636},"none":{"draws":283,"losses":1192,"wins":123}},"model_slug":"cohere-north-mini-code","official_rank_by_reasoning":{"medium":73},"overall":{"max":46.459938565179655,"mean":15.084876593448286,"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":115,"losses":341,"wins":38},"GB2-04":{"draws":304,"losses":149,"wins":45},"GB2-05":{"draws":0,"losses":722,"wins":338},"GB2-06":{"draws":3,"losses":425,"wins":74},"GB2-07":{"draws":0,"losses":906,"wins":154},"GB2-08":{"draws":394,"losses":572,"wins":110}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":115,"losses":341,"wins":38},"GB2-04":{"draws":304,"losses":149,"wins":45},"GB2-05":{"draws":0,"losses":292,"wins":238},"GB2-06":{"draws":3,"losses":425,"wins":74},"GB2-07":{"draws":0,"losses":383,"wins":147},"GB2-08":{"draws":111,"losses":333,"wins":94}},"none":{"GB2-05":{"draws":0,"losses":430,"wins":100},"GB2-07":{"draws":0,"losses":523,"wins":7},"GB2-08":{"draws":283,"losses":239,"wins":16}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1166.5830721710213,"GB2-04":1406.7045198838086,"GB2-05":1393.346334817669,"GB2-06":923.2003279297945,"GB2-07":1195.969331546531,"GB2-08":1181.3353959366418},"none":{"GB2-05":1007.8678585311259,"GB2-07":463.08041427552416,"GB2-08":1198.247887304458}},"per_game_tracks":{"medium":{"GB2-03":21.941252683309312,"GB2-04":41.17991362597097,"GB2-05":46.459938565179655,"GB2-06":17.784244890458616,"GB2-07":30.23071015102376,"GB2-08":30.13371065193765},"none":{"GB2-05":19.889744317856906,"GB2-07":2.0215551479932716,"GB2-08":31.716955461442385}},"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":23.466221320985,"none":6.703531865911569},"reasoning_agg":{"medium":{"max":46.459938565179655,"mean":23.466221320985,"min":0.0},"none":{"max":31.716955461442385,"mean":6.703531865911569,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.76268945507343},"working_program_strength":{"all":24.58219003520543,"medium":31.288295094646667,"none":17.876084975764186}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:c8bc28f37863669f","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":0.017506999999999998}},"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":11.797871434337962,"none":11.797871434337962},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[32768],"finish_reason_observations":13,"finish_reasons":["stop"],"indexed_attempts":13,"output_token_observations":13,"provider_post_attempt_observations":13,"provider_post_attempts":13,"reasoning_token_observations":13,"reconciliation_get_attempt_observations":13,"requested_max_output_token_observations":13,"requested_max_output_tokens":[32768],"total_output_tokens":20448,"total_visible_output_tokens":20448,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.3319147474047,"score":41.3319147474047},"GB2-03":{"attempts":1,"playable":35.15319170828066,"score":35.15319170828066},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":17.897865019018337,"score":17.897865019018337},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.3319147474047,"score":41.3319147474047},"GB2-03":{"attempts":1,"playable":35.15319170828066,"score":35.15319170828066},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":17.897865019018337,"score":17.897865019018337},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-10-24T14:25:19Z","match_totals_all":{"draws":680,"losses":713,"wins":83},"match_totals_tracks":{"none":{"draws":680,"losses":713,"wins":83}},"model_slug":"gpt-4-1-nano","overall":{"max":41.3319147474047,"mean":11.797871434337962,"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":375,"losses":102,"wins":3},"GB2-03":{"draws":299,"losses":188,"wins":7},"GB2-06":{"draws":6,"losses":423,"wins":73}},"per_game_match_totals_tracks":{"none":{"GB2-02":{"draws":375,"losses":102,"wins":3},"GB2-03":{"draws":299,"losses":188,"wins":7},"GB2-06":{"draws":6,"losses":423,"wins":73}}},"per_game_raw_elo_tracks":{"none":{"GB2-02":1404.7750412109465,"GB2-03":1297.4618367609612,"GB2-06":925.1615076947598}},"per_game_tracks":{"none":{"GB2-02":41.3319147474047,"GB2-03":35.15319170828066,"GB2-06":17.897865019018337}},"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":11.797871434337962},"reasoning_agg":{"none":{"max":41.3319147474047,"mean":11.797871434337962,"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":31.460990491567898,"none":31.460990491567898}}],"public_release_id":"gb2-20261024-562513c4ac28","rating_method":{"bootstrap_iterations":0,"first_player_advantage":true,"method":"bradley_terry_newton","reference_field":{"manifest_sha256":"f02ffdc046ccbb060241b53df78dedf7e60ba7d8e68807f11921754cf4f0345a","population_revision":"62c0f9ac87b4c843aacf3d3e0c418e498bb133c2c43cf3ae7fd93c0d1fef2ed0","rule":"model_balanced_common_field_v1","source":"frozen_manifest","version":"v1"}},"results_cut_id":"gb2-20261024-562513c4ac28","schema_version":2,"snapshot_id":"20261024_194338","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-10-24 19:43 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":27},"claude-fable-5":{"draws":20,"losses":95,"wins":17},"claude-fable-5-1":{"draws":5,"losses":139,"wins":4},"claude-haiku-5-5":{"draws":27,"losses":74,"wins":25},"claude-opus-4-5":{"draws":73,"losses":90,"wins":51},"claude-opus-4-8":{"draws":30,"losses":70,"wins":20},"claude-opus-5":{"draws":27,"losses":179,"wins":20},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":41,"losses":68,"wins":23},"claude-sonnet-5-5":{"draws":28,"losses":79,"wins":25},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":23},"deepseek/deepseek-v4-flash":{"draws":63,"losses":62,"wins":71},"deepseek/deepseek-v4-pro":{"draws":30,"losses":60,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":53,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":60,"wins":32},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":89,"wins":20},"elorian/glimpse":{"draws":16,"losses":34,"wins":22},"fireworks/ember-1":{"draws":37,"losses":69,"wins":26},"gemini-3.1-pro-preview":{"draws":36,"losses":60,"wins":36},"gemini-4-argon":{"draws":3,"losses":123,"wins":6},"google/gemini-3.1-flash-lite":{"draws":28,"losses":17,"wins":43},"google/gemini-3.5-flash":{"draws":37,"losses":82,"wins":47},"google/gemini-3.5-flash-lite":{"draws":78,"losses":74,"wins":82},"google/gemini-3.6-flash":{"draws":67,"losses":134,"wins":53},"google/gemini-3.8-flash":{"draws":30,"losses":79,"wins":23},"google/gemma-4-31b-it":{"draws":27,"losses":24,"wins":25},"gpt-4.1":{"draws":16,"losses":17,"wins":11},"gpt-4.1-nano":{"draws":8,"losses":4,"wins":4},"gpt-5":{"draws":35,"losses":43,"wins":38},"gpt-5.4":{"draws":29,"losses":71,"wins":28},"gpt-5.4-mini":{"draws":35,"losses":25,"wins":28},"gpt-5.4-nano":{"draws":30,"losses":48,"wins":54},"gpt-5.5":{"draws":47,"losses":54,"wins":21},"gpt-5.6-luna":{"draws":43,"losses":42,"wins":47},"gpt-5.6-sol":{"draws":22,"losses":95,"wins":15},"gpt-5.6-terra":{"draws":37,"losses":65,"wins":24},"gpt-6-astra":{"draws":6,"losses":118,"wins":8},"gpt-6-luna":{"draws":39,"losses":54,"wins":39},"gpt-6-sol":{"draws":15,"losses":102,"wins":15},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":36,"losses":24,"wins":32},"inception/mercury-3":{"draws":25,"losses":34,"wins":27},"inclusionai/ling-3.0-flash":{"draws":39,"losses":16,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":40,"losses":41,"wins":63},"meta/muse-glimmer-30b":{"draws":46,"losses":33,"wins":37},"meta/muse-spark-1.2":{"draws":32,"losses":64,"wins":30},"meta/muse-spark-1.3":{"draws":29,"losses":81,"wins":22},"meta/muse-spark-open":{"draws":26,"losses":75,"wins":27},"meta/muse-wonder":{"draws":30,"losses":86,"wins":16},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":37},"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":34,"losses":18,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":13,"wins":8},"moonshotai/kimi-k3":{"draws":36,"losses":60,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":103,"wins":4},"nex-agi/nex-n2-pro":{"draws":18,"losses":12,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":34,"wins":35},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":22,"wins":16},"o3":{"draws":40,"losses":88,"wins":56},"openai/gpt-oss-120b":{"draws":40,"losses":32,"wins":42},"poolside/laguna-s-2.1":{"draws":48,"losses":40,"wins":40},"qwen/qwen3.7-max":{"draws":26,"losses":27,"wins":23},"qwen/qwen3.7-plus":{"draws":22,"losses":20,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":66,"wins":25},"qwen/qwen3.8-27b":{"draws":23,"losses":48,"wins":23},"qwen/qwen3.8-flash":{"draws":29,"losses":39,"wins":20},"qwen/qwen3.8-max":{"draws":47,"losses":52,"wins":33},"qwen/qwen3.8-max-0902":{"draws":37,"losses":74,"wins":21},"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":101,"losses":251,"wins":88},"stealth/space-bunny-alpha":{"draws":35,"losses":38,"wins":31},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":23,"losses":23,"wins":26},"tencent/hy4-preview":{"draws":41,"losses":72,"wins":15},"thinkingmachines/inkling":{"draws":61,"losses":46,"wins":71},"thinkingmachines/inkling-small":{"draws":48,"losses":30,"wins":54},"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":84,"wins":18},"x-ai/grok-4.6":{"draws":35,"losses":82,"wins":15},"x-ai/grok-4.7":{"draws":6,"losses":91,"wins":17},"x-ai/grok-build-0.1":{"draws":16,"losses":10,"wins":18},"xiaomi/mimo-v2.5":{"draws":72,"losses":52,"wins":80},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":24,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":49,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":57,"wins":18},"z-ai/glm-5.2":{"draws":96,"losses":96,"wins":72},"z-ai/glm-5.3":{"draws":25,"losses":84,"wins":17},"z-ai/glm-5.3-flash":{"draws":29,"losses":74,"wins":29},"z-ai/glm-5.3-flashx":{"draws":24,"losses":83,"wins":25}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":17,"wins":95},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":9,"losses":133,"wins":20},"claude-haiku-5-5":{"draws":24,"losses":42,"wins":72},"claude-opus-4-5":{"draws":38,"losses":36,"wins":160},"claude-opus-4-8":{"draws":26,"losses":35,"wins":71},"claude-opus-5":{"draws":42,"losses":139,"wins":65},"claude-opus-5-5":{"draws":10,"losses":126,"wins":20},"claude-sonnet-5":{"draws":26,"losses":25,"wins":93},"claude-sonnet-5-5":{"draws":26,"losses":57,"wins":61},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":37,"losses":14,"wins":165},"deepseek/deepseek-v4-pro":{"draws":25,"losses":27,"wins":80},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":27,"wins":85},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":36,"wins":72},"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":28,"losses":30,"wins":86},"gemini-4-argon":{"draws":13,"losses":101,"wins":30},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":82},"google/gemini-3.5-flash":{"draws":32,"losses":33,"wins":115},"google/gemini-3.5-flash-lite":{"draws":45,"losses":28,"wins":179},"google/gemini-3.6-flash":{"draws":48,"losses":80,"wins":148},"google/gemini-3.8-flash":{"draws":23,"losses":54,"wins":67},"google/gemma-4-31b-it":{"draws":18,"losses":8,"wins":58},"gpt-4.1":{"draws":9,"losses":12,"wins":27},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":24,"losses":21,"wins":81},"gpt-5.4":{"draws":33,"losses":40,"wins":65},"gpt-5.4-mini":{"draws":22,"losses":11,"wins":63},"gpt-5.4-nano":{"draws":19,"losses":13,"wins":112},"gpt-5.5":{"draws":32,"losses":38,"wins":62},"gpt-5.6-luna":{"draws":33,"losses":18,"wins":93},"gpt-5.6-sol":{"draws":17,"losses":59,"wins":68},"gpt-5.6-terra":{"draws":39,"losses":19,"wins":80},"gpt-6-astra":{"draws":10,"losses":110,"wins":24},"gpt-6-luna":{"draws":31,"losses":27,"wins":86},"gpt-6-sol":{"draws":21,"losses":82,"wins":41},"gpt-6.1-sol":{"draws":10,"losses":102,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":26,"losses":5,"wins":71},"inception/mercury-3":{"draws":24,"losses":13,"wins":59},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":80},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":18,"losses":20,"wins":118},"meta/muse-glimmer-30b":{"draws":26,"losses":7,"wins":93},"meta/muse-spark-1.2":{"draws":21,"losses":32,"wins":85},"meta/muse-spark-1.3":{"draws":24,"losses":43,"wins":77},"meta/muse-spark-open":{"draws":21,"losses":31,"wins":86},"meta/muse-wonder":{"draws":25,"losses":57,"wins":62},"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":18,"losses":23,"wins":49},"mistralai/mistral-medium-3-5":{"draws":20,"losses":6,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":24},"moonshotai/kimi-k3":{"draws":27,"losses":27,"wins":84},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":97,"wins":30},"nex-agi/nex-n2-pro":{"draws":13,"losses":2,"wins":57},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":11,"wins":87},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":4,"wins":49},"o3":{"draws":18,"losses":29,"wins":151},"openai/gpt-oss-120b":{"draws":29,"losses":11,"wins":86},"poolside/laguna-s-2.1":{"draws":26,"losses":21,"wins":91},"qwen/qwen3.7-max":{"draws":13,"losses":13,"wins":58},"qwen/qwen3.7-plus":{"draws":12,"losses":8,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":35,"wins":75},"qwen/qwen3.8-27b":{"draws":20,"losses":16,"wins":66},"qwen/qwen3.8-flash":{"draws":22,"losses":19,"wins":55},"qwen/qwen3.8-max":{"draws":27,"losses":37,"wins":80},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"wins":81},"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":79,"losses":117,"wins":278},"stealth/space-bunny-alpha":{"draws":30,"losses":15,"wins":69},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":82},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":22,"losses":11,"wins":45},"tencent/hy4-preview":{"draws":23,"losses":32,"wins":83},"thinkingmachines/inkling":{"draws":38,"losses":12,"wins":142},"thinkingmachines/inkling-small":{"draws":27,"losses":14,"wins":103},"unbiased/pareto-26.10":{"draws":1,"losses":43,"wins":4},"unbiased/pareto-26.10-preview":{"draws":5,"losses":33,"wins":10},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":28},"x-ai/grok-4.5":{"draws":23,"losses":47,"wins":74},"x-ai/grok-4.6":{"draws":33,"losses":50,"wins":61},"x-ai/grok-4.7":{"draws":7,"losses":77,"wins":42},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":32},"xiaomi/mimo-v2.5":{"draws":42,"losses":6,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":65},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":41,"wins":47},"z-ai/glm-5.2":{"draws":60,"losses":43,"wins":185},"z-ai/glm-5.3":{"draws":21,"losses":64,"wins":53},"z-ai/glm-5.3-flash":{"draws":23,"losses":44,"wins":77},"z-ai/glm-5.3-flashx":{"draws":27,"losses":44,"wins":73}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":139},"claude-fable-5":{"draws":9,"losses":20,"wins":133},"claude-fable-5-1":{"draws":14,"losses":59,"wins":59},"claude-haiku-5-5":{"draws":8,"losses":8,"wins":138},"claude-opus-4-5":{"draws":14,"losses":11,"wins":237},"claude-opus-4-8":{"draws":8,"losses":10,"wins":128},"claude-opus-5":{"draws":25,"losses":80,"wins":173},"claude-opus-5-5":{"draws":16,"losses":93,"wins":65},"claude-sonnet-5":{"draws":9,"losses":6,"wins":147},"claude-sonnet-5-5":{"draws":9,"losses":35,"wins":118},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":232},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":137},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":3,"wins":143},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":12,"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":11,"wins":146},"gemini-3.1-pro-preview":{"draws":8,"losses":4,"wins":150},"gemini-4-argon":{"draws":14,"losses":53,"wins":95},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":101},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":183},"google/gemini-3.5-flash-lite":{"draws":20,"losses":2,"wins":262},"google/gemini-3.6-flash":{"draws":20,"losses":19,"wins":273},"google/gemini-3.8-flash":{"draws":7,"losses":14,"wins":141},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":89},"gpt-4.1":{"draws":3,"losses":2,"wins":49},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":20},"gpt-5":{"draws":5,"losses":1,"wins":136},"gpt-5.4":{"draws":10,"losses":16,"wins":130},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":103},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":151},"gpt-5.5":{"draws":5,"losses":19,"wins":126},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":147},"gpt-5.6-sol":{"draws":12,"losses":19,"wins":131},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":142},"gpt-6-astra":{"draws":16,"losses":85,"wins":61},"gpt-6-luna":{"draws":11,"losses":7,"wins":144},"gpt-6-sol":{"draws":15,"losses":38,"wins":109},"gpt-6.1-sol":{"draws":12,"losses":75,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":105},"inception/mercury-3":{"draws":4,"losses":1,"wins":101},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":109},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":164},"meta/muse-glimmer-30b":{"draws":8,"losses":1,"wins":134},"meta/muse-spark-1.2":{"draws":8,"losses":8,"wins":140},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":135},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":137},"meta/muse-wonder":{"draws":13,"losses":31,"wins":118},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":84},"minimax/minimax-m3.1-flash":{"draws":8,"losses":5,"wins":131},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":92},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":88},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":37},"moonshotai/kimi-k3":{"draws":8,"losses":12,"wins":136},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":43,"wins":96},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":78},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":129},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":71},"o3":{"draws":5,"losses":9,"wins":204},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":135},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":145},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":88},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":72},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":6,"wins":145},"qwen/qwen3.8-27b":{"draws":7,"losses":1,"wins":106},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":97},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":151},"qwen/qwen3.8-max-0902":{"draws":6,"losses":15,"wins":141},"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":32,"losses":29,"wins":489},"stealth/space-bunny-alpha":{"draws":6,"losses":3,"wins":121},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":111},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":74},"tencent/hy4-preview":{"draws":9,"losses":12,"wins":135},"thinkingmachines/inkling":{"draws":9,"losses":0,"wins":209},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":154},"unbiased/pareto-26.10":{"draws":7,"losses":26,"wins":21},"unbiased/pareto-26.10-preview":{"draws":3,"losses":29,"wins":22},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":37},"x-ai/grok-4.5":{"draws":10,"losses":10,"wins":142},"x-ai/grok-4.6":{"draws":9,"losses":23,"wins":130},"x-ai/grok-4.7":{"draws":6,"losses":36,"wins":98},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":52},"xiaomi/mimo-v2.5":{"draws":13,"losses":5,"wins":226},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":84},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":83},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":11,"wins":84},"z-ai/glm-5.2":{"draws":21,"losses":8,"wins":295},"z-ai/glm-5.3":{"draws":11,"losses":21,"wins":124},"z-ai/glm-5.3-flash":{"draws":10,"losses":13,"wins":139},"z-ai/glm-5.3-flashx":{"draws":13,"losses":12,"wins":137}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":74},"claude-fable-5":{"draws":24,"losses":72,"wins":42},"claude-fable-5-1":{"draws":8,"losses":138,"wins":8},"claude-haiku-5-5":{"draws":16,"losses":36,"wins":36},"claude-opus-4-5":{"draws":64,"losses":57,"wins":105},"claude-opus-4-8":{"draws":28,"losses":57,"wins":45},"claude-opus-5":{"draws":35,"losses":160,"wins":39},"claude-opus-5-5":{"draws":16,"losses":126,"wins":8},"claude-sonnet-5":{"draws":35,"losses":40,"wins":63},"claude-sonnet-5-5":{"draws":25,"losses":70,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":57,"losses":30,"wins":121},"deepseek/deepseek-v4-pro":{"draws":35,"losses":41,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":29,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":39,"wins":56},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":61,"wins":52},"elorian/glimpse":{"draws":11,"losses":29,"wins":34},"fireworks/ember-1":{"draws":36,"losses":38,"wins":64},"gemini-3.1-pro-preview":{"draws":32,"losses":46,"wins":60},"gemini-4-argon":{"draws":14,"losses":98,"wins":26},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":66},"google/gemini-3.5-flash":{"draws":39,"losses":58,"wins":77},"google/gemini-3.5-flash-lite":{"draws":53,"losses":40,"wins":149},"google/gemini-3.6-flash":{"draws":65,"losses":99,"wins":100},"google/gemini-3.8-flash":{"draws":33,"losses":62,"wins":43},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":50},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":9},"gpt-5":{"draws":31,"losses":27,"wins":62},"gpt-5.4":{"draws":31,"losses":50,"wins":51},"gpt-5.4-mini":{"draws":27,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":27,"losses":39,"wins":76},"gpt-5.5":{"draws":46,"losses":35,"wins":45},"gpt-5.6-luna":{"draws":40,"losses":24,"wins":74},"gpt-5.6-sol":{"draws":21,"losses":76,"wins":41},"gpt-5.6-terra":{"draws":39,"losses":37,"wins":56},"gpt-6-astra":{"draws":10,"losses":121,"wins":7},"gpt-6-luna":{"draws":36,"losses":39,"wins":63},"gpt-6-sol":{"draws":27,"losses":84,"wins":27},"gpt-6.1-sol":{"draws":15,"losses":113,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":68},"inception/mercury-3":{"draws":23,"losses":29,"wins":40},"inclusionai/ling-3.0-flash":{"draws":32,"losses":5,"wins":61},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":96},"meta/muse-glimmer-30b":{"draws":37,"losses":15,"wins":68},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":65},"meta/muse-spark-1.3":{"draws":26,"losses":51,"wins":61},"meta/muse-spark-open":{"draws":19,"losses":55,"wins":58},"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":30,"losses":28,"wins":28},"mistralai/mistral-medium-3-5":{"draws":22,"losses":4,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":15},"moonshotai/kimi-k3":{"draws":34,"losses":40,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":98,"wins":20},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":26,"wins":66},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":20,"wins":33},"o3":{"draws":32,"losses":61,"wins":101},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":78},"poolside/laguna-s-2.1":{"draws":34,"losses":35,"wins":61},"qwen/qwen3.7-max":{"draws":27,"losses":20,"wins":35},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":47,"wins":55},"qwen/qwen3.8-27b":{"draws":22,"losses":29,"wins":47},"qwen/qwen3.8-flash":{"draws":28,"losses":19,"wins":45},"qwen/qwen3.8-max":{"draws":34,"losses":37,"wins":67},"qwen/qwen3.8-max-0902":{"draws":40,"losses":48,"wins":50},"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":96,"losses":165,"wins":173},"stealth/space-bunny-alpha":{"draws":33,"losses":23,"wins":54},"stepfun/step-3.7-flash":{"draws":15,"losses":16,"wins":67},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":20,"wins":31},"tencent/hy4-preview":{"draws":30,"losses":54,"wins":48},"thinkingmachines/inkling":{"draws":49,"losses":23,"wins":110},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":92},"unbiased/pareto-26.10":{"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":60,"wins":48},"x-ai/grok-4.6":{"draws":36,"losses":60,"wins":42},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":20},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":29},"xiaomi/mimo-v2.5":{"draws":56,"losses":31,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":18,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":27,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":43,"wins":32},"z-ai/glm-5.2":{"draws":64,"losses":64,"wins":148},"z-ai/glm-5.3":{"draws":24,"losses":76,"wins":32},"z-ai/glm-5.3-flash":{"draws":27,"losses":57,"wins":54},"z-ai/glm-5.3-flashx":{"draws":27,"losses":51,"wins":60}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":30,"wins":62},"claude-fable-5":{"draws":23,"losses":95,"wins":26},"claude-fable-5-1":{"draws":12,"losses":142,"wins":8},"claude-haiku-5-5":{"draws":40,"losses":55,"wins":43},"claude-opus-4-5":{"draws":63,"losses":52,"wins":71},"claude-opus-4-8":{"draws":37,"losses":57,"wins":38},"claude-opus-5":{"draws":39,"losses":184,"wins":23},"claude-opus-5-5":{"draws":12,"losses":134,"wins":10},"claude-sonnet-5":{"draws":50,"losses":42,"wins":52},"claude-sonnet-5-5":{"draws":30,"losses":74,"wins":40},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":43},"deepseek/deepseek-v4-flash":{"draws":62,"losses":43,"wins":111},"deepseek/deepseek-v4-pro":{"draws":35,"losses":47,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":46,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":62,"wins":44},"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":55,"wins":41},"gemini-3.1-pro-preview":{"draws":36,"losses":47,"wins":61},"gemini-4-argon":{"draws":6,"losses":129,"wins":9},"google/gemini-3.1-flash-lite":{"draws":21,"losses":5,"wins":70},"google/gemini-3.5-flash":{"draws":49,"losses":69,"wins":62},"google/gemini-3.5-flash-lite":{"draws":83,"losses":53,"wins":116},"google/gemini-3.6-flash":{"draws":78,"losses":123,"wins":75},"google/gemini-3.8-flash":{"draws":42,"losses":74,"wins":28},"google/gemma-4-31b-it":{"draws":28,"losses":10,"wins":46},"gpt-4.1":{"draws":20,"losses":12,"wins":16},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":38,"losses":39,"wins":49},"gpt-5.4":{"draws":37,"losses":68,"wins":33},"gpt-5.4-mini":{"draws":39,"losses":20,"wins":37},"gpt-5.4-nano":{"draws":42,"losses":33,"wins":69},"gpt-5.5":{"draws":56,"losses":52,"wins":24},"gpt-5.6-luna":{"draws":53,"losses":31,"wins":60},"gpt-5.6-sol":{"draws":22,"losses":96,"wins":26},"gpt-5.6-terra":{"draws":53,"losses":40,"wins":45},"gpt-6-astra":{"draws":8,"losses":125,"wins":11},"gpt-6-luna":{"draws":44,"losses":48,"wins":52},"gpt-6-sol":{"draws":23,"losses":106,"wins":15},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":43,"losses":6,"wins":53},"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":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":40,"losses":21,"wins":95},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":65},"meta/muse-spark-1.2":{"draws":34,"losses":66,"wins":38},"meta/muse-spark-1.3":{"draws":28,"losses":80,"wins":36},"meta/muse-spark-open":{"draws":37,"losses":59,"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":26,"losses":8,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":9,"wins":18},"moonshotai/kimi-k3":{"draws":48,"losses":48,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":113,"wins":8},"nex-agi/nex-n2-pro":{"draws":17,"losses":9,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":17,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":21,"wins":22},"o3":{"draws":29,"losses":53,"wins":116},"openai/gpt-oss-120b":{"draws":40,"losses":22,"wins":64},"poolside/laguna-s-2.1":{"draws":46,"losses":21,"wins":71},"qwen/qwen3.7-max":{"draws":23,"losses":21,"wins":40},"qwen/qwen3.7-plus":{"draws":22,"losses":15,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":58,"wins":35},"qwen/qwen3.8-27b":{"draws":31,"losses":36,"wins":35},"qwen/qwen3.8-flash":{"draws":33,"losses":31,"wins":32},"qwen/qwen3.8-max":{"draws":41,"losses":60,"wins":43},"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":130,"losses":200,"wins":144},"stealth/space-bunny-alpha":{"draws":36,"losses":27,"wins":51},"stepfun/step-3.7-flash":{"draws":15,"losses":21,"wins":66},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":27,"losses":18,"wins":33},"tencent/hy4-preview":{"draws":35,"losses":62,"wins":41},"thinkingmachines/inkling":{"draws":58,"losses":33,"wins":101},"thinkingmachines/inkling-small":{"draws":47,"losses":18,"wins":79},"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":41,"losses":61,"wins":42},"x-ai/grok-4.6":{"draws":36,"losses":74,"wins":34},"x-ai/grok-4.7":{"draws":11,"losses":91,"wins":24},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":73,"losses":30,"wins":119},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":26,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":43,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":52,"wins":20},"z-ai/glm-5.2":{"draws":90,"losses":80,"wins":118},"z-ai/glm-5.3":{"draws":33,"losses":83,"wins":22},"z-ai/glm-5.3-flash":{"draws":33,"losses":74,"wins":37},"z-ai/glm-5.3-flashx":{"draws":36,"losses":75,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":20,"wins":70},"claude-fable-5":{"draws":26,"losses":71,"wins":35},"claude-fable-5-1":{"draws":8,"losses":128,"wins":10},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":57},"claude-opus-4-5":{"draws":64,"losses":54,"wins":100},"claude-opus-4-8":{"draws":14,"losses":35,"wins":35},"claude-opus-5":{"draws":32,"losses":153,"wins":37},"claude-opus-5-5":{"draws":13,"losses":113,"wins":18},"claude-sonnet-5":{"draws":36,"losses":38,"wins":58},"claude-sonnet-5-5":{"draws":28,"losses":62,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":38},"deepseek/deepseek-v4-flash":{"draws":49,"losses":26,"wins":125},"deepseek/deepseek-v4-pro":{"draws":28,"losses":37,"wins":55},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":38,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":53,"wins":47},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":66,"wins":42},"elorian/glimpse":{"draws":14,"losses":29,"wins":27},"fireworks/ember-1":{"draws":43,"losses":36,"wins":53},"gemini-3.1-pro-preview":{"draws":35,"losses":35,"wins":62},"gemini-4-argon":{"draws":9,"losses":98,"wins":25},"google/gemini-3.1-flash-lite":{"draws":20,"losses":5,"wins":71},"google/gemini-3.5-flash":{"draws":36,"losses":49,"wins":83},"google/gemini-3.5-flash-lite":{"draws":63,"losses":22,"wins":147},"google/gemini-3.6-flash":{"draws":57,"losses":103,"wins":92},"google/gemini-3.8-flash":{"draws":30,"losses":61,"wins":41},"google/gemma-4-31b-it":{"draws":23,"losses":10,"wins":47},"gpt-4.1":{"draws":14,"losses":5,"wins":25},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":30,"losses":30,"wins":54},"gpt-5.4":{"draws":30,"losses":55,"wins":41},"gpt-5.4-mini":{"draws":22,"losses":22,"wins":44},"gpt-5.4-nano":{"draws":25,"losses":31,"wins":84},"gpt-5.5":{"draws":38,"losses":48,"wins":34},"gpt-5.6-luna":{"draws":39,"losses":29,"wins":64},"gpt-5.6-sol":{"draws":18,"losses":72,"wins":42},"gpt-5.6-terra":{"draws":31,"losses":36,"wins":59},"gpt-6-astra":{"draws":8,"losses":114,"wins":10},"gpt-6-luna":{"draws":33,"losses":36,"wins":63},"gpt-6-sol":{"draws":20,"losses":79,"wins":33},"gpt-6.1-sol":{"draws":7,"losses":111,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":9,"wins":57},"inception/mercury-3":{"draws":24,"losses":20,"wins":44},"inclusionai/ling-3.0-flash":{"draws":29,"losses":0,"wins":65},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":32,"losses":21,"wins":91},"meta/muse-glimmer-30b":{"draws":31,"losses":16,"wins":67},"meta/muse-spark-1.2":{"draws":30,"losses":43,"wins":53},"meta/muse-spark-1.3":{"draws":25,"losses":55,"wins":52},"meta/muse-spark-open":{"draws":27,"losses":47,"wins":52},"meta/muse-wonder":{"draws":26,"losses":62,"wins":44},"minimax/minimax-m3":{"draws":16,"losses":10,"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":25,"losses":6,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":7,"wins":19},"moonshotai/kimi-k3":{"draws":33,"losses":43,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":105,"wins":12},"nex-agi/nex-n2-pro":{"draws":16,"losses":3,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":18,"wins":77},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":12,"wins":35},"o3":{"draws":27,"losses":56,"wins":107},"openai/gpt-oss-120b":{"draws":36,"losses":10,"wins":68},"poolside/laguna-s-2.1":{"draws":37,"losses":17,"wins":68},"qwen/qwen3.7-max":{"draws":25,"losses":20,"wins":35},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":50,"wins":44},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":43},"qwen/qwen3.8-flash":{"draws":31,"losses":16,"wins":41},"qwen/qwen3.8-max":{"draws":26,"losses":45,"wins":61},"qwen/qwen3.8-max-0902":{"draws":33,"losses":48,"wins":51},"recursive/flint-v1.0":{"draws":11,"losses":2,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":32,"wins":61},"stealth/ox-alpha":{"draws":84,"losses":157,"wins":153},"stealth/space-bunny-alpha":{"draws":30,"losses":23,"wins":53},"stepfun/step-3.7-flash":{"draws":16,"losses":18,"wins":60},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":38},"tencent/hy4-preview":{"draws":30,"losses":50,"wins":46},"thinkingmachines/inkling":{"draws":43,"losses":21,"wins":108},"thinkingmachines/inkling-small":{"draws":39,"losses":12,"wins":81},"unbiased/pareto-26.10":{"draws":4,"losses":36,"wins":4},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":35,"losses":51,"wins":46},"x-ai/grok-4.6":{"draws":31,"losses":58,"wins":43},"x-ai/grok-4.7":{"draws":15,"losses":72,"wins":31},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":27},"xiaomi/mimo-v2.5":{"draws":62,"losses":24,"wins":132},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":38,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":42,"wins":35},"z-ai/glm-5.2":{"draws":74,"losses":59,"wins":131},"z-ai/glm-5.3":{"draws":21,"losses":73,"wins":32},"z-ai/glm-5.3-flash":{"draws":19,"losses":61,"wins":52},"z-ai/glm-5.3-flashx":{"draws":25,"losses":48,"wins":59}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":179},"claude-fable-5":{"draws":42,"losses":65,"wins":139},"claude-fable-5-1":{"draws":25,"losses":173,"wins":80},"claude-haiku-5-5":{"draws":35,"losses":39,"wins":160},"claude-opus-4-5":{"draws":70,"losses":39,"wins":289},"claude-opus-4-8":{"draws":32,"losses":37,"wins":153},"claude-opus-5":{"draws":54,"losses":165,"wins":165},"claude-opus-5-5":{"draws":25,"losses":166,"wins":79},"claude-sonnet-5":{"draws":32,"losses":33,"wins":181},"claude-sonnet-5-5":{"draws":26,"losses":83,"wins":137},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":80},"deepseek/deepseek-v4-flash":{"draws":42,"losses":21,"wins":299},"deepseek/deepseek-v4-pro":{"draws":27,"losses":32,"wins":173},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":27,"wins":174},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":37,"wins":170},"deepseek/deepseek-v4.1-flash-1017":{"draws":35,"losses":53,"wins":158},"elorian/glimpse":{"draws":19,"losses":28,"wins":91},"fireworks/ember-1":{"draws":26,"losses":44,"wins":176},"gemini-3.1-pro-preview":{"draws":23,"losses":37,"wins":186},"gemini-4-argon":{"draws":30,"losses":114,"wins":102},"google/gemini-3.1-flash-lite":{"draws":18,"losses":8,"wins":124},"google/gemini-3.5-flash":{"draws":35,"losses":31,"wins":238},"google/gemini-3.5-flash-lite":{"draws":50,"losses":32,"wins":342},"google/gemini-3.6-flash":{"draws":61,"losses":84,"wins":323},"google/gemini-3.8-flash":{"draws":28,"losses":53,"wins":165},"google/gemma-4-31b-it":{"draws":21,"losses":10,"wins":109},"gpt-4.1":{"draws":10,"losses":4,"wins":68},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":18},"gpt-5":{"draws":26,"losses":18,"wins":176},"gpt-5.4":{"draws":30,"losses":36,"wins":168},"gpt-5.4-mini":{"draws":31,"losses":13,"wins":120},"gpt-5.4-nano":{"draws":24,"losses":16,"wins":196},"gpt-5.5":{"draws":31,"losses":45,"wins":156},"gpt-5.6-luna":{"draws":26,"losses":24,"wins":196},"gpt-5.6-sol":{"draws":29,"losses":61,"wins":156},"gpt-5.6-terra":{"draws":29,"losses":21,"wins":184},"gpt-6-astra":{"draws":22,"losses":167,"wins":57},"gpt-6-luna":{"draws":45,"losses":21,"wins":180},"gpt-6-sol":{"draws":33,"losses":93,"wins":120},"gpt-6.1-sol":{"draws":33,"losses":139,"wins":74},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":130},"inception/mercury-3":{"draws":18,"losses":18,"wins":128},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":132},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":25,"losses":22,"wins":209},"meta/muse-glimmer-30b":{"draws":14,"losses":22,"wins":194},"meta/muse-spark-1.2":{"draws":32,"losses":35,"wins":177},"meta/muse-spark-1.3":{"draws":31,"losses":50,"wins":165},"meta/muse-spark-open":{"draws":24,"losses":42,"wins":168},"meta/muse-wonder":{"draws":29,"losses":76,"wins":141},"minimax/minimax-m3":{"draws":15,"losses":7,"wins":116},"minimax/minimax-m3.1-flash":{"draws":29,"losses":21,"wins":160},"mistralai/mistral-large-4-0":{"draws":24,"losses":19,"wins":119},"mistralai/mistral-medium-3-5":{"draws":22,"losses":12,"wins":110},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":58},"moonshotai/kimi-k3":{"draws":37,"losses":39,"wins":168},"moonshotai/kimi-k3.1-pro":{"draws":26,"losses":110,"wins":98},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":108},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":6,"wins":181},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":81},"o3":{"draws":26,"losses":20,"wins":266},"openai/gpt-oss-120b":{"draws":30,"losses":11,"wins":179},"poolside/laguna-s-2.1":{"draws":27,"losses":13,"wins":208},"qwen/qwen3.7-max":{"draws":18,"losses":12,"wins":110},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":93},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":39,"wins":174},"qwen/qwen3.8-27b":{"draws":30,"losses":13,"wins":123},"qwen/qwen3.8-flash":{"draws":21,"losses":14,"wins":129},"qwen/qwen3.8-max":{"draws":36,"losses":30,"wins":180},"qwen/qwen3.8-max-0902":{"draws":34,"losses":42,"wins":170},"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":131,"losses":121,"wins":580},"stealth/space-bunny-alpha":{"draws":30,"losses":14,"wins":152},"stepfun/step-3.7-flash":{"draws":14,"losses":7,"wins":141},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":26,"losses":11,"wins":105},"tencent/hy4-preview":{"draws":25,"losses":35,"wins":174},"thinkingmachines/inkling":{"draws":48,"losses":30,"wins":260},"thinkingmachines/inkling-small":{"draws":37,"losses":10,"wins":199},"unbiased/pareto-26.10":{"draws":7,"losses":51,"wins":24},"unbiased/pareto-26.10-preview":{"draws":3,"losses":50,"wins":29},"upstage/solar-mini4":{"draws":7,"losses":1,"wins":40},"x-ai/grok-4.5":{"draws":38,"losses":42,"wins":166},"x-ai/grok-4.6":{"draws":37,"losses":49,"wins":159},"x-ai/grok-4.7":{"draws":20,"losses":98,"wins":102},"x-ai/grok-build-0.1":{"draws":15,"losses":3,"wins":64},"xiaomi/mimo-v2.5":{"draws":58,"losses":23,"wins":297},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":5,"wins":111},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":17,"wins":119},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":39,"wins":99},"z-ai/glm-5.2":{"draws":74,"losses":33,"wins":385},"z-ai/glm-5.3":{"draws":31,"losses":63,"wins":140},"z-ai/glm-5.3-flash":{"draws":35,"losses":46,"wins":165},"z-ai/glm-5.3-flashx":{"draws":36,"losses":44,"wins":166}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":131},"claude-fable-5":{"draws":10,"losses":20,"wins":126},"claude-fable-5-1":{"draws":16,"losses":65,"wins":93},"claude-haiku-5-5":{"draws":16,"losses":8,"wins":126},"claude-opus-4-5":{"draws":20,"losses":17,"wins":217},"claude-opus-4-8":{"draws":13,"losses":18,"wins":113},"claude-opus-5":{"draws":25,"losses":79,"wins":166},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":11,"losses":11,"wins":134},"claude-sonnet-5-5":{"draws":16,"losses":29,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"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":11,"wins":137},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":137},"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":10,"losses":9,"wins":177},"google/gemini-3.5-flash-lite":{"draws":18,"losses":1,"wins":253},"google/gemini-3.6-flash":{"draws":22,"losses":21,"wins":253},"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":5,"losses":1,"wins":46},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":5,"wins":124},"gpt-5.4":{"draws":10,"losses":13,"wins":127},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":97},"gpt-5.4-nano":{"draws":7,"losses":2,"wins":151},"gpt-5.5":{"draws":13,"losses":15,"wins":116},"gpt-5.6-luna":{"draws":15,"losses":5,"wins":136},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":123},"gpt-5.6-terra":{"draws":9,"losses":3,"wins":138},"gpt-6-astra":{"draws":16,"losses":72,"wins":68},"gpt-6-luna":{"draws":13,"losses":2,"wins":141},"gpt-6-sol":{"draws":14,"losses":40,"wins":102},"gpt-6.1-sol":{"draws":19,"losses":63,"wins":74},"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":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":156},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":131},"meta/muse-spark-1.2":{"draws":12,"losses":9,"wins":129},"meta/muse-spark-1.3":{"draws":8,"losses":14,"wins":134},"meta/muse-spark-open":{"draws":10,"losses":15,"wins":125},"meta/muse-wonder":{"draws":9,"losses":31,"wins":116},"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":14,"losses":5,"wins":79},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":85},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":36},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":132},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":50,"wins":88},"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":4,"losses":2,"wins":136},"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":5,"losses":0,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":127},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":10,"losses":3,"wins":91},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":131},"qwen/qwen3.8-max-0902":{"draws":16,"losses":12,"wins":128},"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":46,"losses":28,"wins":432},"stealth/space-bunny-alpha":{"draws":6,"losses":1,"wins":115},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":106},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":16},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":78},"tencent/hy4-preview":{"draws":12,"losses":13,"wins":125},"thinkingmachines/inkling":{"draws":18,"losses":0,"wins":186},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":146},"unbiased/pareto-26.10":{"draws":4,"losses":21,"wins":27},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":26},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":17,"losses":16,"wins":123},"x-ai/grok-4.6":{"draws":17,"losses":15,"wins":124},"x-ai/grok-4.7":{"draws":11,"losses":29,"wins":98},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":227},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":82},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":2,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":80},"z-ai/glm-5.2":{"draws":18,"losses":12,"wins":282},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":116},"z-ai/glm-5.3-flash":{"draws":12,"losses":10,"wins":134},"z-ai/glm-5.3-flashx":{"draws":15,"losses":10,"wins":131}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":23,"wins":68},"claude-fable-5":{"draws":26,"losses":93,"wins":25},"claude-fable-5-1":{"draws":9,"losses":147,"wins":6},"claude-haiku-5-5":{"draws":35,"losses":63,"wins":40},"claude-opus-4-5":{"draws":77,"losses":81,"wins":76},"claude-opus-4-8":{"draws":36,"losses":58,"wins":38},"claude-opus-5":{"draws":32,"losses":181,"wins":33},"claude-opus-5-5":{"draws":11,"losses":134,"wins":11},"claude-sonnet-5":{"draws":26,"losses":35,"wins":35},"claude-sonnet-5-5":{"draws":25,"losses":83,"wins":36},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":38},"deepseek/deepseek-v4-flash":{"draws":63,"losses":40,"wins":113},"deepseek/deepseek-v4-pro":{"draws":40,"losses":47,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":48,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":53,"wins":47},"deepseek/deepseek-v4.1-flash-1017":{"draws":31,"losses":81,"wins":32},"elorian/glimpse":{"draws":18,"losses":31,"wins":29},"fireworks/ember-1":{"draws":40,"losses":60,"wins":44},"gemini-3.1-pro-preview":{"draws":43,"losses":50,"wins":51},"gemini-4-argon":{"draws":12,"losses":124,"wins":8},"google/gemini-3.1-flash-lite":{"draws":29,"losses":6,"wins":61},"google/gemini-3.5-flash":{"draws":49,"losses":74,"wins":57},"google/gemini-3.5-flash-lite":{"draws":71,"losses":54,"wins":127},"google/gemini-3.6-flash":{"draws":65,"losses":125,"wins":86},"google/gemini-3.8-flash":{"draws":33,"losses":78,"wins":33},"google/gemma-4-31b-it":{"draws":27,"losses":12,"wins":45},"gpt-4.1":{"draws":17,"losses":15,"wins":16},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":37,"losses":35,"wins":54},"gpt-5.4":{"draws":35,"losses":71,"wins":32},"gpt-5.4-mini":{"draws":38,"losses":28,"wins":30},"gpt-5.4-nano":{"draws":33,"losses":40,"wins":71},"gpt-5.5":{"draws":48,"losses":58,"wins":26},"gpt-5.6-luna":{"draws":44,"losses":39,"wins":61},"gpt-5.6-sol":{"draws":20,"losses":105,"wins":19},"gpt-5.6-terra":{"draws":53,"losses":45,"wins":40},"gpt-6-astra":{"draws":6,"losses":130,"wins":8},"gpt-6-luna":{"draws":38,"losses":56,"wins":50},"gpt-6-sol":{"draws":23,"losses":102,"wins":19},"gpt-6.1-sol":{"draws":6,"losses":129,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":38,"losses":10,"wins":54},"inception/mercury-3":{"draws":31,"losses":33,"wins":32},"inclusionai/ling-3.0-flash":{"draws":36,"losses":8,"wins":58},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":41,"losses":30,"wins":85},"meta/muse-glimmer-30b":{"draws":43,"losses":19,"wins":64},"meta/muse-spark-1.2":{"draws":38,"losses":64,"wins":36},"meta/muse-spark-1.3":{"draws":37,"losses":74,"wins":33},"meta/muse-spark-open":{"draws":32,"losses":74,"wins":32},"meta/muse-wonder":{"draws":31,"losses":85,"wins":28},"minimax/minimax-m3":{"draws":21,"losses":15,"wins":42},"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":32,"losses":10,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":41,"losses":58,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":117,"wins":6},"nex-agi/nex-n2-pro":{"draws":24,"losses":11,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":7,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":29,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":17,"wins":31},"o3":{"draws":27,"losses":82,"wins":89},"openai/gpt-oss-120b":{"draws":38,"losses":16,"wins":72},"poolside/laguna-s-2.1":{"draws":41,"losses":27,"wins":70},"qwen/qwen3.7-max":{"draws":27,"losses":17,"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":25,"losses":40,"wins":37},"qwen/qwen3.8-flash":{"draws":30,"losses":33,"wins":33},"qwen/qwen3.8-max":{"draws":47,"losses":54,"wins":43},"qwen/qwen3.8-max-0902":{"draws":42,"losses":66,"wins":36},"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":107,"losses":233,"wins":134},"stealth/space-bunny-alpha":{"draws":30,"losses":37,"wins":47},"stepfun/step-3.7-flash":{"draws":21,"losses":27,"wins":54},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":25,"losses":22,"wins":31},"tencent/hy4-preview":{"draws":40,"losses":64,"wins":34},"thinkingmachines/inkling":{"draws":62,"losses":28,"wins":102},"thinkingmachines/inkling-small":{"draws":47,"losses":24,"wins":73},"unbiased/pareto-26.10":{"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":72,"wins":34},"x-ai/grok-4.6":{"draws":39,"losses":73,"wins":32},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":19,"losses":3,"wins":26},"xiaomi/mimo-v2.5":{"draws":81,"losses":38,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":21,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":49,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":57,"wins":24},"z-ai/glm-5.2":{"draws":79,"losses":88,"wins":121},"z-ai/glm-5.3":{"draws":28,"losses":91,"wins":19},"z-ai/glm-5.3-flash":{"draws":25,"losses":79,"wins":40},"z-ai/glm-5.3-flashx":{"draws":39,"losses":72,"wins":33}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":79},"claude-fable-5":{"draws":26,"losses":61,"wins":57},"claude-fable-5-1":{"draws":9,"losses":118,"wins":35},"claude-haiku-5-5":{"draws":25,"losses":43,"wins":70},"claude-opus-4-5":{"draws":48,"losses":58,"wins":128},"claude-opus-4-8":{"draws":28,"losses":42,"wins":62},"claude-opus-5":{"draws":26,"losses":137,"wins":83},"claude-opus-5-5":{"draws":16,"losses":111,"wins":29},"claude-sonnet-5":{"draws":25,"losses":36,"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":45,"losses":31,"wins":140},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":41,"wins":72},"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":43,"wins":73},"gemini-3.1-pro-preview":{"draws":22,"losses":40,"wins":82},"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":30,"losses":47,"wins":103},"google/gemini-3.5-flash-lite":{"draws":49,"losses":39,"wins":164},"google/gemini-3.6-flash":{"draws":49,"losses":98,"wins":129},"google/gemini-3.8-flash":{"draws":20,"losses":56,"wins":68},"google/gemma-4-31b-it":{"draws":14,"losses":16,"wins":54},"gpt-4.1":{"draws":10,"losses":8,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":26,"losses":26,"wins":74},"gpt-5.4":{"draws":36,"losses":42,"wins":60},"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":15,"losses":71,"wins":58},"gpt-5.6-terra":{"draws":33,"losses":31,"wins":74},"gpt-6-astra":{"draws":11,"losses":102,"wins":31},"gpt-6-luna":{"draws":32,"losses":44,"wins":68},"gpt-6-sol":{"draws":14,"losses":82,"wins":48},"gpt-6.1-sol":{"draws":3,"losses":105,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":65},"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":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":20,"losses":31,"wins":105},"meta/muse-glimmer-30b":{"draws":21,"losses":21,"wins":84},"meta/muse-spark-1.2":{"draws":26,"losses":43,"wins":69},"meta/muse-spark-1.3":{"draws":22,"losses":54,"wins":68},"meta/muse-spark-open":{"draws":24,"losses":52,"wins":62},"meta/muse-wonder":{"draws":21,"losses":54,"wins":69},"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":19,"losses":8,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":28,"losses":46,"wins":64},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":88,"wins":36},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":5,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":22,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":11,"wins":39},"o3":{"draws":17,"losses":46,"wins":135},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":82},"poolside/laguna-s-2.1":{"draws":25,"losses":26,"wins":87},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":44},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":51,"wins":62},"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":23,"losses":42,"wins":79},"qwen/qwen3.8-max-0902":{"draws":27,"losses":51,"wins":66},"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":85,"losses":164,"wins":225},"stealth/space-bunny-alpha":{"draws":22,"losses":24,"wins":68},"stepfun/step-3.7-flash":{"draws":11,"losses":26,"wins":65},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":49},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":67},"thinkingmachines/inkling":{"draws":41,"losses":41,"wins":110},"thinkingmachines/inkling-small":{"draws":32,"losses":21,"wins":91},"unbiased/pareto-26.10":{"draws":4,"losses":36,"wins":8},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"wins":9},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":50,"wins":63},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":61},"x-ai/grok-4.7":{"draws":15,"losses":64,"wins":47},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":49,"losses":27,"wins":146},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":34,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":37,"wins":46},"z-ai/glm-5.2":{"draws":55,"losses":66,"wins":167},"z-ai/glm-5.3":{"draws":24,"losses":62,"wins":52},"z-ai/glm-5.3-flash":{"draws":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":0,"losses":61,"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":9,"losses":38,"wins":3},"claude-opus-5":{"draws":6,"losses":80,"wins":4},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":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":21,"losses":34,"wins":25},"deepseek/deepseek-v4-pro":{"draws":9,"losses":29,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":32,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":33,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":47,"wins":1},"elorian/glimpse":{"draws":3,"losses":21,"wins":6},"fireworks/ember-1":{"draws":11,"losses":34,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":27,"wins":16},"gemini-4-argon":{"draws":0,"losses":52,"wins":2},"google/gemini-3.1-flash-lite":{"draws":11,"losses":14,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":44,"wins":12},"google/gemini-3.5-flash-lite":{"draws":32,"losses":35,"wins":31},"google/gemini-3.6-flash":{"draws":20,"losses":75,"wins":9},"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":6,"losses":9,"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":9,"losses":17,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":36,"wins":13},"gpt-5.5":{"draws":12,"losses":36,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":28,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":47,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":33,"wins":6},"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},"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":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":39,"wins":15},"meta/muse-glimmer-30b":{"draws":18,"losses":17,"wins":15},"meta/muse-spark-1.2":{"draws":3,"losses":40,"wins":9},"meta/muse-spark-1.3":{"draws":4,"losses":48,"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":10,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":35,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":52,"wins":0},"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":15,"losses":20,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":22,"wins":3},"o3":{"draws":13,"losses":61,"wins":14},"openai/gpt-oss-120b":{"draws":15,"losses":20,"wins":15},"poolside/laguna-s-2.1":{"draws":13,"losses":18,"wins":23},"qwen/qwen3.7-max":{"draws":11,"losses":17,"wins":4},"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":41,"wins":4},"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":131,"wins":23},"stealth/space-bunny-alpha":{"draws":11,"losses":28,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":25,"wins":7},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":14,"losses":36,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":33,"wins":21},"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":8,"losses":43,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":41,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":45,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":31,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":23,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":60,"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":63,"losses":71,"wins":62},"claude-fable-5":{"draws":37,"losses":165,"wins":14},"claude-fable-5-1":{"draws":7,"losses":232,"wins":1},"claude-haiku-5-5":{"draws":57,"losses":121,"wins":30},"claude-opus-4-5":{"draws":106,"losses":181,"wins":65},"claude-opus-4-8":{"draws":49,"losses":125,"wins":26},"claude-opus-5":{"draws":42,"losses":299,"wins":21},"claude-opus-5-5":{"draws":13,"losses":218,"wins":5},"claude-sonnet-5":{"draws":63,"losses":113,"wins":40},"claude-sonnet-5-5":{"draws":45,"losses":140,"wins":31},"cohere/north-mini-code":{"draws":21,"losses":25,"wins":34},"deepseek/deepseek-v4-flash":{"draws":80,"losses":90,"wins":90},"deepseek/deepseek-v4-pro":{"draws":53,"losses":99,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":54,"losses":94,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":70,"losses":121,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":40,"losses":150,"wins":26},"elorian/glimpse":{"draws":25,"losses":61,"wins":30},"fireworks/ember-1":{"draws":65,"losses":110,"wins":41},"gemini-3.1-pro-preview":{"draws":67,"losses":96,"wins":53},"gemini-4-argon":{"draws":13,"losses":199,"wins":4},"google/gemini-3.1-flash-lite":{"draws":45,"losses":26,"wins":75},"google/gemini-3.5-flash":{"draws":64,"losses":146,"wins":60},"google/gemini-3.5-flash-lite":{"draws":118,"losses":133,"wins":123},"google/gemini-3.6-flash":{"draws":97,"losses":256,"wins":59},"google/gemini-3.8-flash":{"draws":39,"losses":156,"wins":21},"google/gemma-4-31b-it":{"draws":58,"losses":22,"wins":46},"gpt-4.1":{"draws":22,"losses":34,"wins":16},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":57,"losses":92,"wins":41},"gpt-5.4":{"draws":53,"losses":123,"wins":30},"gpt-5.4-mini":{"draws":56,"losses":51,"wins":37},"gpt-5.4-nano":{"draws":53,"losses":92,"wins":81},"gpt-5.5":{"draws":67,"losses":107,"wins":22},"gpt-5.6-luna":{"draws":84,"losses":82,"wins":50},"gpt-5.6-sol":{"draws":29,"losses":166,"wins":21},"gpt-5.6-terra":{"draws":67,"losses":109,"wins":32},"gpt-6-astra":{"draws":11,"losses":200,"wins":5},"gpt-6-luna":{"draws":66,"losses":105,"wins":45},"gpt-6-sol":{"draws":32,"losses":168,"wins":16},"gpt-6.1-sol":{"draws":13,"losses":197,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":64,"losses":28,"wins":60},"inception/mercury-3":{"draws":43,"losses":70,"wins":37},"inclusionai/ling-3.0-flash":{"draws":63,"losses":42,"wins":53},"inclusionai/ling-3.1-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":64,"losses":76,"wins":94},"meta/muse-glimmer-30b":{"draws":82,"losses":47,"wins":57},"meta/muse-spark-1.2":{"draws":52,"losses":120,"wins":34},"meta/muse-spark-1.3":{"draws":42,"losses":150,"wins":24},"meta/muse-spark-open":{"draws":39,"losses":136,"wins":31},"meta/muse-wonder":{"draws":37,"losses":148,"wins":31},"minimax/minimax-m3":{"draws":34,"losses":43,"wins":43},"minimax/minimax-m3.1-flash":{"draws":39,"losses":86,"wins":61},"mistralai/mistral-large-4-0":{"draws":45,"losses":69,"wins":20},"mistralai/mistral-medium-3-5":{"draws":53,"losses":29,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":29,"wins":11},"moonshotai/kimi-k3":{"draws":59,"losses":105,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":187,"wins":3},"nex-agi/nex-n2-pro":{"draws":25,"losses":32,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":23,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":67,"losses":58,"wins":69},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":44,"wins":32},"o3":{"draws":45,"losses":180,"wins":81},"openai/gpt-oss-120b":{"draws":72,"losses":64,"wins":54},"poolside/laguna-s-2.1":{"draws":75,"losses":72,"wins":63},"qwen/qwen3.7-max":{"draws":53,"losses":49,"wins":28},"qwen/qwen3.7-plus":{"draws":33,"losses":36,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":69,"losses":116,"wins":31},"qwen/qwen3.8-27b":{"draws":38,"losses":81,"wins":35},"qwen/qwen3.8-flash":{"draws":44,"losses":70,"wins":30},"qwen/qwen3.8-max":{"draws":67,"losses":113,"wins":36},"qwen/qwen3.8-max-0902":{"draws":64,"losses":122,"wins":30},"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":165,"losses":400,"wins":131},"stealth/space-bunny-alpha":{"draws":58,"losses":71,"wins":39},"stepfun/step-3.7-flash":{"draws":35,"losses":58,"wins":65},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":35,"losses":43,"wins":38},"tencent/hy4-preview":{"draws":54,"losses":117,"wins":35},"thinkingmachines/inkling":{"draws":94,"losses":98,"wins":92},"thinkingmachines/inkling-small":{"draws":87,"losses":48,"wins":81},"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":39,"losses":144,"wins":33},"x-ai/grok-4.6":{"draws":54,"losses":140,"wins":22},"x-ai/grok-4.7":{"draws":19,"losses":158,"wins":15},"x-ai/grok-build-0.1":{"draws":27,"losses":19,"wins":26},"xiaomi/mimo-v2.5":{"draws":117,"losses":108,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":34,"losses":46,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":31,"losses":81,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":95,"wins":24},"z-ai/glm-5.2":{"draws":151,"losses":180,"wins":101},"z-ai/glm-5.3":{"draws":44,"losses":150,"wins":12},"z-ai/glm-5.3-flash":{"draws":54,"losses":119,"wins":43},"z-ai/glm-5.3-flashx":{"draws":58,"losses":126,"wins":32}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":32,"wins":60},"claude-fable-5":{"draws":25,"losses":80,"wins":27},"claude-fable-5-1":{"draws":8,"losses":137,"wins":5},"claude-haiku-5-5":{"draws":35,"losses":50,"wins":41},"claude-opus-4-5":{"draws":60,"losses":78,"wins":76},"claude-opus-4-8":{"draws":28,"losses":55,"wins":37},"claude-opus-5":{"draws":27,"losses":173,"wins":32},"claude-opus-5-5":{"draws":11,"losses":128,"wins":5},"claude-sonnet-5":{"draws":40,"losses":45,"wins":47},"claude-sonnet-5-5":{"draws":32,"losses":67,"wins":33},"cohere/north-mini-code":{"draws":9,"losses":14,"wins":29},"deepseek/deepseek-v4-flash":{"draws":53,"losses":44,"wins":99},"deepseek/deepseek-v4-pro":{"draws":20,"losses":30,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":48,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":55,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":79,"wins":24},"elorian/glimpse":{"draws":20,"losses":37,"wins":17},"fireworks/ember-1":{"draws":39,"losses":53,"wins":40},"gemini-3.1-pro-preview":{"draws":33,"losses":46,"wins":53},"gemini-4-argon":{"draws":14,"losses":104,"wins":14},"google/gemini-3.1-flash-lite":{"draws":25,"losses":7,"wins":56},"google/gemini-3.5-flash":{"draws":40,"losses":70,"wins":56},"google/gemini-3.5-flash-lite":{"draws":61,"losses":65,"wins":106},"google/gemini-3.6-flash":{"draws":64,"losses":106,"wins":84},"google/gemini-3.8-flash":{"draws":27,"losses":72,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":14,"wins":34},"gpt-4.1":{"draws":13,"losses":9,"wins":22},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":30,"losses":35,"wins":53},"gpt-5.4":{"draws":27,"losses":63,"wins":38},"gpt-5.4-mini":{"draws":32,"losses":23,"wins":33},"gpt-5.4-nano":{"draws":18,"losses":45,"wins":67},"gpt-5.5":{"draws":37,"losses":60,"wins":27},"gpt-5.6-luna":{"draws":43,"losses":36,"wins":53},"gpt-5.6-sol":{"draws":16,"losses":86,"wins":30},"gpt-5.6-terra":{"draws":40,"losses":42,"wins":44},"gpt-6-astra":{"draws":11,"losses":113,"wins":8},"gpt-6-luna":{"draws":34,"losses":56,"wins":42},"gpt-6-sol":{"draws":12,"losses":98,"wins":22},"gpt-6.1-sol":{"draws":8,"losses":116,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":37,"losses":8,"wins":45},"inception/mercury-3":{"draws":24,"losses":31,"wins":31},"inclusionai/ling-3.0-flash":{"draws":34,"losses":14,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":29,"losses":30,"wins":85},"meta/muse-glimmer-30b":{"draws":37,"losses":27,"wins":56},"meta/muse-spark-1.2":{"draws":24,"losses":59,"wins":45},"meta/muse-spark-1.3":{"draws":22,"losses":75,"wins":35},"meta/muse-spark-open":{"draws":27,"losses":71,"wins":30},"meta/muse-wonder":{"draws":23,"losses":79,"wins":30},"minimax/minimax-m3":{"draws":11,"losses":13,"wins":48},"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":21,"losses":8,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":12,"wins":15},"moonshotai/kimi-k3":{"draws":28,"losses":57,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":102,"wins":11},"nex-agi/nex-n2-pro":{"draws":17,"losses":12,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":19,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":20,"wins":25},"o3":{"draws":22,"losses":70,"wins":92},"openai/gpt-oss-120b":{"draws":35,"losses":26,"wins":55},"poolside/laguna-s-2.1":{"draws":35,"losses":44,"wins":49},"qwen/qwen3.7-max":{"draws":25,"losses":16,"wins":35},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":59,"wins":37},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":31},"qwen/qwen3.8-flash":{"draws":20,"losses":38,"wins":30},"qwen/qwen3.8-max":{"draws":37,"losses":59,"wins":36},"qwen/qwen3.8-max-0902":{"draws":34,"losses":63,"wins":35},"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":104,"losses":206,"wins":132},"stealth/space-bunny-alpha":{"draws":31,"losses":28,"wins":47},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":55},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":24,"losses":18,"wins":30},"tencent/hy4-preview":{"draws":32,"losses":60,"wins":36},"thinkingmachines/inkling":{"draws":56,"losses":31,"wins":93},"thinkingmachines/inkling-small":{"draws":45,"losses":20,"wins":67},"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":59,"wins":39},"x-ai/grok-4.6":{"draws":33,"losses":73,"wins":26},"x-ai/grok-4.7":{"draws":10,"losses":85,"wins":21},"x-ai/grok-build-0.1":{"draws":18,"losses":9,"wins":17},"xiaomi/mimo-v2.5":{"draws":73,"losses":31,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":22,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":35,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":47,"wins":25},"z-ai/glm-5.2":{"draws":89,"losses":76,"wins":99},"z-ai/glm-5.3":{"draws":22,"losses":78,"wins":26},"z-ai/glm-5.3-flash":{"draws":22,"losses":74,"wins":36},"z-ai/glm-5.3-flashx":{"draws":32,"losses":60,"wins":40}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":35,"wins":53},"claude-fable-5":{"draws":20,"losses":85,"wins":27},"claude-fable-5-1":{"draws":4,"losses":143,"wins":3},"claude-haiku-5-5":{"draws":34,"losses":63,"wins":29},"claude-opus-4-5":{"draws":60,"losses":78,"wins":76},"claude-opus-4-8":{"draws":30,"losses":52,"wins":38},"claude-opus-5":{"draws":21,"losses":174,"wins":27},"claude-opus-5-5":{"draws":7,"losses":133,"wins":4},"claude-sonnet-5":{"draws":42,"losses":42,"wins":48},"claude-sonnet-5-5":{"draws":22,"losses":77,"wins":33},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":32},"deepseek/deepseek-v4-flash":{"draws":54,"losses":50,"wins":94},"deepseek/deepseek-v4-pro":{"draws":34,"losses":40,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":34,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":67,"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":34,"losses":56,"wins":42},"gemini-3.1-pro-preview":{"draws":35,"losses":45,"wins":52},"gemini-4-argon":{"draws":13,"losses":111,"wins":8},"google/gemini-3.1-flash-lite":{"draws":27,"losses":8,"wins":53},"google/gemini-3.5-flash":{"draws":40,"losses":74,"wins":52},"google/gemini-3.5-flash-lite":{"draws":72,"losses":48,"wins":112},"google/gemini-3.6-flash":{"draws":57,"losses":120,"wins":77},"google/gemini-3.8-flash":{"draws":28,"losses":70,"wins":34},"google/gemma-4-31b-it":{"draws":31,"losses":7,"wins":38},"gpt-4.1":{"draws":11,"losses":13,"wins":20},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":23,"losses":47,"wins":46},"gpt-5.4":{"draws":23,"losses":68,"wins":37},"gpt-5.4-mini":{"draws":30,"losses":18,"wins":40},"gpt-5.4-nano":{"draws":23,"losses":43,"wins":64},"gpt-5.5":{"draws":30,"losses":54,"wins":38},"gpt-5.6-luna":{"draws":43,"losses":38,"wins":51},"gpt-5.6-sol":{"draws":17,"losses":88,"wins":27},"gpt-5.6-terra":{"draws":37,"losses":52,"wins":39},"gpt-6-astra":{"draws":8,"losses":123,"wins":1},"gpt-6-luna":{"draws":34,"losses":49,"wins":49},"gpt-6-sol":{"draws":13,"losses":99,"wins":20},"gpt-6.1-sol":{"draws":8,"losses":121,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":14,"wins":46},"inception/mercury-3":{"draws":22,"losses":38,"wins":28},"inclusionai/ling-3.0-flash":{"draws":34,"losses":20,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":39,"losses":34,"wins":71},"meta/muse-glimmer-30b":{"draws":34,"losses":21,"wins":61},"meta/muse-spark-1.2":{"draws":25,"losses":61,"wins":40},"meta/muse-spark-1.3":{"draws":26,"losses":67,"wins":39},"meta/muse-spark-open":{"draws":20,"losses":73,"wins":35},"meta/muse-wonder":{"draws":27,"losses":78,"wins":27},"minimax/minimax-m3":{"draws":14,"losses":15,"wins":41},"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":21,"losses":13,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":36,"losses":41,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":104,"wins":10},"nex-agi/nex-n2-pro":{"draws":13,"losses":12,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":20,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":23,"wins":23},"o3":{"draws":27,"losses":57,"wins":100},"openai/gpt-oss-120b":{"draws":36,"losses":27,"wins":51},"poolside/laguna-s-2.1":{"draws":30,"losses":36,"wins":58},"qwen/qwen3.7-max":{"draws":27,"losses":16,"wins":33},"qwen/qwen3.7-plus":{"draws":15,"losses":21,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":58,"wins":43},"qwen/qwen3.8-27b":{"draws":25,"losses":39,"wins":30},"qwen/qwen3.8-flash":{"draws":20,"losses":36,"wins":32},"qwen/qwen3.8-max":{"draws":40,"losses":54,"wins":38},"qwen/qwen3.8-max-0902":{"draws":37,"losses":56,"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":105,"losses":188,"wins":147},"stealth/space-bunny-alpha":{"draws":29,"losses":29,"wins":46},"stepfun/step-3.7-flash":{"draws":21,"losses":20,"wins":55},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":25,"losses":21,"wins":24},"tencent/hy4-preview":{"draws":27,"losses":57,"wins":44},"thinkingmachines/inkling":{"draws":58,"losses":43,"wins":75},"thinkingmachines/inkling-small":{"draws":39,"losses":25,"wins":68},"unbiased/pareto-26.10":{"draws":3,"losses":40,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":3,"wins":26},"x-ai/grok-4.5":{"draws":29,"losses":59,"wins":44},"x-ai/grok-4.6":{"draws":36,"losses":67,"wins":29},"x-ai/grok-4.7":{"draws":9,"losses":82,"wins":23},"x-ai/grok-build-0.1":{"draws":19,"losses":4,"wins":21},"xiaomi/mimo-v2.5":{"draws":64,"losses":40,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":35,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":48,"wins":27},"z-ai/glm-5.2":{"draws":85,"losses":81,"wins":98},"z-ai/glm-5.3":{"draws":23,"losses":78,"wins":25},"z-ai/glm-5.3-flash":{"draws":19,"losses":75,"wins":38},"z-ai/glm-5.3-flashx":{"draws":27,"losses":66,"wins":39}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":32,"wins":60},"claude-fable-5":{"draws":36,"losses":72,"wins":36},"claude-fable-5-1":{"draws":14,"losses":136,"wins":12},"claude-haiku-5-5":{"draws":43,"losses":56,"wins":39},"claude-opus-4-5":{"draws":62,"losses":68,"wins":104},"claude-opus-4-8":{"draws":32,"losses":47,"wins":53},"claude-opus-5":{"draws":39,"losses":170,"wins":37},"claude-opus-5-5":{"draws":10,"losses":132,"wins":14},"claude-sonnet-5":{"draws":44,"losses":47,"wins":53},"claude-sonnet-5-5":{"draws":31,"losses":72,"wins":41},"cohere/north-mini-code":{"draws":13,"losses":8,"wins":33},"deepseek/deepseek-v4-flash":{"draws":70,"losses":25,"wins":121},"deepseek/deepseek-v4-pro":{"draws":35,"losses":42,"wins":55},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":33,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":37,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":33,"losses":70,"wins":41},"elorian/glimpse":{"draws":17,"losses":31,"wins":30},"fireworks/ember-1":{"draws":41,"losses":53,"wins":50},"gemini-3.1-pro-preview":{"draws":41,"losses":48,"wins":55},"gemini-4-argon":{"draws":12,"losses":114,"wins":18},"google/gemini-3.1-flash-lite":{"draws":35,"losses":8,"wins":53},"google/gemini-3.5-flash":{"draws":49,"losses":57,"wins":74},"google/gemini-3.5-flash-lite":{"draws":76,"losses":52,"wins":124},"google/gemini-3.6-flash":{"draws":76,"losses":113,"wins":87},"google/gemini-3.8-flash":{"draws":36,"losses":62,"wins":46},"google/gemma-4-31b-it":{"draws":34,"losses":12,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":24},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":39,"losses":30,"wins":57},"gpt-5.4":{"draws":39,"losses":54,"wins":45},"gpt-5.4-mini":{"draws":37,"losses":20,"wins":39},"gpt-5.4-nano":{"draws":37,"losses":35,"wins":72},"gpt-5.5":{"draws":45,"losses":42,"wins":45},"gpt-5.6-luna":{"draws":52,"losses":28,"wins":64},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":43},"gpt-5.6-terra":{"draws":54,"losses":34,"wins":50},"gpt-6-astra":{"draws":16,"losses":123,"wins":5},"gpt-6-luna":{"draws":46,"losses":40,"wins":58},"gpt-6-sol":{"draws":24,"losses":89,"wins":31},"gpt-6.1-sol":{"draws":13,"losses":115,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":45,"losses":9,"wins":48},"inception/mercury-3":{"draws":27,"losses":29,"wins":40},"inclusionai/ling-3.0-flash":{"draws":44,"losses":9,"wins":49},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":36,"wins":87},"meta/muse-glimmer-30b":{"draws":52,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":33,"losses":52,"wins":53},"meta/muse-spark-1.3":{"draws":30,"losses":62,"wins":52},"meta/muse-spark-open":{"draws":27,"losses":55,"wins":56},"meta/muse-wonder":{"draws":37,"losses":71,"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":30,"losses":9,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":15},"moonshotai/kimi-k3":{"draws":41,"losses":40,"wins":57},"moonshotai/kimi-k3.1-pro":{"draws":23,"losses":95,"wins":20},"nex-agi/nex-n2-pro":{"draws":16,"losses":5,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":22,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":17,"wins":34},"o3":{"draws":39,"losses":63,"wins":96},"openai/gpt-oss-120b":{"draws":40,"losses":24,"wins":62},"poolside/laguna-s-2.1":{"draws":55,"losses":23,"wins":60},"qwen/qwen3.7-max":{"draws":30,"losses":19,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":7,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":50,"wins":58},"qwen/qwen3.8-27b":{"draws":24,"losses":28,"wins":50},"qwen/qwen3.8-flash":{"draws":33,"losses":22,"wins":41},"qwen/qwen3.8-max":{"draws":42,"losses":48,"wins":54},"qwen/qwen3.8-max-0902":{"draws":49,"losses":46,"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":110,"losses":183,"wins":180},"stealth/space-bunny-alpha":{"draws":35,"losses":25,"wins":54},"stepfun/step-3.7-flash":{"draws":24,"losses":16,"wins":62},"stepfun/step-5-preview":{"draws":4,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":26,"losses":16,"wins":36},"tencent/hy4-preview":{"draws":41,"losses":56,"wins":41},"thinkingmachines/inkling":{"draws":63,"losses":30,"wins":99},"thinkingmachines/inkling-small":{"draws":40,"losses":25,"wins":79},"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":65,"wins":48},"x-ai/grok-4.6":{"draws":41,"losses":59,"wins":44},"x-ai/grok-4.7":{"draws":12,"losses":82,"wins":32},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":27},"xiaomi/mimo-v2.5":{"draws":75,"losses":29,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":20,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":30,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":43,"wins":31},"z-ai/glm-5.2":{"draws":103,"losses":63,"wins":122},"z-ai/glm-5.3":{"draws":27,"losses":84,"wins":27},"z-ai/glm-5.3-flash":{"draws":26,"losses":60,"wins":58},"z-ai/glm-5.3-flashx":{"draws":40,"losses":61,"wins":43}},"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":24,"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},"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":0,"losses":0,"wins":6},"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":27,"losses":38,"wins":73},"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":8,"losses":2,"wins":26},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":81},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":102,"wins":23},"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":22,"losses":10,"wins":94},"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":230},"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":0,"losses":4,"wins":8},"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":10,"losses":14,"wins":54},"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":73},"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},"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":0,"losses":0,"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":7,"wins":9},"moonshotai/kimi-k3":{"draws":19,"losses":26,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":56,"wins":11},"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":15,"losses":7,"wins":44},"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":0,"losses":2,"wins":6},"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":6,"losses":14,"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":37,"losses":26,"wins":69},"claude-fable-5":{"draws":30,"losses":92,"wins":22},"claude-fable-5-1":{"draws":5,"losses":146,"wins":11},"claude-haiku-5-5":{"draws":36,"losses":64,"wins":38},"claude-opus-4-5":{"draws":78,"losses":66,"wins":90},"claude-opus-4-8":{"draws":43,"losses":53,"wins":36},"claude-opus-5":{"draws":26,"losses":176,"wins":44},"claude-opus-5-5":{"draws":8,"losses":137,"wins":11},"claude-sonnet-5":{"draws":40,"losses":44,"wins":60},"claude-sonnet-5-5":{"draws":28,"losses":73,"wins":43},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":34},"deepseek/deepseek-v4-flash":{"draws":65,"losses":41,"wins":110},"deepseek/deepseek-v4-pro":{"draws":39,"losses":40,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":50,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":34,"losses":78,"wins":32},"elorian/glimpse":{"draws":18,"losses":29,"wins":31},"fireworks/ember-1":{"draws":26,"losses":35,"wins":35},"gemini-3.1-pro-preview":{"draws":33,"losses":45,"wins":66},"gemini-4-argon":{"draws":10,"losses":118,"wins":16},"google/gemini-3.1-flash-lite":{"draws":17,"losses":8,"wins":71},"google/gemini-3.5-flash":{"draws":47,"losses":64,"wins":69},"google/gemini-3.5-flash-lite":{"draws":87,"losses":52,"wins":113},"google/gemini-3.6-flash":{"draws":77,"losses":97,"wins":102},"google/gemini-3.8-flash":{"draws":35,"losses":61,"wins":48},"google/gemma-4-31b-it":{"draws":31,"losses":12,"wins":41},"gpt-4.1":{"draws":13,"losses":16,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":8},"gpt-5":{"draws":32,"losses":34,"wins":60},"gpt-5.4":{"draws":36,"losses":62,"wins":40},"gpt-5.4-mini":{"draws":36,"losses":15,"wins":45},"gpt-5.4-nano":{"draws":33,"losses":31,"wins":80},"gpt-5.5":{"draws":40,"losses":50,"wins":42},"gpt-5.6-luna":{"draws":46,"losses":43,"wins":55},"gpt-5.6-sol":{"draws":23,"losses":83,"wins":38},"gpt-5.6-terra":{"draws":42,"losses":38,"wins":58},"gpt-6-astra":{"draws":10,"losses":128,"wins":6},"gpt-6-luna":{"draws":37,"losses":43,"wins":64},"gpt-6-sol":{"draws":21,"losses":100,"wins":23},"gpt-6.1-sol":{"draws":9,"losses":118,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":42,"losses":7,"wins":53},"inception/mercury-3":{"draws":33,"losses":32,"wins":31},"inclusionai/ling-3.0-flash":{"draws":41,"losses":5,"wins":56},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":40,"losses":26,"wins":90},"meta/muse-glimmer-30b":{"draws":40,"losses":19,"wins":67},"meta/muse-spark-1.2":{"draws":37,"losses":48,"wins":53},"meta/muse-spark-1.3":{"draws":37,"losses":65,"wins":42},"meta/muse-spark-open":{"draws":29,"losses":59,"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":24,"losses":9,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":43,"losses":38,"wins":57},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":114,"wins":9},"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":45,"losses":22,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":19,"wins":29},"o3":{"draws":38,"losses":50,"wins":110},"openai/gpt-oss-120b":{"draws":45,"losses":18,"wins":63},"poolside/laguna-s-2.1":{"draws":47,"losses":26,"wins":65},"qwen/qwen3.7-max":{"draws":26,"losses":19,"wins":39},"qwen/qwen3.7-plus":{"draws":21,"losses":13,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":49,"losses":47,"wins":48},"qwen/qwen3.8-27b":{"draws":30,"losses":37,"wins":35},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":33},"qwen/qwen3.8-max":{"draws":44,"losses":42,"wins":58},"qwen/qwen3.8-max-0902":{"draws":41,"losses":61,"wins":42},"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":116,"losses":184,"wins":174},"stealth/space-bunny-alpha":{"draws":32,"losses":27,"wins":55},"stepfun/step-3.7-flash":{"draws":23,"losses":18,"wins":61},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":28,"losses":14,"wins":36},"tencent/hy4-preview":{"draws":40,"losses":54,"wins":44},"thinkingmachines/inkling":{"draws":58,"losses":26,"wins":108},"thinkingmachines/inkling-small":{"draws":45,"losses":20,"wins":79},"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":33,"losses":71,"wins":40},"x-ai/grok-4.6":{"draws":38,"losses":63,"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":74,"losses":34,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":41,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":45,"wins":30},"z-ai/glm-5.2":{"draws":89,"losses":71,"wins":128},"z-ai/glm-5.3":{"draws":24,"losses":87,"wins":27},"z-ai/glm-5.3-flash":{"draws":26,"losses":72,"wins":46},"z-ai/glm-5.3-flashx":{"draws":29,"losses":65,"wins":50}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":36,"wins":60},"claude-fable-5":{"draws":28,"losses":86,"wins":30},"claude-fable-5-1":{"draws":8,"losses":150,"wins":4},"claude-haiku-5-5":{"draws":32,"losses":60,"wins":46},"claude-opus-4-5":{"draws":61,"losses":97,"wins":76},"claude-opus-4-8":{"draws":35,"losses":62,"wins":35},"claude-opus-5":{"draws":23,"losses":186,"wins":37},"claude-opus-5-5":{"draws":9,"losses":137,"wins":10},"claude-sonnet-5":{"draws":43,"losses":51,"wins":50},"claude-sonnet-5-5":{"draws":22,"losses":82,"wins":40},"cohere/north-mini-code":{"draws":11,"losses":16,"wins":27},"deepseek/deepseek-v4-flash":{"draws":67,"losses":53,"wins":96},"deepseek/deepseek-v4-pro":{"draws":33,"losses":53,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":52,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":55,"wins":48},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":81,"wins":37},"elorian/glimpse":{"draws":15,"losses":32,"wins":31},"fireworks/ember-1":{"draws":33,"losses":66,"wins":45},"gemini-3.1-pro-preview":{"draws":26,"losses":35,"wins":35},"gemini-4-argon":{"draws":11,"losses":118,"wins":15},"google/gemini-3.1-flash-lite":{"draws":22,"losses":18,"wins":56},"google/gemini-3.5-flash":{"draws":41,"losses":81,"wins":58},"google/gemini-3.5-flash-lite":{"draws":83,"losses":64,"wins":105},"google/gemini-3.6-flash":{"draws":67,"losses":125,"wins":84},"google/gemini-3.8-flash":{"draws":28,"losses":81,"wins":35},"google/gemma-4-31b-it":{"draws":30,"losses":15,"wins":39},"gpt-4.1":{"draws":15,"losses":15,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":41,"losses":35,"wins":50},"gpt-5.4":{"draws":29,"losses":67,"wins":42},"gpt-5.4-mini":{"draws":36,"losses":25,"wins":35},"gpt-5.4-nano":{"draws":35,"losses":40,"wins":69},"gpt-5.5":{"draws":37,"losses":62,"wins":33},"gpt-5.6-luna":{"draws":45,"losses":46,"wins":53},"gpt-5.6-sol":{"draws":17,"losses":96,"wins":31},"gpt-5.6-terra":{"draws":46,"losses":44,"wins":48},"gpt-6-astra":{"draws":10,"losses":130,"wins":4},"gpt-6-luna":{"draws":36,"losses":47,"wins":61},"gpt-6-sol":{"draws":16,"losses":100,"wins":28},"gpt-6.1-sol":{"draws":7,"losses":127,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":40},"inception/mercury-3":{"draws":32,"losses":39,"wins":25},"inclusionai/ling-3.0-flash":{"draws":39,"losses":10,"wins":53},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":37,"losses":45,"wins":74},"meta/muse-glimmer-30b":{"draws":50,"losses":16,"wins":60},"meta/muse-spark-1.2":{"draws":33,"losses":57,"wins":48},"meta/muse-spark-1.3":{"draws":26,"losses":78,"wins":40},"meta/muse-spark-open":{"draws":29,"losses":69,"wins":40},"meta/muse-wonder":{"draws":26,"losses":94,"wins":24},"minimax/minimax-m3":{"draws":17,"losses":23,"wins":38},"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":30,"losses":11,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":61,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":103,"wins":20},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":8,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":29,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":25,"wins":26},"o3":{"draws":31,"losses":91,"wins":76},"openai/gpt-oss-120b":{"draws":42,"losses":31,"wins":53},"poolside/laguna-s-2.1":{"draws":44,"losses":34,"wins":60},"qwen/qwen3.7-max":{"draws":26,"losses":29,"wins":29},"qwen/qwen3.7-plus":{"draws":23,"losses":14,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":64,"wins":45},"qwen/qwen3.8-27b":{"draws":23,"losses":47,"wins":32},"qwen/qwen3.8-flash":{"draws":36,"losses":30,"wins":30},"qwen/qwen3.8-max":{"draws":43,"losses":56,"wins":45},"qwen/qwen3.8-max-0902":{"draws":40,"losses":65,"wins":39},"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":104,"losses":225,"wins":145},"stealth/space-bunny-alpha":{"draws":35,"losses":35,"wins":44},"stepfun/step-3.7-flash":{"draws":21,"losses":32,"wins":49},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":23,"losses":22,"wins":33},"tencent/hy4-preview":{"draws":33,"losses":65,"wins":40},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":87},"thinkingmachines/inkling-small":{"draws":45,"losses":28,"wins":71},"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":31,"losses":73,"wins":40},"x-ai/grok-4.6":{"draws":40,"losses":76,"wins":28},"x-ai/grok-4.7":{"draws":14,"losses":88,"wins":24},"x-ai/grok-build-0.1":{"draws":17,"losses":12,"wins":19},"xiaomi/mimo-v2.5":{"draws":74,"losses":49,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":26,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":42,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":56,"wins":24},"z-ai/glm-5.2":{"draws":85,"losses":94,"wins":109},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":30},"z-ai/glm-5.3-flash":{"draws":36,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":37,"losses":69,"wins":38}},"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},"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":0,"losses":0,"wins":6},"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":11,"losses":21,"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":4,"losses":3,"wins":29},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":117},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":57,"wins":67},"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":9,"losses":3,"wins":114},"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":0,"losses":2,"wins":10},"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":2,"losses":4,"wins":72},"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":28,"losses":43,"wins":17},"claude-fable-5":{"draws":10,"losses":82,"wins":4},"claude-fable-5-1":{"draws":5,"losses":101,"wins":0},"claude-haiku-5-5":{"draws":22,"losses":66,"wins":8},"claude-opus-4-5":{"draws":37,"losses":114,"wins":9},"claude-opus-4-8":{"draws":20,"losses":71,"wins":5},"claude-opus-5":{"draws":18,"losses":124,"wins":8},"claude-opus-5-5":{"draws":8,"losses":96,"wins":0},"claude-sonnet-5":{"draws":29,"losses":61,"wins":6},"claude-sonnet-5-5":{"draws":15,"losses":69,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4-flash":{"draws":45,"losses":75,"wins":26},"deepseek/deepseek-v4-pro":{"draws":25,"losses":56,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":53,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":53,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":78,"wins":4},"elorian/glimpse":{"draws":13,"losses":30,"wins":7},"fireworks/ember-1":{"draws":17,"losses":71,"wins":8},"gemini-3.1-pro-preview":{"draws":22,"losses":56,"wins":18},"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":31,"losses":81,"wins":14},"google/gemini-3.5-flash-lite":{"draws":46,"losses":93,"wins":35},"google/gemini-3.6-flash":{"draws":41,"losses":130,"wins":15},"google/gemini-3.8-flash":{"draws":24,"losses":70,"wins":2},"google/gemma-4-31b-it":{"draws":19,"losses":26,"wins":15},"gpt-4.1":{"draws":11,"losses":17,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":25,"losses":56,"wins":3},"gpt-5.4":{"draws":19,"losses":67,"wins":8},"gpt-5.4-mini":{"draws":20,"losses":38,"wins":6},"gpt-5.4-nano":{"draws":22,"losses":64,"wins":22},"gpt-5.5":{"draws":25,"losses":58,"wins":5},"gpt-5.6-luna":{"draws":25,"losses":50,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":83,"wins":5},"gpt-5.6-terra":{"draws":29,"losses":54,"wins":7},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":27,"losses":58,"wins":11},"gpt-6-sol":{"draws":14,"losses":80,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":92,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":27,"losses":26,"wins":19},"inception/mercury-3":{"draws":13,"losses":40,"wins":7},"inclusionai/ling-3.0-flash":{"draws":24,"losses":23,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":62,"wins":28},"meta/muse-glimmer-30b":{"draws":33,"losses":30,"wins":19},"meta/muse-spark-1.2":{"draws":21,"losses":60,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":77,"wins":5},"meta/muse-spark-open":{"draws":15,"losses":73,"wins":6},"meta/muse-wonder":{"draws":9,"losses":84,"wins":3},"minimax/minimax-m3":{"draws":13,"losses":25,"wins":16},"minimax/minimax-m3.1-flash":{"draws":17,"losses":59,"wins":10},"mistralai/mistral-large-4-0":{"draws":17,"losses":39,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":23,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":21,"wins":1},"moonshotai/kimi-k3":{"draws":23,"losses":56,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":91,"wins":0},"nex-agi/nex-n2-pro":{"draws":10,"losses":27,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":14,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":42,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":31,"wins":6},"o3":{"draws":23,"losses":124,"wins":11},"openai/gpt-oss-120b":{"draws":24,"losses":39,"wins":19},"poolside/laguna-s-2.1":{"draws":26,"losses":43,"wins":17},"qwen/qwen3.7-max":{"draws":19,"losses":34,"wins":7},"qwen/qwen3.7-plus":{"draws":13,"losses":31,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":67,"wins":4},"qwen/qwen3.8-27b":{"draws":15,"losses":45,"wins":10},"qwen/qwen3.8-flash":{"draws":21,"losses":33,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":66,"wins":1},"qwen/qwen3.8-max-0902":{"draws":28,"losses":66,"wins":2},"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":53,"losses":191,"wins":28},"stealth/space-bunny-alpha":{"draws":21,"losses":47,"wins":12},"stepfun/step-3.7-flash":{"draws":16,"losses":48,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":17,"losses":22,"wins":13},"tencent/hy4-preview":{"draws":23,"losses":68,"wins":3},"thinkingmachines/inkling":{"draws":34,"losses":58,"wins":34},"thinkingmachines/inkling-small":{"draws":33,"losses":35,"wins":28},"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":19,"losses":75,"wins":2},"x-ai/grok-4.6":{"draws":19,"losses":73,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":78,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":19,"wins":3},"xiaomi/mimo-v2.5":{"draws":58,"losses":70,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":46,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":43,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":50,"wins":5},"z-ai/glm-5.2":{"draws":42,"losses":127,"wins":23},"z-ai/glm-5.3":{"draws":15,"losses":76,"wins":1},"z-ai/glm-5.3-flash":{"draws":21,"losses":63,"wins":12},"z-ai/glm-5.3-flashx":{"draws":26,"losses":63,"wins":7}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":47,"wins":82},"claude-fable-5":{"draws":32,"losses":115,"wins":33},"claude-fable-5-1":{"draws":11,"losses":183,"wins":8},"claude-haiku-5-5":{"draws":39,"losses":77,"wins":58},"claude-opus-4-5":{"draws":85,"losses":98,"wins":111},"claude-opus-4-8":{"draws":36,"losses":83,"wins":49},"claude-opus-5":{"draws":35,"losses":238,"wins":31},"claude-opus-5-5":{"draws":10,"losses":177,"wins":9},"claude-sonnet-5":{"draws":49,"losses":57,"wins":74},"claude-sonnet-5-5":{"draws":30,"losses":103,"wins":47},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":44},"deepseek/deepseek-v4-flash":{"draws":64,"losses":60,"wins":146},"deepseek/deepseek-v4-pro":{"draws":40,"losses":56,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":52,"wins":74},"deepseek/deepseek-v4.1-flash":{"draws":49,"losses":74,"wins":57},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":101,"wins":50},"elorian/glimpse":{"draws":19,"losses":45,"wins":34},"fireworks/ember-1":{"draws":47,"losses":69,"wins":64},"gemini-3.1-pro-preview":{"draws":41,"losses":58,"wins":81},"gemini-4-argon":{"draws":12,"losses":160,"wins":8},"google/gemini-3.1-flash-lite":{"draws":31,"losses":14,"wins":81},"google/gemini-3.5-flash":{"draws":34,"losses":67,"wins":67},"google/gemini-3.5-flash-lite":{"draws":75,"losses":82,"wins":161},"google/gemini-3.6-flash":{"draws":75,"losses":141,"wins":130},"google/gemini-3.8-flash":{"draws":34,"losses":101,"wins":45},"google/gemma-4-31b-it":{"draws":31,"losses":22,"wins":53},"gpt-4.1":{"draws":14,"losses":17,"wins":29},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":11},"gpt-5":{"draws":36,"losses":53,"wins":69},"gpt-5.4":{"draws":25,"losses":98,"wins":51},"gpt-5.4-mini":{"draws":41,"losses":29,"wins":50},"gpt-5.4-nano":{"draws":30,"losses":49,"wins":105},"gpt-5.5":{"draws":46,"losses":71,"wins":49},"gpt-5.6-luna":{"draws":51,"losses":49,"wins":80},"gpt-5.6-sol":{"draws":18,"losses":121,"wins":41},"gpt-5.6-terra":{"draws":53,"losses":64,"wins":55},"gpt-6-astra":{"draws":11,"losses":162,"wins":7},"gpt-6-luna":{"draws":50,"losses":60,"wins":70},"gpt-6-sol":{"draws":27,"losses":127,"wins":26},"gpt-6.1-sol":{"draws":11,"losses":151,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":45,"losses":16,"wins":67},"inception/mercury-3":{"draws":27,"losses":48,"wins":43},"inclusionai/ling-3.0-flash":{"draws":37,"losses":12,"wins":79},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":35,"losses":39,"wins":124},"meta/muse-glimmer-30b":{"draws":49,"losses":22,"wins":87},"meta/muse-spark-1.2":{"draws":35,"losses":78,"wins":59},"meta/muse-spark-1.3":{"draws":34,"losses":99,"wins":47},"meta/muse-spark-open":{"draws":28,"losses":93,"wins":53},"meta/muse-wonder":{"draws":30,"losses":121,"wins":29},"minimax/minimax-m3":{"draws":20,"losses":25,"wins":53},"minimax/minimax-m3.1-flash":{"draws":32,"losses":53,"wins":72},"mistralai/mistral-large-4-0":{"draws":38,"losses":39,"wins":35},"mistralai/mistral-medium-3-5":{"draws":31,"losses":13,"wins":60},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":16,"wins":19},"moonshotai/kimi-k3":{"draws":50,"losses":63,"wins":59},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":147,"wins":15},"nex-agi/nex-n2-pro":{"draws":22,"losses":17,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":32,"wins":80},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":35},"o3":{"draws":35,"losses":86,"wins":137},"openai/gpt-oss-120b":{"draws":43,"losses":36,"wins":77},"poolside/laguna-s-2.1":{"draws":37,"losses":31,"wins":102},"qwen/qwen3.7-max":{"draws":32,"losses":33,"wins":41},"qwen/qwen3.7-plus":{"draws":20,"losses":21,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":77,"wins":55},"qwen/qwen3.8-27b":{"draws":20,"losses":50,"wins":58},"qwen/qwen3.8-flash":{"draws":32,"losses":39,"wins":49},"qwen/qwen3.8-max":{"draws":56,"losses":62,"wins":62},"qwen/qwen3.8-max-0902":{"draws":47,"losses":85,"wins":48},"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":106,"losses":268,"wins":202},"stealth/space-bunny-alpha":{"draws":42,"losses":35,"wins":67},"stepfun/step-3.7-flash":{"draws":21,"losses":27,"wins":82},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":29,"wins":41},"tencent/hy4-preview":{"draws":39,"losses":88,"wins":47},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":135},"thinkingmachines/inkling-small":{"draws":48,"losses":33,"wins":99},"unbiased/pareto-26.10":{"draws":7,"losses":50,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":55,"wins":5},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":31,"losses":86,"wins":63},"x-ai/grok-4.6":{"draws":47,"losses":96,"wins":37},"x-ai/grok-4.7":{"draws":14,"losses":121,"wins":23},"x-ai/grok-build-0.1":{"draws":19,"losses":8,"wins":33},"xiaomi/mimo-v2.5":{"draws":83,"losses":50,"wins":151},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":30,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":51,"wins":43},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":62,"wins":37},"z-ai/glm-5.2":{"draws":98,"losses":110,"wins":152},"z-ai/glm-5.3":{"draws":30,"losses":106,"wins":36},"z-ai/glm-5.3-flash":{"draws":22,"losses":97,"wins":61},"z-ai/glm-5.3-flashx":{"draws":42,"losses":92,"wins":46}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":78,"losses":82,"wins":74},"claude-fable-5":{"draws":45,"losses":179,"wins":28},"claude-fable-5-1":{"draws":20,"losses":262,"wins":2},"claude-haiku-5-5":{"draws":53,"losses":149,"wins":40},"claude-opus-4-5":{"draws":132,"losses":184,"wins":94},"claude-opus-4-8":{"draws":63,"losses":147,"wins":22},"claude-opus-5":{"draws":50,"losses":342,"wins":32},"claude-opus-5-5":{"draws":18,"losses":253,"wins":1},"claude-sonnet-5":{"draws":71,"losses":127,"wins":54},"claude-sonnet-5-5":{"draws":49,"losses":164,"wins":39},"cohere/north-mini-code":{"draws":32,"losses":31,"wins":35},"deepseek/deepseek-v4-flash":{"draws":118,"losses":123,"wins":133},"deepseek/deepseek-v4-pro":{"draws":61,"losses":106,"wins":65},"deepseek/deepseek-v4-pro-0813":{"draws":72,"losses":112,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":76,"losses":124,"wins":52},"deepseek/deepseek-v4.1-flash-1017":{"draws":38,"losses":183,"wins":31},"elorian/glimpse":{"draws":38,"losses":71,"wins":27},"fireworks/ember-1":{"draws":87,"losses":113,"wins":52},"gemini-3.1-pro-preview":{"draws":83,"losses":105,"wins":64},"gemini-4-argon":{"draws":14,"losses":227,"wins":11},"google/gemini-3.1-flash-lite":{"draws":46,"losses":35,"wins":93},"google/gemini-3.5-flash":{"draws":75,"losses":161,"wins":82},"google/gemini-3.5-flash-lite":{"draws":118,"losses":123,"wins":123},"google/gemini-3.6-flash":{"draws":138,"losses":253,"wins":95},"google/gemini-3.8-flash":{"draws":47,"losses":185,"wins":20},"google/gemma-4-31b-it":{"draws":55,"losses":35,"wins":58},"gpt-4.1":{"draws":28,"losses":29,"wins":27},"gpt-4.1-nano":{"draws":18,"losses":3,"wins":9},"gpt-5":{"draws":64,"losses":97,"wins":59},"gpt-5.4":{"draws":55,"losses":149,"wins":40},"gpt-5.4-mini":{"draws":59,"losses":58,"wins":51},"gpt-5.4-nano":{"draws":51,"losses":95,"wins":106},"gpt-5.5":{"draws":88,"losses":110,"wins":34},"gpt-5.6-luna":{"draws":81,"losses":95,"wins":76},"gpt-5.6-sol":{"draws":36,"losses":195,"wins":21},"gpt-5.6-terra":{"draws":75,"losses":118,"wins":47},"gpt-6-astra":{"draws":14,"losses":237,"wins":1},"gpt-6-luna":{"draws":79,"losses":113,"wins":60},"gpt-6-sol":{"draws":38,"losses":191,"wins":23},"gpt-6.1-sol":{"draws":15,"losses":236,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":74,"losses":39,"wins":67},"inception/mercury-3":{"draws":47,"losses":84,"wins":31},"inclusionai/ling-3.0-flash":{"draws":62,"losses":35,"wins":79},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":74,"losses":83,"wins":121},"meta/muse-glimmer-30b":{"draws":89,"losses":52,"wins":79},"meta/muse-spark-1.2":{"draws":60,"losses":135,"wins":45},"meta/muse-spark-1.3":{"draws":47,"losses":169,"wins":36},"meta/muse-spark-open":{"draws":42,"losses":161,"wins":40},"meta/muse-wonder":{"draws":43,"losses":182,"wins":27},"minimax/minimax-m3":{"draws":34,"losses":47,"wins":53},"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":52,"losses":32,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":32,"wins":14},"moonshotai/kimi-k3":{"draws":77,"losses":119,"wins":44},"moonshotai/kimi-k3.1-pro":{"draws":31,"losses":208,"wins":3},"nex-agi/nex-n2-pro":{"draws":32,"losses":38,"wins":58},"nex-agi/nex-n2.5-pro":{"draws":13,"losses":17,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":82,"losses":68,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":36,"losses":55,"wins":25},"o3":{"draws":57,"losses":201,"wins":98},"openai/gpt-oss-120b":{"draws":68,"losses":75,"wins":75},"poolside/laguna-s-2.1":{"draws":73,"losses":98,"wins":67},"qwen/qwen3.7-max":{"draws":41,"losses":63,"wins":42},"qwen/qwen3.7-plus":{"draws":35,"losses":40,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":80,"losses":130,"wins":42},"qwen/qwen3.8-27b":{"draws":35,"losses":102,"wins":43},"qwen/qwen3.8-flash":{"draws":55,"losses":83,"wins":30},"qwen/qwen3.8-max":{"draws":82,"losses":123,"wins":47},"qwen/qwen3.8-max-0902":{"draws":69,"losses":143,"wins":40},"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":175,"losses":484,"wins":167},"stealth/space-bunny-alpha":{"draws":58,"losses":83,"wins":61},"stepfun/step-3.7-flash":{"draws":49,"losses":60,"wins":71},"stepfun/step-5-preview":{"draws":10,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":49,"losses":58,"wins":29},"tencent/hy4-preview":{"draws":63,"losses":133,"wins":48},"thinkingmachines/inkling":{"draws":92,"losses":113,"wins":133},"thinkingmachines/inkling-small":{"draws":81,"losses":74,"wins":97},"unbiased/pareto-26.10":{"draws":5,"losses":79,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":81,"wins":1},"upstage/solar-mini4":{"draws":20,"losses":25,"wins":23},"x-ai/grok-4.5":{"draws":64,"losses":142,"wins":46},"x-ai/grok-4.6":{"draws":62,"losses":156,"wins":34},"x-ai/grok-4.7":{"draws":20,"losses":170,"wins":28},"x-ai/grok-build-0.1":{"draws":33,"losses":24,"wins":27},"xiaomi/mimo-v2.5":{"draws":124,"losses":131,"wins":137},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":49,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":106,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":118,"wins":29},"z-ai/glm-5.2":{"draws":167,"losses":199,"wins":138},"z-ai/glm-5.3":{"draws":41,"losses":184,"wins":17},"z-ai/glm-5.3-flash":{"draws":51,"losses":154,"wins":47},"z-ai/glm-5.3-flashx":{"draws":63,"losses":141,"wins":48}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":67,"losses":53,"wins":134},"claude-fable-5":{"draws":48,"losses":148,"wins":80},"claude-fable-5-1":{"draws":20,"losses":273,"wins":19},"claude-haiku-5-5":{"draws":65,"losses":100,"wins":99},"claude-opus-4-5":{"draws":131,"losses":115,"wins":202},"claude-opus-4-8":{"draws":57,"losses":92,"wins":103},"claude-opus-5":{"draws":61,"losses":323,"wins":84},"claude-opus-5-5":{"draws":22,"losses":253,"wins":21},"claude-sonnet-5":{"draws":65,"losses":86,"wins":125},"claude-sonnet-5-5":{"draws":49,"losses":129,"wins":98},"cohere/north-mini-code":{"draws":20,"losses":9,"wins":75},"deepseek/deepseek-v4-flash":{"draws":97,"losses":59,"wins":256},"deepseek/deepseek-v4-pro":{"draws":64,"losses":84,"wins":106},"deepseek/deepseek-v4-pro-0813":{"draws":57,"losses":77,"wins":120},"deepseek/deepseek-v4.1-flash":{"draws":76,"losses":87,"wins":113},"deepseek/deepseek-v4.1-flash-1017":{"draws":42,"losses":133,"wins":101},"elorian/glimpse":{"draws":30,"losses":58,"wins":62},"fireworks/ember-1":{"draws":77,"losses":102,"wins":97},"gemini-3.1-pro-preview":{"draws":67,"losses":84,"wins":125},"gemini-4-argon":{"draws":18,"losses":226,"wins":32},"google/gemini-3.1-flash-lite":{"draws":41,"losses":15,"wins":130},"google/gemini-3.5-flash":{"draws":75,"losses":130,"wins":141},"google/gemini-3.5-flash-lite":{"draws":138,"losses":95,"wins":253},"google/gemini-3.6-flash":{"draws":92,"losses":174,"wins":174},"google/gemini-3.8-flash":{"draws":59,"losses":136,"wins":81},"google/gemma-4-31b-it":{"draws":51,"losses":20,"wins":89},"gpt-4.1":{"draws":25,"losses":20,"wins":47},"gpt-4.1-nano":{"draws":14,"losses":2,"wins":18},"gpt-5":{"draws":51,"losses":75,"wins":116},"gpt-5.4":{"draws":54,"losses":115,"wins":97},"gpt-5.4-mini":{"draws":55,"losses":30,"wins":99},"gpt-5.4-nano":{"draws":51,"losses":58,"wins":165},"gpt-5.5":{"draws":73,"losses":93,"wins":88},"gpt-5.6-luna":{"draws":82,"losses":59,"wins":135},"gpt-5.6-sol":{"draws":41,"losses":159,"wins":76},"gpt-5.6-terra":{"draws":83,"losses":66,"wins":115},"gpt-6-astra":{"draws":19,"losses":239,"wins":18},"gpt-6-luna":{"draws":82,"losses":71,"wins":123},"gpt-6-sol":{"draws":35,"losses":182,"wins":59},"gpt-6.1-sol":{"draws":17,"losses":232,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":68,"losses":12,"wins":114},"inception/mercury-3":{"draws":45,"losses":48,"wins":87},"inclusionai/ling-3.0-flash":{"draws":68,"losses":18,"wins":108},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":64,"losses":46,"wins":190},"meta/muse-glimmer-30b":{"draws":78,"losses":36,"wins":128},"meta/muse-spark-1.2":{"draws":53,"losses":105,"wins":106},"meta/muse-spark-1.3":{"draws":48,"losses":131,"wins":97},"meta/muse-spark-open":{"draws":50,"losses":110,"wins":106},"meta/muse-wonder":{"draws":50,"losses":155,"wins":71},"minimax/minimax-m3":{"draws":29,"losses":25,"wins":94},"minimax/minimax-m3.1-flash":{"draws":59,"losses":61,"wins":126},"mistralai/mistral-large-4-0":{"draws":41,"losses":59,"wins":72},"mistralai/mistral-medium-3-5":{"draws":56,"losses":14,"wins":90},"moonshotai/kimi-k2.7-code":{"draws":20,"losses":15,"wins":33},"moonshotai/kimi-k3":{"draws":71,"losses":88,"wins":105},"moonshotai/kimi-k3.1-pro":{"draws":29,"losses":203,"wins":33},"nex-agi/nex-n2-pro":{"draws":26,"losses":17,"wins":95},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":14,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":76,"losses":34,"wins":128},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":31,"wins":62},"o3":{"draws":54,"losses":123,"wins":207},"openai/gpt-oss-120b":{"draws":72,"losses":32,"wins":136},"poolside/laguna-s-2.1":{"draws":75,"losses":50,"wins":137},"qwen/qwen3.7-max":{"draws":46,"losses":38,"wins":76},"qwen/qwen3.7-plus":{"draws":39,"losses":22,"wins":77},"qwen/qwen3.8-2.4t-a95b":{"draws":72,"losses":95,"wins":109},"qwen/qwen3.8-27b":{"draws":43,"losses":64,"wins":91},"qwen/qwen3.8-flash":{"draws":55,"losses":48,"wins":81},"qwen/qwen3.8-max":{"draws":72,"losses":90,"wins":114},"qwen/qwen3.8-max-0902":{"draws":74,"losses":105,"wins":97},"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":197,"losses":360,"wins":359},"stealth/space-bunny-alpha":{"draws":59,"losses":45,"wins":116},"stepfun/step-3.7-flash":{"draws":35,"losses":32,"wins":131},"stepfun/step-5-preview":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":47,"losses":31,"wins":70},"tencent/hy4-preview":{"draws":61,"losses":102,"wins":103},"thinkingmachines/inkling":{"draws":103,"losses":57,"wins":212},"thinkingmachines/inkling-small":{"draws":83,"losses":46,"wins":147},"unbiased/pareto-26.10":{"draws":8,"losses":81,"wins":3},"unbiased/pareto-26.10-preview":{"draws":5,"losses":78,"wins":9},"upstage/solar-mini4":{"draws":14,"losses":9,"wins":49},"x-ai/grok-4.5":{"draws":59,"losses":115,"wins":102},"x-ai/grok-4.6":{"draws":70,"losses":124,"wins":82},"x-ai/grok-4.7":{"draws":15,"losses":170,"wins":55},"x-ai/grok-build-0.1":{"draws":31,"losses":5,"wins":56},"xiaomi/mimo-v2.5":{"draws":129,"losses":51,"wins":244},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":31,"wins":88},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":73,"wins":76},"xiaomi/mimo-v2.6-pro":{"draws":37,"losses":86,"wins":61},"z-ai/glm-5.2":{"draws":152,"losses":150,"wins":250},"z-ai/glm-5.3":{"draws":52,"losses":152,"wins":60},"z-ai/glm-5.3-flash":{"draws":45,"losses":141,"wins":90},"z-ai/glm-5.3-flashx":{"draws":68,"losses":113,"wins":95}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":23,"wins":79},"claude-fable-5":{"draws":23,"losses":67,"wins":54},"claude-fable-5-1":{"draws":7,"losses":141,"wins":14},"claude-haiku-5-5":{"draws":33,"losses":43,"wins":62},"claude-opus-4-5":{"draws":71,"losses":44,"wins":119},"claude-opus-4-8":{"draws":30,"losses":41,"wins":61},"claude-opus-5":{"draws":28,"losses":165,"wins":53},"claude-opus-5-5":{"draws":13,"losses":123,"wins":20},"claude-sonnet-5":{"draws":33,"losses":33,"wins":78},"claude-sonnet-5-5":{"draws":20,"losses":68,"wins":56},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":40},"deepseek/deepseek-v4-flash":{"draws":39,"losses":21,"wins":156},"deepseek/deepseek-v4-pro":{"draws":27,"losses":33,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":34,"wins":70},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":46,"wins":62},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":71,"wins":47},"elorian/glimpse":{"draws":13,"losses":30,"wins":35},"fireworks/ember-1":{"draws":35,"losses":48,"wins":61},"gemini-3.1-pro-preview":{"draws":28,"losses":35,"wins":81},"gemini-4-argon":{"draws":15,"losses":108,"wins":21},"google/gemini-3.1-flash-lite":{"draws":24,"losses":2,"wins":70},"google/gemini-3.5-flash":{"draws":34,"losses":45,"wins":101},"google/gemini-3.5-flash-lite":{"draws":47,"losses":20,"wins":185},"google/gemini-3.6-flash":{"draws":59,"losses":81,"wins":136},"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":25,"losses":30,"wins":71},"gpt-5.4":{"draws":24,"losses":51,"wins":63},"gpt-5.4-mini":{"draws":23,"losses":13,"wins":60},"gpt-5.4-nano":{"draws":29,"losses":24,"wins":91},"gpt-5.5":{"draws":44,"losses":44,"wins":44},"gpt-5.6-luna":{"draws":31,"losses":26,"wins":87},"gpt-5.6-sol":{"draws":19,"losses":72,"wins":53},"gpt-5.6-terra":{"draws":40,"losses":36,"wins":62},"gpt-6-astra":{"draws":14,"losses":120,"wins":10},"gpt-6-luna":{"draws":41,"losses":36,"wins":67},"gpt-6-sol":{"draws":22,"losses":91,"wins":31},"gpt-6.1-sol":{"draws":18,"losses":108,"wins":18},"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":30,"losses":2,"wins":70},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":26,"losses":19,"wins":111},"meta/muse-glimmer-30b":{"draws":33,"losses":15,"wins":78},"meta/muse-spark-1.2":{"draws":24,"losses":56,"wins":58},"meta/muse-spark-1.3":{"draws":32,"losses":51,"wins":61},"meta/muse-spark-open":{"draws":23,"losses":54,"wins":61},"meta/muse-wonder":{"draws":36,"losses":68,"wins":40},"minimax/minimax-m3":{"draws":14,"losses":6,"wins":58},"minimax/minimax-m3.1-flash":{"draws":26,"losses":25,"wins":75},"mistralai/mistral-large-4-0":{"draws":28,"losses":26,"wins":36},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":18,"wins":13},"moonshotai/kimi-k3":{"draws":32,"losses":33,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":22},"nex-agi/nex-n2-pro":{"draws":13,"losses":7,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":9,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":38},"o3":{"draws":23,"losses":44,"wins":131},"openai/gpt-oss-120b":{"draws":26,"losses":8,"wins":92},"poolside/laguna-s-2.1":{"draws":26,"losses":17,"wins":95},"qwen/qwen3.7-max":{"draws":26,"losses":20,"wins":38},"qwen/qwen3.7-plus":{"draws":17,"losses":7,"wins":48},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":44,"wins":66},"qwen/qwen3.8-27b":{"draws":16,"losses":22,"wins":64},"qwen/qwen3.8-flash":{"draws":20,"losses":28,"wins":48},"qwen/qwen3.8-max":{"draws":36,"losses":46,"wins":62},"qwen/qwen3.8-max-0902":{"draws":37,"losses":47,"wins":60},"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":98,"losses":149,"wins":227},"stealth/space-bunny-alpha":{"draws":27,"losses":17,"wins":70},"stepfun/step-3.7-flash":{"draws":16,"losses":9,"wins":77},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":31,"losses":8,"wins":39},"tencent/hy4-preview":{"draws":31,"losses":54,"wins":53},"thinkingmachines/inkling":{"draws":50,"losses":19,"wins":123},"thinkingmachines/inkling-small":{"draws":37,"losses":19,"wins":88},"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":69,"wins":51},"x-ai/grok-4.6":{"draws":40,"losses":52,"wins":52},"x-ai/grok-4.7":{"draws":12,"losses":88,"wins":26},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5":{"draws":60,"losses":20,"wins":142},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":12,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":29,"wins":41},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":48,"wins":28},"z-ai/glm-5.2":{"draws":75,"losses":59,"wins":154},"z-ai/glm-5.3":{"draws":29,"losses":71,"wins":38},"z-ai/glm-5.3-flash":{"draws":20,"losses":55,"wins":69},"z-ai/glm-5.3-flashx":{"draws":26,"losses":52,"wins":66}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":24},"claude-fable-5":{"draws":18,"losses":58,"wins":8},"claude-fable-5-1":{"draws":4,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":23,"losses":50,"wins":9},"claude-opus-4-5":{"draws":46,"losses":77,"wins":15},"claude-opus-4-8":{"draws":23,"losses":47,"wins":10},"claude-opus-5":{"draws":21,"losses":109,"wins":10},"claude-opus-5-5":{"draws":5,"losses":87,"wins":0},"claude-sonnet-5":{"draws":27,"losses":45,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":54,"wins":16},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":58,"losses":46,"wins":22},"deepseek/deepseek-v4-pro":{"draws":28,"losses":34,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":38,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":38,"wins":12},"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":30,"losses":39,"wins":15},"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":31,"losses":53,"wins":22},"google/gemini-3.5-flash-lite":{"draws":55,"losses":58,"wins":35},"google/gemini-3.6-flash":{"draws":51,"losses":89,"wins":20},"google/gemini-3.8-flash":{"draws":23,"losses":52,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":7},"gpt-4.1":{"draws":11,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":31,"losses":32,"wins":9},"gpt-5.4":{"draws":28,"losses":43,"wins":9},"gpt-5.4-mini":{"draws":22,"losses":24,"wins":10},"gpt-5.4-nano":{"draws":26,"losses":43,"wins":17},"gpt-5.5":{"draws":30,"losses":40,"wins":6},"gpt-5.6-luna":{"draws":34,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":11,"losses":67,"wins":6},"gpt-5.6-terra":{"draws":32,"losses":39,"wins":9},"gpt-6-astra":{"draws":4,"losses":80,"wins":0},"gpt-6-luna":{"draws":28,"losses":38,"wins":18},"gpt-6-sol":{"draws":9,"losses":73,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":80,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":16,"wins":18},"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":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":35,"wins":26},"meta/muse-glimmer-30b":{"draws":38,"losses":17,"wins":17},"meta/muse-spark-1.2":{"draws":23,"losses":40,"wins":17},"meta/muse-spark-1.3":{"draws":23,"losses":53,"wins":8},"meta/muse-spark-open":{"draws":20,"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":7,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":29,"losses":38,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":72,"wins":1},"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":40,"losses":18,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":22,"wins":6},"o3":{"draws":26,"losses":71,"wins":21},"openai/gpt-oss-120b":{"draws":31,"losses":33,"wins":10},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":20},"qwen/qwen3.7-max":{"draws":17,"losses":20,"wins":13},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":45,"wins":10},"qwen/qwen3.8-27b":{"draws":19,"losses":29,"wins":10},"qwen/qwen3.8-flash":{"draws":27,"losses":23,"wins":6},"qwen/qwen3.8-max":{"draws":33,"losses":43,"wins":8},"qwen/qwen3.8-max-0902":{"draws":29,"losses":46,"wins":9},"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":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":16,"wins":9},"tencent/hy4-preview":{"draws":26,"losses":43,"wins":11},"thinkingmachines/inkling":{"draws":40,"losses":36,"wins":32},"thinkingmachines/inkling-small":{"draws":35,"losses":25,"wins":24},"unbiased/pareto-26.10":{"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":19,"losses":55,"wins":10},"x-ai/grok-4.6":{"draws":24,"losses":54,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":62,"wins":4},"x-ai/grok-build-0.1":{"draws":11,"losses":9,"wins":8},"xiaomi/mimo-v2.5":{"draws":61,"losses":41,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":32,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":41,"wins":4},"z-ai/glm-5.2":{"draws":69,"losses":70,"wins":29},"z-ai/glm-5.3":{"draws":22,"losses":53,"wins":7},"z-ai/glm-5.3-flash":{"draws":25,"losses":45,"wins":14},"z-ai/glm-5.3-flashx":{"draws":28,"losses":45,"wins":11}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":32,"losses":29,"wins":17},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":16,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":16,"wins":34},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"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":19,"wins":16},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":47,"wins":20},"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":15,"wins":16},"gpt-5.4":{"draws":11,"losses":24,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":10,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":27},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":15,"losses":23,"wins":8},"meta/muse-spark-1.3":{"draws":17,"losses":27,"wins":4},"meta/muse-spark-open":{"draws":7,"losses":27,"wins":11},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"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":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":42,"wins":2},"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":18,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":7},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":20},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":24,"wins":7},"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":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"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":41,"losses":80,"wins":37},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":27},"thinkingmachines/inkling-small":{"draws":15,"losses":13,"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":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":30,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":35,"losses":38,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":28,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":0},"elorian/glimpse":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":9,"losses":8,"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":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-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":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":0},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"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":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10":{"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":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":38,"wins":43},"claude-fable-5":{"draws":24,"losses":81,"wins":21},"claude-fable-5-1":{"draws":5,"losses":136,"wins":1},"claude-haiku-5-5":{"draws":31,"losses":62,"wins":27},"claude-opus-4-5":{"draws":64,"losses":74,"wins":66},"claude-opus-4-8":{"draws":30,"losses":54,"wins":30},"claude-opus-5":{"draws":26,"losses":176,"wins":18},"claude-opus-5-5":{"draws":9,"losses":124,"wins":5},"claude-sonnet-5":{"draws":37,"losses":54,"wins":35},"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":57,"losses":41,"wins":92},"deepseek/deepseek-v4-pro":{"draws":30,"losses":53,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":46,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":57,"wins":30},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":73,"wins":28},"elorian/glimpse":{"draws":14,"losses":34,"wins":22},"fireworks/ember-1":{"draws":32,"losses":60,"wins":34},"gemini-3.1-pro-preview":{"draws":41,"losses":50,"wins":35},"gemini-4-argon":{"draws":4,"losses":113,"wins":9},"google/gemini-3.1-flash-lite":{"draws":25,"losses":3,"wins":56},"google/gemini-3.5-flash":{"draws":36,"losses":69,"wins":53},"google/gemini-3.5-flash-lite":{"draws":64,"losses":59,"wins":97},"google/gemini-3.6-flash":{"draws":51,"losses":116,"wins":75},"google/gemini-3.8-flash":{"draws":25,"losses":71,"wins":30},"google/gemma-4-31b-it":{"draws":31,"losses":9,"wins":32},"gpt-4.1":{"draws":11,"losses":16,"wins":15},"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":27,"losses":27,"wins":30},"gpt-5.4-nano":{"draws":20,"losses":44,"wins":64},"gpt-5.5":{"draws":42,"losses":49,"wins":27},"gpt-5.6-luna":{"draws":40,"losses":36,"wins":50},"gpt-5.6-sol":{"draws":17,"losses":92,"wins":17},"gpt-5.6-terra":{"draws":31,"losses":51,"wins":38},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":39,"losses":45,"wins":42},"gpt-6-sol":{"draws":15,"losses":95,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":115,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":9,"wins":41},"inception/mercury-3":{"draws":17,"losses":40,"wins":27},"inclusionai/ling-3.0-flash":{"draws":31,"losses":22,"wins":35},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":33,"wins":73},"meta/muse-glimmer-30b":{"draws":40,"losses":24,"wins":50},"meta/muse-spark-1.2":{"draws":24,"losses":67,"wins":31},"meta/muse-spark-1.3":{"draws":25,"losses":74,"wins":27},"meta/muse-spark-open":{"draws":27,"losses":71,"wins":24},"meta/muse-wonder":{"draws":23,"losses":80,"wins":23},"minimax/minimax-m3":{"draws":15,"losses":17,"wins":38},"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":22,"losses":16,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":31,"losses":50,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":102,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":17,"wins":33},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":21,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":22,"wins":23},"o3":{"draws":24,"losses":69,"wins":87},"openai/gpt-oss-120b":{"draws":35,"losses":21,"wins":56},"poolside/laguna-s-2.1":{"draws":38,"losses":39,"wins":49},"qwen/qwen3.7-max":{"draws":31,"losses":15,"wins":28},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":56,"wins":33},"qwen/qwen3.8-27b":{"draws":17,"losses":41,"wins":30},"qwen/qwen3.8-flash":{"draws":18,"losses":36,"wins":30},"qwen/qwen3.8-max":{"draws":39,"losses":58,"wins":29},"qwen/qwen3.8-max-0902":{"draws":36,"losses":59,"wins":31},"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":94,"losses":199,"wins":131},"stealth/space-bunny-alpha":{"draws":25,"losses":37,"wins":38},"stepfun/step-3.7-flash":{"draws":21,"losses":18,"wins":53},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":27,"wins":21},"tencent/hy4-preview":{"draws":35,"losses":50,"wins":37},"thinkingmachines/inkling":{"draws":40,"losses":39,"wins":93},"thinkingmachines/inkling-small":{"draws":44,"losses":21,"wins":61},"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":67,"wins":34},"x-ai/grok-4.6":{"draws":35,"losses":72,"wins":19},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":18},"x-ai/grok-build-0.1":{"draws":15,"losses":9,"wins":18},"xiaomi/mimo-v2.5":{"draws":58,"losses":39,"wins":93},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":21,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":38,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":22},"z-ai/glm-5.2":{"draws":82,"losses":76,"wins":94},"z-ai/glm-5.3":{"draws":18,"losses":80,"wins":22},"z-ai/glm-5.3-flash":{"draws":21,"losses":74,"wins":31},"z-ai/glm-5.3-flashx":{"draws":36,"losses":58,"wins":32}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":28,"wins":71},"claude-fable-5":{"draws":33,"losses":65,"wins":40},"claude-fable-5-1":{"draws":10,"losses":130,"wins":16},"claude-haiku-5-5":{"draws":31,"losses":51,"wins":50},"claude-opus-4-5":{"draws":63,"losses":50,"wins":111},"claude-opus-4-8":{"draws":30,"losses":41,"wins":55},"claude-opus-5":{"draws":30,"losses":168,"wins":36},"claude-opus-5-5":{"draws":10,"losses":127,"wins":13},"claude-sonnet-5":{"draws":35,"losses":32,"wins":71},"claude-sonnet-5-5":{"draws":36,"losses":60,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":35},"deepseek/deepseek-v4-flash":{"draws":53,"losses":30,"wins":123},"deepseek/deepseek-v4-pro":{"draws":27,"losses":38,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":37,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":45,"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":36,"losses":40,"wins":62},"gemini-3.1-pro-preview":{"draws":29,"losses":42,"wins":67},"gemini-4-argon":{"draws":13,"losses":103,"wins":22},"google/gemini-3.1-flash-lite":{"draws":19,"losses":8,"wins":67},"google/gemini-3.5-flash":{"draws":25,"losses":51,"wins":98},"google/gemini-3.5-flash-lite":{"draws":55,"losses":40,"wins":149},"google/gemini-3.6-flash":{"draws":54,"losses":97,"wins":115},"google/gemini-3.8-flash":{"draws":24,"losses":63,"wins":51},"google/gemma-4-31b-it":{"draws":28,"losses":9,"wins":43},"gpt-4.1":{"draws":11,"losses":11,"wins":24},"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":28,"losses":6,"wins":58},"gpt-5.4-nano":{"draws":15,"losses":32,"wins":91},"gpt-5.5":{"draws":34,"losses":45,"wins":49},"gpt-5.6-luna":{"draws":45,"losses":22,"wins":71},"gpt-5.6-sol":{"draws":22,"losses":69,"wins":47},"gpt-5.6-terra":{"draws":33,"losses":38,"wins":61},"gpt-6-astra":{"draws":6,"losses":114,"wins":18},"gpt-6-luna":{"draws":42,"losses":37,"wins":59},"gpt-6-sol":{"draws":14,"losses":102,"wins":22},"gpt-6.1-sol":{"draws":11,"losses":108,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":39,"losses":5,"wins":52},"inception/mercury-3":{"draws":16,"losses":30,"wins":44},"inclusionai/ling-3.0-flash":{"draws":23,"losses":17,"wins":58},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":32,"losses":25,"wins":95},"meta/muse-glimmer-30b":{"draws":30,"losses":18,"wins":74},"meta/muse-spark-1.2":{"draws":24,"losses":49,"wins":59},"meta/muse-spark-1.3":{"draws":29,"losses":55,"wins":54},"meta/muse-spark-open":{"draws":27,"losses":55,"wins":52},"meta/muse-wonder":{"draws":29,"losses":66,"wins":43},"minimax/minimax-m3":{"draws":14,"losses":16,"wins":44},"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":21,"losses":14,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":24,"losses":38,"wins":70},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":99,"wins":21},"nex-agi/nex-n2-pro":{"draws":16,"losses":17,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":12,"wins":72},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":14,"wins":34},"o3":{"draws":19,"losses":49,"wins":128},"openai/gpt-oss-120b":{"draws":33,"losses":20,"wins":67},"poolside/laguna-s-2.1":{"draws":31,"losses":21,"wins":80},"qwen/qwen3.7-max":{"draws":17,"losses":18,"wins":45},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":53,"wins":58},"qwen/qwen3.8-27b":{"draws":20,"losses":20,"wins":58},"qwen/qwen3.8-flash":{"draws":19,"losses":28,"wins":45},"qwen/qwen3.8-max":{"draws":33,"losses":52,"wins":53},"qwen/qwen3.8-max-0902":{"draws":29,"losses":46,"wins":63},"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":114,"losses":161,"wins":183},"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":6,"wins":1},"tencent/hy3-preview":{"draws":26,"losses":14,"wins":34},"tencent/hy4-preview":{"draws":28,"losses":49,"wins":57},"thinkingmachines/inkling":{"draws":49,"losses":29,"wins":108},"thinkingmachines/inkling-small":{"draws":38,"losses":17,"wins":83},"unbiased/pareto-26.10":{"draws":4,"losses":38,"wins":4},"unbiased/pareto-26.10-preview":{"draws":2,"losses":38,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":33,"losses":46,"wins":59},"x-ai/grok-4.6":{"draws":36,"losses":55,"wins":47},"x-ai/grok-4.7":{"draws":12,"losses":81,"wins":27},"x-ai/grok-build-0.1":{"draws":11,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":55,"losses":21,"wins":136},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":27,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":38},"z-ai/glm-5.2":{"draws":76,"losses":60,"wins":140},"z-ai/glm-5.3":{"draws":25,"losses":69,"wins":38},"z-ai/glm-5.3-flash":{"draws":16,"losses":59,"wins":63},"z-ai/glm-5.3-flashx":{"draws":29,"losses":55,"wins":54}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":28,"wins":25},"claude-fable-5":{"draws":22,"losses":63,"wins":11},"claude-fable-5-1":{"draws":5,"losses":103,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":53,"wins":12},"claude-opus-4-5":{"draws":57,"losses":64,"wins":35},"claude-opus-4-8":{"draws":22,"losses":44,"wins":22},"claude-opus-5":{"draws":31,"losses":120,"wins":13},"claude-opus-5-5":{"draws":5,"losses":97,"wins":2},"claude-sonnet-5":{"draws":38,"losses":30,"wins":28},"claude-sonnet-5-5":{"draws":17,"losses":62,"wins":17},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":56,"losses":37,"wins":51},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":40,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":39,"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":45,"wins":15},"gemini-3.1-pro-preview":{"draws":36,"losses":35,"wins":25},"gemini-4-argon":{"draws":13,"losses":83,"wins":0},"google/gemini-3.1-flash-lite":{"draws":20,"losses":6,"wins":38},"google/gemini-3.5-flash":{"draws":41,"losses":50,"wins":29},"google/gemini-3.5-flash-lite":{"draws":59,"losses":51,"wins":58},"google/gemini-3.6-flash":{"draws":55,"losses":99,"wins":30},"google/gemini-3.8-flash":{"draws":23,"losses":60,"wins":13},"google/gemma-4-31b-it":{"draws":22,"losses":10,"wins":24},"gpt-4.1":{"draws":12,"losses":7,"wins":13},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":3},"gpt-5":{"draws":27,"losses":30,"wins":27},"gpt-5.4":{"draws":28,"losses":58,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":26,"losses":41,"wins":29},"gpt-5.5":{"draws":40,"losses":33,"wins":15},"gpt-5.6-luna":{"draws":38,"losses":31,"wins":27},"gpt-5.6-sol":{"draws":19,"losses":65,"wins":12},"gpt-5.6-terra":{"draws":39,"losses":32,"wins":21},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":43,"losses":40,"wins":13},"gpt-6-sol":{"draws":13,"losses":72,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":88,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":14,"wins":23},"inception/mercury-3":{"draws":21,"losses":34,"wins":9},"inclusionai/ling-3.0-flash":{"draws":31,"losses":12,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":30,"wins":37},"meta/muse-glimmer-30b":{"draws":43,"losses":11,"wins":30},"meta/muse-spark-1.2":{"draws":27,"losses":45,"wins":20},"meta/muse-spark-1.3":{"draws":20,"losses":65,"wins":11},"meta/muse-spark-open":{"draws":23,"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":28,"losses":20,"wins":12},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":32,"losses":39,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":81,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":21,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":24,"wins":6},"o3":{"draws":26,"losses":71,"wins":35},"openai/gpt-oss-120b":{"draws":32,"losses":21,"wins":31},"poolside/laguna-s-2.1":{"draws":36,"losses":24,"wins":32},"qwen/qwen3.7-max":{"draws":19,"losses":22,"wins":15},"qwen/qwen3.7-plus":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":49,"wins":13},"qwen/qwen3.8-27b":{"draws":17,"losses":32,"wins":19},"qwen/qwen3.8-flash":{"draws":21,"losses":29,"wins":14},"qwen/qwen3.8-max":{"draws":41,"losses":37,"wins":18},"qwen/qwen3.8-max-0902":{"draws":38,"losses":44,"wins":14},"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":91,"losses":163,"wins":62},"stealth/space-bunny-alpha":{"draws":28,"losses":33,"wins":15},"stepfun/step-3.7-flash":{"draws":22,"losses":22,"wins":24},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":21,"losses":17,"wins":14},"tencent/hy4-preview":{"draws":34,"losses":47,"wins":11},"thinkingmachines/inkling":{"draws":48,"losses":37,"wins":43},"thinkingmachines/inkling-small":{"draws":41,"losses":24,"wins":31},"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":30,"losses":52,"wins":14},"x-ai/grok-4.6":{"draws":32,"losses":50,"wins":14},"x-ai/grok-4.7":{"draws":13,"losses":66,"wins":5},"x-ai/grok-build-0.1":{"draws":12,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":56,"losses":39,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":32,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":40,"wins":9},"z-ai/glm-5.2":{"draws":87,"losses":70,"wins":35},"z-ai/glm-5.3":{"draws":21,"losses":62,"wins":9},"z-ai/glm-5.3-flash":{"draws":26,"losses":52,"wins":18},"z-ai/glm-5.3-flashx":{"draws":26,"losses":57,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":54,"wins":48},"claude-fable-5":{"draws":19,"losses":112,"wins":13},"claude-fable-5-1":{"draws":3,"losses":151,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":76,"wins":39},"claude-opus-4-5":{"draws":64,"losses":110,"wins":64},"claude-opus-4-8":{"draws":25,"losses":84,"wins":31},"claude-opus-5":{"draws":24,"losses":196,"wins":16},"claude-opus-5-5":{"draws":7,"losses":151,"wins":2},"claude-sonnet-5":{"draws":33,"losses":71,"wins":40},"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":53,"losses":81,"wins":92},"deepseek/deepseek-v4-pro":{"draws":18,"losses":67,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":64,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":72,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":96,"wins":27},"elorian/glimpse":{"draws":13,"losses":39,"wins":22},"fireworks/ember-1":{"draws":33,"losses":80,"wins":31},"gemini-3.1-pro-preview":{"draws":35,"losses":69,"wins":40},"gemini-4-argon":{"draws":2,"losses":134,"wins":8},"google/gemini-3.1-flash-lite":{"draws":22,"losses":22,"wins":64},"google/gemini-3.5-flash":{"draws":30,"losses":105,"wins":49},"google/gemini-3.5-flash-lite":{"draws":51,"losses":106,"wins":95},"google/gemini-3.6-flash":{"draws":51,"losses":165,"wins":58},"google/gemini-3.8-flash":{"draws":29,"losses":91,"wins":24},"google/gemma-4-31b-it":{"draws":26,"losses":17,"wins":43},"gpt-4.1":{"draws":10,"losses":20,"wins":18},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":7},"gpt-5":{"draws":20,"losses":64,"wins":44},"gpt-5.4":{"draws":15,"losses":91,"wins":32},"gpt-5.4-mini":{"draws":26,"losses":29,"wins":41},"gpt-5.4-nano":{"draws":20,"losses":50,"wins":50},"gpt-5.5":{"draws":33,"losses":64,"wins":33},"gpt-5.6-luna":{"draws":35,"losses":60,"wins":49},"gpt-5.6-sol":{"draws":11,"losses":116,"wins":17},"gpt-5.6-terra":{"draws":26,"losses":72,"wins":38},"gpt-6-astra":{"draws":2,"losses":140,"wins":2},"gpt-6-luna":{"draws":30,"losses":72,"wins":42},"gpt-6-sol":{"draws":20,"losses":112,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":134,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":14,"wins":56},"inception/mercury-3":{"draws":26,"losses":46,"wins":28},"inclusionai/ling-3.0-flash":{"draws":30,"losses":26,"wins":48},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":24,"losses":51,"wins":85},"meta/muse-glimmer-30b":{"draws":31,"losses":42,"wins":49},"meta/muse-spark-1.2":{"draws":23,"losses":69,"wins":44},"meta/muse-spark-1.3":{"draws":25,"losses":90,"wins":29},"meta/muse-spark-open":{"draws":20,"losses":94,"wins":24},"meta/muse-wonder":{"draws":12,"losses":110,"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":16,"losses":48,"wins":24},"mistralai/mistral-medium-3-5":{"draws":19,"losses":16,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":17,"wins":13},"moonshotai/kimi-k3":{"draws":34,"losses":68,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":127,"wins":4},"nex-agi/nex-n2-pro":{"draws":16,"losses":22,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":14,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":45,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":29,"wins":24},"o3":{"draws":20,"losses":103,"wins":103},"openai/gpt-oss-120b":{"draws":35,"losses":47,"wins":44},"poolside/laguna-s-2.1":{"draws":37,"losses":55,"wins":52},"qwen/qwen3.7-max":{"draws":27,"losses":36,"wins":29},"qwen/qwen3.7-plus":{"draws":19,"losses":30,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":80,"wins":27},"qwen/qwen3.8-27b":{"draws":22,"losses":49,"wins":33},"qwen/qwen3.8-flash":{"draws":21,"losses":49,"wins":26},"qwen/qwen3.8-max":{"draws":33,"losses":74,"wins":37},"qwen/qwen3.8-max-0902":{"draws":37,"losses":72,"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":79,"losses":223,"wins":122},"stealth/space-bunny-alpha":{"draws":26,"losses":47,"wins":39},"stepfun/step-3.7-flash":{"draws":16,"losses":34,"wins":60},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":20,"losses":37,"wins":23},"tencent/hy4-preview":{"draws":23,"losses":87,"wins":28},"thinkingmachines/inkling":{"draws":42,"losses":69,"wins":77},"thinkingmachines/inkling-small":{"draws":45,"losses":41,"wins":58},"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":30,"losses":84,"wins":30},"x-ai/grok-4.6":{"draws":24,"losses":95,"wins":25},"x-ai/grok-4.7":{"draws":16,"losses":105,"wins":11},"x-ai/grok-build-0.1":{"draws":10,"losses":14,"wins":24},"xiaomi/mimo-v2.5":{"draws":56,"losses":74,"wins":106},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":37,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":24,"losses":50,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":66,"wins":17},"z-ai/glm-5.2":{"draws":71,"losses":121,"wins":96},"z-ai/glm-5.3":{"draws":19,"losses":96,"wins":21},"z-ai/glm-5.3-flash":{"draws":22,"losses":85,"wins":37},"z-ai/glm-5.3-flashx":{"draws":30,"losses":79,"wins":35}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":21,"wins":54},"claude-fable-5":{"draws":32,"losses":62,"wins":38},"claude-fable-5-1":{"draws":5,"losses":126,"wins":19},"claude-haiku-5-5":{"draws":46,"losses":45,"wins":35},"claude-opus-4-5":{"draws":88,"losses":47,"wins":79},"claude-opus-4-8":{"draws":38,"losses":34,"wins":48},"claude-opus-5":{"draws":31,"losses":156,"wins":45},"claude-opus-5-5":{"draws":13,"losses":116,"wins":15},"claude-sonnet-5":{"draws":48,"losses":26,"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":67,"losses":22,"wins":107},"deepseek/deepseek-v4-pro":{"draws":37,"losses":27,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":38,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":45,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":39,"losses":50,"wins":43},"elorian/glimpse":{"draws":17,"losses":24,"wins":33},"fireworks/ember-1":{"draws":40,"losses":42,"wins":50},"gemini-3.1-pro-preview":{"draws":37,"losses":33,"wins":62},"gemini-4-argon":{"draws":9,"losses":100,"wins":23},"google/gemini-3.1-flash-lite":{"draws":25,"losses":5,"wins":58},"google/gemini-3.5-flash":{"draws":46,"losses":49,"wins":71},"google/gemini-3.5-flash-lite":{"draws":88,"losses":34,"wins":110},"google/gemini-3.6-flash":{"draws":73,"losses":88,"wins":93},"google/gemini-3.8-flash":{"draws":44,"losses":44,"wins":44},"google/gemma-4-31b-it":{"draws":30,"losses":6,"wins":40},"gpt-4.1":{"draws":10,"losses":9,"wins":25},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":4},"gpt-5":{"draws":42,"losses":27,"wins":49},"gpt-5.4":{"draws":34,"losses":49,"wins":45},"gpt-5.4-mini":{"draws":40,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":33,"losses":33,"wins":64},"gpt-5.5":{"draws":36,"losses":22,"wins":22},"gpt-5.6-luna":{"draws":49,"losses":22,"wins":61},"gpt-5.6-sol":{"draws":25,"losses":61,"wins":46},"gpt-5.6-terra":{"draws":49,"losses":29,"wins":48},"gpt-6-astra":{"draws":4,"losses":118,"wins":10},"gpt-6-luna":{"draws":52,"losses":30,"wins":50},"gpt-6-sol":{"draws":19,"losses":83,"wins":30},"gpt-6.1-sol":{"draws":8,"losses":103,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":40,"losses":8,"wins":42},"inception/mercury-3":{"draws":26,"losses":21,"wins":39},"inclusionai/ling-3.0-flash":{"draws":41,"losses":7,"wins":44},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":40,"losses":27,"wins":77},"meta/muse-glimmer-30b":{"draws":48,"losses":16,"wins":56},"meta/muse-spark-1.2":{"draws":26,"losses":44,"wins":58},"meta/muse-spark-1.3":{"draws":32,"losses":52,"wins":48},"meta/muse-spark-open":{"draws":24,"losses":55,"wins":49},"meta/muse-wonder":{"draws":37,"losses":59,"wins":36},"minimax/minimax-m3":{"draws":22,"losses":11,"wins":39},"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":26,"losses":8,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":10,"wins":12},"moonshotai/kimi-k3":{"draws":37,"losses":46,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":93,"wins":23},"nex-agi/nex-n2-pro":{"draws":18,"losses":5,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":8,"wins":53},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":10,"wins":29},"o3":{"draws":36,"losses":44,"wins":104},"openai/gpt-oss-120b":{"draws":44,"losses":16,"wins":56},"poolside/laguna-s-2.1":{"draws":47,"losses":23,"wins":58},"qwen/qwen3.7-max":{"draws":27,"losses":14,"wins":35},"qwen/qwen3.7-plus":{"draws":26,"losses":6,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":45,"wins":47},"qwen/qwen3.8-27b":{"draws":29,"losses":26,"wins":37},"qwen/qwen3.8-flash":{"draws":31,"losses":20,"wins":37},"qwen/qwen3.8-max":{"draws":44,"losses":40,"wins":48},"qwen/qwen3.8-max-0902":{"draws":47,"losses":43,"wins":42},"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":121,"losses":165,"wins":156},"stealth/space-bunny-alpha":{"draws":41,"losses":19,"wins":46},"stepfun/step-3.7-flash":{"draws":26,"losses":14,"wins":54},"stepfun/step-5-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":33,"losses":9,"wins":30},"tencent/hy4-preview":{"draws":44,"losses":44,"wins":40},"thinkingmachines/inkling":{"draws":55,"losses":27,"wins":98},"thinkingmachines/inkling-small":{"draws":46,"losses":20,"wins":66},"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":52,"wins":45},"x-ai/grok-4.6":{"draws":42,"losses":54,"wins":36},"x-ai/grok-4.7":{"draws":10,"losses":69,"wins":37},"x-ai/grok-build-0.1":{"draws":23,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":84,"losses":20,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":14,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":23,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":37,"wins":31},"z-ai/glm-5.2":{"draws":101,"losses":48,"wins":115},"z-ai/glm-5.3":{"draws":31,"losses":72,"wins":23},"z-ai/glm-5.3-flash":{"draws":24,"losses":58,"wins":50},"z-ai/glm-5.3-flashx":{"draws":41,"losses":47,"wins":44}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":47,"wins":42},"claude-fable-5":{"draws":33,"losses":93,"wins":18},"claude-fable-5-1":{"draws":10,"losses":147,"wins":5},"claude-haiku-5-5":{"draws":40,"losses":74,"wins":24},"claude-opus-4-5":{"draws":84,"losses":92,"wins":58},"claude-opus-4-8":{"draws":39,"losses":64,"wins":29},"claude-opus-5":{"draws":26,"losses":196,"wins":24},"claude-opus-5-5":{"draws":15,"losses":136,"wins":5},"claude-sonnet-5":{"draws":44,"losses":61,"wins":39},"claude-sonnet-5-5":{"draws":33,"losses":84,"wins":27},"cohere/north-mini-code":{"draws":16,"losses":10,"wins":28},"deepseek/deepseek-v4-flash":{"draws":84,"losses":50,"wins":82},"deepseek/deepseek-v4-pro":{"draws":43,"losses":53,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":51,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":64,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":90,"wins":25},"elorian/glimpse":{"draws":22,"losses":36,"wins":20},"fireworks/ember-1":{"draws":46,"losses":55,"wins":43},"gemini-3.1-pro-preview":{"draws":45,"losses":53,"wins":46},"gemini-4-argon":{"draws":13,"losses":123,"wins":8},"google/gemini-3.1-flash-lite":{"draws":25,"losses":21,"wins":50},"google/gemini-3.5-flash":{"draws":51,"losses":80,"wins":49},"google/gemini-3.5-flash-lite":{"draws":81,"losses":76,"wins":95},"google/gemini-3.6-flash":{"draws":82,"losses":135,"wins":59},"google/gemini-3.8-flash":{"draws":31,"losses":87,"wins":26},"google/gemma-4-31b-it":{"draws":34,"losses":20,"wins":30},"gpt-4.1":{"draws":17,"losses":17,"wins":14},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":40,"losses":50,"wins":36},"gpt-5.4":{"draws":45,"losses":71,"wins":22},"gpt-5.4-mini":{"draws":38,"losses":27,"wins":31},"gpt-5.4-nano":{"draws":35,"losses":49,"wins":60},"gpt-5.5":{"draws":49,"losses":61,"wins":22},"gpt-5.6-luna":{"draws":40,"losses":28,"wins":28},"gpt-5.6-sol":{"draws":21,"losses":99,"wins":24},"gpt-5.6-terra":{"draws":46,"losses":51,"wins":41},"gpt-6-astra":{"draws":15,"losses":127,"wins":2},"gpt-6-luna":{"draws":48,"losses":58,"wins":38},"gpt-6-sol":{"draws":24,"losses":106,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":125,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":51,"losses":17,"wins":34},"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":3,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":48,"losses":47,"wins":61},"meta/muse-glimmer-30b":{"draws":52,"losses":32,"wins":42},"meta/muse-spark-1.2":{"draws":36,"losses":66,"wins":36},"meta/muse-spark-1.3":{"draws":37,"losses":78,"wins":29},"meta/muse-spark-open":{"draws":34,"losses":71,"wins":33},"meta/muse-wonder":{"draws":28,"losses":91,"wins":25},"minimax/minimax-m3":{"draws":26,"losses":21,"wins":31},"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":34,"losses":12,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":15,"wins":9},"moonshotai/kimi-k3":{"draws":46,"losses":62,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":121,"wins":8},"nex-agi/nex-n2-pro":{"draws":20,"losses":12,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":11,"losses":13,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":33,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":21,"losses":28,"wins":17},"o3":{"draws":40,"losses":89,"wins":69},"openai/gpt-oss-120b":{"draws":57,"losses":27,"wins":42},"poolside/laguna-s-2.1":{"draws":51,"losses":41,"wins":46},"qwen/qwen3.7-max":{"draws":31,"losses":32,"wins":21},"qwen/qwen3.7-plus":{"draws":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":48,"losses":66,"wins":30},"qwen/qwen3.8-max-0902":{"draws":51,"losses":61,"wins":32},"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":145,"losses":228,"wins":101},"stealth/space-bunny-alpha":{"draws":43,"losses":40,"wins":31},"stepfun/step-3.7-flash":{"draws":27,"losses":31,"wins":44},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":29,"losses":28,"wins":21},"tencent/hy4-preview":{"draws":43,"losses":69,"wins":26},"thinkingmachines/inkling":{"draws":63,"losses":44,"wins":85},"thinkingmachines/inkling-small":{"draws":58,"losses":37,"wins":49},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":17},"x-ai/grok-4.5":{"draws":37,"losses":72,"wins":35},"x-ai/grok-4.6":{"draws":37,"losses":86,"wins":21},"x-ai/grok-4.7":{"draws":13,"losses":96,"wins":17},"x-ai/grok-build-0.1":{"draws":19,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":90,"losses":47,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":27,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":41,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":62,"wins":17},"z-ai/glm-5.2":{"draws":108,"losses":110,"wins":70},"z-ai/glm-5.3":{"draws":28,"losses":95,"wins":15},"z-ai/glm-5.3-flash":{"draws":37,"losses":78,"wins":29},"z-ai/glm-5.3-flashx":{"draws":42,"losses":73,"wins":29}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":15,"wins":95},"claude-fable-5":{"draws":17,"losses":68,"wins":59},"claude-fable-5-1":{"draws":12,"losses":131,"wins":19},"claude-haiku-5-5":{"draws":21,"losses":41,"wins":76},"claude-opus-4-5":{"draws":44,"losses":41,"wins":149},"claude-opus-4-8":{"draws":18,"losses":42,"wins":72},"claude-opus-5":{"draws":29,"losses":156,"wins":61},"claude-opus-5-5":{"draws":12,"losses":123,"wins":21},"claude-sonnet-5":{"draws":20,"losses":19,"wins":105},"claude-sonnet-5-5":{"draws":15,"losses":58,"wins":71},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":47},"deepseek/deepseek-v4-flash":{"draws":29,"losses":21,"wins":166},"deepseek/deepseek-v4-pro":{"draws":16,"losses":30,"wins":86},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":27,"wins":88},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":43,"wins":75},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":51,"wins":67},"elorian/glimpse":{"draws":10,"losses":22,"wins":46},"fireworks/ember-1":{"draws":23,"losses":38,"wins":83},"gemini-3.1-pro-preview":{"draws":17,"losses":31,"wins":96},"gemini-4-argon":{"draws":11,"losses":100,"wins":33},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":83},"google/gemini-3.5-flash":{"draws":18,"losses":41,"wins":121},"google/gemini-3.5-flash-lite":{"draws":36,"losses":21,"wins":195},"google/gemini-3.6-flash":{"draws":41,"losses":76,"wins":159},"google/gemini-3.8-flash":{"draws":19,"losses":53,"wins":72},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":67},"gpt-4.1":{"draws":8,"losses":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":19,"losses":12,"wins":65},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":116},"gpt-5.5":{"draws":25,"losses":46,"wins":61},"gpt-5.6-luna":{"draws":21,"losses":24,"wins":99},"gpt-5.6-sol":{"draws":8,"losses":44,"wins":44},"gpt-5.6-terra":{"draws":28,"losses":25,"wins":85},"gpt-6-astra":{"draws":15,"losses":117,"wins":12},"gpt-6-luna":{"draws":28,"losses":24,"wins":92},"gpt-6-sol":{"draws":13,"losses":85,"wins":46},"gpt-6.1-sol":{"draws":13,"losses":109,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":83},"inception/mercury-3":{"draws":14,"losses":17,"wins":65},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":86},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":122},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":99},"meta/muse-spark-1.2":{"draws":17,"losses":33,"wins":88},"meta/muse-spark-1.3":{"draws":21,"losses":48,"wins":75},"meta/muse-spark-open":{"draws":22,"losses":43,"wins":73},"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":5,"losses":7,"wins":24},"moonshotai/kimi-k3":{"draws":23,"losses":32,"wins":83},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":96,"wins":30},"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":16,"losses":10,"wins":100},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":44},"o3":{"draws":14,"losses":31,"wins":153},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":104},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":111},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":59},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":37,"wins":84},"qwen/qwen3.8-27b":{"draws":16,"losses":17,"wins":69},"qwen/qwen3.8-flash":{"draws":16,"losses":18,"wins":62},"qwen/qwen3.8-max":{"draws":26,"losses":30,"wins":88},"qwen/qwen3.8-max-0902":{"draws":23,"losses":34,"wins":87},"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":72,"losses":116,"wins":286},"stealth/space-bunny-alpha":{"draws":20,"losses":14,"wins":80},"stepfun/step-3.7-flash":{"draws":11,"losses":6,"wins":85},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":55},"tencent/hy4-preview":{"draws":20,"losses":48,"wins":70},"thinkingmachines/inkling":{"draws":28,"losses":17,"wins":147},"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":3,"losses":43,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":32},"x-ai/grok-4.5":{"draws":19,"losses":43,"wins":82},"x-ai/grok-4.6":{"draws":28,"losses":57,"wins":59},"x-ai/grok-4.7":{"draws":16,"losses":69,"wins":41},"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":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":35,"wins":44},"z-ai/glm-5.2":{"draws":37,"losses":45,"wins":206},"z-ai/glm-5.3":{"draws":23,"losses":55,"wins":60},"z-ai/glm-5.3-flash":{"draws":25,"losses":47,"wins":72},"z-ai/glm-5.3-flashx":{"draws":23,"losses":41,"wins":80}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":24,"wins":65},"claude-fable-5":{"draws":39,"losses":80,"wins":19},"claude-fable-5-1":{"draws":10,"losses":142,"wins":4},"claude-haiku-5-5":{"draws":39,"losses":56,"wins":37},"claude-opus-4-5":{"draws":79,"losses":77,"wins":68},"claude-opus-4-8":{"draws":31,"losses":59,"wins":36},"claude-opus-5":{"draws":29,"losses":184,"wins":21},"claude-opus-5-5":{"draws":9,"losses":138,"wins":3},"claude-sonnet-5":{"draws":53,"losses":40,"wins":45},"claude-sonnet-5-5":{"draws":33,"losses":74,"wins":31},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":33},"deepseek/deepseek-v4-flash":{"draws":67,"losses":32,"wins":109},"deepseek/deepseek-v4-pro":{"draws":40,"losses":44,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":39,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":50,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":33,"losses":80,"wins":25},"elorian/glimpse":{"draws":19,"losses":32,"wins":25},"fireworks/ember-1":{"draws":42,"losses":58,"wins":38},"gemini-3.1-pro-preview":{"draws":46,"losses":48,"wins":44},"gemini-4-argon":{"draws":14,"losses":116,"wins":8},"google/gemini-3.1-flash-lite":{"draws":29,"losses":7,"wins":54},"google/gemini-3.5-flash":{"draws":53,"losses":55,"wins":64},"google/gemini-3.5-flash-lite":{"draws":75,"losses":47,"wins":118},"google/gemini-3.6-flash":{"draws":83,"losses":115,"wins":66},"google/gemini-3.8-flash":{"draws":40,"losses":62,"wins":36},"google/gemma-4-31b-it":{"draws":32,"losses":9,"wins":39},"gpt-4.1":{"draws":19,"losses":15,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":31,"losses":38,"wins":51},"gpt-5.4":{"draws":33,"losses":61,"wins":38},"gpt-5.4-mini":{"draws":39,"losses":21,"wins":32},"gpt-5.4-nano":{"draws":26,"losses":38,"wins":72},"gpt-5.5":{"draws":49,"losses":48,"wins":29},"gpt-5.6-luna":{"draws":46,"losses":41,"wins":51},"gpt-5.6-sol":{"draws":28,"losses":85,"wins":25},"gpt-5.6-terra":{"draws":32,"losses":28,"wins":28},"gpt-6-astra":{"draws":12,"losses":122,"wins":4},"gpt-6-luna":{"draws":40,"losses":56,"wins":42},"gpt-6-sol":{"draws":23,"losses":98,"wins":17},"gpt-6.1-sol":{"draws":9,"losses":122,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":42,"losses":7,"wins":49},"inception/mercury-3":{"draws":29,"losses":33,"wins":32},"inclusionai/ling-3.0-flash":{"draws":35,"losses":7,"wins":60},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":36,"wins":72},"meta/muse-glimmer-30b":{"draws":47,"losses":16,"wins":57},"meta/muse-spark-1.2":{"draws":39,"losses":54,"wins":39},"meta/muse-spark-1.3":{"draws":34,"losses":66,"wins":38},"meta/muse-spark-open":{"draws":36,"losses":63,"wins":33},"meta/muse-wonder":{"draws":31,"losses":77,"wins":30},"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":26,"losses":8,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":38,"losses":50,"wins":44},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":112,"wins":12},"nex-agi/nex-n2-pro":{"draws":19,"losses":8,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":11,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":17,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":24,"losses":18,"wins":22},"o3":{"draws":37,"losses":65,"wins":84},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":66},"poolside/laguna-s-2.1":{"draws":49,"losses":17,"wins":64},"qwen/qwen3.7-max":{"draws":24,"losses":16,"wins":40},"qwen/qwen3.7-plus":{"draws":28,"losses":11,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":59,"wins":31},"qwen/qwen3.8-27b":{"draws":35,"losses":29,"wins":34},"qwen/qwen3.8-flash":{"draws":27,"losses":31,"wins":34},"qwen/qwen3.8-max":{"draws":58,"losses":44,"wins":36},"qwen/qwen3.8-max-0902":{"draws":48,"losses":55,"wins":35},"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":133,"losses":195,"wins":128},"stealth/space-bunny-alpha":{"draws":37,"losses":32,"wins":39},"stepfun/step-3.7-flash":{"draws":24,"losses":21,"wins":53},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":31,"losses":16,"wins":27},"tencent/hy4-preview":{"draws":37,"losses":59,"wins":36},"thinkingmachines/inkling":{"draws":55,"losses":36,"wins":91},"thinkingmachines/inkling-small":{"draws":45,"losses":22,"wins":71},"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":40,"losses":68,"wins":30},"x-ai/grok-4.6":{"draws":46,"losses":71,"wins":21},"x-ai/grok-4.7":{"draws":12,"losses":87,"wins":21},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":24},"xiaomi/mimo-v2.5":{"draws":78,"losses":16,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":12,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":28,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":45,"wins":23},"z-ai/glm-5.2":{"draws":116,"losses":66,"wins":94},"z-ai/glm-5.3":{"draws":36,"losses":75,"wins":21},"z-ai/glm-5.3-flash":{"draws":33,"losses":65,"wins":40},"z-ai/glm-5.3-flashx":{"draws":38,"losses":63,"wins":37}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":118},"claude-fable-5":{"draws":10,"losses":24,"wins":110},"claude-fable-5-1":{"draws":16,"losses":61,"wins":85},"claude-haiku-5-5":{"draws":10,"losses":7,"wins":121},"claude-opus-4-5":{"draws":14,"losses":15,"wins":205},"claude-opus-4-8":{"draws":8,"losses":10,"wins":114},"claude-opus-5":{"draws":22,"losses":57,"wins":167},"claude-opus-5-5":{"draws":16,"losses":68,"wins":72},"claude-sonnet-5":{"draws":6,"losses":8,"wins":130},"claude-sonnet-5-5":{"draws":11,"losses":31,"wins":102},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":200},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":113},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":1,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":5,"wins":123},"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":6,"wins":128},"gemini-3.1-pro-preview":{"draws":10,"losses":4,"wins":130},"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":11,"losses":7,"wins":162},"google/gemini-3.5-flash-lite":{"draws":14,"losses":1,"wins":237},"google/gemini-3.6-flash":{"draws":19,"losses":18,"wins":239},"google/gemini-3.8-flash":{"draws":14,"losses":10,"wins":120},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":80},"gpt-4.1":{"draws":3,"losses":0,"wins":45},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":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":2,"losses":2,"wins":140},"gpt-5.5":{"draws":4,"losses":10,"wins":118},"gpt-5.6-luna":{"draws":15,"losses":2,"wins":127},"gpt-5.6-sol":{"draws":15,"losses":12,"wins":117},"gpt-5.6-terra":{"draws":12,"losses":4,"wins":122},"gpt-6-astra":{"draws":8,"losses":44,"wins":44},"gpt-6-luna":{"draws":15,"losses":9,"wins":120},"gpt-6-sol":{"draws":16,"losses":26,"wins":102},"gpt-6.1-sol":{"draws":18,"losses":50,"wins":76},"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":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":146},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":120},"meta/muse-spark-1.2":{"draws":7,"losses":4,"wins":127},"meta/muse-spark-1.3":{"draws":14,"losses":12,"wins":118},"meta/muse-spark-open":{"draws":7,"losses":3,"wins":128},"meta/muse-wonder":{"draws":14,"losses":16,"wins":114},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":75},"minimax/minimax-m3.1-flash":{"draws":9,"losses":0,"wins":117},"mistralai/mistral-large-4-0":{"draws":9,"losses":5,"wins":76},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":33},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":119},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":38,"wins":89},"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":9,"losses":1,"wins":116},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":64},"o3":{"draws":7,"losses":2,"wins":189},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":114},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":131},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":77},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":69},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":133},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":97},"qwen/qwen3.8-flash":{"draws":13,"losses":3,"wins":80},"qwen/qwen3.8-max":{"draws":13,"losses":2,"wins":129},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":129},"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":21,"wins":418},"stealth/space-bunny-alpha":{"draws":6,"losses":0,"wins":108},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":96},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":0,"wins":67},"tencent/hy4-preview":{"draws":9,"losses":5,"wins":124},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":178},"thinkingmachines/inkling-small":{"draws":9,"losses":0,"wins":135},"unbiased/pareto-26.10":{"draws":8,"losses":18,"wins":22},"unbiased/pareto-26.10-preview":{"draws":6,"losses":20,"wins":22},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":121},"x-ai/grok-4.6":{"draws":11,"losses":13,"wins":120},"x-ai/grok-4.7":{"draws":10,"losses":22,"wins":94},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":207},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":74},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":81},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":80},"z-ai/glm-5.2":{"draws":19,"losses":11,"wins":258},"z-ai/glm-5.3":{"draws":18,"losses":11,"wins":109},"z-ai/glm-5.3-flash":{"draws":11,"losses":8,"wins":125},"z-ai/glm-5.3-flashx":{"draws":14,"losses":9,"wins":121}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":39,"wins":54},"claude-fable-5":{"draws":31,"losses":86,"wins":27},"claude-fable-5-1":{"draws":11,"losses":144,"wins":7},"claude-haiku-5-5":{"draws":36,"losses":63,"wins":39},"claude-opus-4-5":{"draws":78,"losses":80,"wins":76},"claude-opus-4-8":{"draws":33,"losses":63,"wins":36},"claude-opus-5":{"draws":45,"losses":180,"wins":21},"claude-opus-5-5":{"draws":13,"losses":141,"wins":2},"claude-sonnet-5":{"draws":38,"losses":50,"wins":56},"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":66,"losses":45,"wins":105},"deepseek/deepseek-v4-pro":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":49,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":58,"wins":40},"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":64,"wins":43},"gemini-3.1-pro-preview":{"draws":36,"losses":61,"wins":47},"gemini-4-argon":{"draws":10,"losses":126,"wins":8},"google/gemini-3.1-flash-lite":{"draws":27,"losses":11,"wins":58},"google/gemini-3.5-flash":{"draws":50,"losses":70,"wins":60},"google/gemini-3.5-flash-lite":{"draws":79,"losses":60,"wins":113},"google/gemini-3.6-flash":{"draws":82,"losses":123,"wins":71},"google/gemini-3.8-flash":{"draws":41,"losses":67,"wins":36},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":38},"gpt-4.1":{"draws":10,"losses":19,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":7},"gpt-5":{"draws":39,"losses":42,"wins":45},"gpt-5.4":{"draws":42,"losses":59,"wins":37},"gpt-5.4-mini":{"draws":43,"losses":13,"wins":40},"gpt-5.4-nano":{"draws":30,"losses":42,"wins":72},"gpt-5.5":{"draws":52,"losses":50,"wins":30},"gpt-5.6-luna":{"draws":48,"losses":38,"wins":58},"gpt-5.6-sol":{"draws":28,"losses":92,"wins":24},"gpt-5.6-terra":{"draws":40,"losses":42,"wins":56},"gpt-6-astra":{"draws":15,"losses":120,"wins":9},"gpt-6-luna":{"draws":24,"losses":36,"wins":36},"gpt-6-sol":{"draws":23,"losses":102,"wins":19},"gpt-6.1-sol":{"draws":13,"losses":125,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":41,"losses":9,"wins":52},"inception/mercury-3":{"draws":26,"losses":31,"wins":39},"inclusionai/ling-3.0-flash":{"draws":35,"losses":13,"wins":54},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":38,"losses":34,"wins":84},"meta/muse-glimmer-30b":{"draws":45,"losses":18,"wins":63},"meta/muse-spark-1.2":{"draws":37,"losses":63,"wins":38},"meta/muse-spark-1.3":{"draws":25,"losses":83,"wins":36},"meta/muse-spark-open":{"draws":31,"losses":64,"wins":43},"meta/muse-wonder":{"draws":34,"losses":77,"wins":33},"minimax/minimax-m3":{"draws":21,"losses":15,"wins":42},"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":30,"losses":7,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":10,"wins":13},"moonshotai/kimi-k3":{"draws":45,"losses":51,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":118,"wins":6},"nex-agi/nex-n2-pro":{"draws":15,"losses":12,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":8,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":25,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":34,"losses":64,"wins":100},"openai/gpt-oss-120b":{"draws":41,"losses":26,"wins":59},"poolside/laguna-s-2.1":{"draws":43,"losses":36,"wins":59},"qwen/qwen3.7-max":{"draws":22,"losses":27,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":12,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":59,"wins":48},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":41},"qwen/qwen3.8-flash":{"draws":28,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":37,"losses":57,"wins":50},"qwen/qwen3.8-max-0902":{"draws":41,"losses":55,"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":112,"losses":208,"wins":154},"stealth/space-bunny-alpha":{"draws":41,"losses":23,"wins":50},"stepfun/step-3.7-flash":{"draws":21,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":26,"losses":20,"wins":32},"tencent/hy4-preview":{"draws":40,"losses":63,"wins":35},"thinkingmachines/inkling":{"draws":56,"losses":40,"wins":96},"thinkingmachines/inkling-small":{"draws":40,"losses":32,"wins":72},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":34,"losses":65,"wins":45},"x-ai/grok-4.6":{"draws":38,"losses":82,"wins":24},"x-ai/grok-4.7":{"draws":10,"losses":96,"wins":20},"x-ai/grok-build-0.1":{"draws":20,"losses":4,"wins":24},"xiaomi/mimo-v2.5":{"draws":79,"losses":29,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":19,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":36,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":50,"wins":27},"z-ai/glm-5.2":{"draws":102,"losses":73,"wins":113},"z-ai/glm-5.3":{"draws":26,"losses":85,"wins":27},"z-ai/glm-5.3-flash":{"draws":39,"losses":71,"wins":34},"z-ai/glm-5.3-flashx":{"draws":30,"losses":71,"wins":43}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":102},"claude-fable-5":{"draws":21,"losses":41,"wins":82},"claude-fable-5-1":{"draws":15,"losses":109,"wins":38},"claude-haiku-5-5":{"draws":27,"losses":27,"wins":84},"claude-opus-4-5":{"draws":35,"losses":25,"wins":174},"claude-opus-4-8":{"draws":20,"losses":33,"wins":79},"claude-opus-5":{"draws":33,"losses":120,"wins":93},"claude-opus-5-5":{"draws":14,"losses":102,"wins":40},"claude-sonnet-5":{"draws":23,"losses":19,"wins":102},"claude-sonnet-5-5":{"draws":14,"losses":48,"wins":82},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":49},"deepseek/deepseek-v4-flash":{"draws":32,"losses":16,"wins":168},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":99},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":31,"wins":89},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":40,"wins":89},"elorian/glimpse":{"draws":10,"losses":15,"wins":53},"fireworks/ember-1":{"draws":21,"losses":23,"wins":100},"gemini-3.1-pro-preview":{"draws":16,"losses":28,"wins":100},"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":27,"losses":26,"wins":127},"google/gemini-3.5-flash-lite":{"draws":38,"losses":23,"wins":191},"google/gemini-3.6-flash":{"draws":35,"losses":59,"wins":182},"google/gemini-3.8-flash":{"draws":22,"losses":31,"wins":91},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":73},"gpt-4.1":{"draws":7,"losses":7,"wins":34},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":15,"losses":16,"wins":95},"gpt-5.4":{"draws":14,"losses":22,"wins":102},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":72},"gpt-5.4-nano":{"draws":20,"losses":12,"wins":112},"gpt-5.5":{"draws":19,"losses":30,"wins":83},"gpt-5.6-luna":{"draws":24,"losses":14,"wins":106},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":85},"gpt-5.6-terra":{"draws":23,"losses":17,"wins":98},"gpt-6-astra":{"draws":16,"losses":102,"wins":26},"gpt-6-luna":{"draws":23,"losses":19,"wins":102},"gpt-6-sol":{"draws":12,"losses":42,"wins":42},"gpt-6.1-sol":{"draws":17,"losses":91,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":82},"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":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":132},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":97},"meta/muse-spark-1.2":{"draws":18,"losses":24,"wins":96},"meta/muse-spark-1.3":{"draws":23,"losses":22,"wins":99},"meta/muse-spark-open":{"draws":12,"losses":22,"wins":104},"meta/muse-wonder":{"draws":18,"losses":45,"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":7,"losses":2,"wins":27},"moonshotai/kimi-k3":{"draws":14,"losses":27,"wins":97},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":82,"wins":39},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":61},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":106},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":52},"o3":{"draws":10,"losses":17,"wins":171},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":101},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":58},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":32,"wins":93},"qwen/qwen3.8-27b":{"draws":16,"losses":14,"wins":72},"qwen/qwen3.8-flash":{"draws":9,"losses":19,"wins":68},"qwen/qwen3.8-max":{"draws":17,"losses":28,"wins":99},"qwen/qwen3.8-max-0902":{"draws":18,"losses":27,"wins":99},"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":73,"wins":340},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":87},"stepfun/step-3.7-flash":{"draws":13,"losses":4,"wins":85},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":58},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":92},"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":5,"losses":34,"wins":9},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":32},"x-ai/grok-4.5":{"draws":19,"losses":32,"wins":93},"x-ai/grok-4.6":{"draws":20,"losses":32,"wins":92},"x-ai/grok-4.7":{"draws":13,"losses":60,"wins":53},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":38},"xiaomi/mimo-v2.5":{"draws":35,"losses":17,"wins":170},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":64},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":24,"wins":54},"z-ai/glm-5.2":{"draws":43,"losses":34,"wins":211},"z-ai/glm-5.3":{"draws":21,"losses":47,"wins":70},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":18,"losses":40,"wins":86}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":114},"claude-fable-5":{"draws":10,"losses":32,"wins":102},"claude-fable-5-1":{"draws":12,"losses":75,"wins":75},"claude-haiku-5-5":{"draws":15,"losses":10,"wins":113},"claude-opus-4-5":{"draws":20,"losses":16,"wins":198},"claude-opus-4-8":{"draws":7,"losses":14,"wins":111},"claude-opus-5":{"draws":33,"losses":74,"wins":139},"claude-opus-5-5":{"draws":19,"losses":74,"wins":63},"claude-sonnet-5":{"draws":6,"losses":9,"wins":129},"claude-sonnet-5-5":{"draws":3,"losses":36,"wins":105},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":197},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":116},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":121},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":115},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":107},"elorian/glimpse":{"draws":4,"losses":10,"wins":64},"fireworks/ember-1":{"draws":9,"losses":17,"wins":118},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":127},"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":11,"losses":18,"wins":151},"google/gemini-3.5-flash-lite":{"draws":15,"losses":1,"wins":236},"google/gemini-3.6-flash":{"draws":17,"losses":27,"wins":232},"google/gemini-3.8-flash":{"draws":18,"losses":18,"wins":108},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":80},"gpt-4.1":{"draws":4,"losses":1,"wins":43},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":17},"gpt-5":{"draws":6,"losses":5,"wins":115},"gpt-5.4":{"draws":11,"losses":19,"wins":108},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":88},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":134},"gpt-5.5":{"draws":8,"losses":21,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":13,"losses":22,"wins":109},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":122},"gpt-6-astra":{"draws":18,"losses":76,"wins":50},"gpt-6-luna":{"draws":13,"losses":6,"wins":125},"gpt-6-sol":{"draws":17,"losses":36,"wins":91},"gpt-6.1-sol":{"draws":2,"losses":47,"wins":47},"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":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":139},"meta/muse-glimmer-30b":{"draws":8,"losses":1,"wins":117},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":110},"meta/muse-spark-1.3":{"draws":13,"losses":14,"wins":117},"meta/muse-spark-open":{"draws":7,"losses":13,"wins":118},"meta/muse-wonder":{"draws":19,"losses":29,"wins":96},"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":3,"losses":3,"wins":30},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":115},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":47,"wins":77},"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":8,"losses":6,"wins":112},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":58},"o3":{"draws":3,"losses":9,"wins":186},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":118},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":128},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":75},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":113},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":91},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":82},"qwen/qwen3.8-max":{"draws":10,"losses":9,"wins":125},"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":42,"losses":31,"wins":401},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":100},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":99},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":68},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":118},"thinkingmachines/inkling":{"draws":13,"losses":6,"wins":173},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":138},"unbiased/pareto-26.10":{"draws":6,"losses":25,"wins":17},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":18},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":35},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":118},"x-ai/grok-4.6":{"draws":16,"losses":14,"wins":114},"x-ai/grok-4.7":{"draws":7,"losses":40,"wins":79},"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":7,"losses":1,"wins":70},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":79},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":20,"wins":62},"z-ai/glm-5.2":{"draws":30,"losses":10,"wins":248},"z-ai/glm-5.3":{"draws":21,"losses":25,"wins":92},"z-ai/glm-5.3-flash":{"draws":13,"losses":16,"wins":115},"z-ai/glm-5.3-flashx":{"draws":18,"losses":18,"wins":108}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"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},"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},"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":0,"wins":1},"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},"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":36,"losses":32,"wins":24},"claude-fable-5":{"draws":26,"losses":71,"wins":5},"claude-fable-5-1":{"draws":9,"losses":105,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":68,"wins":4},"claude-opus-4-5":{"draws":72,"losses":88,"wins":8},"claude-opus-4-8":{"draws":32,"losses":57,"wins":9},"claude-opus-5":{"draws":30,"losses":130,"wins":6},"claude-opus-5-5":{"draws":8,"losses":102,"wins":0},"claude-sonnet-5":{"draws":38,"losses":54,"wins":10},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":13,"wins":15},"deepseek/deepseek-v4-flash":{"draws":64,"losses":60,"wins":28},"deepseek/deepseek-v4-pro":{"draws":37,"losses":45,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":46,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":48,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":30,"losses":66,"wins":6},"elorian/glimpse":{"draws":15,"losses":32,"wins":5},"fireworks/ember-1":{"draws":42,"losses":53,"wins":7},"gemini-3.1-pro-preview":{"draws":40,"losses":40,"wins":22},"gemini-4-argon":{"draws":8,"losses":94,"wins":0},"google/gemini-3.1-flash-lite":{"draws":27,"losses":19,"wins":26},"google/gemini-3.5-flash":{"draws":45,"losses":67,"wins":16},"google/gemini-3.5-flash-lite":{"draws":74,"losses":67,"wins":39},"google/gemini-3.6-flash":{"draws":68,"losses":114,"wins":12},"google/gemini-3.8-flash":{"draws":31,"losses":67,"wins":4},"google/gemma-4-31b-it":{"draws":30,"losses":18,"wins":16},"gpt-4.1":{"draws":15,"losses":11,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":5,"wins":3},"gpt-5":{"draws":34,"losses":41,"wins":9},"gpt-5.4":{"draws":39,"losses":52,"wins":5},"gpt-5.4-mini":{"draws":31,"losses":23,"wins":14},"gpt-5.4-nano":{"draws":32,"losses":56,"wins":14},"gpt-5.5":{"draws":40,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":51,"losses":34,"wins":17},"gpt-5.6-sol":{"draws":19,"losses":83,"wins":0},"gpt-5.6-terra":{"draws":42,"losses":49,"wins":7},"gpt-6-astra":{"draws":7,"losses":95,"wins":0},"gpt-6-luna":{"draws":41,"losses":52,"wins":9},"gpt-6-sol":{"draws":16,"losses":82,"wins":4},"gpt-6.1-sol":{"draws":9,"losses":93,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":10,"wins":10},"inception/mercury-3":{"draws":30,"losses":30,"wins":8},"inclusionai/ling-3.0-flash":{"draws":35,"losses":19,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":42,"wins":28},"meta/muse-glimmer-30b":{"draws":44,"losses":23,"wins":17},"meta/muse-spark-1.2":{"draws":34,"losses":51,"wins":11},"meta/muse-spark-1.3":{"draws":29,"losses":65,"wins":8},"meta/muse-spark-open":{"draws":27,"losses":63,"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":29,"losses":16,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":2},"moonshotai/kimi-k3":{"draws":44,"losses":44,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":81,"wins":1},"nex-agi/nex-n2-pro":{"draws":20,"losses":16,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":26,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":25,"wins":6},"o3":{"draws":31,"losses":88,"wins":17},"openai/gpt-oss-120b":{"draws":38,"losses":29,"wins":21},"poolside/laguna-s-2.1":{"draws":38,"losses":28,"wins":24},"qwen/qwen3.7-max":{"draws":25,"losses":23,"wins":12},"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":43,"losses":51,"wins":8},"qwen/qwen3.8-max-0902":{"draws":44,"losses":48,"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":100,"losses":176,"wins":34},"stealth/space-bunny-alpha":{"draws":37,"losses":35,"wins":10},"stepfun/step-3.7-flash":{"draws":20,"losses":38,"wins":10},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":39,"losses":49,"wins":8},"thinkingmachines/inkling":{"draws":52,"losses":44,"wins":32},"thinkingmachines/inkling-small":{"draws":47,"losses":31,"wins":24},"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":31,"losses":64,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":72,"wins":3},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":78,"losses":67,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":25,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":41,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":48,"wins":1},"z-ai/glm-5.2":{"draws":87,"losses":98,"wins":19},"z-ai/glm-5.3":{"draws":28,"losses":69,"wins":3},"z-ai/glm-5.3-flash":{"draws":24,"losses":66,"wins":12},"z-ai/glm-5.3-flashx":{"draws":30,"losses":67,"wins":5}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":27,"wins":34},"claude-fable-5":{"draws":24,"losses":59,"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":37,"wins":70},"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":39},"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":33},"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},"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":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":25,"losses":27,"wins":50},"meta/muse-glimmer-30b":{"draws":24,"losses":17,"wins":41},"meta/muse-spark-1.2":{"draws":26,"losses":42,"wins":24},"meta/muse-spark-1.3":{"draws":19,"losses":55,"wins":22},"meta/muse-spark-open":{"draws":18,"losses":50,"wins":22},"meta/muse-wonder":{"draws":24,"losses":49,"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":6,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":26,"losses":30,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":71,"wins":8},"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":29,"losses":18,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":10,"wins":21},"o3":{"draws":17,"losses":36,"wins":75},"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":40,"wins":26},"qwen/qwen3.8-max-0902":{"draws":27,"losses":39,"wins":30},"recursive/flint-v1.0":{"draws":8,"losses":6,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":31,"wins":29},"stealth/ox-alpha":{"draws":79,"losses":130,"wins":103},"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":0,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":17,"losses":13,"wins":22},"tencent/hy4-preview":{"draws":22,"losses":40,"wins":28},"thinkingmachines/inkling":{"draws":43,"losses":26,"wins":53},"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":30,"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":13,"losses":14,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":22,"wins":28},"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":22,"losses":38,"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":39,"losses":39,"wins":16},"claude-fable-5":{"draws":18,"losses":80,"wins":4},"claude-fable-5-1":{"draws":5,"losses":109,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":61,"wins":5},"claude-opus-4-5":{"draws":59,"losses":88,"wins":19},"claude-opus-4-8":{"draws":29,"losses":65,"wins":0},"claude-opus-5":{"draws":26,"losses":132,"wins":8},"claude-opus-5-5":{"draws":8,"losses":106,"wins":0},"claude-sonnet-5":{"draws":36,"losses":58,"wins":8},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":7},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":13},"deepseek/deepseek-v4-flash":{"draws":63,"losses":53,"wins":42},"deepseek/deepseek-v4-pro":{"draws":34,"losses":44,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":44,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":49,"wins":9},"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":56,"wins":5},"gemini-3.1-pro-preview":{"draws":39,"losses":53,"wins":10},"gemini-4-argon":{"draws":7,"losses":91,"wins":4},"google/gemini-3.1-flash-lite":{"draws":24,"losses":19,"wins":23},"google/gemini-3.5-flash":{"draws":37,"losses":79,"wins":12},"google/gemini-3.5-flash-lite":{"draws":62,"losses":79,"wins":35},"google/gemini-3.6-flash":{"draws":68,"losses":108,"wins":18},"google/gemini-3.8-flash":{"draws":30,"losses":70,"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":31,"losses":35,"wins":22},"gpt-5.4":{"draws":23,"losses":58,"wins":17},"gpt-5.4-mini":{"draws":31,"losses":25,"wins":12},"gpt-5.4-nano":{"draws":30,"losses":48,"wins":26},"gpt-5.5":{"draws":41,"losses":44,"wins":7},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":86,"wins":4},"gpt-5.6-terra":{"draws":35,"losses":60,"wins":7},"gpt-6-astra":{"draws":5,"losses":96,"wins":1},"gpt-6-luna":{"draws":35,"losses":54,"wins":13},"gpt-6-sol":{"draws":15,"losses":79,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":98,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":35,"losses":18,"wins":19},"inception/mercury-3":{"draws":20,"losses":38,"wins":16},"inclusionai/ling-3.0-flash":{"draws":22,"losses":15,"wins":15},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":39,"wins":24},"meta/muse-glimmer-30b":{"draws":50,"losses":22,"wins":14},"meta/muse-spark-1.2":{"draws":27,"losses":58,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":77,"wins":9},"meta/muse-spark-open":{"draws":17,"losses":73,"wins":8},"meta/muse-wonder":{"draws":18,"losses":79,"wins":5},"minimax/minimax-m3":{"draws":17,"losses":23,"wins":14},"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":25,"losses":18,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":31,"losses":53,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":84,"wins":1},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":4,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":26,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":22,"wins":10},"o3":{"draws":29,"losses":90,"wins":21},"openai/gpt-oss-120b":{"draws":38,"losses":40,"wins":8},"poolside/laguna-s-2.1":{"draws":41,"losses":36,"wins":17},"qwen/qwen3.7-max":{"draws":29,"losses":24,"wins":7},"qwen/qwen3.7-plus":{"draws":20,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":57,"wins":4},"qwen/qwen3.8-27b":{"draws":15,"losses":46,"wins":13},"qwen/qwen3.8-flash":{"draws":25,"losses":38,"wins":5},"qwen/qwen3.8-max":{"draws":41,"losses":47,"wins":14},"qwen/qwen3.8-max-0902":{"draws":39,"losses":54,"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":90,"losses":209,"wins":29},"stealth/space-bunny-alpha":{"draws":34,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":26,"losses":30,"wins":20},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":25,"wins":7},"tencent/hy4-preview":{"draws":37,"losses":56,"wins":5},"thinkingmachines/inkling":{"draws":51,"losses":52,"wins":27},"thinkingmachines/inkling-small":{"draws":46,"losses":33,"wins":23},"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":35,"losses":62,"wins":5},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":5},"x-ai/grok-build-0.1":{"draws":13,"losses":18,"wins":3},"xiaomi/mimo-v2.5":{"draws":72,"losses":54,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":27,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":41,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":49,"wins":5},"z-ai/glm-5.2":{"draws":101,"losses":78,"wins":25},"z-ai/glm-5.3":{"draws":22,"losses":71,"wins":3},"z-ai/glm-5.3-flash":{"draws":32,"losses":57,"wins":13},"z-ai/glm-5.3-flashx":{"draws":34,"losses":60,"wins":8}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"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":0,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inception/mercury-3":{"draws":0,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":6,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":2},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":63,"wins":41},"claude-fable-5":{"draws":18,"losses":118,"wins":20},"claude-fable-5-1":{"draws":5,"losses":164,"wins":6},"claude-haiku-5-5":{"draws":33,"losses":96,"wins":21},"claude-opus-4-5":{"draws":65,"losses":153,"wins":36},"claude-opus-4-8":{"draws":32,"losses":91,"wins":21},"claude-opus-5":{"draws":25,"losses":209,"wins":22},"claude-opus-5-5":{"draws":10,"losses":156,"wins":6},"claude-sonnet-5":{"draws":41,"losses":85,"wins":30},"claude-sonnet-5-5":{"draws":20,"losses":105,"wins":31},"cohere/north-mini-code":{"draws":14,"losses":15,"wins":39},"deepseek/deepseek-v4-flash":{"draws":64,"losses":94,"wins":76},"deepseek/deepseek-v4-pro":{"draws":29,"losses":85,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":71,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":87,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":108,"wins":22},"elorian/glimpse":{"draws":17,"losses":47,"wins":20},"fireworks/ember-1":{"draws":40,"losses":90,"wins":26},"gemini-3.1-pro-preview":{"draws":37,"losses":74,"wins":45},"gemini-4-argon":{"draws":8,"losses":138,"wins":10},"google/gemini-3.1-flash-lite":{"draws":22,"losses":28,"wins":62},"google/gemini-3.5-flash":{"draws":35,"losses":124,"wins":39},"google/gemini-3.5-flash-lite":{"draws":74,"losses":121,"wins":83},"google/gemini-3.6-flash":{"draws":64,"losses":190,"wins":46},"google/gemini-3.8-flash":{"draws":26,"losses":111,"wins":19},"google/gemma-4-31b-it":{"draws":33,"losses":26,"wins":35},"gpt-4.1":{"draws":16,"losses":27,"wins":9},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":32,"losses":73,"wins":33},"gpt-5.4":{"draws":32,"losses":95,"wins":25},"gpt-5.4-mini":{"draws":37,"losses":37,"wins":30},"gpt-5.4-nano":{"draws":24,"losses":85,"wins":51},"gpt-5.5":{"draws":40,"losses":77,"wins":27},"gpt-5.6-luna":{"draws":48,"losses":61,"wins":47},"gpt-5.6-sol":{"draws":20,"losses":122,"wins":14},"gpt-5.6-terra":{"draws":40,"losses":72,"wins":36},"gpt-6-astra":{"draws":8,"losses":146,"wins":2},"gpt-6-luna":{"draws":38,"losses":84,"wins":34},"gpt-6-sol":{"draws":11,"losses":132,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":139,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":42,"losses":28,"wins":42},"inception/mercury-3":{"draws":25,"losses":50,"wins":27},"inclusionai/ling-3.0-flash":{"draws":45,"losses":24,"wins":39},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":38,"losses":45,"wins":45},"meta/muse-glimmer-30b":{"draws":45,"losses":47,"wins":44},"meta/muse-spark-1.2":{"draws":28,"losses":93,"wins":27},"meta/muse-spark-1.3":{"draws":29,"losses":103,"wins":24},"meta/muse-spark-open":{"draws":28,"losses":106,"wins":18},"meta/muse-wonder":{"draws":31,"losses":105,"wins":20},"minimax/minimax-m3":{"draws":15,"losses":31,"wins":38},"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":34,"losses":23,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":24,"wins":7},"moonshotai/kimi-k3":{"draws":41,"losses":81,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":132,"wins":7},"nex-agi/nex-n2-pro":{"draws":16,"losses":28,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":17,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":46,"wins":48},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":36,"wins":16},"o3":{"draws":32,"losses":140,"wins":60},"openai/gpt-oss-120b":{"draws":43,"losses":38,"wins":57},"poolside/laguna-s-2.1":{"draws":45,"losses":56,"wins":49},"qwen/qwen3.7-max":{"draws":28,"losses":45,"wins":19},"qwen/qwen3.7-plus":{"draws":15,"losses":31,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":92,"wins":24},"qwen/qwen3.8-27b":{"draws":21,"losses":69,"wins":18},"qwen/qwen3.8-flash":{"draws":30,"losses":49,"wins":25},"qwen/qwen3.8-max":{"draws":46,"losses":82,"wins":28},"qwen/qwen3.8-max-0902":{"draws":26,"losses":105,"wins":25},"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":106,"losses":324,"wins":80},"stealth/space-bunny-alpha":{"draws":39,"losses":59,"wins":28},"stepfun/step-3.7-flash":{"draws":20,"losses":49,"wins":45},"stepfun/step-5-preview":{"draws":7,"losses":8,"wins":1},"tencent/hy3-preview":{"draws":24,"losses":33,"wins":25},"tencent/hy4-preview":{"draws":37,"losses":92,"wins":23},"thinkingmachines/inkling":{"draws":54,"losses":77,"wins":75},"thinkingmachines/inkling-small":{"draws":49,"losses":48,"wins":59},"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":102,"wins":24},"x-ai/grok-4.6":{"draws":36,"losses":98,"wins":22},"x-ai/grok-4.7":{"draws":8,"losses":121,"wins":7},"x-ai/grok-build-0.1":{"draws":17,"losses":18,"wins":17},"xiaomi/mimo-v2.5":{"draws":74,"losses":81,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":42,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":55,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":74,"wins":11},"z-ai/glm-5.2":{"draws":88,"losses":150,"wins":74},"z-ai/glm-5.3":{"draws":26,"losses":115,"wins":11},"z-ai/glm-5.3-flash":{"draws":25,"losses":98,"wins":33},"z-ai/glm-5.3-flashx":{"draws":32,"losses":104,"wins":20}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":46,"losses":37,"wins":33},"claude-fable-5":{"draws":26,"losses":93,"wins":7},"claude-fable-5-1":{"draws":8,"losses":134,"wins":1},"claude-haiku-5-5":{"draws":37,"losses":68,"wins":15},"claude-opus-4-5":{"draws":74,"losses":101,"wins":29},"claude-opus-4-8":{"draws":31,"losses":67,"wins":16},"claude-opus-5":{"draws":14,"losses":194,"wins":22},"claude-opus-5-5":{"draws":7,"losses":131,"wins":0},"claude-sonnet-5":{"draws":43,"losses":64,"wins":19},"claude-sonnet-5-5":{"draws":21,"losses":84,"wins":21},"cohere/north-mini-code":{"draws":18,"losses":15,"wins":17},"deepseek/deepseek-v4-flash":{"draws":82,"losses":57,"wins":47},"deepseek/deepseek-v4-pro":{"draws":37,"losses":56,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":61,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":60,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":30,"losses":84,"wins":12},"elorian/glimpse":{"draws":19,"losses":36,"wins":17},"fireworks/ember-1":{"draws":40,"losses":67,"wins":19},"gemini-3.1-pro-preview":{"draws":50,"losses":60,"wins":16},"gemini-4-argon":{"draws":13,"losses":109,"wins":4},"google/gemini-3.1-flash-lite":{"draws":33,"losses":19,"wins":30},"google/gemini-3.5-flash":{"draws":49,"losses":87,"wins":22},"google/gemini-3.5-flash-lite":{"draws":89,"losses":79,"wins":52},"google/gemini-3.6-flash":{"draws":78,"losses":128,"wins":36},"google/gemini-3.8-flash":{"draws":33,"losses":78,"wins":15},"google/gemma-4-31b-it":{"draws":38,"losses":17,"wins":17},"gpt-4.1":{"draws":19,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":2},"gpt-5":{"draws":40,"losses":50,"wins":24},"gpt-5.4":{"draws":30,"losses":74,"wins":18},"gpt-5.4-mini":{"draws":43,"losses":30,"wins":11},"gpt-5.4-nano":{"draws":31,"losses":49,"wins":42},"gpt-5.5":{"draws":48,"losses":56,"wins":16},"gpt-5.6-luna":{"draws":52,"losses":42,"wins":32},"gpt-5.6-sol":{"draws":19,"losses":99,"wins":8},"gpt-5.6-terra":{"draws":47,"losses":57,"wins":16},"gpt-6-astra":{"draws":6,"losses":120,"wins":0},"gpt-6-luna":{"draws":45,"losses":63,"wins":18},"gpt-6-sol":{"draws":19,"losses":97,"wins":10},"gpt-6.1-sol":{"draws":8,"losses":117,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":44,"losses":17,"wins":23},"inception/mercury-3":{"draws":24,"losses":41,"wins":17},"inclusionai/ling-3.0-flash":{"draws":50,"losses":14,"wins":22},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":44,"wins":47},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":18},"meta/muse-spark-1.2":{"draws":33,"losses":72,"wins":19},"meta/muse-spark-1.3":{"draws":36,"losses":74,"wins":16},"meta/muse-spark-open":{"draws":28,"losses":78,"wins":16},"meta/muse-wonder":{"draws":26,"losses":85,"wins":15},"minimax/minimax-m3":{"draws":21,"losses":27,"wins":22},"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":35,"losses":10,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":17,"wins":10},"moonshotai/kimi-k3":{"draws":38,"losses":67,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":20,"losses":100,"wins":0},"nex-agi/nex-n2-pro":{"draws":25,"losses":15,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":27,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":11},"o3":{"draws":34,"losses":103,"wins":35},"openai/gpt-oss-120b":{"draws":47,"losses":38,"wins":27},"poolside/laguna-s-2.1":{"draws":52,"losses":42,"wins":30},"qwen/qwen3.7-max":{"draws":29,"losses":27,"wins":16},"qwen/qwen3.7-plus":{"draws":25,"losses":15,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":64,"wins":15},"qwen/qwen3.8-27b":{"draws":25,"losses":47,"wins":14},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":21},"qwen/qwen3.8-max":{"draws":41,"losses":61,"wins":24},"qwen/qwen3.8-max-0902":{"draws":46,"losses":68,"wins":12},"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":100,"losses":268,"wins":58},"stealth/space-bunny-alpha":{"draws":39,"losses":36,"wins":27},"stepfun/step-3.7-flash":{"draws":20,"losses":27,"wins":41},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":31,"wins":13},"tencent/hy4-preview":{"draws":43,"losses":69,"wins":10},"thinkingmachines/inkling":{"draws":60,"losses":56,"wins":58},"thinkingmachines/inkling-small":{"draws":54,"losses":26,"wins":46},"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":40,"losses":78,"wins":8},"x-ai/grok-4.7":{"draws":6,"losses":92,"wins":14},"x-ai/grok-build-0.1":{"draws":18,"losses":14,"wins":10},"xiaomi/mimo-v2.5":{"draws":80,"losses":50,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":28,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":43,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":13},"z-ai/glm-5.2":{"draws":114,"losses":95,"wins":43},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":12},"z-ai/glm-5.3-flash":{"draws":28,"losses":81,"wins":17},"z-ai/glm-5.3-flashx":{"draws":36,"losses":71,"wins":19}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":30,"wins":64},"claude-fable-5":{"draws":21,"losses":85,"wins":32},"claude-fable-5-1":{"draws":8,"losses":140,"wins":8},"claude-haiku-5-5":{"draws":26,"losses":65,"wins":41},"claude-opus-4-5":{"draws":61,"losses":60,"wins":103},"claude-opus-4-8":{"draws":30,"losses":53,"wins":43},"claude-opus-5":{"draws":32,"losses":177,"wins":35},"claude-opus-5-5":{"draws":12,"losses":129,"wins":9},"claude-sonnet-5":{"draws":38,"losses":36,"wins":64},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":43},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":40},"deepseek/deepseek-v4-flash":{"draws":52,"losses":34,"wins":120},"deepseek/deepseek-v4-pro":{"draws":24,"losses":45,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":40,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":53,"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":37,"losses":53,"wins":48},"gemini-3.1-pro-preview":{"draws":33,"losses":48,"wins":57},"gemini-4-argon":{"draws":10,"losses":114,"wins":14},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":60},"google/gemini-3.5-flash":{"draws":35,"losses":59,"wins":78},"google/gemini-3.5-flash-lite":{"draws":60,"losses":45,"wins":135},"google/gemini-3.6-flash":{"draws":53,"losses":106,"wins":105},"google/gemini-3.8-flash":{"draws":24,"losses":58,"wins":56},"google/gemma-4-31b-it":{"draws":23,"losses":17,"wins":40},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":24,"losses":31,"wins":67},"gpt-5.4":{"draws":24,"losses":59,"wins":49},"gpt-5.4-mini":{"draws":27,"losses":20,"wins":45},"gpt-5.4-nano":{"draws":23,"losses":44,"wins":69},"gpt-5.5":{"draws":26,"losses":58,"wins":44},"gpt-5.6-luna":{"draws":36,"losses":36,"wins":66},"gpt-5.6-sol":{"draws":17,"losses":88,"wins":33},"gpt-5.6-terra":{"draws":39,"losses":39,"wins":54},"gpt-6-astra":{"draws":7,"losses":127,"wins":4},"gpt-6-luna":{"draws":37,"losses":38,"wins":63},"gpt-6-sol":{"draws":18,"losses":96,"wins":24},"gpt-6.1-sol":{"draws":10,"losses":110,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":34,"losses":11,"wins":51},"inception/mercury-3":{"draws":26,"losses":24,"wins":42},"inclusionai/ling-3.0-flash":{"draws":27,"losses":11,"wins":58},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":28,"losses":27,"wins":93},"meta/muse-glimmer-30b":{"draws":33,"losses":19,"wins":72},"meta/muse-spark-1.2":{"draws":20,"losses":34,"wins":34},"meta/muse-spark-1.3":{"draws":27,"losses":59,"wins":52},"meta/muse-spark-open":{"draws":27,"losses":62,"wins":43},"meta/muse-wonder":{"draws":26,"losses":71,"wins":41},"minimax/minimax-m3":{"draws":14,"losses":10,"wins":52},"minimax/minimax-m3.1-flash":{"draws":25,"losses":39,"wins":56},"mistralai/mistral-large-4-0":{"draws":16,"losses":27,"wins":45},"mistralai/mistral-medium-3-5":{"draws":21,"losses":11,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":27,"losses":51,"wins":56},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":108,"wins":11},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":19,"wins":68},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":13,"wins":32},"o3":{"draws":22,"losses":69,"wins":95},"openai/gpt-oss-120b":{"draws":32,"losses":14,"wins":76},"poolside/laguna-s-2.1":{"draws":29,"losses":19,"wins":86},"qwen/qwen3.7-max":{"draws":11,"losses":19,"wins":50},"qwen/qwen3.7-plus":{"draws":16,"losses":12,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":54,"wins":48},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":36},"qwen/qwen3.8-flash":{"draws":22,"losses":28,"wins":42},"qwen/qwen3.8-max":{"draws":35,"losses":52,"wins":51},"qwen/qwen3.8-max-0902":{"draws":31,"losses":55,"wins":52},"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":106,"losses":203,"wins":149},"stealth/space-bunny-alpha":{"draws":30,"losses":26,"wins":54},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":21,"losses":13,"wins":42},"tencent/hy4-preview":{"draws":19,"losses":60,"wins":53},"thinkingmachines/inkling":{"draws":50,"losses":35,"wins":101},"thinkingmachines/inkling-small":{"draws":36,"losses":27,"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":33,"losses":69,"wins":36},"x-ai/grok-4.6":{"draws":30,"losses":77,"wins":31},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":28},"x-ai/grok-build-0.1":{"draws":10,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":62,"losses":27,"wins":123},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":21,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":28,"wins":47},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":54,"wins":27},"z-ai/glm-5.2":{"draws":65,"losses":75,"wins":136},"z-ai/glm-5.3":{"draws":22,"losses":68,"wins":42},"z-ai/glm-5.3-flash":{"draws":20,"losses":60,"wins":58},"z-ai/glm-5.3-flashx":{"draws":28,"losses":59,"wins":51}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":22,"wins":81},"claude-fable-5":{"draws":24,"losses":77,"wins":43},"claude-fable-5-1":{"draws":10,"losses":135,"wins":17},"claude-haiku-5-5":{"draws":26,"losses":61,"wins":51},"claude-opus-4-5":{"draws":54,"losses":54,"wins":126},"claude-opus-4-8":{"draws":25,"losses":52,"wins":55},"claude-opus-5":{"draws":31,"losses":165,"wins":50},"claude-opus-5-5":{"draws":8,"losses":134,"wins":14},"claude-sonnet-5":{"draws":37,"losses":33,"wins":74},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":54},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":48},"deepseek/deepseek-v4-flash":{"draws":42,"losses":24,"wins":150},"deepseek/deepseek-v4-pro":{"draws":22,"losses":35,"wins":75},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":39,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":52,"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":37,"losses":42,"wins":65},"gemini-3.1-pro-preview":{"draws":26,"losses":40,"wins":78},"gemini-4-argon":{"draws":12,"losses":113,"wins":19},"google/gemini-3.1-flash-lite":{"draws":14,"losses":5,"wins":77},"google/gemini-3.5-flash":{"draws":34,"losses":47,"wins":99},"google/gemini-3.5-flash-lite":{"draws":47,"losses":36,"wins":169},"google/gemini-3.6-flash":{"draws":48,"losses":97,"wins":131},"google/gemini-3.8-flash":{"draws":32,"losses":61,"wins":51},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":53},"gpt-4.1":{"draws":17,"losses":4,"wins":27},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":25,"losses":27,"wins":74},"gpt-5.4":{"draws":29,"losses":54,"wins":55},"gpt-5.4-mini":{"draws":20,"losses":11,"wins":65},"gpt-5.4-nano":{"draws":25,"losses":29,"wins":90},"gpt-5.5":{"draws":32,"losses":48,"wins":52},"gpt-5.6-luna":{"draws":37,"losses":29,"wins":78},"gpt-5.6-sol":{"draws":21,"losses":75,"wins":48},"gpt-5.6-terra":{"draws":34,"losses":38,"wins":66},"gpt-6-astra":{"draws":14,"losses":118,"wins":12},"gpt-6-luna":{"draws":25,"losses":36,"wins":83},"gpt-6-sol":{"draws":23,"losses":99,"wins":22},"gpt-6.1-sol":{"draws":13,"losses":117,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":8,"wins":65},"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":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":29,"losses":24,"wins":103},"meta/muse-glimmer-30b":{"draws":36,"losses":16,"wins":74},"meta/muse-spark-1.2":{"draws":27,"losses":52,"wins":59},"meta/muse-spark-1.3":{"draws":16,"losses":40,"wins":40},"meta/muse-spark-open":{"draws":22,"losses":52,"wins":64},"meta/muse-wonder":{"draws":28,"losses":74,"wins":42},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":62},"minimax/minimax-m3.1-flash":{"draws":19,"losses":29,"wins":78},"mistralai/mistral-large-4-0":{"draws":24,"losses":22,"wins":44},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":15,"wins":13},"moonshotai/kimi-k3":{"draws":30,"losses":43,"wins":65},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":111,"wins":16},"nex-agi/nex-n2-pro":{"draws":11,"losses":6,"wins":55},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":12,"wins":85},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":19,"wins":37},"o3":{"draws":19,"losses":53,"wins":126},"openai/gpt-oss-120b":{"draws":32,"losses":12,"wins":82},"poolside/laguna-s-2.1":{"draws":29,"losses":26,"wins":83},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":47},"qwen/qwen3.7-plus":{"draws":14,"losses":13,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":50,"wins":59},"qwen/qwen3.8-27b":{"draws":19,"losses":31,"wins":52},"qwen/qwen3.8-flash":{"draws":21,"losses":28,"wins":47},"qwen/qwen3.8-max":{"draws":34,"losses":39,"wins":71},"qwen/qwen3.8-max-0902":{"draws":38,"losses":54,"wins":52},"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":91,"losses":163,"wins":220},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":69},"stepfun/step-3.7-flash":{"draws":10,"losses":13,"wins":79},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":15,"losses":14,"wins":49},"tencent/hy4-preview":{"draws":28,"losses":50,"wins":60},"thinkingmachines/inkling":{"draws":33,"losses":18,"wins":141},"thinkingmachines/inkling-small":{"draws":35,"losses":14,"wins":95},"unbiased/pareto-26.10":{"draws":3,"losses":45,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":26},"x-ai/grok-4.5":{"draws":23,"losses":60,"wins":61},"x-ai/grok-4.6":{"draws":34,"losses":57,"wins":53},"x-ai/grok-4.7":{"draws":11,"losses":83,"wins":32},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":56,"losses":19,"wins":147},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":26,"wins":51},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":49,"wins":32},"z-ai/glm-5.2":{"draws":58,"losses":67,"wins":163},"z-ai/glm-5.3":{"draws":25,"losses":73,"wins":40},"z-ai/glm-5.3-flash":{"draws":25,"losses":69,"wins":50},"z-ai/glm-5.3-flashx":{"draws":28,"losses":57,"wins":59}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":75},"claude-fable-5":{"draws":21,"losses":86,"wins":31},"claude-fable-5-1":{"draws":4,"losses":137,"wins":15},"claude-haiku-5-5":{"draws":19,"losses":58,"wins":55},"claude-opus-4-5":{"draws":61,"losses":61,"wins":102},"claude-opus-4-8":{"draws":27,"losses":52,"wins":47},"claude-opus-5":{"draws":24,"losses":168,"wins":42},"claude-opus-5-5":{"draws":10,"losses":125,"wins":15},"claude-sonnet-5":{"draws":32,"losses":32,"wins":74},"claude-sonnet-5-5":{"draws":24,"losses":62,"wins":52},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":41},"deepseek/deepseek-v4-flash":{"draws":39,"losses":31,"wins":136},"deepseek/deepseek-v4-pro":{"draws":27,"losses":30,"wins":71},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":35,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":56,"wins":55},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":73,"wins":38},"elorian/glimpse":{"draws":13,"losses":35,"wins":28},"fireworks/ember-1":{"draws":29,"losses":50,"wins":59},"gemini-3.1-pro-preview":{"draws":29,"losses":40,"wins":69},"gemini-4-argon":{"draws":11,"losses":106,"wins":21},"google/gemini-3.1-flash-lite":{"draws":15,"losses":6,"wins":73},"google/gemini-3.5-flash":{"draws":28,"losses":53,"wins":93},"google/gemini-3.5-flash-lite":{"draws":42,"losses":40,"wins":161},"google/gemini-3.6-flash":{"draws":50,"losses":106,"wins":110},"google/gemini-3.8-flash":{"draws":23,"losses":61,"wins":54},"google/gemma-4-31b-it":{"draws":20,"losses":6,"wins":54},"gpt-4.1":{"draws":7,"losses":11,"wins":27},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":6},"gpt-5":{"draws":27,"losses":24,"wins":71},"gpt-5.4":{"draws":27,"losses":52,"wins":55},"gpt-5.4-mini":{"draws":23,"losses":14,"wins":55},"gpt-5.4-nano":{"draws":20,"losses":24,"wins":94},"gpt-5.5":{"draws":24,"losses":49,"wins":55},"gpt-5.6-luna":{"draws":34,"losses":33,"wins":71},"gpt-5.6-sol":{"draws":22,"losses":73,"wins":43},"gpt-5.6-terra":{"draws":36,"losses":33,"wins":63},"gpt-6-astra":{"draws":7,"losses":128,"wins":3},"gpt-6-luna":{"draws":31,"losses":43,"wins":64},"gpt-6-sol":{"draws":12,"losses":104,"wins":22},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":27,"losses":6,"wins":63},"inception/mercury-3":{"draws":18,"losses":22,"wins":50},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":73},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":28,"losses":18,"wins":106},"meta/muse-glimmer-30b":{"draws":28,"losses":16,"wins":78},"meta/muse-spark-1.2":{"draws":27,"losses":43,"wins":62},"meta/muse-spark-1.3":{"draws":22,"losses":64,"wins":52},"meta/muse-spark-open":{"draws":16,"losses":36,"wins":36},"meta/muse-wonder":{"draws":22,"losses":69,"wins":47},"minimax/minimax-m3":{"draws":15,"losses":5,"wins":54},"minimax/minimax-m3.1-flash":{"draws":22,"losses":34,"wins":66},"mistralai/mistral-large-4-0":{"draws":16,"losses":24,"wins":46},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":21},"moonshotai/kimi-k3":{"draws":30,"losses":44,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":110,"wins":10},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":49},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":16,"wins":76},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":11,"wins":40},"o3":{"draws":21,"losses":41,"wins":134},"openai/gpt-oss-120b":{"draws":27,"losses":10,"wins":83},"poolside/laguna-s-2.1":{"draws":25,"losses":21,"wins":86},"qwen/qwen3.7-max":{"draws":16,"losses":18,"wins":46},"qwen/qwen3.7-plus":{"draws":15,"losses":10,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":50,"wins":56},"qwen/qwen3.8-27b":{"draws":21,"losses":29,"wins":48},"qwen/qwen3.8-flash":{"draws":19,"losses":31,"wins":42},"qwen/qwen3.8-max":{"draws":28,"losses":44,"wins":66},"qwen/qwen3.8-max-0902":{"draws":30,"losses":56,"wins":52},"recursive/flint-v1.0":{"draws":5,"losses":3,"wins":32},"reflection/beam-1.0-501b-a23b":{"draws":27,"losses":34,"wins":65},"stealth/ox-alpha":{"draws":85,"losses":160,"wins":213},"stealth/space-bunny-alpha":{"draws":24,"losses":24,"wins":62},"stepfun/step-3.7-flash":{"draws":13,"losses":16,"wins":71},"stepfun/step-5-preview":{"draws":0,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":17,"losses":17,"wins":40},"tencent/hy4-preview":{"draws":22,"losses":48,"wins":64},"thinkingmachines/inkling":{"draws":40,"losses":23,"wins":123},"thinkingmachines/inkling-small":{"draws":30,"losses":15,"wins":93},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":43,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":29},"x-ai/grok-4.5":{"draws":28,"losses":61,"wins":49},"x-ai/grok-4.6":{"draws":30,"losses":65,"wins":43},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":26},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":29},"xiaomi/mimo-v2.5":{"draws":53,"losses":19,"wins":140},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":11,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":29,"wins":47},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":42,"wins":37},"z-ai/glm-5.2":{"draws":69,"losses":61,"wins":146},"z-ai/glm-5.3":{"draws":19,"losses":78,"wins":35},"z-ai/glm-5.3-flash":{"draws":21,"losses":57,"wins":60},"z-ai/glm-5.3-flashx":{"draws":27,"losses":57,"wins":54}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":16,"wins":86},"claude-fable-5":{"draws":25,"losses":62,"wins":57},"claude-fable-5-1":{"draws":13,"losses":118,"wins":31},"claude-haiku-5-5":{"draws":30,"losses":29,"wins":79},"claude-opus-4-5":{"draws":47,"losses":48,"wins":139},"claude-opus-4-8":{"draws":26,"losses":44,"wins":62},"claude-opus-5":{"draws":29,"losses":141,"wins":76},"claude-opus-5-5":{"draws":9,"losses":116,"wins":31},"claude-sonnet-5":{"draws":31,"losses":28,"wins":85},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":54},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":47},"deepseek/deepseek-v4-flash":{"draws":37,"losses":31,"wins":148},"deepseek/deepseek-v4-pro":{"draws":23,"losses":30,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":27,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":71},"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":26,"losses":24,"wins":94},"gemini-4-argon":{"draws":17,"losses":95,"wins":32},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":84},"google/gemini-3.5-flash":{"draws":30,"losses":29,"wins":121},"google/gemini-3.5-flash-lite":{"draws":43,"losses":27,"wins":182},"google/gemini-3.6-flash":{"draws":50,"losses":71,"wins":155},"google/gemini-3.8-flash":{"draws":36,"losses":40,"wins":68},"google/gemma-4-31b-it":{"draws":17,"losses":7,"wins":60},"gpt-4.1":{"draws":7,"losses":6,"wins":35},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":23,"losses":23,"wins":80},"gpt-5.4":{"draws":29,"losses":43,"wins":66},"gpt-5.4-mini":{"draws":24,"losses":10,"wins":62},"gpt-5.4-nano":{"draws":12,"losses":22,"wins":110},"gpt-5.5":{"draws":37,"losses":36,"wins":59},"gpt-5.6-luna":{"draws":28,"losses":25,"wins":91},"gpt-5.6-sol":{"draws":22,"losses":57,"wins":65},"gpt-5.6-terra":{"draws":31,"losses":30,"wins":77},"gpt-6-astra":{"draws":14,"losses":114,"wins":16},"gpt-6-luna":{"draws":34,"losses":33,"wins":77},"gpt-6-sol":{"draws":18,"losses":81,"wins":45},"gpt-6.1-sol":{"draws":19,"losses":96,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":70},"inception/mercury-3":{"draws":24,"losses":22,"wins":49},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":31,"losses":20,"wins":105},"meta/muse-glimmer-30b":{"draws":26,"losses":15,"wins":85},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":71},"meta/muse-spark-1.3":{"draws":28,"losses":42,"wins":74},"meta/muse-spark-open":{"draws":22,"losses":47,"wins":69},"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":7,"losses":8,"wins":21},"moonshotai/kimi-k3":{"draws":26,"losses":27,"wins":85},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":82,"wins":38},"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":36,"losses":8,"wins":82},"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":11,"wins":105},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":61},"qwen/qwen3.7-plus":{"draws":15,"losses":2,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":44,"wins":73},"qwen/qwen3.8-27b":{"draws":19,"losses":14,"wins":69},"qwen/qwen3.8-flash":{"draws":24,"losses":12,"wins":60},"qwen/qwen3.8-max":{"draws":31,"losses":32,"wins":81},"qwen/qwen3.8-max-0902":{"draws":33,"losses":33,"wins":78},"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":12,"losses":10,"wins":80},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":15,"losses":12,"wins":51},"tencent/hy4-preview":{"draws":28,"losses":39,"wins":71},"thinkingmachines/inkling":{"draws":44,"losses":22,"wins":126},"thinkingmachines/inkling-small":{"draws":33,"losses":15,"wins":96},"unbiased/pareto-26.10":{"draws":6,"losses":34,"wins":8},"unbiased/pareto-26.10-preview":{"draws":4,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":3,"losses":1,"wins":32},"x-ai/grok-4.5":{"draws":29,"losses":36,"wins":79},"x-ai/grok-4.6":{"draws":41,"losses":41,"wins":62},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":38},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":33},"xiaomi/mimo-v2.5":{"draws":45,"losses":17,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":56},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":22,"wins":63},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":36,"wins":43},"z-ai/glm-5.2":{"draws":65,"losses":45,"wins":178},"z-ai/glm-5.3":{"draws":17,"losses":59,"wins":62},"z-ai/glm-5.3-flash":{"draws":30,"losses":43,"wins":71},"z-ai/glm-5.3-flashx":{"draws":34,"losses":37,"wins":73}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":37,"wins":15},"claude-fable-5":{"draws":18,"losses":54,"wins":6},"claude-fable-5-1":{"draws":1,"losses":84,"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":16,"losses":48,"wins":10},"claude-opus-5":{"draws":15,"losses":116,"wins":7},"claude-opus-5-5":{"draws":2,"losses":83,"wins":1},"claude-sonnet-5":{"draws":21,"losses":42,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":52,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":34,"losses":43,"wins":43},"deepseek/deepseek-v4-pro":{"draws":11,"losses":48,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":41,"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":17,"losses":38,"wins":23},"gemini-4-argon":{"draws":2,"losses":75,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":16,"wins":25},"google/gemini-3.5-flash":{"draws":20,"losses":53,"wins":25},"google/gemini-3.5-flash-lite":{"draws":34,"losses":53,"wins":47},"google/gemini-3.6-flash":{"draws":29,"losses":94,"wins":25},"google/gemini-3.8-flash":{"draws":14,"losses":58,"wins":6},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":16},"gpt-4.1":{"draws":8,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":5,"losses":1,"wins":2},"gpt-5":{"draws":15,"losses":38,"wins":17},"gpt-5.4":{"draws":14,"losses":44,"wins":16},"gpt-5.4-mini":{"draws":15,"losses":18,"wins":19},"gpt-5.4-nano":{"draws":15,"losses":40,"wins":29},"gpt-5.5":{"draws":22,"losses":39,"wins":11},"gpt-5.6-luna":{"draws":26,"losses":31,"wins":21},"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":75,"wins":2},"gpt-6-luna":{"draws":21,"losses":42,"wins":15},"gpt-6-sol":{"draws":9,"losses":62,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":70,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":11,"wins":19},"inception/mercury-3":{"draws":16,"losses":29,"wins":9},"inclusionai/ling-3.0-flash":{"draws":17,"losses":14,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":15,"losses":38,"wins":31},"meta/muse-glimmer-30b":{"draws":21,"losses":22,"wins":27},"meta/muse-spark-1.2":{"draws":14,"losses":52,"wins":10},"meta/muse-spark-1.3":{"draws":9,"losses":62,"wins":7},"meta/muse-spark-open":{"draws":15,"losses":54,"wins":5},"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":15,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":49,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":70,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":14,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":25,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":15,"wins":12},"o3":{"draws":13,"losses":72,"wins":27},"openai/gpt-oss-120b":{"draws":20,"losses":27,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":34,"wins":25},"qwen/qwen3.7-max":{"draws":15,"losses":24,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":18,"wins":14},"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":25,"wins":18},"qwen/qwen3.8-max":{"draws":20,"losses":44,"wins":14},"qwen/qwen3.8-max-0902":{"draws":19,"losses":51,"wins":8},"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":50,"losses":152,"wins":40},"stealth/space-bunny-alpha":{"draws":15,"losses":34,"wins":13},"stepfun/step-3.7-flash":{"draws":11,"losses":18,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":19,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":52,"wins":7},"thinkingmachines/inkling":{"draws":26,"losses":44,"wins":34},"thinkingmachines/inkling-small":{"draws":21,"losses":20,"wins":37},"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":58,"wins":4},"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":39,"losses":44,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":21,"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":41,"losses":75,"wins":40},"z-ai/glm-5.3":{"draws":15,"losses":53,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":48,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":48,"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":72,"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},"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":0,"losses":0,"wins":2},"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":22,"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":5,"losses":14,"wins":11},"moonshotai/kimi-k3":{"draws":29,"losses":51,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":97,"wins":11},"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":27,"losses":31,"wins":46},"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":0,"losses":3,"wins":1},"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":80},"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":9,"losses":29,"wins":30},"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":18,"losses":49,"wins":23},"claude-fable-5-1":{"draws":4,"losses":92,"wins":6},"claude-haiku-5-5":{"draws":30,"losses":28,"wins":28},"claude-opus-4-5":{"draws":46,"losses":53,"wins":47},"claude-opus-4-8":{"draws":18,"losses":31,"wins":33},"claude-opus-5":{"draws":24,"losses":119,"wins":19},"claude-opus-5-5":{"draws":14,"losses":79,"wins":5},"claude-sonnet-5":{"draws":27,"losses":39,"wins":24},"claude-sonnet-5-5":{"draws":23,"losses":43,"wins":24},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":20},"deepseek/deepseek-v4-flash":{"draws":45,"losses":20,"wins":69},"deepseek/deepseek-v4-pro":{"draws":26,"losses":26,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":28,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":31,"wins":26},"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":17,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":38,"losses":35,"wins":39},"google/gemini-3.5-flash-lite":{"draws":52,"losses":29,"wins":75},"google/gemini-3.6-flash":{"draws":41,"losses":72,"wins":59},"google/gemini-3.8-flash":{"draws":28,"losses":36,"wins":26},"google/gemma-4-31b-it":{"draws":19,"losses":9,"wins":24},"gpt-4.1":{"draws":12,"losses":8,"wins":10},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":30,"losses":16,"wins":34},"gpt-5.4":{"draws":30,"losses":40,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":12,"wins":20},"gpt-5.4-nano":{"draws":16,"losses":24,"wins":48},"gpt-5.5":{"draws":29,"losses":33,"wins":22},"gpt-5.6-luna":{"draws":32,"losses":15,"wins":43},"gpt-5.6-sol":{"draws":19,"losses":51,"wins":20},"gpt-5.6-terra":{"draws":41,"losses":19,"wins":26},"gpt-6-astra":{"draws":9,"losses":76,"wins":5},"gpt-6-luna":{"draws":27,"losses":32,"wins":31},"gpt-6-sol":{"draws":15,"losses":61,"wins":14},"gpt-6.1-sol":{"draws":9,"losses":70,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":27},"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":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":16,"wins":46},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":36},"meta/muse-spark-1.2":{"draws":16,"losses":45,"wins":27},"meta/muse-spark-1.3":{"draws":24,"losses":44,"wins":22},"meta/muse-spark-open":{"draws":16,"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":6,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":30,"losses":31,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":72,"wins":6},"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":28,"losses":18,"wins":32},"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":98,"losses":120,"wins":82},"stealth/space-bunny-alpha":{"draws":26,"losses":14,"wins":32},"stepfun/step-3.7-flash":{"draws":20,"losses":9,"wins":33},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":22,"losses":36,"wins":28},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":58},"thinkingmachines/inkling-small":{"draws":31,"losses":14,"wins":45},"unbiased/pareto-26.10":{"draws":3,"losses":26,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":24,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":13},"x-ai/grok-4.5":{"draws":20,"losses":41,"wins":29},"x-ai/grok-4.6":{"draws":30,"losses":43,"wins":17},"x-ai/grok-4.7":{"draws":14,"losses":50,"wins":16},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":58,"losses":19,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":11,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":20,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":28,"wins":19},"z-ai/glm-5.2":{"draws":71,"losses":37,"wins":72},"z-ai/glm-5.3":{"draws":15,"losses":51,"wins":20},"z-ai/glm-5.3-flash":{"draws":26,"losses":42,"wins":22},"z-ai/glm-5.3-flashx":{"draws":29,"losses":34,"wins":27}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":26,"wins":18},"claude-fable-5":{"draws":20,"losses":58,"wins":6},"claude-fable-5-1":{"draws":5,"losses":88,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":54,"wins":4},"claude-opus-4-5":{"draws":44,"losses":80,"wins":12},"claude-opus-4-8":{"draws":25,"losses":45,"wins":6},"claude-opus-5":{"draws":22,"losses":110,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":32,"losses":42,"wins":10},"claude-sonnet-5-5":{"draws":19,"losses":57,"wins":8},"cohere/north-mini-code":{"draws":9,"losses":12,"wins":11},"deepseek/deepseek-v4-flash":{"draws":53,"losses":42,"wins":29},"deepseek/deepseek-v4-pro":{"draws":21,"losses":47,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":42,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":45,"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":24,"losses":51,"wins":9},"gemini-3.1-pro-preview":{"draws":30,"losses":43,"wins":11},"gemini-4-argon":{"draws":3,"losses":79,"wins":2},"google/gemini-3.1-flash-lite":{"draws":14,"losses":17,"wins":23},"google/gemini-3.5-flash":{"draws":31,"losses":60,"wins":13},"google/gemini-3.5-flash-lite":{"draws":52,"losses":64,"wins":32},"google/gemini-3.6-flash":{"draws":56,"losses":90,"wins":14},"google/gemini-3.8-flash":{"draws":19,"losses":59,"wins":6},"google/gemma-4-31b-it":{"draws":22,"losses":21,"wins":7},"gpt-4.1":{"draws":13,"losses":10,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":22,"losses":34,"wins":16},"gpt-5.4":{"draws":21,"losses":45,"wins":14},"gpt-5.4-mini":{"draws":24,"losses":24,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":47,"wins":16},"gpt-5.5":{"draws":26,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":34,"losses":38,"wins":12},"gpt-5.6-sol":{"draws":13,"losses":66,"wins":5},"gpt-5.6-terra":{"draws":26,"losses":46,"wins":8},"gpt-6-astra":{"draws":6,"losses":78,"wins":0},"gpt-6-luna":{"draws":30,"losses":47,"wins":7},"gpt-6-sol":{"draws":7,"losses":73,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":81,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":17,"wins":16},"inception/mercury-3":{"draws":16,"losses":34,"wins":6},"inclusionai/ling-3.0-flash":{"draws":25,"losses":15,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":35,"wins":23},"meta/muse-glimmer-30b":{"draws":35,"losses":27,"wins":10},"meta/muse-spark-1.2":{"draws":21,"losses":48,"wins":11},"meta/muse-spark-1.3":{"draws":18,"losses":62,"wins":4},"meta/muse-spark-open":{"draws":17,"losses":55,"wins":8},"meta/muse-wonder":{"draws":16,"losses":62,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":17,"wins":15},"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":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":46,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":77,"wins":0},"nex-agi/nex-n2-pro":{"draws":14,"losses":8,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":25,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":20,"wins":5},"o3":{"draws":25,"losses":71,"wins":14},"openai/gpt-oss-120b":{"draws":34,"losses":26,"wins":14},"poolside/laguna-s-2.1":{"draws":33,"losses":33,"wins":16},"qwen/qwen3.7-max":{"draws":24,"losses":20,"wins":4},"qwen/qwen3.7-plus":{"draws":17,"losses":13,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":56,"wins":3},"qwen/qwen3.8-27b":{"draws":20,"losses":34,"wins":4},"qwen/qwen3.8-flash":{"draws":20,"losses":31,"wins":5},"qwen/qwen3.8-max":{"draws":26,"losses":49,"wins":9},"qwen/qwen3.8-max-0902":{"draws":29,"losses":49,"wins":6},"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":70,"losses":172,"wins":40},"stealth/space-bunny-alpha":{"draws":24,"losses":30,"wins":12},"stepfun/step-3.7-flash":{"draws":19,"losses":24,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":25,"losses":48,"wins":7},"thinkingmachines/inkling":{"draws":39,"losses":49,"wins":22},"thinkingmachines/inkling-small":{"draws":37,"losses":31,"wins":16},"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":21,"losses":56,"wins":7},"x-ai/grok-4.6":{"draws":27,"losses":51,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":3},"x-ai/grok-build-0.1":{"draws":14,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":58,"losses":45,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":23,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":33,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":42,"wins":7},"z-ai/glm-5.2":{"draws":74,"losses":75,"wins":19},"z-ai/glm-5.3":{"draws":15,"losses":63,"wins":4},"z-ai/glm-5.3-flash":{"draws":24,"losses":50,"wins":10},"z-ai/glm-5.3-flashx":{"draws":21,"losses":55,"wins":8}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":13},"claude-fable-5":{"draws":6,"losses":24,"wins":6},"claude-fable-5-1":{"draws":2,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":17,"losses":28,"wins":15},"claude-opus-4-8":{"draws":10,"losses":19,"wins":7},"claude-opus-5":{"draws":6,"losses":58,"wins":4},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":11,"losses":8,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":11,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":15,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":13,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":2},"elorian/glimpse":{"draws":4,"losses":9,"wins":7},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":16},"google/gemini-3.5-flash-lite":{"draws":16,"losses":14,"wins":32},"google/gemini-3.6-flash":{"draws":20,"losses":33,"wins":15},"google/gemini-3.8-flash":{"draws":5,"losses":13,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":6,"losses":21,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":13},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":17},"gpt-5.5":{"draws":12,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":24,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":11},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":13,"losses":13,"wins":10},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":14},"inception/mercury-3":{"draws":6,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":15},"meta/muse-spark-open":{"draws":7,"losses":21,"wins":6},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":13},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":32,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":8},"o3":{"draws":5,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":11,"wins":13},"stealth/ox-alpha":{"draws":24,"losses":49,"wins":29},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":28},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":23,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":11,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":24,"wins":31},"z-ai/glm-5.3":{"draws":10,"losses":20,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":12,"wins":13}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":30,"wins":60},"claude-fable-5":{"draws":27,"losses":84,"wins":27},"claude-fable-5-1":{"draws":8,"losses":136,"wins":12},"claude-haiku-5-5":{"draws":34,"losses":58,"wins":40},"claude-opus-4-5":{"draws":76,"losses":66,"wins":82},"claude-opus-4-8":{"draws":33,"losses":50,"wins":43},"claude-opus-5":{"draws":37,"losses":168,"wins":39},"claude-opus-5-5":{"draws":5,"losses":132,"wins":13},"claude-sonnet-5":{"draws":41,"losses":39,"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":42,"wins":105},"deepseek/deepseek-v4-pro":{"draws":28,"losses":43,"wins":57},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":49,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":57,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":81,"wins":39},"elorian/glimpse":{"draws":19,"losses":31,"wins":26},"fireworks/ember-1":{"draws":43,"losses":57,"wins":38},"gemini-3.1-pro-preview":{"draws":36,"losses":41,"wins":61},"gemini-4-argon":{"draws":6,"losses":117,"wins":15},"google/gemini-3.1-flash-lite":{"draws":23,"losses":11,"wins":56},"google/gemini-3.5-flash":{"draws":50,"losses":59,"wins":63},"google/gemini-3.5-flash-lite":{"draws":77,"losses":44,"wins":119},"google/gemini-3.6-flash":{"draws":71,"losses":105,"wins":88},"google/gemini-3.8-flash":{"draws":32,"losses":73,"wins":33},"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":31,"losses":41,"wins":50},"gpt-5.4":{"draws":24,"losses":70,"wins":38},"gpt-5.4-mini":{"draws":32,"losses":21,"wins":39},"gpt-5.4-nano":{"draws":34,"losses":34,"wins":68},"gpt-5.5":{"draws":37,"losses":45,"wins":46},"gpt-5.6-luna":{"draws":46,"losses":30,"wins":62},"gpt-5.6-sol":{"draws":23,"losses":83,"wins":32},"gpt-5.6-terra":{"draws":38,"losses":44,"wins":50},"gpt-6-astra":{"draws":9,"losses":119,"wins":10},"gpt-6-luna":{"draws":45,"losses":42,"wins":51},"gpt-6-sol":{"draws":14,"losses":97,"wins":27},"gpt-6.1-sol":{"draws":9,"losses":115,"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":31,"losses":12,"wins":53},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":41,"losses":26,"wins":81},"meta/muse-glimmer-30b":{"draws":38,"losses":19,"wins":67},"meta/muse-spark-1.2":{"draws":27,"losses":56,"wins":51},"meta/muse-spark-1.3":{"draws":30,"losses":65,"wins":43},"meta/muse-spark-open":{"draws":30,"losses":58,"wins":44},"meta/muse-wonder":{"draws":26,"losses":85,"wins":27},"minimax/minimax-m3":{"draws":13,"losses":14,"wins":49},"minimax/minimax-m3.1-flash":{"draws":29,"losses":40,"wins":51},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":31},"mistralai/mistral-medium-3-5":{"draws":25,"losses":9,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":26,"losses":31,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":108,"wins":12},"nex-agi/nex-n2-pro":{"draws":16,"losses":10,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":28,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":16,"wins":29},"o3":{"draws":29,"losses":71,"wins":86},"openai/gpt-oss-120b":{"draws":35,"losses":19,"wins":68},"poolside/laguna-s-2.1":{"draws":44,"losses":23,"wins":67},"qwen/qwen3.7-max":{"draws":20,"losses":19,"wins":41},"qwen/qwen3.7-plus":{"draws":25,"losses":15,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":48,"wins":51},"qwen/qwen3.8-27b":{"draws":28,"losses":27,"wins":41},"qwen/qwen3.8-flash":{"draws":28,"losses":31,"wins":33},"qwen/qwen3.8-max":{"draws":40,"losses":51,"wins":47},"qwen/qwen3.8-max-0902":{"draws":35,"losses":69,"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":109,"losses":182,"wins":167},"stealth/space-bunny-alpha":{"draws":37,"losses":20,"wins":53},"stepfun/step-3.7-flash":{"draws":21,"losses":16,"wins":59},"stepfun/step-5-preview":{"draws":2,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":28},"tencent/hy4-preview":{"draws":33,"losses":55,"wins":44},"thinkingmachines/inkling":{"draws":53,"losses":39,"wins":94},"thinkingmachines/inkling-small":{"draws":46,"losses":21,"wins":71},"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":30,"losses":63,"wins":45},"x-ai/grok-4.6":{"draws":34,"losses":70,"wins":34},"x-ai/grok-4.7":{"draws":10,"losses":85,"wins":27},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":25},"xiaomi/mimo-v2.5":{"draws":74,"losses":33,"wins":105},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":23,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":32,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":49,"wins":25},"z-ai/glm-5.2":{"draws":95,"losses":70,"wins":111},"z-ai/glm-5.3":{"draws":28,"losses":65,"wins":39},"z-ai/glm-5.3-flash":{"draws":30,"losses":64,"wins":44},"z-ai/glm-5.3-flashx":{"draws":40,"losses":62,"wins":36}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":4,"wins":103},"claude-fable-5":{"draws":11,"losses":30,"wins":97},"claude-fable-5-1":{"draws":15,"losses":96,"wins":43},"claude-haiku-5-5":{"draws":16,"losses":20,"wins":98},"claude-opus-4-5":{"draws":25,"losses":13,"wins":188},"claude-opus-4-8":{"draws":13,"losses":12,"wins":105},"claude-opus-5":{"draws":26,"losses":98,"wins":110},"claude-opus-5-5":{"draws":12,"losses":88,"wins":50},"claude-sonnet-5":{"draws":15,"losses":6,"wins":117},"claude-sonnet-5-5":{"draws":14,"losses":36,"wins":88},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":19,"losses":3,"wins":187},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":102},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":10,"wins":104},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":20,"wins":95},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":23,"wins":102},"elorian/glimpse":{"draws":7,"losses":11,"wins":56},"fireworks/ember-1":{"draws":15,"losses":9,"wins":114},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":103},"gemini-4-argon":{"draws":15,"losses":67,"wins":57},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":91},"google/gemini-3.5-flash":{"draws":12,"losses":15,"wins":147},"google/gemini-3.5-flash-lite":{"draws":31,"losses":3,"wins":208},"google/gemini-3.6-flash":{"draws":29,"losses":33,"wins":203},"google/gemini-3.8-flash":{"draws":13,"losses":22,"wins":103},"google/gemma-4-31b-it":{"draws":9,"losses":1,"wins":72},"gpt-4.1":{"draws":2,"losses":2,"wins":42},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":15},"gpt-5":{"draws":9,"losses":9,"wins":102},"gpt-5.4":{"draws":12,"losses":21,"wins":99},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":81},"gpt-5.4-nano":{"draws":11,"losses":4,"wins":127},"gpt-5.5":{"draws":10,"losses":23,"wins":93},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":121},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":96},"gpt-5.6-terra":{"draws":9,"losses":12,"wins":112},"gpt-6-astra":{"draws":11,"losses":89,"wins":38},"gpt-6-luna":{"draws":14,"losses":6,"wins":118},"gpt-6-sol":{"draws":17,"losses":39,"wins":82},"gpt-6.1-sol":{"draws":14,"losses":77,"wins":47},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":1,"wins":81},"inception/mercury-3":{"draws":13,"losses":8,"wins":71},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":84},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":132},"meta/muse-glimmer-30b":{"draws":20,"losses":0,"wins":100},"meta/muse-spark-1.2":{"draws":13,"losses":11,"wins":108},"meta/muse-spark-1.3":{"draws":11,"losses":16,"wins":111},"meta/muse-spark-open":{"draws":12,"losses":10,"wins":110},"meta/muse-wonder":{"draws":18,"losses":38,"wins":82},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":70},"minimax/minimax-m3.1-flash":{"draws":12,"losses":11,"wins":97},"mistralai/mistral-large-4-0":{"draws":8,"losses":6,"wins":72},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":77},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":32},"moonshotai/kimi-k3":{"draws":12,"losses":12,"wins":108},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":39,"wins":39},"nex-agi/nex-n2-pro":{"draws":7,"losses":0,"wins":61},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":107},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":56},"o3":{"draws":6,"losses":15,"wins":173},"openai/gpt-oss-120b":{"draws":15,"losses":2,"wins":103},"poolside/laguna-s-2.1":{"draws":18,"losses":4,"wins":108},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":69},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":13,"wins":108},"qwen/qwen3.8-27b":{"draws":12,"losses":4,"wins":82},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":73},"qwen/qwen3.8-max":{"draws":6,"losses":19,"wins":113},"qwen/qwen3.8-max-0902":{"draws":12,"losses":15,"wins":111},"recursive/flint-v1.0":{"draws":7,"losses":0,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":110},"stealth/ox-alpha":{"draws":54,"losses":32,"wins":348},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":97},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":94},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":63},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":103},"thinkingmachines/inkling":{"draws":19,"losses":2,"wins":162},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":122},"unbiased/pareto-26.10":{"draws":5,"losses":26,"wins":15},"unbiased/pareto-26.10-preview":{"draws":5,"losses":25,"wins":16},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":36},"x-ai/grok-4.5":{"draws":19,"losses":21,"wins":98},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":104},"x-ai/grok-4.7":{"draws":11,"losses":42,"wins":69},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":37},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":190},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":65},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":6,"wins":70},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":23,"wins":53},"z-ai/glm-5.2":{"draws":32,"losses":15,"wins":229},"z-ai/glm-5.3":{"draws":19,"losses":33,"wins":80},"z-ai/glm-5.3-flash":{"draws":16,"losses":19,"wins":103},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":109}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":36,"wins":12},"claude-fable-5":{"draws":13,"losses":57,"wins":2},"claude-fable-5-1":{"draws":4,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":43,"wins":10},"claude-opus-4-5":{"draws":27,"losses":74,"wins":15},"claude-opus-4-8":{"draws":16,"losses":45,"wins":3},"claude-opus-5":{"draws":3,"losses":108,"wins":5},"claude-opus-5-5":{"draws":6,"losses":74,"wins":0},"claude-sonnet-5":{"draws":24,"losses":37,"wins":11},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":12,"wins":17},"deepseek/deepseek-v4-flash":{"draws":25,"losses":51,"wins":32},"deepseek/deepseek-v4-pro":{"draws":17,"losses":37,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":41,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":51,"wins":5},"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":20,"losses":41,"wins":11},"gemini-4-argon":{"draws":8,"losses":59,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":13,"wins":27},"google/gemini-3.5-flash":{"draws":22,"losses":51,"wins":17},"google/gemini-3.5-flash-lite":{"draws":32,"losses":58,"wins":38},"google/gemini-3.6-flash":{"draws":26,"losses":95,"wins":17},"google/gemini-3.8-flash":{"draws":13,"losses":52,"wins":7},"google/gemma-4-31b-it":{"draws":17,"losses":16,"wins":11},"gpt-4.1":{"draws":5,"losses":14,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":14,"losses":33,"wins":17},"gpt-5.4":{"draws":16,"losses":37,"wins":17},"gpt-5.4-mini":{"draws":19,"losses":17,"wins":12},"gpt-5.4-nano":{"draws":16,"losses":34,"wins":22},"gpt-5.5":{"draws":18,"losses":43,"wins":5},"gpt-5.6-luna":{"draws":20,"losses":40,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":59,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":41,"wins":8},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"gpt-6-luna":{"draws":15,"losses":45,"wins":12},"gpt-6-sol":{"draws":7,"losses":61,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":68,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":16,"wins":16},"inception/mercury-3":{"draws":10,"losses":30,"wins":8},"inclusionai/ling-3.0-flash":{"draws":19,"losses":17,"wins":12},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":42,"wins":28},"meta/muse-glimmer-30b":{"draws":25,"losses":22,"wins":15},"meta/muse-spark-1.2":{"draws":11,"losses":46,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":55,"wins":6},"meta/muse-spark-open":{"draws":12,"losses":49,"wins":9},"meta/muse-wonder":{"draws":13,"losses":53,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":16,"wins":14},"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":14,"losses":22,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":42,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":61,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":10,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":28,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":10},"o3":{"draws":10,"losses":76,"wins":20},"openai/gpt-oss-120b":{"draws":19,"losses":23,"wins":24},"poolside/laguna-s-2.1":{"draws":26,"losses":32,"wins":14},"qwen/qwen3.7-max":{"draws":13,"losses":24,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":16,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":47,"wins":9},"qwen/qwen3.8-27b":{"draws":12,"losses":29,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":28,"wins":6},"qwen/qwen3.8-max":{"draws":21,"losses":45,"wins":6},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":9},"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":59,"losses":161,"wins":30},"stealth/space-bunny-alpha":{"draws":17,"losses":28,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":27,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":13},"tencent/hy4-preview":{"draws":17,"losses":47,"wins":6},"thinkingmachines/inkling":{"draws":26,"losses":40,"wins":28},"thinkingmachines/inkling-small":{"draws":22,"losses":31,"wins":19},"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":3,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":12,"losses":51,"wins":9},"x-ai/grok-4.6":{"draws":18,"losses":50,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":46,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":18,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":31,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":36,"wins":4},"z-ai/glm-5.2":{"draws":57,"losses":70,"wins":17},"z-ai/glm-5.3":{"draws":14,"losses":55,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":49,"wins":9},"z-ai/glm-5.3-flashx":{"draws":14,"losses":53,"wins":5}},"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},"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":0,"losses":0,"wins":2},"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":4,"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":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":17,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":27,"wins":0},"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":7,"losses":6,"wins":11},"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":0,"losses":3,"wins":1},"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":3,"losses":5,"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":47,"losses":35,"wins":34},"claude-fable-5":{"draws":28,"losses":87,"wins":11},"claude-fable-5-1":{"draws":7,"losses":129,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":66,"wins":26},"claude-opus-4-5":{"draws":79,"losses":99,"wins":30},"claude-opus-4-8":{"draws":27,"losses":77,"wins":18},"claude-opus-5":{"draws":27,"losses":181,"wins":6},"claude-opus-5-5":{"draws":4,"losses":136,"wins":2},"claude-sonnet-5":{"draws":45,"losses":52,"wins":29},"claude-sonnet-5-5":{"draws":22,"losses":82,"wins":22},"cohere/north-mini-code":{"draws":15,"losses":13,"wins":20},"deepseek/deepseek-v4-flash":{"draws":67,"losses":69,"wins":58},"deepseek/deepseek-v4-pro":{"draws":40,"losses":55,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":56,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":58,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":22,"losses":94,"wins":10},"elorian/glimpse":{"draws":15,"losses":44,"wins":7},"fireworks/ember-1":{"draws":45,"losses":59,"wins":22},"gemini-3.1-pro-preview":{"draws":47,"losses":50,"wins":29},"gemini-4-argon":{"draws":9,"losses":114,"wins":3},"google/gemini-3.1-flash-lite":{"draws":26,"losses":22,"wins":42},"google/gemini-3.5-flash":{"draws":48,"losses":80,"wins":32},"google/gemini-3.5-flash-lite":{"draws":82,"losses":70,"wins":68},"google/gemini-3.6-flash":{"draws":76,"losses":128,"wins":34},"google/gemini-3.8-flash":{"draws":35,"losses":82,"wins":9},"google/gemma-4-31b-it":{"draws":40,"losses":18,"wins":18},"gpt-4.1":{"draws":18,"losses":17,"wins":7},"gpt-4.1-nano":{"draws":8,"losses":2,"wins":4},"gpt-5":{"draws":37,"losses":52,"wins":21},"gpt-5.4":{"draws":36,"losses":72,"wins":12},"gpt-5.4-mini":{"draws":39,"losses":24,"wins":21},"gpt-5.4-nano":{"draws":35,"losses":60,"wins":45},"gpt-5.5":{"draws":53,"losses":53,"wins":8},"gpt-5.6-luna":{"draws":51,"losses":42,"wins":33},"gpt-5.6-sol":{"draws":16,"losses":100,"wins":10},"gpt-5.6-terra":{"draws":46,"losses":57,"wins":17},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":42,"losses":59,"wins":25},"gpt-6-sol":{"draws":12,"losses":106,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":112,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":44,"losses":22,"wins":26},"inception/mercury-3":{"draws":29,"losses":41,"wins":18},"inclusionai/ling-3.0-flash":{"draws":45,"losses":21,"wins":26},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":48,"wins":46},"meta/muse-glimmer-30b":{"draws":55,"losses":26,"wins":27},"meta/muse-spark-1.2":{"draws":33,"losses":68,"wins":19},"meta/muse-spark-1.3":{"draws":29,"losses":85,"wins":12},"meta/muse-spark-open":{"draws":28,"losses":76,"wins":16},"meta/muse-wonder":{"draws":36,"losses":82,"wins":8},"minimax/minimax-m3":{"draws":21,"losses":26,"wins":25},"minimax/minimax-m3.1-flash":{"draws":27,"losses":46,"wins":31},"mistralai/mistral-large-4-0":{"draws":28,"losses":32,"wins":18},"mistralai/mistral-medium-3-5":{"draws":37,"losses":12,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":20,"wins":5},"moonshotai/kimi-k3":{"draws":40,"losses":52,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":107,"wins":4},"nex-agi/nex-n2-pro":{"draws":22,"losses":12,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":11,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":19,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":33,"wins":12},"o3":{"draws":39,"losses":101,"wins":44},"openai/gpt-oss-120b":{"draws":46,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":56,"losses":36,"wins":32},"qwen/qwen3.7-max":{"draws":35,"losses":26,"wins":17},"qwen/qwen3.7-plus":{"draws":23,"losses":23,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":49,"losses":63,"wins":14},"qwen/qwen3.8-27b":{"draws":29,"losses":40,"wins":19},"qwen/qwen3.8-flash":{"draws":33,"losses":37,"wins":14},"qwen/qwen3.8-max":{"draws":48,"losses":56,"wins":22},"qwen/qwen3.8-max-0902":{"draws":49,"losses":65,"wins":12},"recursive/flint-v1.0":{"draws":10,"losses":13,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":27,"losses":69,"wins":18},"stealth/ox-alpha":{"draws":103,"losses":211,"wins":60},"stealth/space-bunny-alpha":{"draws":41,"losses":32,"wins":25},"stepfun/step-3.7-flash":{"draws":26,"losses":30,"wins":34},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":37,"losses":21,"wins":14},"tencent/hy4-preview":{"draws":42,"losses":64,"wins":14},"thinkingmachines/inkling":{"draws":52,"losses":51,"wins":59},"thinkingmachines/inkling-small":{"draws":51,"losses":35,"wins":40},"unbiased/pareto-26.10":{"draws":2,"losses":40,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":14,"wins":13},"x-ai/grok-4.5":{"draws":31,"losses":84,"wins":11},"x-ai/grok-4.6":{"draws":47,"losses":67,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":99,"wins":9},"x-ai/grok-build-0.1":{"draws":21,"losses":12,"wins":9},"xiaomi/mimo-v2.5":{"draws":85,"losses":58,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":33,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":56,"wins":10},"z-ai/glm-5.2":{"draws":108,"losses":90,"wins":54},"z-ai/glm-5.3":{"draws":25,"losses":82,"wins":13},"z-ai/glm-5.3-flash":{"draws":30,"losses":62,"wins":34},"z-ai/glm-5.3-flashx":{"draws":31,"losses":74,"wins":21}},"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},"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":21,"wins":10},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":2},"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":6,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":29,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":56,"wins":4},"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":13,"losses":12,"wins":33},"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":0,"losses":5,"wins":3},"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":7,"losses":10,"wins":19},"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":40,"losses":56,"wins":88},"claude-fable-5":{"draws":18,"losses":151,"wins":29},"claude-fable-5-1":{"draws":5,"losses":204,"wins":9},"claude-haiku-5-5":{"draws":32,"losses":101,"wins":61},"claude-opus-4-5":{"draws":47,"losses":184,"wins":95},"claude-opus-4-8":{"draws":27,"losses":107,"wins":56},"claude-opus-5":{"draws":26,"losses":266,"wins":20},"claude-opus-5-5":{"draws":11,"losses":204,"wins":3},"claude-sonnet-5":{"draws":27,"losses":89,"wins":82},"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":45,"losses":81,"wins":180},"deepseek/deepseek-v4-pro":{"draws":22,"losses":92,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":100,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":96,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":124,"wins":56},"elorian/glimpse":{"draws":14,"losses":56,"wins":36},"fireworks/ember-1":{"draws":38,"losses":110,"wins":50},"gemini-3.1-pro-preview":{"draws":31,"losses":76,"wins":91},"gemini-4-argon":{"draws":2,"losses":187,"wins":9},"google/gemini-3.1-flash-lite":{"draws":23,"losses":11,"wins":124},"google/gemini-3.5-flash":{"draws":35,"losses":137,"wins":86},"google/gemini-3.5-flash-lite":{"draws":57,"losses":98,"wins":201},"google/gemini-3.6-flash":{"draws":54,"losses":207,"wins":123},"google/gemini-3.8-flash":{"draws":23,"losses":131,"wins":44},"google/gemma-4-31b-it":{"draws":26,"losses":21,"wins":71},"gpt-4.1":{"draws":13,"losses":27,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":10},"gpt-5":{"draws":24,"losses":87,"wins":69},"gpt-5.4":{"draws":19,"losses":128,"wins":49},"gpt-5.4-mini":{"draws":26,"losses":35,"wins":71},"gpt-5.4-nano":{"draws":20,"losses":103,"wins":103},"gpt-5.5":{"draws":36,"losses":104,"wins":44},"gpt-5.6-luna":{"draws":40,"losses":69,"wins":89},"gpt-5.6-sol":{"draws":14,"losses":153,"wins":31},"gpt-5.6-terra":{"draws":37,"losses":84,"wins":65},"gpt-6-astra":{"draws":7,"losses":189,"wins":2},"gpt-6-luna":{"draws":34,"losses":100,"wins":64},"gpt-6-sol":{"draws":10,"losses":171,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":186,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":17,"wins":88},"inception/mercury-3":{"draws":17,"losses":75,"wins":36},"inclusionai/ling-3.0-flash":{"draws":29,"losses":21,"wins":90},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":32,"losses":60,"wins":140},"meta/muse-glimmer-30b":{"draws":34,"losses":35,"wins":103},"meta/muse-spark-1.2":{"draws":22,"losses":95,"wins":69},"meta/muse-spark-1.3":{"draws":19,"losses":126,"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":27,"wins":72},"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":25,"losses":14,"wins":71},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":24,"wins":21},"moonshotai/kimi-k3":{"draws":29,"losses":86,"wins":71},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":173,"wins":15},"nex-agi/nex-n2-pro":{"draws":10,"losses":20,"wins":76},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":15,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":44,"wins":101},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":49,"wins":33},"o3":{"draws":26,"losses":121,"wins":121},"openai/gpt-oss-120b":{"draws":24,"losses":29,"wins":119},"poolside/laguna-s-2.1":{"draws":34,"losses":60,"wins":98},"qwen/qwen3.7-max":{"draws":26,"losses":42,"wins":56},"qwen/qwen3.7-plus":{"draws":13,"losses":29,"wins":68},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":111,"wins":58},"qwen/qwen3.8-27b":{"draws":13,"losses":73,"wins":58},"qwen/qwen3.8-flash":{"draws":22,"losses":63,"wins":47},"qwen/qwen3.8-max":{"draws":37,"losses":98,"wins":63},"qwen/qwen3.8-max-0902":{"draws":35,"losses":99,"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":85,"losses":317,"wins":202},"stealth/space-bunny-alpha":{"draws":26,"losses":56,"wins":78},"stepfun/step-3.7-flash":{"draws":24,"losses":43,"wins":93},"stepfun/step-5-preview":{"draws":8,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":22,"losses":40,"wins":42},"tencent/hy4-preview":{"draws":30,"losses":105,"wins":61},"thinkingmachines/inkling":{"draws":42,"losses":57,"wins":167},"thinkingmachines/inkling-small":{"draws":38,"losses":44,"wins":116},"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":10,"losses":13,"wins":39},"x-ai/grok-4.5":{"draws":21,"losses":120,"wins":57},"x-ai/grok-4.6":{"draws":36,"losses":118,"wins":44},"x-ai/grok-4.7":{"draws":12,"losses":130,"wins":36},"x-ai/grok-build-0.1":{"draws":13,"losses":15,"wins":38},"xiaomi/mimo-v2.5":{"draws":58,"losses":63,"wins":195},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":44,"wins":62},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":73,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":95,"wins":26},"z-ai/glm-5.2":{"draws":73,"losses":150,"wins":173},"z-ai/glm-5.3":{"draws":17,"losses":136,"wins":35},"z-ai/glm-5.3-flash":{"draws":24,"losses":99,"wins":75},"z-ai/glm-5.3-flashx":{"draws":21,"losses":119,"wins":58}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":42,"wins":32},"claude-fable-5":{"draws":29,"losses":86,"wins":11},"claude-fable-5-1":{"draws":7,"losses":135,"wins":0},"claude-haiku-5-5":{"draws":30,"losses":78,"wins":12},"claude-opus-4-5":{"draws":66,"losses":106,"wins":32},"claude-opus-4-8":{"draws":36,"losses":68,"wins":10},"claude-opus-5":{"draws":30,"losses":179,"wins":11},"claude-opus-5-5":{"draws":9,"losses":129,"wins":0},"claude-sonnet-5":{"draws":38,"losses":72,"wins":16},"claude-sonnet-5-5":{"draws":26,"losses":82,"wins":18},"cohere/north-mini-code":{"draws":15,"losses":15,"wins":20},"deepseek/deepseek-v4-flash":{"draws":72,"losses":54,"wins":64},"deepseek/deepseek-v4-pro":{"draws":35,"losses":55,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":51,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":62,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":84,"wins":17},"elorian/glimpse":{"draws":14,"losses":36,"wins":18},"fireworks/ember-1":{"draws":45,"losses":63,"wins":18},"gemini-3.1-pro-preview":{"draws":42,"losses":53,"wins":31},"gemini-4-argon":{"draws":3,"losses":121,"wins":2},"google/gemini-3.1-flash-lite":{"draws":24,"losses":19,"wins":39},"google/gemini-3.5-flash":{"draws":43,"losses":77,"wins":36},"google/gemini-3.5-flash-lite":{"draws":68,"losses":75,"wins":75},"google/gemini-3.6-flash":{"draws":72,"losses":136,"wins":32},"google/gemini-3.8-flash":{"draws":26,"losses":92,"wins":8},"google/gemma-4-31b-it":{"draws":31,"losses":10,"wins":33},"gpt-4.1":{"draws":13,"losses":20,"wins":9},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":4},"gpt-5":{"draws":35,"losses":56,"wins":21},"gpt-5.4":{"draws":33,"losses":67,"wins":20},"gpt-5.4-mini":{"draws":32,"losses":31,"wins":21},"gpt-5.4-nano":{"draws":35,"losses":44,"wins":47},"gpt-5.5":{"draws":44,"losses":56,"wins":16},"gpt-5.6-luna":{"draws":57,"losses":42,"wins":27},"gpt-5.6-sol":{"draws":15,"losses":104,"wins":7},"gpt-5.6-terra":{"draws":42,"losses":66,"wins":12},"gpt-6-astra":{"draws":12,"losses":114,"wins":0},"gpt-6-luna":{"draws":41,"losses":59,"wins":26},"gpt-6-sol":{"draws":19,"losses":101,"wins":6},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":38,"losses":21,"wins":29},"inception/mercury-3":{"draws":26,"losses":39,"wins":21},"inclusionai/ling-3.0-flash":{"draws":38,"losses":8,"wins":40},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":43,"losses":57,"wins":38},"meta/muse-glimmer-30b":{"draws":47,"losses":27,"wins":38},"meta/muse-spark-1.2":{"draws":32,"losses":76,"wins":14},"meta/muse-spark-1.3":{"draws":32,"losses":82,"wins":12},"meta/muse-spark-open":{"draws":27,"losses":83,"wins":10},"meta/muse-wonder":{"draws":23,"losses":93,"wins":10},"minimax/minimax-m3":{"draws":20,"losses":23,"wins":27},"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":34,"losses":14,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":6},"moonshotai/kimi-k3":{"draws":35,"losses":68,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":103,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":24,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":16,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":28,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":35,"wins":10},"o3":{"draws":24,"losses":119,"wins":29},"openai/gpt-oss-120b":{"draws":22,"losses":25,"wins":25},"poolside/laguna-s-2.1":{"draws":49,"losses":41,"wins":36},"qwen/qwen3.7-max":{"draws":29,"losses":31,"wins":14},"qwen/qwen3.7-plus":{"draws":21,"losses":21,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":72,"wins":12},"qwen/qwen3.8-27b":{"draws":22,"losses":46,"wins":18},"qwen/qwen3.8-flash":{"draws":27,"losses":34,"wins":23},"qwen/qwen3.8-max":{"draws":41,"losses":75,"wins":10},"qwen/qwen3.8-max-0902":{"draws":39,"losses":72,"wins":15},"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":108,"losses":257,"wins":59},"stealth/space-bunny-alpha":{"draws":33,"losses":44,"wins":23},"stepfun/step-3.7-flash":{"draws":29,"losses":36,"wins":23},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":27,"wins":19},"tencent/hy4-preview":{"draws":38,"losses":64,"wins":18},"thinkingmachines/inkling":{"draws":47,"losses":65,"wins":56},"thinkingmachines/inkling-small":{"draws":48,"losses":31,"wins":47},"unbiased/pareto-26.10":{"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":34,"losses":79,"wins":13},"x-ai/grok-4.6":{"draws":37,"losses":79,"wins":10},"x-ai/grok-4.7":{"draws":9,"losses":98,"wins":5},"x-ai/grok-build-0.1":{"draws":17,"losses":16,"wins":9},"xiaomi/mimo-v2.5":{"draws":66,"losses":54,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":27,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":53,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":62,"wins":6},"z-ai/glm-5.2":{"draws":95,"losses":108,"wins":49},"z-ai/glm-5.3":{"draws":31,"losses":87,"wins":4},"z-ai/glm-5.3-flash":{"draws":26,"losses":80,"wins":20},"z-ai/glm-5.3-flashx":{"draws":36,"losses":77,"wins":13}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":48,"losses":40,"wins":40},"claude-fable-5":{"draws":26,"losses":91,"wins":21},"claude-fable-5-1":{"draws":5,"losses":145,"wins":2},"claude-haiku-5-5":{"draws":34,"losses":61,"wins":35},"claude-opus-4-5":{"draws":76,"losses":108,"wins":38},"claude-opus-4-8":{"draws":37,"losses":68,"wins":17},"claude-opus-5":{"draws":27,"losses":208,"wins":13},"claude-opus-5-5":{"draws":10,"losses":144,"wins":0},"claude-sonnet-5":{"draws":41,"losses":70,"wins":27},"claude-sonnet-5-5":{"draws":25,"losses":87,"wins":26},"cohere/north-mini-code":{"draws":13,"losses":23,"wins":18},"deepseek/deepseek-v4-flash":{"draws":75,"losses":63,"wins":72},"deepseek/deepseek-v4-pro":{"draws":35,"losses":49,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":58,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":55,"losses":60,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":93,"wins":18},"elorian/glimpse":{"draws":18,"losses":40,"wins":16},"fireworks/ember-1":{"draws":47,"losses":65,"wins":26},"gemini-3.1-pro-preview":{"draws":44,"losses":60,"wins":34},"gemini-4-argon":{"draws":8,"losses":127,"wins":3},"google/gemini-3.1-flash-lite":{"draws":26,"losses":17,"wins":43},"google/gemini-3.5-flash":{"draws":37,"losses":102,"wins":31},"google/gemini-3.5-flash-lite":{"draws":73,"losses":67,"wins":98},"google/gemini-3.6-flash":{"draws":75,"losses":137,"wins":50},"google/gemini-3.8-flash":{"draws":26,"losses":95,"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":3,"wins":2},"gpt-5":{"draws":38,"losses":49,"wins":39},"gpt-5.4":{"draws":31,"losses":80,"wins":21},"gpt-5.4-mini":{"draws":36,"losses":32,"wins":24},"gpt-5.4-nano":{"draws":37,"losses":52,"wins":55},"gpt-5.5":{"draws":47,"losses":58,"wins":23},"gpt-5.6-luna":{"draws":51,"losses":46,"wins":41},"gpt-5.6-sol":{"draws":19,"losses":111,"wins":8},"gpt-5.6-terra":{"draws":49,"losses":64,"wins":17},"gpt-6-astra":{"draws":7,"losses":131,"wins":0},"gpt-6-luna":{"draws":43,"losses":59,"wins":36},"gpt-6-sol":{"draws":22,"losses":105,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":128,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":38,"losses":24,"wins":28},"inception/mercury-3":{"draws":30,"losses":49,"wins":17},"inclusionai/ling-3.0-flash":{"draws":41,"losses":17,"wins":36},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":49,"wins":56},"meta/muse-glimmer-30b":{"draws":52,"losses":30,"wins":42},"meta/muse-spark-1.2":{"draws":29,"losses":86,"wins":19},"meta/muse-spark-1.3":{"draws":29,"losses":83,"wins":26},"meta/muse-spark-open":{"draws":25,"losses":86,"wins":21},"meta/muse-wonder":{"draws":22,"losses":105,"wins":11},"minimax/minimax-m3":{"draws":19,"losses":25,"wins":34},"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":33,"losses":16,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":44,"losses":67,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":108,"wins":4},"nex-agi/nex-n2-pro":{"draws":26,"losses":14,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":32,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":31,"wins":15},"o3":{"draws":34,"losses":98,"wins":60},"openai/gpt-oss-120b":{"draws":49,"losses":36,"wins":41},"poolside/laguna-s-2.1":{"draws":36,"losses":34,"wins":34},"qwen/qwen3.7-max":{"draws":32,"losses":29,"wins":21},"qwen/qwen3.7-plus":{"draws":22,"losses":13,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":80,"wins":15},"qwen/qwen3.8-27b":{"draws":26,"losses":46,"wins":22},"qwen/qwen3.8-flash":{"draws":29,"losses":42,"wins":21},"qwen/qwen3.8-max":{"draws":46,"losses":59,"wins":33},"qwen/qwen3.8-max-0902":{"draws":43,"losses":72,"wins":23},"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":118,"losses":270,"wins":90},"stealth/space-bunny-alpha":{"draws":32,"losses":42,"wins":32},"stepfun/step-3.7-flash":{"draws":31,"losses":30,"wins":37},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":27,"wins":22},"tencent/hy4-preview":{"draws":40,"losses":67,"wins":25},"thinkingmachines/inkling":{"draws":58,"losses":55,"wins":75},"thinkingmachines/inkling-small":{"draws":49,"losses":24,"wins":65},"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":36,"losses":86,"wins":16},"x-ai/grok-4.7":{"draws":12,"losses":99,"wins":13},"x-ai/grok-build-0.1":{"draws":21,"losses":14,"wins":11},"xiaomi/mimo-v2.5":{"draws":64,"losses":57,"wins":81},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":25,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":55,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":64,"wins":18},"z-ai/glm-5.2":{"draws":111,"losses":96,"wins":69},"z-ai/glm-5.3":{"draws":25,"losses":92,"wins":15},"z-ai/glm-5.3-flash":{"draws":32,"losses":75,"wins":31},"z-ai/glm-5.3-flashx":{"draws":40,"losses":75,"wins":23}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":27},"claude-fable-5":{"draws":13,"losses":58,"wins":13},"claude-fable-5-1":{"draws":3,"losses":88,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":35,"wins":20},"claude-opus-4-5":{"draws":43,"losses":62,"wins":33},"claude-opus-4-8":{"draws":25,"losses":35,"wins":20},"claude-opus-5":{"draws":18,"losses":110,"wins":12},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":27,"losses":40,"wins":17},"claude-sonnet-5-5":{"draws":18,"losses":44,"wins":22},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":53,"losses":28,"wins":49},"deepseek/deepseek-v4-pro":{"draws":25,"losses":35,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":33,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":35,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":58,"wins":11},"elorian/glimpse":{"draws":8,"losses":22,"wins":14},"fireworks/ember-1":{"draws":26,"losses":39,"wins":19},"gemini-3.1-pro-preview":{"draws":26,"losses":29,"wins":29},"gemini-4-argon":{"draws":4,"losses":73,"wins":7},"google/gemini-3.1-flash-lite":{"draws":19,"losses":7,"wins":34},"google/gemini-3.5-flash":{"draws":32,"losses":41,"wins":33},"google/gemini-3.5-flash-lite":{"draws":41,"losses":42,"wins":63},"google/gemini-3.6-flash":{"draws":46,"losses":76,"wins":38},"google/gemini-3.8-flash":{"draws":26,"losses":38,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":13,"wins":20},"gpt-4.1":{"draws":13,"losses":5,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":31,"losses":28,"wins":15},"gpt-5.4":{"draws":17,"losses":45,"wins":18},"gpt-5.4-mini":{"draws":19,"losses":15,"wins":22},"gpt-5.4-nano":{"draws":27,"losses":29,"wins":36},"gpt-5.5":{"draws":27,"losses":35,"wins":14},"gpt-5.6-luna":{"draws":31,"losses":21,"wins":32},"gpt-5.6-sol":{"draws":11,"losses":59,"wins":14},"gpt-5.6-terra":{"draws":24,"losses":40,"wins":16},"gpt-6-astra":{"draws":6,"losses":77,"wins":1},"gpt-6-luna":{"draws":22,"losses":35,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":7,"losses":75,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":23},"inception/mercury-3":{"draws":15,"losses":25,"wins":18},"inclusionai/ling-3.0-flash":{"draws":29,"losses":7,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":19,"wins":45},"meta/muse-glimmer-30b":{"draws":29,"losses":16,"wins":27},"meta/muse-spark-1.2":{"draws":11,"losses":50,"wins":19},"meta/muse-spark-1.3":{"draws":18,"losses":47,"wins":19},"meta/muse-spark-open":{"draws":16,"losses":46,"wins":18},"meta/muse-wonder":{"draws":11,"losses":61,"wins":12},"minimax/minimax-m3":{"draws":15,"losses":9,"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":24,"losses":4,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":20,"losses":41,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":69,"wins":6},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":17,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":16},"o3":{"draws":26,"losses":56,"wins":42},"openai/gpt-oss-120b":{"draws":29,"losses":14,"wins":31},"poolside/laguna-s-2.1":{"draws":32,"losses":21,"wins":29},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":13,"losses":12,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":37,"wins":18},"qwen/qwen3.8-27b":{"draws":16,"losses":26,"wins":18},"qwen/qwen3.8-flash":{"draws":18,"losses":22,"wins":16},"qwen/qwen3.8-max":{"draws":31,"losses":30,"wins":23},"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":62,"losses":137,"wins":59},"stealth/space-bunny-alpha":{"draws":21,"losses":22,"wins":23},"stepfun/step-3.7-flash":{"draws":16,"losses":12,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":17},"tencent/hy4-preview":{"draws":18,"losses":44,"wins":18},"thinkingmachines/inkling":{"draws":34,"losses":17,"wins":59},"thinkingmachines/inkling-small":{"draws":30,"losses":17,"wins":37},"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":21,"losses":47,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":51,"wins":15},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":9},"xiaomi/mimo-v2.5":{"draws":53,"losses":27,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":14,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":28,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":55,"losses":60,"wins":53},"z-ai/glm-5.3":{"draws":18,"losses":49,"wins":13},"z-ai/glm-5.3-flash":{"draws":25,"losses":41,"wins":18},"z-ai/glm-5.3-flashx":{"draws":22,"losses":42,"wins":20}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":22,"wins":20},"claude-fable-5":{"draws":12,"losses":52,"wins":8},"claude-fable-5-1":{"draws":5,"losses":72,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":50,"wins":8},"claude-opus-4-5":{"draws":40,"losses":52,"wins":28},"claude-opus-4-8":{"draws":16,"losses":45,"wins":11},"claude-opus-5":{"draws":15,"losses":93,"wins":8},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":20,"losses":36,"wins":16},"claude-sonnet-5-5":{"draws":16,"losses":43,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":33,"losses":43,"wins":36},"deepseek/deepseek-v4-pro":{"draws":16,"losses":35,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":28,"wins":21},"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":21,"losses":38,"wins":13},"gemini-3.1-pro-preview":{"draws":23,"losses":35,"wins":14},"gemini-4-argon":{"draws":3,"losses":68,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":12,"wins":31},"google/gemini-3.5-flash":{"draws":20,"losses":51,"wins":21},"google/gemini-3.5-flash-lite":{"draws":35,"losses":51,"wins":40},"google/gemini-3.6-flash":{"draws":39,"losses":77,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":48,"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":16,"losses":36,"wins":10},"gpt-5.4":{"draws":10,"losses":50,"wins":8},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":18},"gpt-5.4-nano":{"draws":19,"losses":33,"wins":30},"gpt-5.5":{"draws":26,"losses":32,"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":28,"losses":29,"wins":11},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"gpt-6-luna":{"draws":25,"losses":35,"wins":12},"gpt-6-sol":{"draws":10,"losses":55,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":66,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":9,"wins":23},"inception/mercury-3":{"draws":15,"losses":25,"wins":8},"inclusionai/ling-3.0-flash":{"draws":20,"losses":14,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":32,"wins":31},"meta/muse-glimmer-30b":{"draws":25,"losses":20,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":40,"wins":12},"meta/muse-spark-1.3":{"draws":14,"losses":45,"wins":13},"meta/muse-spark-open":{"draws":15,"losses":43,"wins":10},"meta/muse-wonder":{"draws":15,"losses":55,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":14,"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":17,"losses":10,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":28,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":60,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":9,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":8,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":22,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":16,"wins":9},"o3":{"draws":13,"losses":68,"wins":29},"openai/gpt-oss-120b":{"draws":21,"losses":20,"wins":21},"poolside/laguna-s-2.1":{"draws":22,"losses":31,"wins":13},"qwen/qwen3.7-max":{"draws":13,"losses":21,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":35,"wins":9},"qwen/qwen3.8-27b":{"draws":11,"losses":28,"wins":15},"qwen/qwen3.8-flash":{"draws":14,"losses":18,"wins":16},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":16},"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":43,"losses":132,"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":16,"losses":41,"wins":11},"thinkingmachines/inkling":{"draws":27,"losses":29,"wins":38},"thinkingmachines/inkling-small":{"draws":26,"losses":25,"wins":21},"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":21,"losses":44,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":52,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":42,"losses":37,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":23,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":29,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":45,"losses":68,"wins":31},"z-ai/glm-5.3":{"draws":15,"losses":45,"wins":7},"z-ai/glm-5.3-flash":{"draws":17,"losses":42,"wins":13},"z-ai/glm-5.3-flashx":{"draws":17,"losses":45,"wins":10}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":25,"wins":66},"claude-fable-5":{"draws":34,"losses":75,"wins":35},"claude-fable-5-1":{"draws":11,"losses":145,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":55,"wins":47},"claude-opus-4-5":{"draws":85,"losses":59,"wins":90},"claude-opus-4-8":{"draws":38,"losses":44,"wins":50},"claude-opus-5":{"draws":33,"losses":174,"wins":39},"claude-opus-5-5":{"draws":11,"losses":127,"wins":18},"claude-sonnet-5":{"draws":45,"losses":37,"wins":62},"claude-sonnet-5-5":{"draws":31,"losses":62,"wins":51},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":45},"deepseek/deepseek-v4-flash":{"draws":69,"losses":31,"wins":116},"deepseek/deepseek-v4-pro":{"draws":36,"losses":37,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":43,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":58,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":73,"wins":43},"elorian/glimpse":{"draws":20,"losses":29,"wins":29},"fireworks/ember-1":{"draws":49,"losses":48,"wins":47},"gemini-3.1-pro-preview":{"draws":35,"losses":45,"wins":64},"gemini-4-argon":{"draws":9,"losses":112,"wins":23},"google/gemini-3.1-flash-lite":{"draws":25,"losses":4,"wins":67},"google/gemini-3.5-flash":{"draws":48,"losses":55,"wins":77},"google/gemini-3.5-flash-lite":{"draws":80,"losses":42,"wins":130},"google/gemini-3.6-flash":{"draws":72,"losses":109,"wins":95},"google/gemini-3.8-flash":{"draws":34,"losses":66,"wins":44},"google/gemma-4-31b-it":{"draws":29,"losses":10,"wins":45},"gpt-4.1":{"draws":17,"losses":7,"wins":24},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":37,"losses":33,"wins":56},"gpt-5.4":{"draws":27,"losses":58,"wins":53},"gpt-5.4-mini":{"draws":34,"losses":13,"wins":49},"gpt-5.4-nano":{"draws":37,"losses":27,"wins":80},"gpt-5.5":{"draws":40,"losses":47,"wins":45},"gpt-5.6-luna":{"draws":51,"losses":27,"wins":66},"gpt-5.6-sol":{"draws":23,"losses":84,"wins":37},"gpt-5.6-terra":{"draws":48,"losses":31,"wins":59},"gpt-6-astra":{"draws":5,"losses":133,"wins":6},"gpt-6-luna":{"draws":37,"losses":48,"wins":59},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":11,"losses":113,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":6,"wins":56},"inception/mercury-3":{"draws":32,"losses":30,"wins":34},"inclusionai/ling-3.0-flash":{"draws":41,"losses":4,"wins":57},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":40,"losses":24,"wins":92},"meta/muse-glimmer-30b":{"draws":47,"losses":15,"wins":64},"meta/muse-spark-1.2":{"draws":36,"losses":48,"wins":54},"meta/muse-spark-1.3":{"draws":35,"losses":59,"wins":50},"meta/muse-spark-open":{"draws":32,"losses":56,"wins":50},"meta/muse-wonder":{"draws":27,"losses":73,"wins":44},"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":25,"losses":3,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":9,"wins":15},"moonshotai/kimi-k3":{"draws":39,"losses":51,"wins":48},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":108,"wins":13},"nex-agi/nex-n2-pro":{"draws":16,"losses":9,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":14,"wins":63},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":29,"losses":58,"wins":111},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":72},"poolside/laguna-s-2.1":{"draws":43,"losses":15,"wins":80},"qwen/qwen3.7-max":{"draws":29,"losses":18,"wins":37},"qwen/qwen3.7-plus":{"draws":28,"losses":9,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":35},"qwen/qwen3.8-27b":{"draws":40,"losses":26,"wins":36},"qwen/qwen3.8-flash":{"draws":26,"losses":31,"wins":39},"qwen/qwen3.8-max":{"draws":45,"losses":49,"wins":50},"qwen/qwen3.8-max-0902":{"draws":46,"losses":53,"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":120,"losses":176,"wins":178},"stealth/space-bunny-alpha":{"draws":40,"losses":27,"wins":47},"stepfun/step-3.7-flash":{"draws":16,"losses":15,"wins":71},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":28,"losses":15,"wins":35},"tencent/hy4-preview":{"draws":40,"losses":52,"wins":46},"thinkingmachines/inkling":{"draws":59,"losses":25,"wins":108},"thinkingmachines/inkling-small":{"draws":45,"losses":17,"wins":82},"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":62,"wins":48},"x-ai/grok-4.6":{"draws":34,"losses":61,"wins":49},"x-ai/grok-4.7":{"draws":9,"losses":87,"wins":30},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":88,"losses":25,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":41,"wins":31},"z-ai/glm-5.2":{"draws":104,"losses":70,"wins":114},"z-ai/glm-5.3":{"draws":27,"losses":82,"wins":29},"z-ai/glm-5.3-flash":{"draws":31,"losses":65,"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":23,"losses":23,"wins":48},"claude-fable-5":{"draws":20,"losses":66,"wins":16},"claude-fable-5-1":{"draws":7,"losses":106,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":47,"wins":29},"claude-opus-4-5":{"draws":50,"losses":48,"wins":68},"claude-opus-4-8":{"draws":20,"losses":43,"wins":31},"claude-opus-5":{"draws":30,"losses":123,"wins":13},"claude-opus-5-5":{"draws":5,"losses":98,"wins":3},"claude-sonnet-5":{"draws":25,"losses":37,"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":31,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":30,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":50,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":61,"wins":26},"elorian/glimpse":{"draws":11,"losses":22,"wins":21},"fireworks/ember-1":{"draws":30,"losses":35,"wins":37},"gemini-3.1-pro-preview":{"draws":23,"losses":32,"wins":47},"gemini-4-argon":{"draws":7,"losses":88,"wins":7},"google/gemini-3.1-flash-lite":{"draws":15,"losses":10,"wins":45},"google/gemini-3.5-flash":{"draws":20,"losses":58,"wins":50},"google/gemini-3.5-flash-lite":{"draws":35,"losses":43,"wins":102},"google/gemini-3.6-flash":{"draws":43,"losses":91,"wins":64},"google/gemini-3.8-flash":{"draws":16,"losses":64,"wins":22},"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":17,"losses":19,"wins":32},"gpt-5.4-nano":{"draws":22,"losses":33,"wins":49},"gpt-5.5":{"draws":29,"losses":37,"wins":26},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":45},"gpt-5.6-sol":{"draws":16,"losses":69,"wins":17},"gpt-5.6-terra":{"draws":35,"losses":34,"wins":29},"gpt-6-astra":{"draws":4,"losses":97,"wins":1},"gpt-6-luna":{"draws":26,"losses":41,"wins":35},"gpt-6-sol":{"draws":16,"losses":72,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":91,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":7,"wins":43},"inception/mercury-3":{"draws":20,"losses":21,"wins":25},"inclusionai/ling-3.0-flash":{"draws":15,"losses":13,"wins":46},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":21,"losses":18,"wins":69},"meta/muse-glimmer-30b":{"draws":25,"losses":14,"wins":47},"meta/muse-spark-1.2":{"draws":21,"losses":36,"wins":39},"meta/muse-spark-1.3":{"draws":19,"losses":52,"wins":31},"meta/muse-spark-open":{"draws":21,"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":20,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k3":{"draws":28,"losses":41,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":82,"wins":4},"nex-agi/nex-n2-pro":{"draws":12,"losses":7,"wins":29},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":19,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":13,"wins":21},"o3":{"draws":13,"losses":58,"wins":73},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":46},"poolside/laguna-s-2.1":{"draws":26,"losses":22,"wins":46},"qwen/qwen3.7-max":{"draws":16,"losses":18,"wins":26},"qwen/qwen3.7-plus":{"draws":11,"losses":15,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":36,"wins":26},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":16,"losses":30,"wins":22},"qwen/qwen3.8-max":{"draws":33,"losses":34,"wins":35},"qwen/qwen3.8-max-0902":{"draws":26,"losses":49,"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":74,"losses":150,"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":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":13,"wins":26},"tencent/hy4-preview":{"draws":26,"losses":45,"wins":27},"thinkingmachines/inkling":{"draws":37,"losses":30,"wins":71},"thinkingmachines/inkling-small":{"draws":29,"losses":16,"wins":57},"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":27,"losses":52,"wins":23},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":13,"losses":1,"wins":20},"xiaomi/mimo-v2.5":{"draws":44,"losses":29,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":26,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":36,"wins":20},"z-ai/glm-5.2":{"draws":66,"losses":70,"wins":68},"z-ai/glm-5.3":{"draws":26,"losses":58,"wins":12},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":32},"z-ai/glm-5.3-flashx":{"draws":24,"losses":53,"wins":25}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":20,"wins":39},"claude-fable-5":{"draws":22,"losses":55,"wins":19},"claude-fable-5-1":{"draws":6,"losses":97,"wins":5},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":19},"claude-opus-4-5":{"draws":55,"losses":53,"wins":48},"claude-opus-4-8":{"draws":31,"losses":41,"wins":16},"claude-opus-5":{"draws":21,"losses":129,"wins":14},"claude-opus-5-5":{"draws":10,"losses":91,"wins":3},"claude-sonnet-5":{"draws":30,"losses":33,"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":44,"losses":30,"wins":70},"deepseek/deepseek-v4-pro":{"draws":20,"losses":30,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":32,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":41,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":51,"wins":24},"elorian/glimpse":{"draws":13,"losses":22,"wins":17},"fireworks/ember-1":{"draws":31,"losses":33,"wins":32},"gemini-3.1-pro-preview":{"draws":36,"losses":30,"wins":30},"gemini-4-argon":{"draws":12,"losses":73,"wins":11},"google/gemini-3.1-flash-lite":{"draws":21,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":32,"losses":49,"wins":39},"google/gemini-3.5-flash-lite":{"draws":55,"losses":30,"wins":83},"google/gemini-3.6-flash":{"draws":55,"losses":81,"wins":48},"google/gemini-3.8-flash":{"draws":20,"losses":48,"wins":28},"google/gemma-4-31b-it":{"draws":27,"losses":6,"wins":23},"gpt-4.1":{"draws":11,"losses":5,"wins":16},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":18,"losses":30,"wins":36},"gpt-5.4":{"draws":19,"losses":45,"wins":28},"gpt-5.4-mini":{"draws":21,"losses":14,"wins":29},"gpt-5.4-nano":{"draws":21,"losses":26,"wins":49},"gpt-5.5":{"draws":31,"losses":37,"wins":20},"gpt-5.6-luna":{"draws":31,"losses":28,"wins":37},"gpt-5.6-sol":{"draws":16,"losses":62,"wins":18},"gpt-5.6-terra":{"draws":27,"losses":34,"wins":31},"gpt-6-astra":{"draws":13,"losses":80,"wins":3},"gpt-6-luna":{"draws":28,"losses":35,"wins":33},"gpt-6-sol":{"draws":9,"losses":68,"wins":19},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":6,"wins":33},"inception/mercury-3":{"draws":19,"losses":21,"wins":24},"inclusionai/ling-3.0-flash":{"draws":25,"losses":5,"wins":38},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":25,"wins":49},"meta/muse-glimmer-30b":{"draws":31,"losses":21,"wins":32},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":28},"meta/muse-spark-1.3":{"draws":21,"losses":47,"wins":28},"meta/muse-spark-open":{"draws":19,"losses":42,"wins":31},"meta/muse-wonder":{"draws":24,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":18,"wins":25},"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":20,"losses":5,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":28,"losses":33,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":73,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":6,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":14,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":12,"wins":18},"o3":{"draws":22,"losses":47,"wins":63},"openai/gpt-oss-120b":{"draws":27,"losses":23,"wins":34},"poolside/laguna-s-2.1":{"draws":29,"losses":21,"wins":42},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":22},"qwen/qwen3.7-plus":{"draws":14,"losses":16,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":39,"wins":31},"qwen/qwen3.8-27b":{"draws":16,"losses":22,"wins":30},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":31,"losses":38,"wins":27},"qwen/qwen3.8-max-0902":{"draws":31,"losses":33,"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":83,"losses":129,"wins":104},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":30},"stepfun/step-3.7-flash":{"draws":14,"losses":14,"wins":40},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":22},"tencent/hy4-preview":{"draws":24,"losses":40,"wins":28},"thinkingmachines/inkling":{"draws":43,"losses":25,"wins":60},"thinkingmachines/inkling-small":{"draws":36,"losses":20,"wins":40},"unbiased/pareto-26.10":{"draws":4,"losses":28,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":26,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":25,"losses":44,"wins":27},"x-ai/grok-4.6":{"draws":35,"losses":45,"wins":16},"x-ai/grok-4.7":{"draws":8,"losses":63,"wins":13},"x-ai/grok-build-0.1":{"draws":15,"losses":4,"wins":13},"xiaomi/mimo-v2.5":{"draws":57,"losses":31,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":13,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":22,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":35,"wins":16},"z-ai/glm-5.2":{"draws":65,"losses":54,"wins":73},"z-ai/glm-5.3":{"draws":23,"losses":55,"wins":14},"z-ai/glm-5.3-flash":{"draws":20,"losses":42,"wins":34},"z-ai/glm-5.3-flashx":{"draws":29,"losses":42,"wins":25}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":33,"wins":52},"claude-fable-5":{"draws":27,"losses":80,"wins":37},"claude-fable-5-1":{"draws":8,"losses":151,"wins":3},"claude-haiku-5-5":{"draws":34,"losses":67,"wins":37},"claude-opus-4-5":{"draws":74,"losses":68,"wins":92},"claude-opus-4-8":{"draws":26,"losses":61,"wins":45},"claude-opus-5":{"draws":36,"losses":180,"wins":30},"claude-opus-5-5":{"draws":13,"losses":131,"wins":12},"claude-sonnet-5":{"draws":47,"losses":43,"wins":54},"claude-sonnet-5-5":{"draws":23,"losses":79,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":41},"deepseek/deepseek-v4-flash":{"draws":67,"losses":36,"wins":113},"deepseek/deepseek-v4-pro":{"draws":37,"losses":36,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":38,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":54,"wins":48},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":82,"wins":33},"elorian/glimpse":{"draws":17,"losses":30,"wins":31},"fireworks/ember-1":{"draws":44,"losses":58,"wins":42},"gemini-3.1-pro-preview":{"draws":43,"losses":45,"wins":56},"gemini-4-argon":{"draws":9,"losses":123,"wins":12},"google/gemini-3.1-flash-lite":{"draws":29,"losses":1,"wins":66},"google/gemini-3.5-flash":{"draws":56,"losses":62,"wins":62},"google/gemini-3.5-flash-lite":{"draws":82,"losses":47,"wins":123},"google/gemini-3.6-flash":{"draws":72,"losses":114,"wins":90},"google/gemini-3.8-flash":{"draws":36,"losses":62,"wins":46},"google/gemma-4-31b-it":{"draws":33,"losses":8,"wins":43},"gpt-4.1":{"draws":19,"losses":13,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":39,"losses":29,"wins":58},"gpt-5.4":{"draws":33,"losses":53,"wins":52},"gpt-5.4-mini":{"draws":41,"losses":18,"wins":37},"gpt-5.4-nano":{"draws":33,"losses":37,"wins":74},"gpt-5.5":{"draws":44,"losses":48,"wins":40},"gpt-5.6-luna":{"draws":48,"losses":30,"wins":66},"gpt-5.6-sol":{"draws":26,"losses":88,"wins":30},"gpt-5.6-terra":{"draws":58,"losses":36,"wins":44},"gpt-6-astra":{"draws":13,"losses":129,"wins":2},"gpt-6-luna":{"draws":37,"losses":50,"wins":57},"gpt-6-sol":{"draws":17,"losses":99,"wins":28},"gpt-6.1-sol":{"draws":10,"losses":125,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":43,"losses":8,"wins":51},"inception/mercury-3":{"draws":30,"losses":26,"wins":40},"inclusionai/ling-3.0-flash":{"draws":41,"losses":14,"wins":47},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":46,"losses":28,"wins":82},"meta/muse-glimmer-30b":{"draws":41,"losses":24,"wins":61},"meta/muse-spark-1.2":{"draws":35,"losses":51,"wins":52},"meta/muse-spark-1.3":{"draws":34,"losses":71,"wins":39},"meta/muse-spark-open":{"draws":28,"losses":66,"wins":44},"meta/muse-wonder":{"draws":31,"losses":81,"wins":32},"minimax/minimax-m3":{"draws":20,"losses":14,"wins":44},"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":26,"losses":9,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":40,"losses":47,"wins":51},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":113,"wins":19},"nex-agi/nex-n2-pro":{"draws":21,"losses":6,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":7,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":22,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":18,"wins":31},"o3":{"draws":37,"losses":63,"wins":98},"openai/gpt-oss-120b":{"draws":41,"losses":10,"wins":75},"poolside/laguna-s-2.1":{"draws":46,"losses":33,"wins":59},"qwen/qwen3.7-max":{"draws":31,"losses":23,"wins":30},"qwen/qwen3.7-plus":{"draws":27,"losses":16,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":50,"wins":49},"qwen/qwen3.8-27b":{"draws":33,"losses":35,"wins":34},"qwen/qwen3.8-flash":{"draws":31,"losses":27,"wins":38},"qwen/qwen3.8-max":{"draws":28,"losses":34,"wins":34},"qwen/qwen3.8-max-0902":{"draws":38,"losses":62,"wins":44},"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":125,"losses":191,"wins":158},"stealth/space-bunny-alpha":{"draws":37,"losses":31,"wins":46},"stepfun/step-3.7-flash":{"draws":24,"losses":17,"wins":61},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":30,"losses":13,"wins":35},"tencent/hy4-preview":{"draws":37,"losses":58,"wins":43},"thinkingmachines/inkling":{"draws":61,"losses":33,"wins":98},"thinkingmachines/inkling-small":{"draws":42,"losses":39,"wins":63},"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":65,"wins":47},"x-ai/grok-4.6":{"draws":40,"losses":64,"wins":40},"x-ai/grok-4.7":{"draws":11,"losses":89,"wins":26},"x-ai/grok-build-0.1":{"draws":19,"losses":9,"wins":20},"xiaomi/mimo-v2.5":{"draws":76,"losses":41,"wins":105},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":24,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":36,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":52,"wins":19},"z-ai/glm-5.2":{"draws":97,"losses":77,"wins":114},"z-ai/glm-5.3":{"draws":29,"losses":79,"wins":30},"z-ai/glm-5.3-flash":{"draws":32,"losses":57,"wins":55},"z-ai/glm-5.3-flashx":{"draws":40,"losses":56,"wins":48}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":21,"wins":74},"claude-fable-5":{"draws":29,"losses":81,"wins":34},"claude-fable-5-1":{"draws":6,"losses":141,"wins":15},"claude-haiku-5-5":{"draws":40,"losses":50,"wins":48},"claude-opus-4-5":{"draws":67,"losses":77,"wins":90},"claude-opus-4-8":{"draws":33,"losses":51,"wins":48},"claude-opus-5":{"draws":34,"losses":170,"wins":42},"claude-opus-5-5":{"draws":16,"losses":128,"wins":12},"claude-sonnet-5":{"draws":42,"losses":36,"wins":66},"claude-sonnet-5-5":{"draws":27,"losses":66,"wins":51},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":41},"deepseek/deepseek-v4-flash":{"draws":64,"losses":30,"wins":122},"deepseek/deepseek-v4-pro":{"draws":34,"losses":35,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":39,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":49,"losses":49,"wins":46},"deepseek/deepseek-v4.1-flash-1017":{"draws":32,"losses":72,"wins":40},"elorian/glimpse":{"draws":20,"losses":28,"wins":30},"fireworks/ember-1":{"draws":41,"losses":42,"wins":61},"gemini-3.1-pro-preview":{"draws":40,"losses":39,"wins":65},"gemini-4-argon":{"draws":12,"losses":118,"wins":14},"google/gemini-3.1-flash-lite":{"draws":28,"losses":2,"wins":66},"google/gemini-3.5-flash":{"draws":47,"losses":48,"wins":85},"google/gemini-3.5-flash-lite":{"draws":69,"losses":40,"wins":143},"google/gemini-3.6-flash":{"draws":74,"losses":97,"wins":105},"google/gemini-3.8-flash":{"draws":37,"losses":60,"wins":47},"google/gemma-4-31b-it":{"draws":29,"losses":9,"wins":46},"gpt-4.1":{"draws":18,"losses":7,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":36,"losses":31,"wins":59},"gpt-5.4":{"draws":29,"losses":63,"wins":46},"gpt-5.4-mini":{"draws":38,"losses":14,"wins":44},"gpt-5.4-nano":{"draws":37,"losses":35,"wins":72},"gpt-5.5":{"draws":47,"losses":42,"wins":43},"gpt-5.6-luna":{"draws":51,"losses":32,"wins":61},"gpt-5.6-sol":{"draws":23,"losses":87,"wins":34},"gpt-5.6-terra":{"draws":48,"losses":35,"wins":55},"gpt-6-astra":{"draws":9,"losses":129,"wins":6},"gpt-6-luna":{"draws":41,"losses":48,"wins":55},"gpt-6-sol":{"draws":18,"losses":99,"wins":27},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":44,"losses":10,"wins":48},"inception/mercury-3":{"draws":27,"losses":30,"wins":39},"inclusionai/ling-3.0-flash":{"draws":39,"losses":9,"wins":54},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":25,"wins":105},"meta/muse-glimmer-30b":{"draws":46,"losses":12,"wins":68},"meta/muse-spark-1.2":{"draws":31,"losses":52,"wins":55},"meta/muse-spark-1.3":{"draws":38,"losses":52,"wins":54},"meta/muse-spark-open":{"draws":30,"losses":52,"wins":56},"meta/muse-wonder":{"draws":33,"losses":78,"wins":33},"minimax/minimax-m3":{"draws":19,"losses":8,"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":29,"losses":6,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":35,"losses":34,"wins":69},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":111,"wins":15},"nex-agi/nex-n2-pro":{"draws":21,"losses":9,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":12,"wins":65},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":16,"wins":32},"o3":{"draws":35,"losses":64,"wins":99},"openai/gpt-oss-120b":{"draws":39,"losses":15,"wins":72},"poolside/laguna-s-2.1":{"draws":43,"losses":23,"wins":72},"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":46,"losses":45,"wins":53},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":49},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":33},"qwen/qwen3.8-max":{"draws":38,"losses":44,"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":110,"losses":176,"wins":188},"stealth/space-bunny-alpha":{"draws":36,"losses":20,"wins":58},"stepfun/step-3.7-flash":{"draws":25,"losses":19,"wins":58},"stepfun/step-5-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":27,"losses":14,"wins":37},"tencent/hy4-preview":{"draws":34,"losses":54,"wins":50},"thinkingmachines/inkling":{"draws":54,"losses":30,"wins":108},"thinkingmachines/inkling-small":{"draws":47,"losses":16,"wins":81},"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":44,"losses":66,"wins":34},"x-ai/grok-4.7":{"draws":19,"losses":79,"wins":28},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":25},"xiaomi/mimo-v2.5":{"draws":83,"losses":28,"wins":111},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":20,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":37,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":52,"wins":29},"z-ai/glm-5.2":{"draws":98,"losses":57,"wins":133},"z-ai/glm-5.3":{"draws":35,"losses":73,"wins":30},"z-ai/glm-5.3-flash":{"draws":38,"losses":53,"wins":53},"z-ai/glm-5.3-flashx":{"draws":35,"losses":58,"wins":51}},"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},"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":0,"losses":1,"wins":1},"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":5,"losses":32,"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":7,"wins":2},"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":10,"losses":17,"wins":13},"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":0,"losses":2,"wins":2},"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":14,"wins":7},"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":61,"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},"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":28,"losses":29,"wins":31},"inclusionai/ling-3.0-flash":{"draws":29,"losses":16,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"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":27,"losses":65,"wins":34},"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":10,"losses":13,"wins":11},"moonshotai/kimi-k3":{"draws":35,"losses":52,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":110,"wins":7},"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":27,"losses":18,"wins":69},"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":0,"losses":6,"wins":6},"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":12,"losses":21,"wins":37},"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":101,"losses":88,"wins":251},"claude-fable-5":{"draws":79,"losses":278,"wins":117},"claude-fable-5-1":{"draws":32,"losses":489,"wins":29},"claude-haiku-5-5":{"draws":96,"losses":173,"wins":165},"claude-opus-4-5":{"draws":199,"losses":215,"wins":336},"claude-opus-4-8":{"draws":84,"losses":153,"wins":157},"claude-opus-5":{"draws":131,"losses":580,"wins":121},"claude-opus-5-5":{"draws":46,"losses":432,"wins":28},"claude-sonnet-5":{"draws":107,"losses":134,"wins":233},"claude-sonnet-5-5":{"draws":85,"losses":225,"wins":164},"cohere/north-mini-code":{"draws":24,"losses":23,"wins":131},"deepseek/deepseek-v4-flash":{"draws":165,"losses":131,"wins":400},"deepseek/deepseek-v4-pro":{"draws":104,"losses":132,"wins":206},"deepseek/deepseek-v4-pro-0813":{"draws":105,"losses":147,"wins":188},"deepseek/deepseek-v4.1-flash":{"draws":110,"losses":180,"wins":183},"deepseek/deepseek-v4.1-flash-1017":{"draws":79,"losses":230,"wins":163},"elorian/glimpse":{"draws":65,"losses":94,"wins":107},"fireworks/ember-1":{"draws":116,"losses":174,"wins":184},"gemini-3.1-pro-preview":{"draws":104,"losses":145,"wins":225},"gemini-4-argon":{"draws":45,"losses":380,"wins":49},"google/gemini-3.1-flash-lite":{"draws":53,"losses":28,"wins":191},"google/gemini-3.5-flash":{"draws":106,"losses":202,"wins":268},"google/gemini-3.5-flash-lite":{"draws":175,"losses":167,"wins":484},"google/gemini-3.6-flash":{"draws":197,"losses":359,"wins":360},"google/gemini-3.8-flash":{"draws":98,"losses":227,"wins":149},"google/gemma-4-31b-it":{"draws":60,"losses":40,"wins":160},"gpt-4.1":{"draws":41,"losses":37,"wins":80},"gpt-4.1-nano":{"draws":33,"losses":5,"wins":34},"gpt-5":{"draws":94,"losses":131,"wins":199},"gpt-5.4":{"draws":114,"losses":183,"wins":161},"gpt-5.4-mini":{"draws":91,"losses":62,"wins":163},"gpt-5.4-nano":{"draws":79,"losses":122,"wins":223},"gpt-5.5":{"draws":121,"losses":156,"wins":165},"gpt-5.6-luna":{"draws":145,"losses":101,"wins":228},"gpt-5.6-sol":{"draws":72,"losses":286,"wins":116},"gpt-5.6-terra":{"draws":133,"losses":128,"wins":195},"gpt-6-astra":{"draws":35,"losses":418,"wins":21},"gpt-6-luna":{"draws":112,"losses":154,"wins":208},"gpt-6-sol":{"draws":61,"losses":340,"wins":73},"gpt-6.1-sol":{"draws":42,"losses":401,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":100,"losses":34,"wins":176},"inception/mercury-3":{"draws":79,"losses":103,"wins":130},"inclusionai/ling-3.0-flash":{"draws":90,"losses":29,"wins":209},"inclusionai/ling-3.1-flash":{"draws":6,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":106,"losses":80,"wins":324},"meta/muse-glimmer-30b":{"draws":100,"losses":58,"wins":268},"meta/muse-spark-1.2":{"draws":106,"losses":149,"wins":203},"meta/muse-spark-1.3":{"draws":91,"losses":220,"wins":163},"meta/muse-spark-open":{"draws":85,"losses":213,"wins":160},"meta/muse-wonder":{"draws":93,"losses":253,"wins":128},"minimax/minimax-m3":{"draws":50,"losses":40,"wins":152},"minimax/minimax-m3.1-flash":{"draws":87,"losses":115,"wins":224},"mistralai/mistral-large-4-0":{"draws":98,"losses":82,"wins":120},"mistralai/mistral-medium-3-5":{"draws":70,"losses":40,"wins":172},"moonshotai/kimi-k2.7-code":{"draws":24,"losses":29,"wins":49},"moonshotai/kimi-k3":{"draws":109,"losses":167,"wins":182},"moonshotai/kimi-k3.1-pro":{"draws":54,"losses":348,"wins":32},"nex-agi/nex-n2-pro":{"draws":59,"losses":30,"wins":161},"nex-agi/nex-n2.5-pro":{"draws":26,"losses":20,"wins":62},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":103,"losses":60,"wins":211},"nvidia/nemotron-3.5-super-vl":{"draws":55,"losses":54,"wins":101},"o3":{"draws":85,"losses":202,"wins":317},"openai/gpt-oss-120b":{"draws":108,"losses":59,"wins":257},"poolside/laguna-s-2.1":{"draws":118,"losses":90,"wins":270},"qwen/qwen3.7-max":{"draws":62,"losses":59,"wins":137},"qwen/qwen3.7-plus":{"draws":43,"losses":27,"wins":132},"qwen/qwen3.8-2.4t-a95b":{"draws":120,"losses":178,"wins":176},"qwen/qwen3.8-27b":{"draws":74,"losses":108,"wins":150},"qwen/qwen3.8-flash":{"draws":83,"losses":104,"wins":129},"qwen/qwen3.8-max":{"draws":125,"losses":158,"wins":191},"qwen/qwen3.8-max-0902":{"draws":110,"losses":188,"wins":176},"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":286,"losses":677,"wins":677},"stealth/space-bunny-alpha":{"draws":97,"losses":84,"wins":189},"stepfun/step-3.7-flash":{"draws":51,"losses":57,"wins":224},"stepfun/step-5-preview":{"draws":8,"losses":15,"wins":9},"tencent/hy3-preview":{"draws":71,"losses":45,"wins":126},"tencent/hy4-preview":{"draws":102,"losses":199,"wins":157},"thinkingmachines/inkling":{"draws":164,"losses":120,"wins":374},"thinkingmachines/inkling-small":{"draws":126,"losses":73,"wins":275},"unbiased/pareto-26.10":{"draws":11,"losses":143,"wins":4},"unbiased/pareto-26.10-preview":{"draws":10,"losses":141,"wins":7},"upstage/solar-mini4":{"draws":13,"losses":15,"wins":74},"x-ai/grok-4.5":{"draws":100,"losses":206,"wins":168},"x-ai/grok-4.6":{"draws":136,"losses":195,"wins":143},"x-ai/grok-4.7":{"draws":44,"losses":281,"wins":75},"x-ai/grok-build-0.1":{"draws":38,"losses":19,"wins":101},"xiaomi/mimo-v2.5":{"draws":171,"losses":96,"wins":379},"xiaomi/mimo-v2.5-pro":{"draws":44,"losses":59,"wins":139},"xiaomi/mimo-v2.6-flash":{"draws":55,"losses":111,"wins":132},"xiaomi/mimo-v2.6-pro":{"draws":57,"losses":154,"wins":105},"z-ai/glm-5.2":{"draws":250,"losses":224,"wins":474},"z-ai/glm-5.3":{"draws":82,"losses":258,"wins":118},"z-ai/glm-5.3-flash":{"draws":78,"losses":213,"wins":183},"z-ai/glm-5.3-flashx":{"draws":85,"losses":222,"wins":167}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":31,"wins":38},"claude-fable-5":{"draws":30,"losses":69,"wins":15},"claude-fable-5-1":{"draws":6,"losses":121,"wins":3},"claude-haiku-5-5":{"draws":33,"losses":54,"wins":23},"claude-opus-4-5":{"draws":58,"losses":79,"wins":49},"claude-opus-4-8":{"draws":30,"losses":53,"wins":23},"claude-opus-5":{"draws":30,"losses":152,"wins":14},"claude-opus-5-5":{"draws":6,"losses":115,"wins":1},"claude-sonnet-5":{"draws":30,"losses":47,"wins":37},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":24},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-flash":{"draws":58,"losses":39,"wins":71},"deepseek/deepseek-v4-pro":{"draws":31,"losses":47,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":46,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":54,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":76,"wins":18},"elorian/glimpse":{"draws":13,"losses":31,"wins":18},"fireworks/ember-1":{"draws":32,"losses":55,"wins":27},"gemini-3.1-pro-preview":{"draws":35,"losses":44,"wins":35},"gemini-4-argon":{"draws":7,"losses":103,"wins":4},"google/gemini-3.1-flash-lite":{"draws":21,"losses":12,"wins":47},"google/gemini-3.5-flash":{"draws":42,"losses":67,"wins":35},"google/gemini-3.5-flash-lite":{"draws":58,"losses":61,"wins":83},"google/gemini-3.6-flash":{"draws":59,"losses":116,"wins":45},"google/gemini-3.8-flash":{"draws":27,"losses":70,"wins":17},"google/gemma-4-31b-it":{"draws":26,"losses":16,"wins":26},"gpt-4.1":{"draws":15,"losses":10,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":25,"losses":38,"wins":37},"gpt-5.4":{"draws":30,"losses":61,"wins":19},"gpt-5.4-mini":{"draws":28,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":26,"losses":39,"wins":47},"gpt-5.5":{"draws":41,"losses":46,"wins":19},"gpt-5.6-luna":{"draws":43,"losses":31,"wins":40},"gpt-5.6-sol":{"draws":20,"losses":80,"wins":14},"gpt-5.6-terra":{"draws":37,"losses":39,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":41,"losses":50,"wins":23},"gpt-6-sol":{"draws":16,"losses":87,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":100,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":37,"losses":10,"wins":35},"inception/mercury-3":{"draws":19,"losses":33,"wins":20},"inclusionai/ling-3.0-flash":{"draws":34,"losses":11,"wins":31},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":39,"losses":28,"wins":59},"meta/muse-glimmer-30b":{"draws":39,"losses":27,"wins":36},"meta/muse-spark-1.2":{"draws":30,"losses":54,"wins":26},"meta/muse-spark-1.3":{"draws":24,"losses":69,"wins":21},"meta/muse-spark-open":{"draws":24,"losses":62,"wins":24},"meta/muse-wonder":{"draws":28,"losses":68,"wins":18},"minimax/minimax-m3":{"draws":15,"losses":13,"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":24,"losses":12,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":37,"losses":53,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":97,"wins":6},"nex-agi/nex-n2-pro":{"draws":17,"losses":13,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":25,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":21,"wins":16},"o3":{"draws":26,"losses":78,"wins":56},"openai/gpt-oss-120b":{"draws":33,"losses":23,"wins":44},"poolside/laguna-s-2.1":{"draws":32,"losses":32,"wins":42},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":22},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":47,"wins":27},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":28,"losses":30,"wins":18},"qwen/qwen3.8-max":{"draws":37,"losses":46,"wins":31},"qwen/qwen3.8-max-0902":{"draws":36,"losses":58,"wins":20},"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":97,"losses":189,"wins":84},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":18},"stepfun/step-3.7-flash":{"draws":19,"losses":23,"wins":38},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":21},"tencent/hy4-preview":{"draws":33,"losses":51,"wins":26},"thinkingmachines/inkling":{"draws":50,"losses":44,"wins":60},"thinkingmachines/inkling-small":{"draws":38,"losses":29,"wins":47},"unbiased/pareto-26.10":{"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":31,"losses":63,"wins":20},"x-ai/grok-4.6":{"draws":36,"losses":59,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":16},"xiaomi/mimo-v2.5":{"draws":71,"losses":38,"wins":69},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":15,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":37,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":38,"wins":19},"z-ai/glm-5.2":{"draws":89,"losses":74,"wins":65},"z-ai/glm-5.3":{"draws":25,"losses":76,"wins":9},"z-ai/glm-5.3-flash":{"draws":30,"losses":67,"wins":17},"z-ai/glm-5.3-flashx":{"draws":33,"losses":59,"wins":22}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":38,"wins":33},"claude-fable-5":{"draws":13,"losses":82,"wins":7},"claude-fable-5-1":{"draws":3,"losses":111,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":67,"wins":16},"claude-opus-4-5":{"draws":32,"losses":94,"wins":40},"claude-opus-4-8":{"draws":16,"losses":60,"wins":18},"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":35,"losses":65,"wins":58},"deepseek/deepseek-v4-pro":{"draws":17,"losses":55,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":55,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":62,"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":23,"losses":61,"wins":18},"gemini-3.1-pro-preview":{"draws":21,"losses":49,"wins":32},"gemini-4-argon":{"draws":0,"losses":98,"wins":4},"google/gemini-3.1-flash-lite":{"draws":16,"losses":10,"wins":48},"google/gemini-3.5-flash":{"draws":21,"losses":82,"wins":27},"google/gemini-3.5-flash-lite":{"draws":49,"losses":71,"wins":60},"google/gemini-3.6-flash":{"draws":35,"losses":131,"wins":32},"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":22,"losses":24,"wins":22},"gpt-5.4-nano":{"draws":16,"losses":60,"wins":34},"gpt-5.5":{"draws":26,"losses":54,"wins":14},"gpt-5.6-luna":{"draws":27,"losses":44,"wins":31},"gpt-5.6-sol":{"draws":11,"losses":85,"wins":6},"gpt-5.6-terra":{"draws":24,"losses":53,"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},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":10,"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":0,"wins":0},"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":12,"losses":80,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":27,"wins":18},"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":4,"losses":15,"wins":5},"moonshotai/kimi-k3":{"draws":21,"losses":59,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":94,"wins":0},"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":26,"losses":34,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":30,"wins":7},"o3":{"draws":24,"losses":93,"wins":43},"openai/gpt-oss-120b":{"draws":29,"losses":23,"wins":36},"poolside/laguna-s-2.1":{"draws":31,"losses":37,"wins":30},"qwen/qwen3.7-max":{"draws":16,"losses":34,"wins":12},"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":24,"losses":61,"wins":17},"qwen/qwen3.8-max-0902":{"draws":25,"losses":58,"wins":19},"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":224,"wins":57},"stealth/space-bunny-alpha":{"draws":19,"losses":38,"wins":23},"stepfun/step-3.7-flash":{"draws":10,"losses":19,"wins":19},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":22,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":63,"wins":17},"thinkingmachines/inkling":{"draws":38,"losses":38,"wins":62},"thinkingmachines/inkling-small":{"draws":28,"losses":37,"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":10,"losses":9,"wins":15},"xiaomi/mimo-v2.5":{"draws":44,"losses":54,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":34,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":44,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":52,"wins":8},"z-ai/glm-5.2":{"draws":50,"losses":105,"wins":49},"z-ai/glm-5.3":{"draws":15,"losses":78,"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":4,"losses":4,"wins":4},"claude-fable-5":{"draws":2,"losses":5,"wins":5},"claude-fable-5-1":{"draws":0,"losses":10,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-5":{"draws":3,"losses":7,"wins":10},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":0,"losses":17,"wins":7},"claude-opus-5-5":{"draws":0,"losses":16,"wins":4},"claude-sonnet-5":{"draws":3,"losses":3,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":8,"wins":4},"elorian/glimpse":{"draws":0,"losses":6,"wins":2},"fireworks/ember-1":{"draws":3,"losses":5,"wins":4},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":4},"gemini-4-argon":{"draws":0,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":5,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":0,"wins":7},"gpt-5.4":{"draws":5,"losses":1,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":9},"gpt-5.5":{"draws":6,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":6},"gpt-6-astra":{"draws":0,"losses":8,"wins":4},"gpt-6-luna":{"draws":3,"losses":3,"wins":6},"gpt-6-sol":{"draws":1,"losses":8,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":5},"inception/mercury-3":{"draws":0,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":5},"meta/muse-spark-open":{"draws":0,"losses":7,"wins":5},"meta/muse-wonder":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":3},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":5},"o3":{"draws":8,"losses":2,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":5},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"wins":6},"stealth/ox-alpha":{"draws":8,"losses":9,"wins":15},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":6},"unbiased/pareto-26.10":{"draws":0,"losses":4,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":13},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":7},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":8}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":26,"wins":23},"claude-fable-5":{"draws":22,"losses":45,"wins":11},"claude-fable-5-1":{"draws":8,"losses":74,"wins":4},"claude-haiku-5-5":{"draws":25,"losses":31,"wins":20},"claude-opus-4-5":{"draws":46,"losses":52,"wins":30},"claude-opus-4-8":{"draws":20,"losses":38,"wins":16},"claude-opus-5":{"draws":26,"losses":105,"wins":11},"claude-opus-5-5":{"draws":8,"losses":78,"wins":0},"claude-sonnet-5":{"draws":25,"losses":31,"wins":22},"claude-sonnet-5-5":{"draws":19,"losses":49,"wins":10},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":13},"deepseek/deepseek-v4-flash":{"draws":35,"losses":38,"wins":43},"deepseek/deepseek-v4-pro":{"draws":24,"losses":30,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":24,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":36,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":48,"wins":10},"elorian/glimpse":{"draws":12,"losses":19,"wins":11},"fireworks/ember-1":{"draws":28,"losses":36,"wins":14},"gemini-3.1-pro-preview":{"draws":23,"losses":33,"wins":22},"gemini-4-argon":{"draws":4,"losses":71,"wins":3},"google/gemini-3.1-flash-lite":{"draws":17,"losses":13,"wins":22},"google/gemini-3.5-flash":{"draws":28,"losses":41,"wins":29},"google/gemini-3.5-flash-lite":{"draws":49,"losses":29,"wins":58},"google/gemini-3.6-flash":{"draws":47,"losses":70,"wins":31},"google/gemini-3.8-flash":{"draws":31,"losses":39,"wins":8},"google/gemma-4-31b-it":{"draws":21,"losses":9,"wins":16},"gpt-4.1":{"draws":10,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":20,"losses":21,"wins":27},"gpt-5.4":{"draws":26,"losses":34,"wins":14},"gpt-5.4-mini":{"draws":21,"losses":14,"wins":17},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":37},"gpt-5.5":{"draws":33,"losses":30,"wins":9},"gpt-5.6-luna":{"draws":29,"losses":21,"wins":28},"gpt-5.6-sol":{"draws":14,"losses":55,"wins":9},"gpt-5.6-terra":{"draws":31,"losses":27,"wins":16},"gpt-6-astra":{"draws":11,"losses":67,"wins":0},"gpt-6-luna":{"draws":26,"losses":32,"wins":20},"gpt-6-sol":{"draws":15,"losses":58,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":68,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":12,"wins":16},"inception/mercury-3":{"draws":17,"losses":22,"wins":13},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":25,"wins":33},"meta/muse-glimmer-30b":{"draws":26,"losses":13,"wins":31},"meta/muse-spark-1.2":{"draws":21,"losses":42,"wins":13},"meta/muse-spark-1.3":{"draws":15,"losses":49,"wins":14},"meta/muse-spark-open":{"draws":17,"losses":40,"wins":17},"meta/muse-wonder":{"draws":15,"losses":51,"wins":12},"minimax/minimax-m3":{"draws":14,"losses":11,"wins":19},"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":18,"losses":12,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":6},"moonshotai/kimi-k3":{"draws":28,"losses":28,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":63,"wins":3},"nex-agi/nex-n2-pro":{"draws":12,"losses":13,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":14,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":16,"wins":7},"o3":{"draws":22,"losses":42,"wins":40},"openai/gpt-oss-120b":{"draws":22,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":27,"losses":22,"wins":27},"qwen/qwen3.7-max":{"draws":19,"losses":17,"wins":10},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":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":30,"losses":35,"wins":13},"qwen/qwen3.8-max-0902":{"draws":27,"losses":37,"wins":14},"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":71,"losses":126,"wins":45},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":17},"stepfun/step-3.7-flash":{"draws":18,"losses":12,"wins":22},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":31,"wins":19},"thinkingmachines/inkling":{"draws":31,"losses":26,"wins":47},"thinkingmachines/inkling-small":{"draws":31,"losses":16,"wins":31},"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":22,"losses":46,"wins":10},"x-ai/grok-4.7":{"draws":12,"losses":55,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.5":{"draws":48,"losses":33,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":15,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":26,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.2":{"draws":53,"losses":56,"wins":47},"z-ai/glm-5.3":{"draws":14,"losses":50,"wins":10},"z-ai/glm-5.3-flash":{"draws":22,"losses":42,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":48,"wins":14}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":15,"wins":72},"claude-fable-5":{"draws":23,"losses":83,"wins":32},"claude-fable-5-1":{"draws":9,"losses":135,"wins":12},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":54},"claude-opus-4-5":{"draws":63,"losses":58,"wins":103},"claude-opus-4-8":{"draws":30,"losses":46,"wins":50},"claude-opus-5":{"draws":25,"losses":174,"wins":35},"claude-opus-5-5":{"draws":12,"losses":125,"wins":13},"claude-sonnet-5":{"draws":40,"losses":34,"wins":64},"claude-sonnet-5-5":{"draws":24,"losses":67,"wins":47},"cohere/north-mini-code":{"draws":14,"losses":4,"wins":36},"deepseek/deepseek-v4-flash":{"draws":54,"losses":35,"wins":117},"deepseek/deepseek-v4-pro":{"draws":32,"losses":36,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":44,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":41,"wins":56},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":71,"wins":43},"elorian/glimpse":{"draws":13,"losses":33,"wins":30},"fireworks/ember-1":{"draws":40,"losses":44,"wins":54},"gemini-3.1-pro-preview":{"draws":33,"losses":40,"wins":65},"gemini-4-argon":{"draws":15,"losses":105,"wins":18},"google/gemini-3.1-flash-lite":{"draws":23,"losses":3,"wins":68},"google/gemini-3.5-flash":{"draws":39,"losses":47,"wins":88},"google/gemini-3.5-flash-lite":{"draws":63,"losses":48,"wins":133},"google/gemini-3.6-flash":{"draws":61,"losses":103,"wins":102},"google/gemini-3.8-flash":{"draws":31,"losses":53,"wins":54},"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":5,"losses":0,"wins":11},"gpt-5":{"draws":35,"losses":37,"wins":50},"gpt-5.4":{"draws":28,"losses":57,"wins":49},"gpt-5.4-mini":{"draws":34,"losses":11,"wins":47},"gpt-5.4-nano":{"draws":23,"losses":28,"wins":87},"gpt-5.5":{"draws":44,"losses":40,"wins":44},"gpt-5.6-luna":{"draws":43,"losses":26,"wins":69},"gpt-5.6-sol":{"draws":20,"losses":70,"wins":48},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":59},"gpt-6-astra":{"draws":9,"losses":124,"wins":5},"gpt-6-luna":{"draws":40,"losses":35,"wins":63},"gpt-6-sol":{"draws":19,"losses":92,"wins":27},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":39,"losses":8,"wins":49},"inception/mercury-3":{"draws":22,"losses":28,"wins":40},"inclusionai/ling-3.0-flash":{"draws":37,"losses":5,"wins":56},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":37,"losses":23,"wins":92},"meta/muse-glimmer-30b":{"draws":43,"losses":10,"wins":69},"meta/muse-spark-1.2":{"draws":19,"losses":53,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":60,"wins":50},"meta/muse-spark-open":{"draws":22,"losses":64,"wins":48},"meta/muse-wonder":{"draws":28,"losses":71,"wins":39},"minimax/minimax-m3":{"draws":15,"losses":7,"wins":52},"minimax/minimax-m3.1-flash":{"draws":26,"losses":41,"wins":55},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":36},"mistralai/mistral-medium-3-5":{"draws":25,"losses":7,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":33,"losses":44,"wins":55},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":16},"nex-agi/nex-n2-pro":{"draws":17,"losses":6,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":14,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":16,"wins":33},"o3":{"draws":30,"losses":61,"wins":105},"openai/gpt-oss-120b":{"draws":38,"losses":18,"wins":64},"poolside/laguna-s-2.1":{"draws":40,"losses":25,"wins":67},"qwen/qwen3.7-max":{"draws":18,"losses":18,"wins":44},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":46,"wins":52},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":45},"qwen/qwen3.8-flash":{"draws":24,"losses":28,"wins":40},"qwen/qwen3.8-max":{"draws":37,"losses":43,"wins":58},"qwen/qwen3.8-max-0902":{"draws":34,"losses":50,"wins":54},"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":102,"losses":157,"wins":199},"stealth/space-bunny-alpha":{"draws":33,"losses":26,"wins":51},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":63},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":31},"tencent/hy4-preview":{"draws":20,"losses":34,"wins":34},"thinkingmachines/inkling":{"draws":50,"losses":29,"wins":107},"thinkingmachines/inkling-small":{"draws":42,"losses":15,"wins":81},"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":30,"losses":55,"wins":53},"x-ai/grok-4.6":{"draws":43,"losses":62,"wins":33},"x-ai/grok-4.7":{"draws":12,"losses":74,"wins":34},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":24},"xiaomi/mimo-v2.5":{"draws":69,"losses":20,"wins":123},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":35,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":43,"wins":33},"z-ai/glm-5.2":{"draws":73,"losses":56,"wins":147},"z-ai/glm-5.3":{"draws":22,"losses":84,"wins":26},"z-ai/glm-5.3-flash":{"draws":25,"losses":63,"wins":50},"z-ai/glm-5.3-flashx":{"draws":31,"losses":50,"wins":57}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":61,"losses":71,"wins":46},"claude-fable-5":{"draws":38,"losses":142,"wins":12},"claude-fable-5-1":{"draws":9,"losses":209,"wins":0},"claude-haiku-5-5":{"draws":49,"losses":110,"wins":23},"claude-opus-4-5":{"draws":102,"losses":160,"wins":48},"claude-opus-4-8":{"draws":43,"losses":108,"wins":21},"claude-opus-5":{"draws":48,"losses":260,"wins":30},"claude-opus-5-5":{"draws":18,"losses":186,"wins":0},"claude-sonnet-5":{"draws":62,"losses":102,"wins":28},"claude-sonnet-5-5":{"draws":41,"losses":110,"wins":41},"cohere/north-mini-code":{"draws":18,"losses":21,"wins":33},"deepseek/deepseek-v4-flash":{"draws":94,"losses":92,"wins":98},"deepseek/deepseek-v4-pro":{"draws":56,"losses":93,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":75,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":63,"losses":99,"wins":30},"deepseek/deepseek-v4.1-flash-1017":{"draws":46,"losses":121,"wins":25},"elorian/glimpse":{"draws":27,"losses":53,"wins":26},"fireworks/ember-1":{"draws":58,"losses":108,"wins":26},"gemini-3.1-pro-preview":{"draws":57,"losses":87,"wins":48},"gemini-4-argon":{"draws":17,"losses":164,"wins":11},"google/gemini-3.1-flash-lite":{"draws":34,"losses":34,"wins":58},"google/gemini-3.5-flash":{"draws":57,"losses":135,"wins":48},"google/gemini-3.5-flash-lite":{"draws":92,"losses":133,"wins":113},"google/gemini-3.6-flash":{"draws":103,"losses":212,"wins":57},"google/gemini-3.8-flash":{"draws":50,"losses":123,"wins":19},"google/gemma-4-31b-it":{"draws":40,"losses":32,"wins":36},"gpt-4.1":{"draws":17,"losses":27,"wins":20},"gpt-4.1-nano":{"draws":14,"losses":1,"wins":7},"gpt-5":{"draws":40,"losses":93,"wins":39},"gpt-5.4":{"draws":49,"losses":108,"wins":29},"gpt-5.4-mini":{"draws":48,"losses":43,"wins":37},"gpt-5.4-nano":{"draws":42,"losses":77,"wins":69},"gpt-5.5":{"draws":55,"losses":98,"wins":27},"gpt-5.6-luna":{"draws":63,"losses":85,"wins":44},"gpt-5.6-sol":{"draws":28,"losses":147,"wins":17},"gpt-5.6-terra":{"draws":55,"losses":91,"wins":36},"gpt-6-astra":{"draws":11,"losses":178,"wins":3},"gpt-6-luna":{"draws":56,"losses":96,"wins":40},"gpt-6-sol":{"draws":25,"losses":154,"wins":13},"gpt-6.1-sol":{"draws":13,"losses":173,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":52,"losses":32,"wins":44},"inception/mercury-3":{"draws":43,"losses":53,"wins":26},"inclusionai/ling-3.0-flash":{"draws":51,"losses":27,"wins":52},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":54,"losses":75,"wins":77},"meta/muse-glimmer-30b":{"draws":60,"losses":58,"wins":56},"meta/muse-spark-1.2":{"draws":50,"losses":101,"wins":35},"meta/muse-spark-1.3":{"draws":33,"losses":141,"wins":18},"meta/muse-spark-open":{"draws":40,"losses":123,"wins":23},"meta/muse-wonder":{"draws":44,"losses":126,"wins":22},"minimax/minimax-m3":{"draws":26,"losses":34,"wins":44},"minimax/minimax-m3.1-flash":{"draws":41,"losses":80,"wins":52},"mistralai/mistral-large-4-0":{"draws":42,"losses":58,"wins":22},"mistralai/mistral-medium-3-5":{"draws":39,"losses":22,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":28,"wins":10},"moonshotai/kimi-k3":{"draws":53,"losses":94,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":162,"wins":2},"nex-agi/nex-n2-pro":{"draws":26,"losses":28,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":17,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":59,"wins":51},"nvidia/nemotron-3.5-super-vl":{"draws":25,"losses":42,"wins":19},"o3":{"draws":42,"losses":167,"wins":57},"openai/gpt-oss-120b":{"draws":47,"losses":56,"wins":65},"poolside/laguna-s-2.1":{"draws":58,"losses":75,"wins":55},"qwen/qwen3.7-max":{"draws":34,"losses":59,"wins":17},"qwen/qwen3.7-plus":{"draws":27,"losses":38,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":108,"wins":25},"qwen/qwen3.8-27b":{"draws":37,"losses":71,"wins":30},"qwen/qwen3.8-flash":{"draws":43,"losses":60,"wins":25},"qwen/qwen3.8-max":{"draws":61,"losses":98,"wins":33},"qwen/qwen3.8-max-0902":{"draws":54,"losses":108,"wins":30},"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":164,"losses":374,"wins":120},"stealth/space-bunny-alpha":{"draws":50,"losses":60,"wins":44},"stepfun/step-3.7-flash":{"draws":38,"losses":62,"wins":38},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":31,"losses":47,"wins":26},"tencent/hy4-preview":{"draws":50,"losses":107,"wins":29},"thinkingmachines/inkling":{"draws":68,"losses":68,"wins":68},"thinkingmachines/inkling-small":{"draws":70,"losses":47,"wins":75},"unbiased/pareto-26.10":{"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":53,"losses":115,"wins":24},"x-ai/grok-4.6":{"draws":64,"losses":107,"wins":21},"x-ai/grok-4.7":{"draws":21,"losses":134,"wins":13},"x-ai/grok-build-0.1":{"draws":22,"losses":26,"wins":16},"xiaomi/mimo-v2.5":{"draws":96,"losses":112,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":58,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":29,"losses":69,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":89,"wins":14},"z-ai/glm-5.2":{"draws":118,"losses":172,"wins":94},"z-ai/glm-5.3":{"draws":35,"losses":127,"wins":20},"z-ai/glm-5.3-flash":{"draws":40,"losses":121,"wins":31},"z-ai/glm-5.3-flashx":{"draws":44,"losses":123,"wins":25}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":48,"losses":54,"wins":30},"claude-fable-5":{"draws":27,"losses":103,"wins":14},"claude-fable-5-1":{"draws":8,"losses":154,"wins":0},"claude-haiku-5-5":{"draws":33,"losses":92,"wins":13},"claude-opus-4-5":{"draws":77,"losses":124,"wins":33},"claude-opus-4-8":{"draws":39,"losses":81,"wins":12},"claude-opus-5":{"draws":37,"losses":199,"wins":10},"claude-opus-5-5":{"draws":10,"losses":146,"wins":0},"claude-sonnet-5":{"draws":47,"losses":73,"wins":24},"claude-sonnet-5-5":{"draws":32,"losses":91,"wins":21},"cohere/north-mini-code":{"draws":15,"losses":17,"wins":22},"deepseek/deepseek-v4-flash":{"draws":87,"losses":81,"wins":48},"deepseek/deepseek-v4-pro":{"draws":45,"losses":67,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":68,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":79,"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":45,"losses":79,"wins":20},"gemini-3.1-pro-preview":{"draws":45,"losses":71,"wins":28},"gemini-4-argon":{"draws":16,"losses":124,"wins":4},"google/gemini-3.1-flash-lite":{"draws":33,"losses":28,"wins":35},"google/gemini-3.5-flash":{"draws":48,"losses":99,"wins":33},"google/gemini-3.5-flash-lite":{"draws":81,"losses":97,"wins":74},"google/gemini-3.6-flash":{"draws":83,"losses":147,"wins":46},"google/gemini-3.8-flash":{"draws":37,"losses":88,"wins":19},"google/gemma-4-31b-it":{"draws":35,"losses":24,"wins":25},"gpt-4.1":{"draws":15,"losses":20,"wins":13},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":44,"losses":61,"wins":21},"gpt-5.4":{"draws":38,"losses":83,"wins":17},"gpt-5.4-mini":{"draws":41,"losses":31,"wins":24},"gpt-5.4-nano":{"draws":45,"losses":58,"wins":41},"gpt-5.5":{"draws":46,"losses":66,"wins":20},"gpt-5.6-luna":{"draws":58,"losses":49,"wins":37},"gpt-5.6-sol":{"draws":22,"losses":109,"wins":13},"gpt-5.6-terra":{"draws":45,"losses":71,"wins":22},"gpt-6-astra":{"draws":9,"losses":135,"wins":0},"gpt-6-luna":{"draws":40,"losses":72,"wins":32},"gpt-6-sol":{"draws":18,"losses":118,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":138,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":47,"losses":24,"wins":31},"inception/mercury-3":{"draws":29,"losses":52,"wins":15},"inclusionai/ling-3.0-flash":{"draws":46,"losses":23,"wins":33},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":49,"losses":59,"wins":48},"meta/muse-glimmer-30b":{"draws":54,"losses":46,"wins":26},"meta/muse-spark-1.2":{"draws":36,"losses":75,"wins":27},"meta/muse-spark-1.3":{"draws":35,"losses":95,"wins":14},"meta/muse-spark-open":{"draws":30,"losses":93,"wins":15},"meta/muse-wonder":{"draws":33,"losses":96,"wins":15},"minimax/minimax-m3":{"draws":21,"losses":37,"wins":20},"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":37,"losses":16,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":46,"losses":71,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":122,"wins":5},"nex-agi/nex-n2-pro":{"draws":22,"losses":19,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":10,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":40,"wins":35},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":38,"wins":9},"o3":{"draws":38,"losses":116,"wins":44},"openai/gpt-oss-120b":{"draws":48,"losses":47,"wins":31},"poolside/laguna-s-2.1":{"draws":49,"losses":65,"wins":24},"qwen/qwen3.7-max":{"draws":30,"losses":37,"wins":17},"qwen/qwen3.7-plus":{"draws":26,"losses":21,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":82,"wins":17},"qwen/qwen3.8-27b":{"draws":29,"losses":57,"wins":16},"qwen/qwen3.8-flash":{"draws":36,"losses":40,"wins":20},"qwen/qwen3.8-max":{"draws":42,"losses":63,"wins":39},"qwen/qwen3.8-max-0902":{"draws":47,"losses":81,"wins":16},"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":126,"losses":275,"wins":73},"stealth/space-bunny-alpha":{"draws":38,"losses":47,"wins":29},"stepfun/step-3.7-flash":{"draws":28,"losses":37,"wins":37},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":31,"losses":31,"wins":16},"tencent/hy4-preview":{"draws":42,"losses":81,"wins":15},"thinkingmachines/inkling":{"draws":70,"losses":75,"wins":47},"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":41,"losses":86,"wins":17},"x-ai/grok-4.7":{"draws":15,"losses":109,"wins":2},"x-ai/grok-build-0.1":{"draws":20,"losses":14,"wins":14},"xiaomi/mimo-v2.5":{"draws":85,"losses":75,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":35,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":56,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":71,"wins":12},"z-ai/glm-5.2":{"draws":104,"losses":126,"wins":58},"z-ai/glm-5.3":{"draws":25,"losses":103,"wins":10},"z-ai/glm-5.3-flash":{"draws":32,"losses":91,"wins":21},"z-ai/glm-5.3-flashx":{"draws":32,"losses":89,"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},"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":2},"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":2,"losses":2,"wins":42},"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":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":1,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":15,"wins":26},"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":40},"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":4},"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":0,"losses":1,"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":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"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":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":0,"losses":2,"wins":30},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"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":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":16,"wins":25},"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":41},"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":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"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":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"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":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":14,"wins":15},"claude-fable-5":{"draws":4,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":27,"wins":4},"claude-opus-4-5":{"draws":9,"losses":39,"wins":12},"claude-opus-4-8":{"draws":6,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":40,"wins":1},"claude-opus-5-5":{"draws":2,"losses":34,"wins":0},"claude-sonnet-5":{"draws":6,"losses":22,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":26,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":28,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":26,"wins":4},"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":20,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":14,"losses":49,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":11},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":4,"losses":23,"wins":3},"gpt-5.4":{"draws":3,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":15},"gpt-5.5":{"draws":5,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":32,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":25,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":1,"losses":25,"wins":10},"gpt-6-sol":{"draws":1,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":11},"inception/mercury-3":{"draws":2,"losses":15,"wins":3},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":17,"wins":16},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":26,"wins":8},"meta/muse-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":6,"wins":2},"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":3,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":13,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":2},"o3":{"draws":10,"losses":39,"wins":13},"openai/gpt-oss-120b":{"draws":6,"losses":11,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":26,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":22,"wins":9},"qwen/qwen3.8-max-0902":{"draws":2,"losses":29,"wins":5},"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},"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":16,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":48,"wins":16},"z-ai/glm-5.3":{"draws":2,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":22,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":18,"wins":84},"claude-fable-5":{"draws":23,"losses":74,"wins":47},"claude-fable-5-1":{"draws":10,"losses":142,"wins":10},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":60},"claude-opus-4-5":{"draws":64,"losses":64,"wins":106},"claude-opus-4-8":{"draws":35,"losses":46,"wins":51},"claude-opus-5":{"draws":38,"losses":166,"wins":42},"claude-opus-5-5":{"draws":17,"losses":123,"wins":16},"claude-sonnet-5":{"draws":38,"losses":34,"wins":72},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":43},"deepseek/deepseek-v4-flash":{"draws":39,"losses":33,"wins":144},"deepseek/deepseek-v4-pro":{"draws":34,"losses":39,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":44,"wins":59},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":48,"wins":65},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":61,"wins":56},"elorian/glimpse":{"draws":14,"losses":28,"wins":36},"fireworks/ember-1":{"draws":33,"losses":40,"wins":71},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":73},"gemini-4-argon":{"draws":10,"losses":108,"wins":26},"google/gemini-3.1-flash-lite":{"draws":19,"losses":2,"wins":75},"google/gemini-3.5-flash":{"draws":31,"losses":63,"wins":86},"google/gemini-3.5-flash-lite":{"draws":64,"losses":46,"wins":142},"google/gemini-3.6-flash":{"draws":59,"losses":102,"wins":115},"google/gemini-3.8-flash":{"draws":24,"losses":51,"wins":69},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":55},"gpt-4.1":{"draws":11,"losses":9,"wins":28},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":25,"losses":34,"wins":67},"gpt-5.4":{"draws":33,"losses":59,"wins":46},"gpt-5.4-mini":{"draws":30,"losses":14,"wins":52},"gpt-5.4-nano":{"draws":30,"losses":30,"wins":84},"gpt-5.5":{"draws":35,"losses":45,"wins":52},"gpt-5.6-luna":{"draws":37,"losses":35,"wins":72},"gpt-5.6-sol":{"draws":19,"losses":82,"wins":43},"gpt-5.6-terra":{"draws":40,"losses":30,"wins":68},"gpt-6-astra":{"draws":9,"losses":121,"wins":14},"gpt-6-luna":{"draws":34,"losses":45,"wins":65},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":10,"losses":118,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":4,"wins":64},"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":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":30,"losses":24,"wins":102},"meta/muse-glimmer-30b":{"draws":31,"losses":14,"wins":81},"meta/muse-spark-1.2":{"draws":33,"losses":36,"wins":69},"meta/muse-spark-1.3":{"draws":23,"losses":61,"wins":60},"meta/muse-spark-open":{"draws":28,"losses":49,"wins":61},"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":21,"losses":7,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":4,"wins":23},"moonshotai/kimi-k3":{"draws":30,"losses":45,"wins":63},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":98,"wins":21},"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":31,"losses":11,"wins":84},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":10,"wins":37},"o3":{"draws":21,"losses":57,"wins":120},"openai/gpt-oss-120b":{"draws":34,"losses":13,"wins":79},"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":48,"wins":62},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":25,"losses":27,"wins":44},"qwen/qwen3.8-max":{"draws":32,"losses":47,"wins":65},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":61},"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":100,"losses":168,"wins":206},"stealth/space-bunny-alpha":{"draws":31,"losses":20,"wins":63},"stepfun/step-3.7-flash":{"draws":12,"losses":19,"wins":71},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":24,"losses":7,"wins":47},"tencent/hy4-preview":{"draws":30,"losses":53,"wins":55},"thinkingmachines/inkling":{"draws":53,"losses":24,"wins":115},"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":32,"losses":32,"wins":32},"x-ai/grok-4.6":{"draws":42,"losses":54,"wins":48},"x-ai/grok-4.7":{"draws":16,"losses":82,"wins":28},"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":13,"losses":22,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":32,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":71,"losses":59,"wins":158},"z-ai/glm-5.3":{"draws":27,"losses":79,"wins":32},"z-ai/glm-5.3-flash":{"draws":20,"losses":64,"wins":60},"z-ai/glm-5.3-flashx":{"draws":25,"losses":61,"wins":58}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":15,"wins":82},"claude-fable-5":{"draws":33,"losses":61,"wins":50},"claude-fable-5-1":{"draws":9,"losses":130,"wins":23},"claude-haiku-5-5":{"draws":36,"losses":42,"wins":60},"claude-opus-4-5":{"draws":59,"losses":53,"wins":122},"claude-opus-4-8":{"draws":31,"losses":43,"wins":58},"claude-opus-5":{"draws":37,"losses":159,"wins":49},"claude-opus-5-5":{"draws":17,"losses":124,"wins":15},"claude-sonnet-5":{"draws":39,"losses":32,"wins":73},"claude-sonnet-5-5":{"draws":24,"losses":61,"wins":59},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":41},"deepseek/deepseek-v4-flash":{"draws":54,"losses":22,"wins":140},"deepseek/deepseek-v4-pro":{"draws":33,"losses":26,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":29,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":44,"wins":59},"deepseek/deepseek-v4.1-flash-1017":{"draws":40,"losses":57,"wins":47},"elorian/glimpse":{"draws":20,"losses":25,"wins":33},"fireworks/ember-1":{"draws":38,"losses":43,"wins":63},"gemini-3.1-pro-preview":{"draws":40,"losses":28,"wins":76},"gemini-4-argon":{"draws":19,"losses":105,"wins":20},"google/gemini-3.1-flash-lite":{"draws":19,"losses":4,"wins":73},"google/gemini-3.5-flash":{"draws":47,"losses":37,"wins":96},"google/gemini-3.5-flash-lite":{"draws":62,"losses":34,"wins":156},"google/gemini-3.6-flash":{"draws":70,"losses":82,"wins":124},"google/gemini-3.8-flash":{"draws":40,"losses":52,"wins":52},"google/gemma-4-31b-it":{"draws":24,"losses":6,"wins":54},"gpt-4.1":{"draws":19,"losses":6,"wins":23},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":35,"losses":19,"wins":72},"gpt-5.4":{"draws":36,"losses":47,"wins":55},"gpt-5.4-mini":{"draws":32,"losses":14,"wins":50},"gpt-5.4-nano":{"draws":24,"losses":25,"wins":95},"gpt-5.5":{"draws":42,"losses":36,"wins":54},"gpt-5.6-luna":{"draws":37,"losses":21,"wins":86},"gpt-5.6-sol":{"draws":28,"losses":59,"wins":57},"gpt-5.6-terra":{"draws":46,"losses":21,"wins":71},"gpt-6-astra":{"draws":11,"losses":120,"wins":13},"gpt-6-luna":{"draws":38,"losses":24,"wins":82},"gpt-6-sol":{"draws":20,"losses":92,"wins":32},"gpt-6.1-sol":{"draws":16,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":64},"inception/mercury-3":{"draws":29,"losses":19,"wins":48},"inclusionai/ling-3.0-flash":{"draws":35,"losses":5,"wins":62},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":36,"losses":22,"wins":98},"meta/muse-glimmer-30b":{"draws":40,"losses":8,"wins":78},"meta/muse-spark-1.2":{"draws":30,"losses":31,"wins":77},"meta/muse-spark-1.3":{"draws":34,"losses":53,"wins":57},"meta/muse-spark-open":{"draws":30,"losses":43,"wins":65},"meta/muse-wonder":{"draws":41,"losses":62,"wins":41},"minimax/minimax-m3":{"draws":16,"losses":4,"wins":58},"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":27,"losses":6,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":8,"wins":18},"moonshotai/kimi-k3":{"draws":34,"losses":34,"wins":70},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":104,"wins":24},"nex-agi/nex-n2-pro":{"draws":18,"losses":4,"wins":50},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":3,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":12,"wins":67},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":10,"wins":42},"o3":{"draws":36,"losses":44,"wins":118},"openai/gpt-oss-120b":{"draws":37,"losses":10,"wins":79},"poolside/laguna-s-2.1":{"draws":36,"losses":16,"wins":86},"qwen/qwen3.7-max":{"draws":21,"losses":16,"wins":47},"qwen/qwen3.7-plus":{"draws":21,"losses":7,"wins":44},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":49,"wins":61},"qwen/qwen3.8-27b":{"draws":27,"losses":23,"wins":52},"qwen/qwen3.8-flash":{"draws":35,"losses":16,"wins":45},"qwen/qwen3.8-max":{"draws":40,"losses":40,"wins":64},"qwen/qwen3.8-max-0902":{"draws":44,"losses":34,"wins":66},"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":136,"losses":143,"wins":195},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":67},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":10,"wins":46},"tencent/hy4-preview":{"draws":43,"losses":33,"wins":62},"thinkingmachines/inkling":{"draws":64,"losses":21,"wins":107},"thinkingmachines/inkling-small":{"draws":41,"losses":17,"wins":86},"unbiased/pareto-26.10":{"draws":6,"losses":40,"wins":2},"unbiased/pareto-26.10-preview":{"draws":4,"losses":40,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":42,"losses":48,"wins":54},"x-ai/grok-4.6":{"draws":38,"losses":29,"wins":29},"x-ai/grok-4.7":{"draws":15,"losses":80,"wins":31},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":27},"xiaomi/mimo-v2.5":{"draws":74,"losses":20,"wins":128},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":10,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":31,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":41,"wins":34},"z-ai/glm-5.2":{"draws":78,"losses":50,"wins":160},"z-ai/glm-5.3":{"draws":29,"losses":66,"wins":43},"z-ai/glm-5.3-flash":{"draws":36,"losses":49,"wins":59},"z-ai/glm-5.3-flashx":{"draws":33,"losses":52,"wins":59}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":17,"wins":91},"claude-fable-5":{"draws":7,"losses":42,"wins":77},"claude-fable-5-1":{"draws":6,"losses":98,"wins":36},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":90},"claude-opus-4-5":{"draws":16,"losses":34,"wins":156},"claude-opus-4-8":{"draws":15,"losses":31,"wins":72},"claude-opus-5":{"draws":20,"losses":102,"wins":98},"claude-opus-5-5":{"draws":11,"losses":98,"wins":29},"claude-sonnet-5":{"draws":12,"losses":24,"wins":90},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":64},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":45},"deepseek/deepseek-v4-flash":{"draws":19,"losses":15,"wins":158},"deepseek/deepseek-v4-pro":{"draws":10,"losses":21,"wins":85},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":23,"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":14,"losses":24,"wins":88},"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":14,"losses":23,"wins":121},"google/gemini-3.5-flash-lite":{"draws":20,"losses":28,"wins":170},"google/gemini-3.6-flash":{"draws":15,"losses":55,"wins":170},"google/gemini-3.8-flash":{"draws":12,"losses":26,"wins":88},"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":16,"losses":11,"wins":105},"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":41,"wins":69},"gpt-5.6-terra":{"draws":12,"losses":21,"wins":87},"gpt-6-astra":{"draws":10,"losses":94,"wins":22},"gpt-6-luna":{"draws":10,"losses":20,"wins":96},"gpt-6-sol":{"draws":13,"losses":53,"wins":60},"gpt-6.1-sol":{"draws":7,"losses":79,"wins":40},"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":0,"losses":0,"wins":6},"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":9,"losses":28,"wins":85},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":83},"meta/muse-spark-open":{"draws":9,"losses":26,"wins":85},"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":3,"losses":8,"wins":23},"moonshotai/kimi-k3":{"draws":10,"losses":27,"wins":85},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":69,"wins":42},"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":9,"wins":99},"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":15,"wins":51},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":30,"wins":87},"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":26,"wins":89},"qwen/qwen3.8-max-0902":{"draws":19,"losses":28,"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":44,"losses":75,"wins":281},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":73},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":75},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":12,"losses":3,"wins":55},"tencent/hy4-preview":{"draws":12,"losses":34,"wins":74},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":134},"thinkingmachines/inkling-small":{"draws":15,"losses":2,"wins":109},"unbiased/pareto-26.10":{"draws":5,"losses":27,"wins":10},"unbiased/pareto-26.10-preview":{"draws":3,"losses":31,"wins":8},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":23},"x-ai/grok-4.5":{"draws":16,"losses":28,"wins":82},"x-ai/grok-4.6":{"draws":15,"losses":31,"wins":80},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":35},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":35},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":55},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":58},"z-ai/glm-5.2":{"draws":29,"losses":37,"wins":186},"z-ai/glm-5.3":{"draws":17,"losses":33,"wins":70},"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":16,"losses":18,"wins":10},"claude-fable-5":{"draws":10,"losses":32,"wins":6},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":39,"wins":12},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":15,"losses":64,"wins":3},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":26,"wins":19},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"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":17,"losses":19,"wins":12},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":33,"wins":8},"google/gemini-3.5-flash-lite":{"draws":33,"losses":27,"wins":24},"google/gemini-3.6-flash":{"draws":31,"losses":56,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":18,"wins":9},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":24,"wins":14},"gpt-5.5":{"draws":23,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":24,"wins":5},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":8},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":10,"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":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":37,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":9,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":13,"losses":38,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":21,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":15,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":9},"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":38,"losses":101,"wins":19},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":26},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":14},"unbiased/pareto-26.10":{"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":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":33,"losses":19,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":42,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":72,"losses":80,"wins":52},"claude-fable-5":{"draws":42,"losses":174,"wins":6},"claude-fable-5-1":{"draws":13,"losses":226,"wins":5},"claude-haiku-5-5":{"draws":56,"losses":133,"wins":31},"claude-opus-4-5":{"draws":130,"losses":183,"wins":55},"claude-opus-4-8":{"draws":62,"losses":132,"wins":24},"claude-opus-5":{"draws":58,"losses":297,"wins":23},"claude-opus-5-5":{"draws":11,"losses":227,"wins":4},"claude-sonnet-5":{"draws":81,"losses":103,"wins":38},"claude-sonnet-5-5":{"draws":49,"losses":146,"wins":27},"cohere/north-mini-code":{"draws":21,"losses":28,"wins":31},"deepseek/deepseek-v4-flash":{"draws":117,"losses":109,"wins":108},"deepseek/deepseek-v4-pro":{"draws":73,"losses":98,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":64,"losses":98,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":75,"losses":118,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":47,"losses":159,"wins":16},"elorian/glimpse":{"draws":34,"losses":64,"wins":20},"fireworks/ember-1":{"draws":74,"losses":114,"wins":34},"gemini-3.1-pro-preview":{"draws":74,"losses":99,"wins":49},"gemini-4-argon":{"draws":16,"losses":205,"wins":1},"google/gemini-3.1-flash-lite":{"draws":58,"losses":34,"wins":70},"google/gemini-3.5-flash":{"draws":83,"losses":151,"wins":50},"google/gemini-3.5-flash-lite":{"draws":124,"losses":137,"wins":131},"google/gemini-3.6-flash":{"draws":129,"losses":244,"wins":51},"google/gemini-3.8-flash":{"draws":60,"losses":142,"wins":20},"google/gemma-4-31b-it":{"draws":61,"losses":32,"wins":41},"gpt-4.1":{"draws":30,"losses":28,"wins":16},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":9},"gpt-5":{"draws":58,"losses":93,"wins":39},"gpt-5.4":{"draws":55,"losses":136,"wins":21},"gpt-5.4-mini":{"draws":56,"losses":53,"wins":39},"gpt-5.4-nano":{"draws":56,"losses":106,"wins":74},"gpt-5.5":{"draws":84,"losses":98,"wins":20},"gpt-5.6-luna":{"draws":90,"losses":85,"wins":47},"gpt-5.6-sol":{"draws":36,"losses":174,"wins":12},"gpt-5.6-terra":{"draws":78,"losses":118,"wins":16},"gpt-6-astra":{"draws":13,"losses":207,"wins":2},"gpt-6-luna":{"draws":79,"losses":114,"wins":29},"gpt-6-sol":{"draws":35,"losses":170,"wins":17},"gpt-6.1-sol":{"draws":18,"losses":196,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":78,"losses":21,"wins":67},"inception/mercury-3":{"draws":52,"losses":70,"wins":24},"inclusionai/ling-3.0-flash":{"draws":72,"losses":34,"wins":54},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":74,"losses":83,"wins":81},"meta/muse-glimmer-30b":{"draws":80,"losses":62,"wins":50},"meta/muse-spark-1.2":{"draws":62,"losses":123,"wins":27},"meta/muse-spark-1.3":{"draws":56,"losses":147,"wins":19},"meta/muse-spark-open":{"draws":53,"losses":140,"wins":19},"meta/muse-wonder":{"draws":45,"losses":160,"wins":17},"minimax/minimax-m3":{"draws":39,"losses":41,"wins":44},"minimax/minimax-m3.1-flash":{"draws":46,"losses":91,"wins":55},"mistralai/mistral-large-4-0":{"draws":58,"losses":61,"wins":19},"mistralai/mistral-medium-3-5":{"draws":58,"losses":25,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":30,"wins":11},"moonshotai/kimi-k3":{"draws":74,"losses":105,"wins":33},"moonshotai/kimi-k3.1-pro":{"draws":26,"losses":190,"wins":4},"nex-agi/nex-n2-pro":{"draws":30,"losses":26,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":11,"losses":18,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":85,"losses":65,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":47,"wins":24},"o3":{"draws":58,"losses":195,"wins":63},"openai/gpt-oss-120b":{"draws":66,"losses":68,"wins":54},"poolside/laguna-s-2.1":{"draws":64,"losses":81,"wins":57},"qwen/qwen3.7-max":{"draws":53,"losses":54,"wins":27},"qwen/qwen3.7-plus":{"draws":42,"losses":43,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":88,"losses":109,"wins":25},"qwen/qwen3.8-27b":{"draws":44,"losses":87,"wins":29},"qwen/qwen3.8-flash":{"draws":57,"losses":60,"wins":31},"qwen/qwen3.8-max":{"draws":76,"losses":105,"wins":41},"qwen/qwen3.8-max-0902":{"draws":83,"losses":111,"wins":28},"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":171,"losses":379,"wins":96},"stealth/space-bunny-alpha":{"draws":71,"losses":69,"wins":38},"stepfun/step-3.7-flash":{"draws":44,"losses":58,"wins":54},"stepfun/step-5-preview":{"draws":8,"losses":12,"wins":0},"tencent/hy3-preview":{"draws":48,"losses":47,"wins":33},"tencent/hy4-preview":{"draws":69,"losses":123,"wins":20},"thinkingmachines/inkling":{"draws":96,"losses":82,"wins":112},"thinkingmachines/inkling-small":{"draws":85,"losses":62,"wins":75},"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":16,"losses":30,"wins":16},"x-ai/grok-4.5":{"draws":59,"losses":145,"wins":18},"x-ai/grok-4.6":{"draws":74,"losses":128,"wins":20},"x-ai/grok-4.7":{"draws":22,"losses":160,"wins":16},"x-ai/grok-build-0.1":{"draws":33,"losses":22,"wins":19},"xiaomi/mimo-v2.5":{"draws":120,"losses":92,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":40,"losses":59,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":37,"losses":84,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":36,"losses":98,"wins":14},"z-ai/glm-5.2":{"draws":166,"losses":188,"wins":90},"z-ai/glm-5.3":{"draws":47,"losses":159,"wins":4},"z-ai/glm-5.3-flash":{"draws":52,"losses":133,"wins":37},"z-ai/glm-5.3-flashx":{"draws":72,"losses":134,"wins":16}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":24,"wins":24},"claude-fable-5":{"draws":8,"losses":65,"wins":5},"claude-fable-5-1":{"draws":2,"losses":84,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":41,"wins":18},"claude-opus-4-5":{"draws":31,"losses":59,"wins":38},"claude-opus-4-8":{"draws":16,"losses":43,"wins":15},"claude-opus-5":{"draws":12,"losses":111,"wins":5},"claude-opus-5-5":{"draws":3,"losses":82,"wins":1},"claude-sonnet-5":{"draws":11,"losses":46,"wins":21},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":15},"deepseek/deepseek-v4-flash":{"draws":34,"losses":40,"wins":46},"deepseek/deepseek-v4-pro":{"draws":11,"losses":39,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":38,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":37,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":54,"wins":14},"elorian/glimpse":{"draws":6,"losses":22,"wins":14},"fireworks/ember-1":{"draws":22,"losses":36,"wins":20},"gemini-3.1-pro-preview":{"draws":18,"losses":34,"wins":26},"gemini-4-argon":{"draws":2,"losses":72,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":46},"google/gemini-3.5-flash":{"draws":19,"losses":51,"wins":30},"google/gemini-3.5-flash-lite":{"draws":39,"losses":50,"wins":49},"google/gemini-3.6-flash":{"draws":31,"losses":88,"wins":31},"google/gemini-3.8-flash":{"draws":15,"losses":51,"wins":12},"google/gemma-4-31b-it":{"draws":19,"losses":5,"wins":22},"gpt-4.1":{"draws":7,"losses":12,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":18,"losses":31,"wins":21},"gpt-5.4":{"draws":11,"losses":51,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":22,"wins":18},"gpt-5.4-nano":{"draws":14,"losses":35,"wins":37},"gpt-5.5":{"draws":20,"losses":38,"wins":14},"gpt-5.6-luna":{"draws":28,"losses":23,"wins":27},"gpt-5.6-sol":{"draws":10,"losses":54,"wins":14},"gpt-5.6-terra":{"draws":16,"losses":46,"wins":12},"gpt-6-astra":{"draws":3,"losses":74,"wins":1},"gpt-6-luna":{"draws":18,"losses":41,"wins":19},"gpt-6-sol":{"draws":5,"losses":64,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":70,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":12,"wins":25},"inception/mercury-3":{"draws":13,"losses":25,"wins":14},"inclusionai/ling-3.0-flash":{"draws":18,"losses":11,"wins":27},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":24,"wins":42},"meta/muse-glimmer-30b":{"draws":21,"losses":19,"wins":28},"meta/muse-spark-1.2":{"draws":10,"losses":43,"wins":21},"meta/muse-spark-1.3":{"draws":10,"losses":54,"wins":14},"meta/muse-spark-open":{"draws":14,"losses":51,"wins":11},"meta/muse-wonder":{"draws":7,"losses":56,"wins":15},"minimax/minimax-m3":{"draws":9,"losses":14,"wins":21},"minimax/minimax-m3.1-flash":{"draws":9,"losses":30,"wins":29},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":13,"losses":8,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":35,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":65,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":12,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":18,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":19,"wins":10},"o3":{"draws":16,"losses":62,"wins":44},"openai/gpt-oss-120b":{"draws":18,"losses":23,"wins":27},"poolside/laguna-s-2.1":{"draws":17,"losses":34,"wins":25},"qwen/qwen3.7-max":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":9,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":44,"wins":19},"qwen/qwen3.8-27b":{"draws":10,"losses":26,"wins":20},"qwen/qwen3.8-flash":{"draws":11,"losses":28,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":44,"wins":24},"qwen/qwen3.8-max-0902":{"draws":15,"losses":43,"wins":20},"recursive/flint-v1.0":{"draws":3,"losses":7,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":37,"wins":21},"stealth/ox-alpha":{"draws":44,"losses":139,"wins":59},"stealth/space-bunny-alpha":{"draws":22,"losses":25,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":14,"wins":15},"tencent/hy4-preview":{"draws":16,"losses":45,"wins":15},"thinkingmachines/inkling":{"draws":22,"losses":24,"wins":58},"thinkingmachines/inkling-small":{"draws":24,"losses":19,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":25,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":13,"losses":43,"wins":22},"x-ai/grok-4.6":{"draws":18,"losses":50,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":60,"wins":7},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":40,"losses":25,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":29,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":29,"wins":16},"z-ai/glm-5.2":{"draws":46,"losses":61,"wins":49},"z-ai/glm-5.3":{"draws":15,"losses":55,"wins":4},"z-ai/glm-5.3-flash":{"draws":9,"losses":55,"wins":14},"z-ai/glm-5.3-flashx":{"draws":20,"losses":42,"wins":16}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":49},"claude-fable-5":{"draws":18,"losses":50,"wins":22},"claude-fable-5-1":{"draws":6,"losses":83,"wins":11},"claude-haiku-5-5":{"draws":21,"losses":38,"wins":27},"claude-opus-4-5":{"draws":33,"losses":45,"wins":68},"claude-opus-4-8":{"draws":16,"losses":28,"wins":38},"claude-opus-5":{"draws":16,"losses":119,"wins":17},"claude-opus-5-5":{"draws":9,"losses":87,"wins":2},"claude-sonnet-5":{"draws":16,"losses":25,"wins":49},"claude-sonnet-5-5":{"draws":10,"losses":46,"wins":34},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":23},"deepseek/deepseek-v4-flash":{"draws":31,"losses":26,"wins":81},"deepseek/deepseek-v4-pro":{"draws":19,"losses":28,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":37,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":35,"wins":30},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":53,"wins":22},"elorian/glimpse":{"draws":5,"losses":17,"wins":26},"fireworks/ember-1":{"draws":13,"losses":36,"wins":41},"gemini-3.1-pro-preview":{"draws":17,"losses":31,"wins":42},"gemini-4-argon":{"draws":3,"losses":79,"wins":8},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":43},"google/gemini-3.5-flash":{"draws":18,"losses":43,"wins":51},"google/gemini-3.5-flash-lite":{"draws":28,"losses":22,"wins":106},"google/gemini-3.6-flash":{"draws":23,"losses":76,"wins":73},"google/gemini-3.8-flash":{"draws":20,"losses":41,"wins":29},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":32},"gpt-4.1":{"draws":10,"losses":4,"wins":16},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":16,"losses":26,"wins":38},"gpt-5.4":{"draws":21,"losses":38,"wins":27},"gpt-5.4-mini":{"draws":13,"losses":15,"wins":32},"gpt-5.4-nano":{"draws":24,"losses":20,"wins":50},"gpt-5.5":{"draws":25,"losses":34,"wins":23},"gpt-5.6-luna":{"draws":23,"losses":26,"wins":41},"gpt-5.6-sol":{"draws":9,"losses":62,"wins":19},"gpt-5.6-terra":{"draws":21,"losses":37,"wins":28},"gpt-6-astra":{"draws":3,"losses":81,"wins":6},"gpt-6-luna":{"draws":22,"losses":32,"wins":36},"gpt-6-sol":{"draws":9,"losses":62,"wins":19},"gpt-6.1-sol":{"draws":4,"losses":79,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":41},"inception/mercury-3":{"draws":12,"losses":28,"wins":22},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":41},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":18,"wins":55},"meta/muse-glimmer-30b":{"draws":19,"losses":16,"wins":43},"meta/muse-spark-1.2":{"draws":11,"losses":47,"wins":28},"meta/muse-spark-1.3":{"draws":13,"losses":51,"wins":26},"meta/muse-spark-open":{"draws":10,"losses":47,"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":12,"losses":7,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":11},"moonshotai/kimi-k3":{"draws":23,"losses":31,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":70,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":15,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":18},"o3":{"draws":18,"losses":37,"wins":73},"openai/gpt-oss-120b":{"draws":20,"losses":7,"wins":53},"poolside/laguna-s-2.1":{"draws":22,"losses":13,"wins":55},"qwen/qwen3.7-max":{"draws":14,"losses":12,"wins":28},"qwen/qwen3.7-plus":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":33,"wins":35},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":26},"qwen/qwen3.8-flash":{"draws":14,"losses":24,"wins":22},"qwen/qwen3.8-max":{"draws":21,"losses":33,"wins":36},"qwen/qwen3.8-max-0902":{"draws":18,"losses":35,"wins":37},"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":55,"losses":132,"wins":111},"stealth/space-bunny-alpha":{"draws":18,"losses":15,"wins":37},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":44},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":26},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":35},"thinkingmachines/inkling":{"draws":29,"losses":22,"wins":69},"thinkingmachines/inkling-small":{"draws":25,"losses":9,"wins":56},"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":19,"losses":40,"wins":31},"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":37,"losses":15,"wins":84},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":30,"wins":17},"z-ai/glm-5.2":{"draws":39,"losses":50,"wins":91},"z-ai/glm-5.3":{"draws":14,"losses":54,"wins":18},"z-ai/glm-5.3-flash":{"draws":13,"losses":44,"wins":33},"z-ai/glm-5.3-flashx":{"draws":21,"losses":36,"wins":33}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":57},"claude-fable-5":{"draws":8,"losses":47,"wins":41},"claude-fable-5-1":{"draws":13,"losses":84,"wins":11},"claude-haiku-5-5":{"draws":17,"losses":32,"wins":43},"claude-opus-4-5":{"draws":39,"losses":32,"wins":85},"claude-opus-4-8":{"draws":11,"losses":35,"wins":42},"claude-opus-5":{"draws":26,"losses":99,"wins":39},"claude-opus-5-5":{"draws":10,"losses":80,"wins":14},"claude-sonnet-5":{"draws":15,"losses":24,"wins":57},"claude-sonnet-5-5":{"draws":13,"losses":46,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":31},"deepseek/deepseek-v4-flash":{"draws":25,"losses":24,"wins":95},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":27,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":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":30,"wins":45},"gemini-3.1-pro-preview":{"draws":16,"losses":24,"wins":56},"gemini-4-argon":{"draws":9,"losses":64,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":50},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":62},"google/gemini-3.5-flash-lite":{"draws":21,"losses":29,"wins":118},"google/gemini-3.6-flash":{"draws":37,"losses":61,"wins":86},"google/gemini-3.8-flash":{"draws":20,"losses":28,"wins":48},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":41},"gpt-4.1":{"draws":6,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":8},"gpt-5":{"draws":11,"losses":22,"wins":51},"gpt-5.4":{"draws":15,"losses":38,"wins":39},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":40},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":66},"gpt-5.5":{"draws":20,"losses":31,"wins":37},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":62},"gpt-5.6-sol":{"draws":17,"losses":44,"wins":35},"gpt-5.6-terra":{"draws":24,"losses":23,"wins":45},"gpt-6-astra":{"draws":9,"losses":80,"wins":7},"gpt-6-luna":{"draws":19,"losses":27,"wins":50},"gpt-6-sol":{"draws":18,"losses":54,"wins":24},"gpt-6.1-sol":{"draws":14,"losses":62,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":1,"wins":48},"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":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":19,"losses":11,"wins":74},"meta/muse-glimmer-30b":{"draws":15,"losses":13,"wins":56},"meta/muse-spark-1.2":{"draws":11,"losses":27,"wins":54},"meta/muse-spark-1.3":{"draws":15,"losses":32,"wins":49},"meta/muse-spark-open":{"draws":13,"losses":37,"wins":42},"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":5,"losses":3,"wins":16},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":53,"wins":23},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":13,"wins":27},"o3":{"draws":11,"losses":26,"wins":95},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":62},"poolside/laguna-s-2.1":{"draws":10,"losses":18,"wins":64},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":34},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":31,"wins":41},"qwen/qwen3.8-27b":{"draws":12,"losses":20,"wins":36},"qwen/qwen3.8-flash":{"draws":13,"losses":16,"wins":35},"qwen/qwen3.8-max":{"draws":25,"losses":19,"wins":52},"qwen/qwen3.8-max-0902":{"draws":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":57,"losses":105,"wins":154},"stealth/space-bunny-alpha":{"draws":19,"losses":19,"wins":38},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":52},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":33},"tencent/hy4-preview":{"draws":16,"losses":33,"wins":43},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":89},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":71},"unbiased/pareto-26.10":{"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":17,"losses":35,"wins":44},"x-ai/grok-4.6":{"draws":21,"losses":34,"wins":41},"x-ai/grok-4.7":{"draws":6,"losses":58,"wins":20},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":22},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":49,"losses":37,"wins":106},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":34},"z-ai/glm-5.3-flash":{"draws":16,"losses":30,"wins":50},"z-ai/glm-5.3-flashx":{"draws":17,"losses":35,"wins":44}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":96,"losses":72,"wins":96},"claude-fable-5":{"draws":60,"losses":185,"wins":43},"claude-fable-5-1":{"draws":21,"losses":295,"wins":8},"claude-haiku-5-5":{"draws":64,"losses":148,"wins":64},"claude-opus-4-5":{"draws":149,"losses":184,"wins":135},"claude-opus-4-8":{"draws":74,"losses":131,"wins":59},"claude-opus-5":{"draws":74,"losses":385,"wins":33},"claude-opus-5-5":{"draws":18,"losses":282,"wins":12},"claude-sonnet-5":{"draws":79,"losses":121,"wins":88},"claude-sonnet-5-5":{"draws":55,"losses":167,"wins":66},"cohere/north-mini-code":{"draws":30,"losses":18,"wins":60},"deepseek/deepseek-v4-flash":{"draws":151,"losses":101,"wins":180},"deepseek/deepseek-v4-pro":{"draws":89,"losses":99,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":85,"losses":98,"wins":81},"deepseek/deepseek-v4.1-flash":{"draws":103,"losses":122,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":62,"losses":173,"wins":53},"elorian/glimpse":{"draws":35,"losses":72,"wins":49},"fireworks/ember-1":{"draws":89,"losses":128,"wins":71},"gemini-3.1-pro-preview":{"draws":85,"losses":109,"wins":94},"gemini-4-argon":{"draws":27,"losses":247,"wins":14},"google/gemini-3.1-flash-lite":{"draws":42,"losses":23,"wins":127},"google/gemini-3.5-flash":{"draws":98,"losses":152,"wins":110},"google/gemini-3.5-flash-lite":{"draws":167,"losses":138,"wins":199},"google/gemini-3.6-flash":{"draws":152,"losses":250,"wins":150},"google/gemini-3.8-flash":{"draws":75,"losses":154,"wins":59},"google/gemma-4-31b-it":{"draws":69,"losses":29,"wins":70},"gpt-4.1":{"draws":35,"losses":23,"wins":38},"gpt-4.1-nano":{"draws":21,"losses":0,"wins":15},"gpt-5":{"draws":82,"losses":94,"wins":76},"gpt-5.4":{"draws":76,"losses":140,"wins":60},"gpt-5.4-mini":{"draws":87,"losses":35,"wins":70},"gpt-5.4-nano":{"draws":71,"losses":96,"wins":121},"gpt-5.5":{"draws":101,"losses":115,"wins":48},"gpt-5.6-luna":{"draws":108,"losses":70,"wins":110},"gpt-5.6-sol":{"draws":37,"losses":206,"wins":45},"gpt-5.6-terra":{"draws":116,"losses":94,"wins":66},"gpt-6-astra":{"draws":19,"losses":258,"wins":11},"gpt-6-luna":{"draws":102,"losses":113,"wins":73},"gpt-6-sol":{"draws":43,"losses":211,"wins":34},"gpt-6.1-sol":{"draws":30,"losses":248,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":87,"losses":19,"wins":98},"inception/mercury-3":{"draws":64,"losses":80,"wins":48},"inclusionai/ling-3.0-flash":{"draws":101,"losses":25,"wins":78},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":88,"losses":74,"wins":150},"meta/muse-glimmer-30b":{"draws":114,"losses":43,"wins":95},"meta/muse-spark-1.2":{"draws":65,"losses":136,"wins":75},"meta/muse-spark-1.3":{"draws":58,"losses":163,"wins":67},"meta/muse-spark-open":{"draws":69,"losses":146,"wins":61},"meta/muse-wonder":{"draws":65,"losses":178,"wins":45},"minimax/minimax-m3":{"draws":41,"losses":40,"wins":75},"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":74,"losses":19,"wins":75},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":31,"wins":24},"moonshotai/kimi-k3":{"draws":95,"losses":111,"wins":70},"moonshotai/kimi-k3.1-pro":{"draws":32,"losses":229,"wins":15},"nex-agi/nex-n2-pro":{"draws":57,"losses":17,"wins":70},"nex-agi/nex-n2.5-pro":{"draws":16,"losses":21,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":108,"losses":54,"wins":90},"nvidia/nemotron-3.5-super-vl":{"draws":42,"losses":46,"wins":44},"o3":{"draws":73,"losses":173,"wins":150},"openai/gpt-oss-120b":{"draws":95,"losses":49,"wins":108},"poolside/laguna-s-2.1":{"draws":111,"losses":69,"wins":96},"qwen/qwen3.7-max":{"draws":55,"losses":53,"wins":60},"qwen/qwen3.7-plus":{"draws":45,"losses":31,"wins":68},"qwen/qwen3.8-2.4t-a95b":{"draws":104,"losses":114,"wins":70},"qwen/qwen3.8-27b":{"draws":66,"losses":68,"wins":70},"qwen/qwen3.8-flash":{"draws":65,"losses":73,"wins":54},"qwen/qwen3.8-max":{"draws":97,"losses":114,"wins":77},"qwen/qwen3.8-max-0902":{"draws":98,"losses":133,"wins":57},"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":250,"losses":474,"wins":224},"stealth/space-bunny-alpha":{"draws":89,"losses":65,"wins":74},"stepfun/step-3.7-flash":{"draws":50,"losses":49,"wins":105},"stepfun/step-5-preview":{"draws":8,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":53,"losses":47,"wins":56},"tencent/hy4-preview":{"draws":73,"losses":147,"wins":56},"thinkingmachines/inkling":{"draws":118,"losses":94,"wins":172},"thinkingmachines/inkling-small":{"draws":104,"losses":58,"wins":126},"unbiased/pareto-26.10":{"draws":4,"losses":91,"wins":1},"unbiased/pareto-26.10-preview":{"draws":4,"losses":88,"wins":4},"upstage/solar-mini4":{"draws":8,"losses":16,"wins":48},"x-ai/grok-4.5":{"draws":71,"losses":158,"wins":59},"x-ai/grok-4.6":{"draws":78,"losses":160,"wins":50},"x-ai/grok-4.7":{"draws":29,"losses":186,"wins":37},"x-ai/grok-build-0.1":{"draws":42,"losses":18,"wins":36},"xiaomi/mimo-v2.5":{"draws":166,"losses":90,"wins":188},"xiaomi/mimo-v2.5-pro":{"draws":46,"losses":49,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":39,"losses":91,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":49,"losses":106,"wins":37},"z-ai/glm-5.2":{"draws":180,"losses":150,"wins":150},"z-ai/glm-5.3":{"draws":64,"losses":174,"wins":38},"z-ai/glm-5.3-flash":{"draws":71,"losses":156,"wins":61},"z-ai/glm-5.3-flashx":{"draws":82,"losses":142,"wins":64}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":17,"wins":84},"claude-fable-5":{"draws":21,"losses":53,"wins":64},"claude-fable-5-1":{"draws":11,"losses":124,"wins":21},"claude-haiku-5-5":{"draws":24,"losses":32,"wins":76},"claude-opus-4-5":{"draws":48,"losses":31,"wins":145},"claude-opus-4-8":{"draws":21,"losses":32,"wins":73},"claude-opus-5":{"draws":31,"losses":140,"wins":63},"claude-opus-5-5":{"draws":9,"losses":116,"wins":25},"claude-sonnet-5":{"draws":28,"losses":19,"wins":91},"claude-sonnet-5-5":{"draws":24,"losses":52,"wins":62},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":44,"losses":12,"wins":150},"deepseek/deepseek-v4-pro":{"draws":22,"losses":26,"wins":78},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":25,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":27,"wins":84},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":41,"wins":73},"elorian/glimpse":{"draws":13,"losses":15,"wins":46},"fireworks/ember-1":{"draws":24,"losses":27,"wins":87},"gemini-3.1-pro-preview":{"draws":25,"losses":30,"wins":83},"gemini-4-argon":{"draws":15,"losses":83,"wins":40},"google/gemini-3.1-flash-lite":{"draws":15,"losses":1,"wins":76},"google/gemini-3.5-flash":{"draws":30,"losses":36,"wins":106},"google/gemini-3.5-flash-lite":{"draws":41,"losses":17,"wins":184},"google/gemini-3.6-flash":{"draws":52,"losses":60,"wins":152},"google/gemini-3.8-flash":{"draws":29,"losses":38,"wins":71},"google/gemma-4-31b-it":{"draws":22,"losses":7,"wins":53},"gpt-4.1":{"draws":7,"losses":8,"wins":31},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":18,"losses":22,"wins":80},"gpt-5.4":{"draws":25,"losses":38,"wins":69},"gpt-5.4-mini":{"draws":21,"losses":9,"wins":62},"gpt-5.4-nano":{"draws":19,"losses":21,"wins":96},"gpt-5.5":{"draws":31,"losses":23,"wins":72},"gpt-5.6-luna":{"draws":28,"losses":15,"wins":95},"gpt-5.6-sol":{"draws":23,"losses":60,"wins":55},"gpt-5.6-terra":{"draws":36,"losses":21,"wins":75},"gpt-6-astra":{"draws":18,"losses":109,"wins":11},"gpt-6-luna":{"draws":26,"losses":27,"wins":85},"gpt-6-sol":{"draws":21,"losses":70,"wins":47},"gpt-6.1-sol":{"draws":21,"losses":92,"wins":25},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":28,"losses":3,"wins":69},"inception/mercury-3":{"draws":22,"losses":21,"wins":49},"inclusionai/ling-3.0-flash":{"draws":22,"losses":3,"wins":71},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":26,"losses":11,"wins":115},"meta/muse-glimmer-30b":{"draws":25,"losses":12,"wins":83},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":68},"meta/muse-spark-1.3":{"draws":25,"losses":40,"wins":73},"meta/muse-spark-open":{"draws":19,"losses":35,"wins":78},"meta/muse-wonder":{"draws":17,"losses":62,"wins":59},"minimax/minimax-m3":{"draws":15,"losses":6,"wins":53},"minimax/minimax-m3.1-flash":{"draws":17,"losses":25,"wins":78},"mistralai/mistral-large-4-0":{"draws":15,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":4,"wins":20},"moonshotai/kimi-k3":{"draws":28,"losses":39,"wins":65},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":80,"wins":33},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":55},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":13,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":51},"o3":{"draws":17,"losses":35,"wins":136},"openai/gpt-oss-120b":{"draws":31,"losses":4,"wins":87},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":92},"qwen/qwen3.7-max":{"draws":18,"losses":13,"wins":49},"qwen/qwen3.7-plus":{"draws":15,"losses":7,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":29,"wins":82},"qwen/qwen3.8-27b":{"draws":26,"losses":12,"wins":58},"qwen/qwen3.8-flash":{"draws":23,"losses":14,"wins":55},"qwen/qwen3.8-max":{"draws":29,"losses":30,"wins":79},"qwen/qwen3.8-max-0902":{"draws":35,"losses":30,"wins":73},"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":82,"losses":118,"wins":258},"stealth/space-bunny-alpha":{"draws":25,"losses":9,"wins":76},"stepfun/step-3.7-flash":{"draws":15,"losses":3,"wins":78},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":6},"tencent/hy3-preview":{"draws":14,"losses":10,"wins":50},"tencent/hy4-preview":{"draws":22,"losses":26,"wins":84},"thinkingmachines/inkling":{"draws":35,"losses":20,"wins":127},"thinkingmachines/inkling-small":{"draws":25,"losses":10,"wins":103},"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":27,"losses":32,"wins":79},"x-ai/grok-4.6":{"draws":29,"losses":43,"wins":66},"x-ai/grok-4.7":{"draws":17,"losses":70,"wins":33},"x-ai/grok-build-0.1":{"draws":11,"losses":1,"wins":34},"xiaomi/mimo-v2.5":{"draws":47,"losses":4,"wins":159},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":4,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":18,"wins":54},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":34,"wins":43},"z-ai/glm-5.2":{"draws":64,"losses":38,"wins":174},"z-ai/glm-5.3":{"draws":20,"losses":34,"wins":34},"z-ai/glm-5.3-flash":{"draws":32,"losses":32,"wins":74},"z-ai/glm-5.3-flashx":{"draws":27,"losses":33,"wins":78}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":29,"wins":74},"claude-fable-5":{"draws":23,"losses":77,"wins":44},"claude-fable-5-1":{"draws":10,"losses":139,"wins":13},"claude-haiku-5-5":{"draws":27,"losses":54,"wins":57},"claude-opus-4-5":{"draws":55,"losses":55,"wins":124},"claude-opus-4-8":{"draws":19,"losses":52,"wins":61},"claude-opus-5":{"draws":35,"losses":165,"wins":46},"claude-opus-5-5":{"draws":12,"losses":134,"wins":10},"claude-sonnet-5":{"draws":25,"losses":40,"wins":79},"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":54,"losses":43,"wins":119},"deepseek/deepseek-v4-pro":{"draws":22,"losses":36,"wins":74},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":38,"wins":75},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":58,"wins":60},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":73,"wins":45},"elorian/glimpse":{"draws":12,"losses":31,"wins":35},"fireworks/ember-1":{"draws":26,"losses":46,"wins":72},"gemini-3.1-pro-preview":{"draws":36,"losses":42,"wins":66},"gemini-4-argon":{"draws":15,"losses":110,"wins":19},"google/gemini-3.1-flash-lite":{"draws":21,"losses":12,"wins":63},"google/gemini-3.5-flash":{"draws":22,"losses":61,"wins":97},"google/gemini-3.5-flash-lite":{"draws":51,"losses":47,"wins":154},"google/gemini-3.6-flash":{"draws":45,"losses":90,"wins":141},"google/gemini-3.8-flash":{"draws":20,"losses":69,"wins":55},"google/gemma-4-31b-it":{"draws":25,"losses":14,"wins":45},"gpt-4.1":{"draws":6,"losses":14,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":21,"losses":31,"wins":74},"gpt-5.4":{"draws":16,"losses":63,"wins":59},"gpt-5.4-mini":{"draws":26,"losses":18,"wins":52},"gpt-5.4-nano":{"draws":22,"losses":37,"wins":85},"gpt-5.5":{"draws":24,"losses":50,"wins":58},"gpt-5.6-luna":{"draws":37,"losses":29,"wins":78},"gpt-5.6-sol":{"draws":25,"losses":72,"wins":47},"gpt-5.6-terra":{"draws":33,"losses":40,"wins":65},"gpt-6-astra":{"draws":11,"losses":125,"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":13,"losses":115,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":24,"losses":12,"wins":66},"inception/mercury-3":{"draws":22,"losses":36,"wins":38},"inclusionai/ling-3.0-flash":{"draws":32,"losses":13,"wins":57},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":33,"wins":98},"meta/muse-glimmer-30b":{"draws":28,"losses":17,"wins":81},"meta/muse-spark-1.2":{"draws":20,"losses":58,"wins":60},"meta/muse-spark-1.3":{"draws":25,"losses":50,"wins":69},"meta/muse-spark-open":{"draws":21,"losses":60,"wins":57},"meta/muse-wonder":{"draws":30,"losses":71,"wins":43},"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":24,"losses":10,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":17},"moonshotai/kimi-k3":{"draws":30,"losses":44,"wins":64},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":103,"wins":19},"nex-agi/nex-n2-pro":{"draws":14,"losses":9,"wins":49},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":34,"wins":62},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":21,"wins":35},"o3":{"draws":24,"losses":75,"wins":99},"openai/gpt-oss-120b":{"draws":26,"losses":20,"wins":80},"poolside/laguna-s-2.1":{"draws":32,"losses":31,"wins":75},"qwen/qwen3.7-max":{"draws":25,"losses":18,"wins":41},"qwen/qwen3.7-plus":{"draws":17,"losses":13,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":48,"wins":65},"qwen/qwen3.8-27b":{"draws":19,"losses":32,"wins":51},"qwen/qwen3.8-flash":{"draws":20,"losses":34,"wins":42},"qwen/qwen3.8-max":{"draws":32,"losses":55,"wins":57},"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":78,"losses":183,"wins":213},"stealth/space-bunny-alpha":{"draws":30,"losses":17,"wins":67},"stepfun/step-3.7-flash":{"draws":15,"losses":20,"wins":67},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":14,"wins":42},"tencent/hy4-preview":{"draws":25,"losses":50,"wins":63},"thinkingmachines/inkling":{"draws":40,"losses":31,"wins":121},"thinkingmachines/inkling-small":{"draws":32,"losses":21,"wins":91},"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":20,"losses":60,"wins":64},"x-ai/grok-4.6":{"draws":36,"losses":59,"wins":49},"x-ai/grok-4.7":{"draws":16,"losses":76,"wins":34},"x-ai/grok-build-0.1":{"draws":12,"losses":7,"wins":29},"xiaomi/mimo-v2.5":{"draws":52,"losses":37,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":14,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":33,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":50,"wins":30},"z-ai/glm-5.2":{"draws":71,"losses":61,"wins":156},"z-ai/glm-5.3":{"draws":32,"losses":74,"wins":32},"z-ai/glm-5.3-flash":{"draws":12,"losses":42,"wins":42},"z-ai/glm-5.3-flashx":{"draws":33,"losses":52,"wins":59}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":25,"wins":83},"claude-fable-5":{"draws":27,"losses":73,"wins":44},"claude-fable-5-1":{"draws":13,"losses":137,"wins":12},"claude-haiku-5-5":{"draws":27,"losses":60,"wins":51},"claude-opus-4-5":{"draws":52,"losses":55,"wins":127},"claude-opus-4-8":{"draws":25,"losses":59,"wins":48},"claude-opus-5":{"draws":36,"losses":166,"wins":44},"claude-opus-5-5":{"draws":15,"losses":131,"wins":10},"claude-sonnet-5":{"draws":39,"losses":33,"wins":72},"claude-sonnet-5-5":{"draws":24,"losses":66,"wins":54},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":40},"deepseek/deepseek-v4-flash":{"draws":58,"losses":32,"wins":126},"deepseek/deepseek-v4-pro":{"draws":32,"losses":40,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":39,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":72,"wins":48},"elorian/glimpse":{"draws":17,"losses":29,"wins":32},"fireworks/ember-1":{"draws":29,"losses":50,"wins":65},"gemini-3.1-pro-preview":{"draws":37,"losses":38,"wins":69},"gemini-4-argon":{"draws":12,"losses":110,"wins":22},"google/gemini-3.1-flash-lite":{"draws":26,"losses":7,"wins":63},"google/gemini-3.5-flash":{"draws":42,"losses":46,"wins":92},"google/gemini-3.5-flash-lite":{"draws":63,"losses":48,"wins":141},"google/gemini-3.6-flash":{"draws":68,"losses":95,"wins":113},"google/gemini-3.8-flash":{"draws":26,"losses":66,"wins":52},"google/gemma-4-31b-it":{"draws":28,"losses":11,"wins":45},"gpt-4.1":{"draws":11,"losses":7,"wins":30},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":36,"losses":32,"wins":58},"gpt-5.4":{"draws":29,"losses":54,"wins":55},"gpt-5.4-mini":{"draws":26,"losses":13,"wins":57},"gpt-5.4-nano":{"draws":30,"losses":35,"wins":79},"gpt-5.5":{"draws":41,"losses":44,"wins":47},"gpt-5.6-luna":{"draws":42,"losses":29,"wins":73},"gpt-5.6-sol":{"draws":23,"losses":80,"wins":41},"gpt-5.6-terra":{"draws":38,"losses":37,"wins":63},"gpt-6-astra":{"draws":14,"losses":121,"wins":9},"gpt-6-luna":{"draws":30,"losses":43,"wins":71},"gpt-6-sol":{"draws":18,"losses":86,"wins":40},"gpt-6.1-sol":{"draws":18,"losses":108,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":30,"losses":5,"wins":67},"inception/mercury-3":{"draws":21,"losses":33,"wins":42},"inclusionai/ling-3.0-flash":{"draws":34,"losses":8,"wins":60},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":20,"wins":104},"meta/muse-glimmer-30b":{"draws":36,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":28,"losses":51,"wins":59},"meta/muse-spark-1.3":{"draws":28,"losses":59,"wins":57},"meta/muse-spark-open":{"draws":27,"losses":54,"wins":57},"meta/muse-wonder":{"draws":34,"losses":73,"wins":37},"minimax/minimax-m3":{"draws":18,"losses":12,"wins":48},"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":21,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":13,"wins":12},"moonshotai/kimi-k3":{"draws":40,"losses":36,"wins":62},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":109,"wins":17},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":21,"wins":74},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":14,"wins":39},"o3":{"draws":21,"losses":58,"wins":119},"openai/gpt-oss-120b":{"draws":36,"losses":13,"wins":77},"poolside/laguna-s-2.1":{"draws":40,"losses":23,"wins":75},"qwen/qwen3.7-max":{"draws":22,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":17,"losses":10,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":45,"wins":61},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":29,"losses":25,"wins":42},"qwen/qwen3.8-max":{"draws":40,"losses":48,"wins":56},"qwen/qwen3.8-max-0902":{"draws":35,"losses":51,"wins":58},"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":85,"losses":167,"wins":222},"stealth/space-bunny-alpha":{"draws":33,"losses":22,"wins":59},"stepfun/step-3.7-flash":{"draws":13,"losses":14,"wins":75},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":14,"wins":48},"tencent/hy4-preview":{"draws":31,"losses":57,"wins":50},"thinkingmachines/inkling":{"draws":44,"losses":25,"wins":123},"thinkingmachines/inkling-small":{"draws":32,"losses":23,"wins":89},"unbiased/pareto-26.10":{"draws":4,"losses":39,"wins":5},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":25,"losses":58,"wins":61},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":52},"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":72,"losses":16,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":16,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":33,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":82,"losses":64,"wins":142},"z-ai/glm-5.3":{"draws":27,"losses":78,"wins":33},"z-ai/glm-5.3-flash":{"draws":33,"losses":59,"wins":52},"z-ai/glm-5.3-flashx":{"draws":32,"losses":32,"wins":32}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":10},"claude-fable-5":{"draws":9,"losses":35,"wins":4},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":32,"losses":30,"wins":16},"claude-opus-4-8":{"draws":14,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":65,"wins":8},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":17,"losses":23,"wins":8},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":23,"losses":19,"wins":30},"deepseek/deepseek-v4-pro":{"draws":7,"losses":20,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":16,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"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":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":16},"google/gemini-3.5-flash-lite":{"draws":36,"losses":18,"wins":30},"google/gemini-3.6-flash":{"draws":31,"losses":41,"wins":20},"google/gemini-3.8-flash":{"draws":12,"losses":27,"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":16,"losses":15,"wins":11},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":15,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":17},"gpt-5.5":{"draws":21,"losses":14,"wins":9},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":21,"wins":10},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":12},"inception/mercury-3":{"draws":15,"losses":7,"wins":10},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":10,"wins":27},"meta/muse-glimmer-30b":{"draws":20,"losses":9,"wins":13},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":25,"wins":7},"meta/muse-spark-open":{"draws":10,"losses":25,"wins":11},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"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":14,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":22,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":35,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":12,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":5,"wins":7},"o3":{"draws":16,"losses":27,"wins":23},"openai/gpt-oss-120b":{"draws":19,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":23,"losses":8,"wins":15},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":12},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"wins":8},"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":42,"losses":84,"wins":32},"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":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":6},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":20,"losses":9,"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":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.6":{"draws":11,"losses":33,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":38,"losses":30,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":35},"claude-fable-5":{"draws":1,"losses":12,"wins":19},"claude-fable-5-1":{"draws":5,"losses":38,"wins":11},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":3,"losses":9,"wins":66},"claude-opus-4-8":{"draws":3,"losses":12,"wins":29},"claude-opus-5":{"draws":12,"losses":40,"wins":30},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":7,"losses":4,"wins":37},"claude-sonnet-5-5":{"draws":1,"losses":19,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":63},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":33},"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":8,"wins":34},"gemini-4-argon":{"draws":7,"losses":28,"wins":13},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":51},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":72},"google/gemini-3.6-flash":{"draws":11,"losses":16,"wins":65},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":24},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":5,"losses":9,"wins":28},"gpt-5.4":{"draws":7,"losses":16,"wins":23},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":40},"gpt-5.5":{"draws":5,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":38},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":27},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":5,"losses":36,"wins":7},"gpt-6-luna":{"draws":7,"losses":11,"wins":30},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":30},"inception/mercury-3":{"draws":3,"losses":3,"wins":26},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":2,"losses":8,"wins":36},"meta/muse-spark-1.3":{"draws":5,"losses":8,"wins":35},"meta/muse-spark-open":{"draws":1,"losses":11,"wins":34},"meta/muse-wonder":{"draws":5,"losses":15,"wins":28},"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":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":8,"wins":33},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":29,"wins":14},"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":9,"losses":3,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":21},"o3":{"draws":5,"losses":11,"wins":50},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":35},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":11,"wins":33},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":29},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-max":{"draws":6,"losses":9,"wins":33},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":32},"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":17,"losses":19,"wins":122},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":31},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":6,"losses":4,"wins":54},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":40},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"unbiased/pareto-26.10-preview":{"draws":3,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":34},"x-ai/grok-4.6":{"draws":11,"losses":14,"wins":23},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":20},"z-ai/glm-5.2":{"draws":13,"losses":10,"wins":73},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":25},"z-ai/glm-5.3-flash":{"draws":8,"losses":7,"wins":33},"z-ai/glm-5.3-flashx":{"draws":8,"losses":11,"wins":29}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":58},"claude-fable-5":{"draws":0,"losses":5,"wins":61},"claude-fable-5-1":{"draws":8,"losses":9,"wins":39},"claude-haiku-5-5":{"draws":4,"losses":0,"wins":58},"claude-opus-4-5":{"draws":1,"losses":2,"wins":103},"claude-opus-4-8":{"draws":0,"losses":3,"wins":55},"claude-opus-5":{"draws":6,"losses":20,"wins":88},"claude-opus-5-5":{"draws":7,"losses":32,"wins":31},"claude-sonnet-5":{"draws":0,"losses":1,"wins":65},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":52},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":25},"deepseek/deepseek-v4-flash":{"draws":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":2,"losses":3,"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":0,"losses":2,"wins":114},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":122},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":61},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":37},"gpt-4.1":{"draws":0,"losses":0,"wins":22},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":58},"gpt-5.4":{"draws":1,"losses":3,"wins":60},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":44},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":58},"gpt-5.5":{"draws":0,"losses":3,"wins":59},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":64},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":58},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":64},"gpt-6-astra":{"draws":7,"losses":20,"wins":39},"gpt-6-luna":{"draws":1,"losses":1,"wins":64},"gpt-6-sol":{"draws":2,"losses":11,"wins":53},"gpt-6.1-sol":{"draws":2,"losses":23,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":44},"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":2},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":69},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":60},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":60},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":60},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":61},"meta/muse-wonder":{"draws":4,"losses":7,"wins":55},"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":0,"losses":4,"wins":38},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":16},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":60},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":8,"wins":50},"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":50},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":32},"o3":{"draws":0,"losses":1,"wins":85},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":55},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":58},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":66},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":43},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":65},"qwen/qwen3.8-max-0902":{"draws":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":8,"losses":4,"wins":222},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":53},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":31},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":60},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":90},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":65},"unbiased/pareto-26.10":{"draws":5,"losses":7,"wins":10},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":64},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":57},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":50},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":37},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":128},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":58},"z-ai/glm-5.3-flash":{"draws":2,"losses":3,"wins":61},"z-ai/glm-5.3-flashx":{"draws":4,"losses":1,"wins":61}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":34},"claude-fable-5":{"draws":5,"losses":11,"wins":26},"claude-fable-5-1":{"draws":4,"losses":39,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":20},"claude-opus-4-5":{"draws":12,"losses":6,"wins":52},"claude-opus-4-8":{"draws":7,"losses":10,"wins":25},"claude-opus-5":{"draws":10,"losses":38,"wins":22},"claude-opus-5-5":{"draws":6,"losses":32,"wins":8},"claude-sonnet-5":{"draws":5,"losses":4,"wins":33},"claude-sonnet-5-5":{"draws":5,"losses":13,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":6,"losses":5,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":10,"wins":23},"elorian/glimpse":{"draws":2,"losses":6,"wins":14},"fireworks/ember-1":{"draws":5,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":29},"gemini-4-argon":{"draws":8,"losses":16,"wins":18},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":63},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":52},"google/gemini-3.8-flash":{"draws":7,"losses":9,"wins":26},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":23},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":4,"wins":29},"gpt-5.4":{"draws":2,"losses":9,"wins":29},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":39},"gpt-5.5":{"draws":5,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":35},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":22},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":33,"wins":5},"gpt-6-luna":{"draws":6,"losses":6,"wins":30},"gpt-6-sol":{"draws":12,"losses":15,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":31},"inception/mercury-3":{"draws":5,"losses":4,"wins":19},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":30},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":34},"meta/muse-spark-open":{"draws":3,"losses":8,"wins":29},"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":4,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":2,"losses":9,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":22,"wins":12},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":3,"wins":16},"o3":{"draws":2,"losses":11,"wins":49},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":31},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":8,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":3,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":26},"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":17,"losses":21,"wins":80},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":27},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":45},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":40},"unbiased/pareto-26.10":{"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":22,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":5,"losses":9,"wins":70},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":19},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":3,"losses":9,"wins":30}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":7,"losses":33,"wins":8},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":20,"losses":19,"wins":23},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":10,"losses":64,"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":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"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":15,"wins":19},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":22,"wins":23},"google/gemini-3.5-flash-lite":{"draws":29,"losses":20,"wins":35},"google/gemini-3.6-flash":{"draws":25,"losses":43,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":13,"wins":17},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":12,"wins":20},"gpt-5.5":{"draws":16,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":16,"losses":11,"wins":19},"gpt-6-astra":{"draws":1,"losses":45,"wins":2},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"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":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":33},"meta/muse-glimmer-30b":{"draws":16,"losses":3,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":22,"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":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":40,"wins":4},"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":18,"losses":4,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":7},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":26},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":14},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":21,"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":37,"losses":63,"wins":58},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":22},"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":15,"losses":21,"wins":12},"x-ai/grok-4.6":{"draws":13,"losses":26,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":24,"wins":41},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":12},"z-ai/glm-5.3-flashx":{"draws":16,"losses":20,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":5,"wins":31},"claude-fable-5":{"draws":5,"losses":16,"wins":21},"claude-fable-5-1":{"draws":3,"losses":34,"wins":9},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":26},"claude-opus-4-5":{"draws":13,"losses":11,"wins":46},"claude-opus-4-8":{"draws":3,"losses":4,"wins":21},"claude-opus-5":{"draws":10,"losses":37,"wins":23},"claude-opus-5-5":{"draws":9,"losses":27,"wins":10},"claude-sonnet-5":{"draws":8,"losses":5,"wins":29},"claude-sonnet-5-5":{"draws":10,"losses":11,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":6,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":13,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":13,"wins":25},"elorian/glimpse":{"draws":3,"losses":8,"wins":11},"fireworks/ember-1":{"draws":10,"losses":6,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":28},"gemini-4-argon":{"draws":4,"losses":22,"wins":16},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":63},"google/gemini-3.6-flash":{"draws":14,"losses":21,"wins":45},"google/gemini-3.8-flash":{"draws":10,"losses":12,"wins":20},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":5,"wins":28},"gpt-5.4":{"draws":4,"losses":14,"wins":22},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":37},"gpt-5.5":{"draws":8,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":31},"gpt-5.6-sol":{"draws":4,"losses":12,"wins":26},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":32},"gpt-6-astra":{"draws":5,"losses":33,"wins":4},"gpt-6-luna":{"draws":7,"losses":4,"wins":31},"gpt-6-sol":{"draws":8,"losses":18,"wins":16},"gpt-6.1-sol":{"draws":5,"losses":28,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":26},"inception/mercury-3":{"draws":4,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":33},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":28},"meta/muse-spark-1.3":{"draws":6,"losses":11,"wins":25},"meta/muse-spark-open":{"draws":5,"losses":5,"wins":30},"meta/muse-wonder":{"draws":7,"losses":14,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":20},"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":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":17},"o3":{"draws":6,"losses":8,"wins":48},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":30},"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":1,"losses":1,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":32},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":21},"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":24,"losses":20,"wins":74},"stealth/space-bunny-alpha":{"draws":7,"losses":4,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":26},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":46},"thinkingmachines/inkling-small":{"draws":4,"losses":3,"wins":35},"unbiased/pareto-26.10":{"draws":4,"losses":7,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":24},"x-ai/grok-4.6":{"draws":7,"losses":13,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":19,"wins":12},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":10,"losses":9,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":14,"wins":20},"z-ai/glm-5.3-flash":{"draws":3,"losses":13,"wins":26},"z-ai/glm-5.3-flashx":{"draws":8,"losses":4,"wins":30}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":63},"claude-fable-5":{"draws":6,"losses":19,"wins":53},"claude-fable-5-1":{"draws":8,"losses":41,"wins":39},"claude-haiku-5-5":{"draws":1,"losses":11,"wins":62},"claude-opus-4-5":{"draws":8,"losses":10,"wins":108},"claude-opus-4-8":{"draws":2,"losses":14,"wins":54},"claude-opus-5":{"draws":14,"losses":36,"wins":76},"claude-opus-5-5":{"draws":4,"losses":43,"wins":39},"claude-sonnet-5":{"draws":4,"losses":6,"wins":68},"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":1,"losses":8,"wins":105},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":65},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":3,"wins":63},"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":14,"wins":62},"gemini-3.1-pro-preview":{"draws":3,"losses":5,"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":9,"losses":5,"wins":82},"google/gemini-3.5-flash-lite":{"draws":3,"losses":6,"wins":125},"google/gemini-3.6-flash":{"draws":7,"losses":19,"wins":122},"google/gemini-3.8-flash":{"draws":3,"losses":11,"wins":64},"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":4,"wins":65},"gpt-5.4":{"draws":3,"losses":8,"wins":63},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":47},"gpt-5.4-nano":{"draws":3,"losses":6,"wins":65},"gpt-5.5":{"draws":4,"losses":9,"wins":61},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":72},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":60},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":65},"gpt-6-astra":{"draws":7,"losses":48,"wins":23},"gpt-6-luna":{"draws":9,"losses":4,"wins":65},"gpt-6-sol":{"draws":7,"losses":25,"wins":46},"gpt-6.1-sol":{"draws":14,"losses":35,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":48},"inception/mercury-3":{"draws":3,"losses":2,"wins":47},"inclusionai/ling-3.0-flash":{"draws":1,"losses":5,"wins":46},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":73},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":69},"meta/muse-spark-1.2":{"draws":3,"losses":6,"wins":69},"meta/muse-spark-1.3":{"draws":2,"losses":10,"wins":66},"meta/muse-spark-open":{"draws":2,"losses":8,"wins":64},"meta/muse-wonder":{"draws":5,"losses":17,"wins":56},"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":4,"wins":44},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":19},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":64},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":25,"wins":39},"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":3,"losses":4,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":5,"wins":30},"o3":{"draws":2,"losses":6,"wins":88},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":61},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":72},"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":6,"wins":69},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":45},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":50},"qwen/qwen3.8-max":{"draws":2,"losses":6,"wins":70},"qwen/qwen3.8-max-0902":{"draws":3,"losses":9,"wins":66},"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":18,"losses":24,"wins":224},"stealth/space-bunny-alpha":{"draws":4,"losses":2,"wins":56},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":38},"tencent/hy4-preview":{"draws":5,"losses":7,"wins":62},"thinkingmachines/inkling":{"draws":8,"losses":8,"wins":92},"thinkingmachines/inkling-small":{"draws":4,"losses":5,"wins":69},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":14},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":12,"wins":56},"x-ai/grok-4.6":{"draws":6,"losses":9,"wins":63},"x-ai/grok-4.7":{"draws":6,"losses":18,"wins":46},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.5":{"draws":4,"losses":7,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":43},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":41},"z-ai/glm-5.2":{"draws":10,"losses":9,"wins":137},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":61},"z-ai/glm-5.3-flash":{"draws":9,"losses":7,"wins":62},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":64}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":0,"losses":3,"wins":45},"claude-fable-5-1":{"draws":4,"losses":8,"wins":42},"claude-haiku-5-5":{"draws":2,"losses":1,"wins":43},"claude-opus-4-5":{"draws":0,"losses":1,"wins":77},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":5,"losses":10,"wins":67},"claude-opus-5-5":{"draws":3,"losses":7,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":4,"losses":4,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":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":0,"wins":48},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"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":3,"wins":88},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":45},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":0,"wins":42},"gpt-5.4":{"draws":0,"losses":4,"wins":42},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":46},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":44},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":4,"losses":14,"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":9,"losses":7,"wins":32},"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":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":42},"meta/muse-spark-1.3":{"draws":1,"losses":3,"wins":44},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":1,"losses":4,"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":0,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":6,"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":42},"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":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":43},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":31},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":43},"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":2,"losses":1,"wins":155},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":45},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"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":2,"losses":2,"wins":44},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":1,"losses":3,"wins":42},"z-ai/glm-5.3-flash":{"draws":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":26,"wins":14},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":23},"claude-opus-4-5":{"draws":23,"losses":21,"wins":34},"claude-opus-4-8":{"draws":10,"losses":14,"wins":20},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":8,"losses":5,"wins":19},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":47},"deepseek/deepseek-v4-pro":{"draws":9,"losses":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":18,"losses":11,"wins":55},"google/gemini-3.6-flash":{"draws":14,"losses":33,"wins":45},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":30},"gpt-5.5":{"draws":11,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":22},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":23},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":21},"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":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":37},"meta/muse-glimmer-30b":{"draws":8,"losses":6,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":17},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":16},"meta/muse-spark-open":{"draws":10,"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":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":21},"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":5,"losses":7,"wins":16},"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":34,"losses":58,"wins":66},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":30},"unbiased/pareto-26.10":{"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":21,"wins":12},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":21,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":50},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":4,"losses":25,"wins":19},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":0,"wins":37},"claude-fable-5":{"draws":5,"losses":2,"wins":41},"claude-fable-5-1":{"draws":6,"losses":16,"wins":32},"claude-haiku-5-5":{"draws":5,"losses":2,"wins":39},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":5,"losses":1,"wins":38},"claude-opus-5":{"draws":5,"losses":17,"wins":60},"claude-opus-5-5":{"draws":10,"losses":17,"wins":25},"claude-sonnet-5":{"draws":1,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":0,"losses":1,"wins":31},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":69},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":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":0,"losses":3,"wins":45},"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":3,"losses":3,"wins":54},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":80},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":39},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":0,"wins":40},"gpt-5.4":{"draws":9,"losses":0,"wins":37},"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":7,"losses":6,"wins":35},"gpt-6.1-sol":{"draws":1,"losses":15,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"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":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":43},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":44},"meta/muse-spark-open":{"draws":4,"losses":1,"wins":41},"meta/muse-wonder":{"draws":5,"losses":1,"wins":42},"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":12},"moonshotai/kimi-k3":{"draws":4,"losses":1,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":5,"wins":33},"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":1,"wins":39},"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":4,"wins":144},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":3,"losses":0,"wins":43},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":57},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10":{"draws":2,"losses":7,"wins":7},"unbiased/pareto-26.10-preview":{"draws":2,"losses":5,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":1,"wins":41},"x-ai/grok-4.6":{"draws":5,"losses":0,"wins":43},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":90},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":36},"z-ai/glm-5.3-flash":{"draws":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":17,"losses":9,"wins":12},"claude-fable-5":{"draws":7,"losses":28,"wins":7},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":20,"losses":31,"wins":17},"claude-opus-4-8":{"draws":10,"losses":21,"wins":7},"claude-opus-5":{"draws":13,"losses":48,"wins":9},"claude-opus-5-5":{"draws":3,"losses":41,"wins":2},"claude-sonnet-5":{"draws":15,"losses":18,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":15,"losses":15,"wins":20},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":18,"wins":6},"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":17,"losses":12,"wins":13},"gemini-4-argon":{"draws":8,"losses":34,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":18,"losses":21,"wins":13},"google/gemini-3.5-flash-lite":{"draws":29,"losses":25,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":11},"google/gemini-3.8-flash":{"draws":10,"losses":27,"wins":5},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":9},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":13,"wins":8},"gpt-5.4":{"draws":16,"losses":17,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":12},"gpt-5.5":{"draws":16,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":21,"losses":8,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":8},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":19,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":11},"inception/mercury-3":{"draws":11,"losses":10,"wins":9},"inclusionai/ling-3.0-flash":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":7,"wins":19},"meta/muse-glimmer-30b":{"draws":23,"losses":5,"wins":8},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":11,"losses":26,"wins":5},"meta/muse-spark-open":{"draws":10,"losses":22,"wins":8},"meta/muse-wonder":{"draws":8,"losses":25,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":7},"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":15,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":33,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":13,"losses":22,"wins":19},"openai/gpt-oss-120b":{"draws":18,"losses":12,"wins":6},"poolside/laguna-s-2.1":{"draws":19,"losses":10,"wins":9},"qwen/qwen3.7-max":{"draws":15,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":15,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":19,"losses":15,"wins":8},"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":37,"losses":70,"wins":33},"stealth/space-bunny-alpha":{"draws":17,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":17,"wins":10},"thinkingmachines/inkling":{"draws":28,"losses":11,"wins":15},"thinkingmachines/inkling-small":{"draws":22,"losses":7,"wins":13},"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":11,"losses":22,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":21,"wins":7},"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":31,"losses":16,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":3,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":37,"losses":27,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":19,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":24},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":22,"losses":25,"wins":31},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":13,"losses":20,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":24,"wins":9},"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":14,"wins":21},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":20},"google/gemini-3.5-flash-lite":{"draws":25,"losses":22,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":39,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":10},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4":{"draws":15,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":15,"wins":28},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":12,"losses":20,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":11,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":22,"wins":14},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":12},"meta/muse-wonder":{"draws":14,"losses":23,"wins":11},"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":4,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":23,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":36,"wins":5},"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":13,"losses":7,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":8,"losses":23,"wins":35},"openai/gpt-oss-120b":{"draws":14,"losses":10,"wins":18},"poolside/laguna-s-2.1":{"draws":13,"losses":17,"wins":16},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":24,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":24,"wins":13},"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":35,"losses":79,"wins":44},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":21,"wins":15},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":16,"losses":2,"wins":30},"unbiased/pareto-26.10":{"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":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":31,"losses":29,"wins":36},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":18,"wins":19}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":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":16,"losses":20,"wins":42},"claude-opus-4-8":{"draws":11,"losses":14,"wins":19},"claude-opus-5":{"draws":5,"losses":67,"wins":10},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":13,"losses":12,"wins":23},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":15,"losses":15,"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":13,"wins":25},"gemini-3.1-pro-preview":{"draws":9,"losses":15,"wins":24},"gemini-4-argon":{"draws":4,"losses":40,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":20,"wins":28},"google/gemini-3.5-flash-lite":{"draws":21,"losses":7,"wins":56},"google/gemini-3.6-flash":{"draws":18,"losses":35,"wins":39},"google/gemini-3.8-flash":{"draws":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":16,"losses":8,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":21},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":13,"wins":23},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":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":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":21},"meta/muse-spark-1.3":{"draws":11,"losses":17,"wins":20},"meta/muse-spark-open":{"draws":6,"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":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":39,"wins":4},"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":15,"losses":6,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":8,"losses":12,"wins":46},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":23},"poolside/laguna-s-2.1":{"draws":8,"losses":7,"wins":31},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":16},"qwen/qwen3.8-max":{"draws":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":29,"losses":54,"wins":75},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":4,"losses":20,"wins":22},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":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":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":43},"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":2,"losses":19,"wins":11},"z-ai/glm-5.2":{"draws":22,"losses":29,"wins":45},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":16},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":19}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":13,"losses":16,"wins":19},"claude-fable-5-1":{"draws":6,"losses":42,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":15,"losses":12,"wins":51},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":7,"losses":56,"wins":19},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":13,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":13,"losses":1,"wins":58},"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":6,"losses":11,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":14,"wins":25},"elorian/glimpse":{"draws":3,"losses":7,"wins":16},"fireworks/ember-1":{"draws":10,"losses":10,"wins":28},"gemini-3.1-pro-preview":{"draws":10,"losses":12,"wins":26},"gemini-4-argon":{"draws":4,"losses":32,"wins":12},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":40},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":64},"google/gemini-3.6-flash":{"draws":19,"losses":26,"wins":47},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":30},"google/gemma-4-31b-it":{"draws":7,"losses":1,"wins":20},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":8,"losses":13,"wins":25},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":37},"gpt-5.5":{"draws":11,"losses":8,"wins":25},"gpt-5.6-luna":{"draws":12,"losses":3,"wins":33},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":23},"gpt-5.6-terra":{"draws":16,"losses":4,"wins":26},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":12,"losses":6,"wins":30},"gpt-6-sol":{"draws":8,"losses":27,"wins":13},"gpt-6.1-sol":{"draws":2,"losses":37,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":5,"losses":6,"wins":21},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":3,"wins":39},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":13,"wins":26},"meta/muse-spark-1.3":{"draws":10,"losses":13,"wins":25},"meta/muse-spark-open":{"draws":4,"losses":13,"wins":29},"meta/muse-wonder":{"draws":12,"losses":17,"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":8,"losses":0,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":27,"wins":12},"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":12,"losses":3,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":20},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":34},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":9,"wins":27},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":23},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":10,"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":31,"losses":41,"wins":86},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":26},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":13,"wins":24},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":8,"losses":3,"wins":37},"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":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":26},"x-ai/grok-4.7":{"draws":1,"losses":24,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":23,"losses":10,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":13,"wins":28},"z-ai/glm-5.3-flashx":{"draws":13,"losses":12,"wins":23}},"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},"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":0,"losses":0,"wins":2},"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":30},"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":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":10,"wins":33},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":11},"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":3,"wins":35},"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":93},"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":0,"losses":0,"wins":4},"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":3,"losses":4,"wins":19},"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":45,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":18,"losses":14,"wins":46},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":8,"losses":49,"wins":25},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":10,"losses":8,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":6,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":20,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":7,"losses":6,"wins":19},"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":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":21,"losses":11,"wins":52},"google/gemini-3.6-flash":{"draws":16,"losses":27,"wins":49},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":22},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":18},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":7,"wins":30},"gpt-5.4":{"draws":7,"losses":16,"wins":23},"gpt-5.4-mini":{"draws":9,"losses":2,"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":22,"wins":19},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":9,"losses":28,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":35},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":18,"wins":22},"meta/muse-spark-open":{"draws":9,"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":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":36,"wins":6},"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":10,"losses":3,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":12},"o3":{"draws":7,"losses":6,"wins":53},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":10,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":17},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"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":23,"losses":44,"wins":91},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":15,"wins":23},"thinkingmachines/inkling":{"draws":12,"losses":2,"wins":50},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10":{"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":29,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":5,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":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":6,"losses":7,"wins":31},"claude-fable-5":{"draws":4,"losses":24,"wins":20},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":26},"claude-opus-4-5":{"draws":10,"losses":18,"wins":50},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":4,"losses":52,"wins":26},"claude-opus-5-5":{"draws":2,"losses":41,"wins":9},"claude-sonnet-5":{"draws":7,"losses":12,"wins":29},"claude-sonnet-5-5":{"draws":5,"losses":20,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":51},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":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":14,"wins":31},"gemini-3.1-pro-preview":{"draws":5,"losses":6,"wins":21},"gemini-4-argon":{"draws":3,"losses":35,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":25},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":36},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":59},"google/gemini-3.6-flash":{"draws":12,"losses":25,"wins":55},"google/gemini-3.8-flash":{"draws":5,"losses":15,"wins":28},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":5,"losses":5,"wins":32},"gpt-5.4":{"draws":3,"losses":16,"wins":27},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":5,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":29},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":23},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":28},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":5,"losses":8,"wins":35},"gpt-6-sol":{"draws":5,"losses":24,"wins":19},"gpt-6.1-sol":{"draws":4,"losses":34,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":23},"inception/mercury-3":{"draws":9,"losses":7,"wins":16},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":38},"meta/muse-glimmer-30b":{"draws":7,"losses":3,"wins":32},"meta/muse-spark-1.2":{"draws":9,"losses":10,"wins":27},"meta/muse-spark-1.3":{"draws":4,"losses":20,"wins":24},"meta/muse-spark-open":{"draws":6,"losses":11,"wins":29},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"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":5,"losses":3,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":14,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":29,"wins":13},"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":7,"losses":5,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":2,"losses":16,"wins":48},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":30},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":36},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":15,"wins":28},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"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":22,"losses":45,"wins":91},"stealth/space-bunny-alpha":{"draws":6,"losses":7,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":20},"tencent/hy4-preview":{"draws":2,"losses":15,"wins":29},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":43},"thinkingmachines/inkling-small":{"draws":7,"losses":5,"wins":36},"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":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":5,"losses":24,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":18,"wins":22},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":27}},"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},"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":2},"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":12},"moonshotai/kimi-k3":{"draws":1,"losses":4,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":7,"wins":36},"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":40},"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":4},"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":0,"losses":1,"wins":25},"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":9,"losses":14,"wins":5},"claude-fable-5":{"draws":4,"losses":25,"wins":1},"claude-fable-5-1":{"draws":2,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":4},"claude-opus-4-5":{"draws":11,"losses":34,"wins":5},"claude-opus-4-8":{"draws":6,"losses":22,"wins":2},"claude-opus-5":{"draws":7,"losses":37,"wins":2},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":10,"losses":19,"wins":1},"claude-sonnet-5-5":{"draws":3,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":15,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":2},"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":22,"wins":3},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":5},"gemini-4-argon":{"draws":2,"losses":28,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":9},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":3},"google/gemini-3.5-flash-lite":{"draws":21,"losses":25,"wins":10},"google/gemini-3.6-flash":{"draws":13,"losses":40,"wins":5},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":15,"wins":1},"gpt-5.4":{"draws":8,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":22,"wins":6},"gpt-5.5":{"draws":8,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":24,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":14,"wins":3},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":8,"losses":18,"wins":4},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":6,"wins":9},"inception/mercury-3":{"draws":2,"losses":16,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":17,"wins":12},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":6,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":4,"losses":22,"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":6,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":10,"wins":3},"o3":{"draws":10,"losses":35,"wins":5},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":10},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":19,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":1},"qwen/qwen3.8-max-0902":{"draws":9,"losses":19,"wins":2},"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":22,"losses":57,"wins":7},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":15,"wins":13},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":11},"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":24,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":24,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":21,"losses":20,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":37,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":25,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":31},"claude-fable-5":{"draws":7,"losses":26,"wins":15},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":12,"losses":14,"wins":20},"claude-opus-4-5":{"draws":24,"losses":10,"wins":44},"claude-opus-4-8":{"draws":8,"losses":17,"wins":19},"claude-opus-5":{"draws":12,"losses":57,"wins":13},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":12,"losses":12,"wins":24},"claude-sonnet-5-5":{"draws":6,"losses":25,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":55},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":12,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":27},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":9,"losses":13,"wins":26},"gemini-3.1-pro-preview":{"draws":6,"losses":9,"wins":33},"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":10,"losses":4,"wins":30},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"wins":57},"google/gemini-3.6-flash":{"draws":12,"losses":23,"wins":57},"google/gemini-3.8-flash":{"draws":5,"losses":21,"wins":22},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":17},"gpt-4.1":{"draws":2,"losses":1,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":8,"wins":26},"gpt-5.4":{"draws":8,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":36},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":22},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":7,"losses":14,"wins":27},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inception/mercury-3":{"draws":6,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":44},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":12,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":7,"losses":16,"wins":23},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":7,"wins":27},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":4,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":6,"losses":12,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":39},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":21},"qwen/qwen3.8-max":{"draws":14,"losses":11,"wins":23},"qwen/qwen3.8-max-0902":{"draws":9,"losses":22,"wins":17},"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":28,"losses":48,"wins":82},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":19,"wins":21},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":36},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":28},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":9,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":18,"losses":20,"wins":58},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":14},"z-ai/glm-5.3-flash":{"draws":3,"losses":19,"wins":26},"z-ai/glm-5.3-flashx":{"draws":11,"losses":19,"wins":18}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":23,"wins":26},"claude-fable-5":{"draws":12,"losses":55,"wins":11},"claude-fable-5-1":{"draws":6,"losses":84,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":48,"wins":11},"claude-opus-4-5":{"draws":35,"losses":55,"wins":36},"claude-opus-4-8":{"draws":15,"losses":45,"wins":10},"claude-opus-5":{"draws":10,"losses":107,"wins":11},"claude-opus-5-5":{"draws":8,"losses":74,"wins":0},"claude-sonnet-5":{"draws":19,"losses":37,"wins":22},"claude-sonnet-5-5":{"draws":16,"losses":49,"wins":13},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":33,"losses":32,"wins":49},"deepseek/deepseek-v4-pro":{"draws":17,"losses":36,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":31,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":34,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":61,"wins":7},"elorian/glimpse":{"draws":11,"losses":22,"wins":9},"fireworks/ember-1":{"draws":27,"losses":35,"wins":16},"gemini-3.1-pro-preview":{"draws":17,"losses":36,"wins":25},"gemini-4-argon":{"draws":5,"losses":68,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":13,"wins":31},"google/gemini-3.5-flash":{"draws":23,"losses":48,"wins":27},"google/gemini-3.5-flash-lite":{"draws":32,"losses":42,"wins":40},"google/gemini-3.6-flash":{"draws":40,"losses":82,"wins":30},"google/gemini-3.8-flash":{"draws":12,"losses":58,"wins":8},"google/gemma-4-31b-it":{"draws":15,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":9,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":18,"losses":31,"wins":19},"gpt-5.4":{"draws":12,"losses":47,"wins":17},"gpt-5.4-mini":{"draws":19,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":12,"losses":27,"wins":35},"gpt-5.5":{"draws":24,"losses":33,"wins":15},"gpt-5.6-luna":{"draws":25,"losses":27,"wins":26},"gpt-5.6-sol":{"draws":14,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":36,"wins":16},"gpt-6-astra":{"draws":4,"losses":73,"wins":1},"gpt-6-luna":{"draws":22,"losses":38,"wins":18},"gpt-6-sol":{"draws":11,"losses":62,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":75,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":10,"wins":25},"inception/mercury-3":{"draws":10,"losses":26,"wins":12},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":24,"wins":43},"meta/muse-glimmer-30b":{"draws":23,"losses":18,"wins":27},"meta/muse-spark-1.2":{"draws":18,"losses":42,"wins":14},"meta/muse-spark-1.3":{"draws":11,"losses":54,"wins":13},"meta/muse-spark-open":{"draws":11,"losses":48,"wins":17},"meta/muse-wonder":{"draws":10,"losses":59,"wins":9},"minimax/minimax-m3":{"draws":10,"losses":15,"wins":15},"minimax/minimax-m3.1-flash":{"draws":16,"losses":33,"wins":23},"mistralai/mistral-large-4-0":{"draws":14,"losses":21,"wins":13},"mistralai/mistral-medium-3-5":{"draws":13,"losses":11,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":65,"wins":1},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":21,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":13,"wins":11},"o3":{"draws":17,"losses":61,"wins":32},"openai/gpt-oss-120b":{"draws":20,"losses":21,"wins":27},"poolside/laguna-s-2.1":{"draws":21,"losses":30,"wins":21},"qwen/qwen3.7-max":{"draws":9,"losses":19,"wins":16},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":39,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":35,"wins":13},"qwen/qwen3.8-flash":{"draws":16,"losses":29,"wins":7},"qwen/qwen3.8-max":{"draws":26,"losses":38,"wins":14},"qwen/qwen3.8-max-0902":{"draws":19,"losses":43,"wins":16},"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":45,"losses":160,"wins":63},"stealth/space-bunny-alpha":{"draws":13,"losses":29,"wins":22},"stepfun/step-3.7-flash":{"draws":13,"losses":19,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":17,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":45,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":33,"wins":48},"thinkingmachines/inkling-small":{"draws":25,"losses":30,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":20,"losses":40,"wins":18},"x-ai/grok-4.6":{"draws":19,"losses":47,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.5":{"draws":39,"losses":38,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":33,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":9},"z-ai/glm-5.2":{"draws":43,"losses":66,"wins":47},"z-ai/glm-5.3":{"draws":10,"losses":59,"wins":7},"z-ai/glm-5.3-flash":{"draws":16,"losses":50,"wins":12},"z-ai/glm-5.3-flashx":{"draws":16,"losses":44,"wins":18}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":12,"wins":57},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":6,"losses":93,"wins":9},"claude-haiku-5-5":{"draws":22,"losses":24,"wins":46},"claude-opus-4-5":{"draws":37,"losses":25,"wins":94},"claude-opus-4-8":{"draws":15,"losses":30,"wins":43},"claude-opus-5":{"draws":29,"losses":104,"wins":31},"claude-opus-5-5":{"draws":13,"losses":83,"wins":8},"claude-sonnet-5":{"draws":14,"losses":21,"wins":61},"claude-sonnet-5-5":{"draws":18,"losses":36,"wins":42},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":29},"deepseek/deepseek-v4-flash":{"draws":23,"losses":7,"wins":114},"deepseek/deepseek-v4-pro":{"draws":17,"losses":20,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":19,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":23,"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":22,"losses":26,"wins":48},"gemini-3.1-pro-preview":{"draws":18,"losses":24,"wins":54},"gemini-4-argon":{"draws":6,"losses":79,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":54},"google/gemini-3.5-flash":{"draws":22,"losses":34,"wins":64},"google/gemini-3.5-flash-lite":{"draws":36,"losses":19,"wins":113},"google/gemini-3.6-flash":{"draws":26,"losses":42,"wins":84},"google/gemini-3.8-flash":{"draws":20,"losses":40,"wins":36},"google/gemma-4-31b-it":{"draws":15,"losses":2,"wins":39},"gpt-4.1":{"draws":6,"losses":6,"wins":20},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":9},"gpt-5":{"draws":10,"losses":20,"wins":54},"gpt-5.4":{"draws":16,"losses":35,"wins":41},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":44},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":70},"gpt-5.5":{"draws":20,"losses":25,"wins":43},"gpt-5.6-luna":{"draws":21,"losses":18,"wins":57},"gpt-5.6-sol":{"draws":16,"losses":39,"wins":41},"gpt-5.6-terra":{"draws":22,"losses":16,"wins":54},"gpt-6-astra":{"draws":5,"losses":79,"wins":12},"gpt-6-luna":{"draws":27,"losses":17,"wins":52},"gpt-6-sol":{"draws":14,"losses":55,"wins":27},"gpt-6.1-sol":{"draws":8,"losses":75,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":3,"wins":48},"inception/mercury-3":{"draws":14,"losses":9,"wins":41},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":46},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":77},"meta/muse-glimmer-30b":{"draws":20,"losses":9,"wins":55},"meta/muse-spark-1.2":{"draws":16,"losses":26,"wins":50},"meta/muse-spark-1.3":{"draws":16,"losses":37,"wins":43},"meta/muse-spark-open":{"draws":12,"losses":31,"wins":49},"meta/muse-wonder":{"draws":21,"losses":44,"wins":31},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":36},"minimax/minimax-m3.1-flash":{"draws":17,"losses":14,"wins":53},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":32},"mistralai/mistral-medium-3-5":{"draws":16,"losses":2,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":22,"losses":21,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":66,"wins":18},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":4,"wins":30},"o3":{"draws":15,"losses":23,"wins":94},"openai/gpt-oss-120b":{"draws":15,"losses":8,"wins":61},"poolside/laguna-s-2.1":{"draws":20,"losses":13,"wins":59},"qwen/qwen3.7-max":{"draws":19,"losses":7,"wins":30},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":26,"wins":50},"qwen/qwen3.8-27b":{"draws":15,"losses":13,"wins":40},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":39},"qwen/qwen3.8-max":{"draws":22,"losses":19,"wins":55},"qwen/qwen3.8-max-0902":{"draws":26,"losses":34,"wins":36},"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":56,"losses":98,"wins":162},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"wins":51},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":58},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":30},"tencent/hy4-preview":{"draws":18,"losses":21,"wins":53},"thinkingmachines/inkling":{"draws":33,"losses":16,"wins":79},"thinkingmachines/inkling-small":{"draws":25,"losses":6,"wins":65},"unbiased/pareto-26.10":{"draws":3,"losses":28,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":25,"wins":5},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":19},"x-ai/grok-4.5":{"draws":18,"losses":32,"wins":46},"x-ai/grok-4.6":{"draws":20,"losses":32,"wins":44},"x-ai/grok-4.7":{"draws":8,"losses":54,"wins":22},"x-ai/grok-build-0.1":{"draws":10,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":33,"losses":7,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":22,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":30,"wins":22},"z-ai/glm-5.2":{"draws":42,"losses":27,"wins":123},"z-ai/glm-5.3":{"draws":19,"losses":40,"wins":33},"z-ai/glm-5.3-flash":{"draws":15,"losses":40,"wins":41},"z-ai/glm-5.3-flashx":{"draws":26,"losses":35,"wins":35}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":34},"claude-fable-5":{"draws":7,"losses":21,"wins":20},"claude-fable-5-1":{"draws":3,"losses":44,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":11,"losses":19,"wins":48},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":3,"losses":58,"wins":21},"claude-opus-5-5":{"draws":3,"losses":37,"wins":12},"claude-sonnet-5":{"draws":4,"losses":11,"wins":33},"claude-sonnet-5-5":{"draws":4,"losses":22,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":65},"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":17,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":21,"wins":20},"elorian/glimpse":{"draws":1,"losses":7,"wins":18},"fireworks/ember-1":{"draws":5,"losses":17,"wins":26},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":34},"gemini-4-argon":{"draws":2,"losses":31,"wins":15},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":45},"google/gemini-3.5-flash-lite":{"draws":5,"losses":9,"wins":70},"google/gemini-3.6-flash":{"draws":9,"losses":28,"wins":55},"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":3,"losses":9,"wins":30},"gpt-5.4":{"draws":3,"losses":18,"wins":25},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":6,"losses":10,"wins":32},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":33},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":23},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":23},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"gpt-6-luna":{"draws":11,"losses":8,"wins":29},"gpt-6-sol":{"draws":7,"losses":28,"wins":13},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"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":5,"losses":2,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":42},"meta/muse-glimmer-30b":{"draws":4,"losses":7,"wins":31},"meta/muse-spark-1.2":{"draws":3,"losses":14,"wins":29},"meta/muse-spark-1.3":{"draws":8,"losses":18,"wins":22},"meta/muse-spark-open":{"draws":1,"losses":16,"wins":29},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"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":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":10},"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":6,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":9,"wins":12},"o3":{"draws":4,"losses":10,"wins":52},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":38},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":38},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":14,"wins":30},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":26},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":19},"qwen/qwen3.8-max":{"draws":7,"losses":19,"wins":22},"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":22,"losses":43,"wins":93},"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":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":5,"losses":21,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":47},"thinkingmachines/inkling-small":{"draws":6,"losses":10,"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":23,"wins":21},"x-ai/grok-4.6":{"draws":4,"losses":16,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":7,"losses":15,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":9},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":65},"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":6,"losses":16,"wins":26}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":9,"wins":17},"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":22,"wins":11},"claude-opus-4-5":{"draws":33,"losses":18,"wins":27},"claude-opus-4-8":{"draws":14,"losses":16,"wins":14},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":25,"losses":5,"wins":42},"deepseek/deepseek-v4-pro":{"draws":15,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":12},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":13,"losses":18,"wins":17},"gemini-3.1-pro-preview":{"draws":16,"losses":19,"wins":13},"gemini-4-argon":{"draws":1,"losses":45,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":18,"losses":19,"wins":23},"google/gemini-3.5-flash-lite":{"draws":33,"losses":16,"wins":35},"google/gemini-3.6-flash":{"draws":27,"losses":40,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":14},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":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":19,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":18,"losses":12,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":15,"wins":18},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":19,"losses":12,"wins":17},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":19,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":18,"wins":15},"meta/muse-spark-1.3":{"draws":15,"losses":20,"wins":13},"meta/muse-spark-open":{"draws":16,"losses":18,"wins":12},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"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":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":41,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":3,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":7},"o3":{"draws":9,"losses":24,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":14},"qwen/qwen3.7-max":{"draws":13,"losses":4,"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":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":24,"losses":11,"wins":13},"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":14,"losses":15,"wins":15},"stealth/ox-alpha":{"draws":39,"losses":68,"wins":51},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":16,"losses":15,"wins":15},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":18,"losses":6,"wins":24},"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":23,"wins":13},"x-ai/grok-4.6":{"draws":16,"losses":25,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":27,"losses":11,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":36,"losses":21,"wins":39},"z-ai/glm-5.3":{"draws":7,"losses":30,"wins":9},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":18,"losses":15,"wins":15}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":28},"claude-fable-5":{"draws":11,"losses":13,"wins":18},"claude-fable-5-1":{"draws":5,"losses":35,"wins":8},"claude-haiku-5-5":{"draws":6,"losses":12,"wins":22},"claude-opus-4-5":{"draws":11,"losses":8,"wins":49},"claude-opus-4-8":{"draws":6,"losses":9,"wins":23},"claude-opus-5":{"draws":9,"losses":44,"wins":17},"claude-opus-5-5":{"draws":4,"losses":34,"wins":8},"claude-sonnet-5":{"draws":6,"losses":7,"wins":29},"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":4,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":11,"wins":25},"elorian/glimpse":{"draws":3,"losses":6,"wins":15},"fireworks/ember-1":{"draws":4,"losses":8,"wins":30},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":29},"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":4,"losses":7,"wins":43},"google/gemini-3.5-flash-lite":{"draws":9,"losses":5,"wins":62},"google/gemini-3.6-flash":{"draws":14,"losses":13,"wins":55},"google/gemini-3.8-flash":{"draws":2,"losses":14,"wins":26},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":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":4,"losses":5,"wins":31},"gpt-6-astra":{"draws":2,"losses":34,"wins":6},"gpt-6-luna":{"draws":9,"losses":9,"wins":24},"gpt-6-sol":{"draws":2,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":20},"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":0,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":39},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":33},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":27},"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":4,"wins":15},"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":2,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":27,"wins":11},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":15},"o3":{"draws":2,"losses":7,"wins":55},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":29},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":34},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":21},"qwen/qwen3.8-max":{"draws":7,"losses":11,"wins":24},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":27},"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":32,"losses":28,"wins":82},"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":1},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":15},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":28},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":7,"losses":3,"wins":32},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":8,"wins":25},"x-ai/grok-4.6":{"draws":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":10,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":55},"z-ai/glm-5.3":{"draws":4,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":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":11,"losses":3,"wins":26},"claude-fable-5":{"draws":8,"losses":16,"wins":18},"claude-fable-5-1":{"draws":0,"losses":36,"wins":12},"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":5,"losses":34,"wins":31},"claude-opus-5-5":{"draws":1,"losses":36,"wins":9},"claude-sonnet-5":{"draws":7,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":11,"losses":2,"wins":49},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":6,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":8,"wins":22},"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":8,"losses":5,"wins":29},"gemini-4-argon":{"draws":3,"losses":21,"wins":18},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":33},"google/gemini-3.5-flash-lite":{"draws":17,"losses":6,"wins":53},"google/gemini-3.6-flash":{"draws":20,"losses":15,"wins":47},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":17},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":5,"wins":24},"gpt-5.4":{"draws":12,"losses":12,"wins":18},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":32},"gpt-5.5":{"draws":10,"losses":5,"wins":11},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":23},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":25},"gpt-6-astra":{"draws":0,"losses":37,"wins":5},"gpt-6-luna":{"draws":15,"losses":5,"wins":22},"gpt-6-sol":{"draws":3,"losses":23,"wins":16},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inception/mercury-3":{"draws":4,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":35},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":24},"meta/muse-spark-open":{"draws":3,"losses":10,"wins":29},"meta/muse-wonder":{"draws":8,"losses":14,"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":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":24,"wins":14},"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":12,"losses":1,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":15},"o3":{"draws":6,"losses":7,"wins":51},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":7,"losses":4,"wins":29},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":22},"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":31,"losses":30,"wins":81},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":11,"losses":10,"wins":21},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":44},"thinkingmachines/inkling-small":{"draws":9,"losses":2,"wins":31},"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":6,"wins":24},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":19},"x-ai/grok-4.7":{"draws":3,"losses":17,"wins":16},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":1,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":24,"losses":7,"wins":53},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":10},"z-ai/glm-5.3-flash":{"draws":2,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":9,"losses":9,"wins":24}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":9,"wins":19},"claude-fable-5":{"draws":13,"losses":23,"wins":12},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":30,"losses":17,"wins":31},"claude-opus-4-8":{"draws":14,"losses":10,"wins":20},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":13,"losses":13,"wins":22},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":29,"losses":3,"wins":40},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":7,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":23,"wins":16},"elorian/glimpse":{"draws":8,"losses":8,"wins":10},"fireworks/ember-1":{"draws":16,"losses":9,"wins":23},"gemini-3.1-pro-preview":{"draws":15,"losses":12,"wins":21},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":22,"losses":9,"wins":29},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":42},"google/gemini-3.6-flash":{"draws":25,"losses":31,"wins":36},"google/gemini-3.8-flash":{"draws":13,"losses":16,"wins":19},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":14},"gpt-4.1":{"draws":8,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":18,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":18,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":13,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":24,"wins":14},"gpt-5.6-terra":{"draws":17,"losses":7,"wins":22},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":17},"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":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":13,"losses":18,"wins":17},"meta/muse-spark-open":{"draws":14,"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":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":38,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":9},"o3":{"draws":17,"losses":14,"wins":35},"openai/gpt-oss-120b":{"draws":19,"losses":4,"wins":19},"poolside/laguna-s-2.1":{"draws":19,"losses":5,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":11,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-max-0902":{"draws":18,"losses":9,"wins":21},"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":44,"losses":57,"wins":57},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":18,"losses":12,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":5,"wins":38},"thinkingmachines/inkling-small":{"draws":19,"losses":6,"wins":23},"unbiased/pareto-26.10":{"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":14,"wins":25},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":3,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":39,"losses":23,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":37},"claude-fable-5":{"draws":3,"losses":16,"wins":29},"claude-fable-5-1":{"draws":6,"losses":35,"wins":13},"claude-haiku-5-5":{"draws":7,"losses":5,"wins":34},"claude-opus-4-5":{"draws":6,"losses":14,"wins":58},"claude-opus-4-8":{"draws":6,"losses":4,"wins":34},"claude-opus-5":{"draws":7,"losses":39,"wins":36},"claude-opus-5-5":{"draws":6,"losses":31,"wins":15},"claude-sonnet-5":{"draws":0,"losses":3,"wins":45},"claude-sonnet-5-5":{"draws":2,"losses":14,"wins":32},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":65},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":39},"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":8,"wins":35},"gemini-3.1-pro-preview":{"draws":4,"losses":1,"wins":43},"gemini-4-argon":{"draws":1,"losses":30,"wins":17},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":50},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":10,"losses":16,"wins":66},"google/gemini-3.8-flash":{"draws":4,"losses":10,"wins":34},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":0,"losses":3,"wins":39},"gpt-5.4":{"draws":2,"losses":12,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":5,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":2,"losses":6,"wins":40},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":26},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":38},"gpt-6-astra":{"draws":6,"losses":35,"wins":7},"gpt-6-luna":{"draws":9,"losses":2,"wins":37},"gpt-6-sol":{"draws":6,"losses":17,"wins":25},"gpt-6.1-sol":{"draws":5,"losses":32,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"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":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":46},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":39},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":42},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":36},"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":1,"losses":3,"wins":8},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":24,"wins":19},"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":1,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"o3":{"draws":1,"losses":8,"wins":57},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":37},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":44},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":6,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"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":14,"losses":16,"wins":128},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":24},"tencent/hy4-preview":{"draws":3,"losses":14,"wins":29},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":58},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":46},"unbiased/pareto-26.10":{"draws":3,"losses":11,"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":4,"losses":5,"wins":39},"x-ai/grok-4.6":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":19},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":87},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":5,"losses":12,"wins":31},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":14,"losses":24,"wins":10},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":26,"losses":25,"wins":27},"claude-opus-4-8":{"draws":6,"losses":19,"wins":19},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":18,"losses":11,"wins":19},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":19,"losses":9,"wins":44},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":21},"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":15,"losses":14,"wins":19},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":19},"gemini-4-argon":{"draws":3,"losses":40,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":19,"losses":11,"wins":30},"google/gemini-3.5-flash-lite":{"draws":23,"losses":11,"wins":50},"google/gemini-3.6-flash":{"draws":30,"losses":34,"wins":28},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":14},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":11,"wins":20},"gpt-5.4":{"draws":12,"losses":20,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":13,"losses":18,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":21},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":10},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":10,"losses":29,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":7,"losses":10,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":29},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":15},"meta/muse-spark-open":{"draws":14,"losses":19,"wins":13},"meta/muse-wonder":{"draws":8,"losses":26,"wins":14},"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":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":15,"losses":11,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":38,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":3,"wins":10},"o3":{"draws":11,"losses":19,"wins":36},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":22,"wins":13},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":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":39,"losses":62,"wins":57},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":10,"losses":18,"wins":18},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":30},"unbiased/pareto-26.10":{"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":14,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":2,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":21,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":22,"wins":11},"z-ai/glm-5.3-flash":{"draws":9,"losses":20,"wins":19},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":1,"losses":8,"wins":39},"claude-fable-5-1":{"draws":4,"losses":15,"wins":35},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":0,"losses":6,"wins":72},"claude-opus-4-8":{"draws":1,"losses":1,"wins":42},"claude-opus-5":{"draws":3,"losses":9,"wins":70},"claude-opus-5-5":{"draws":4,"losses":16,"wins":32},"claude-sonnet-5":{"draws":0,"losses":2,"wins":46},"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":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":1,"losses":1,"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":1,"wins":47},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"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":3,"losses":0,"wins":81},"google/gemini-3.6-flash":{"draws":2,"losses":5,"wins":85},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":43},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":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":4,"wins":40},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":46},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":41},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":0,"losses":6,"wins":26},"gpt-6-luna":{"draws":3,"losses":0,"wins":45},"gpt-6-sol":{"draws":7,"losses":4,"wins":37},"gpt-6.1-sol":{"draws":5,"losses":8,"wins":35},"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":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":46},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":46},"meta/muse-spark-open":{"draws":2,"losses":0,"wins":44},"meta/muse-wonder":{"draws":3,"losses":3,"wins":42},"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":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":44},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":7,"wins":37},"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":1,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"o3":{"draws":1,"losses":1,"wins":64},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"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":5,"losses":4,"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":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":0,"losses":3,"wins":43},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":4,"losses":1,"wins":11},"unbiased/pareto-26.10-preview":{"draws":3,"losses":5,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":46},"x-ai/grok-4.6":{"draws":0,"losses":1,"wins":47},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":28},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":39},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":45},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":45}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":10,"losses":26,"wins":12},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":5,"losses":20,"wins":21},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":7,"losses":17,"wins":20},"claude-opus-5":{"draws":10,"losses":62,"wins":10},"claude-opus-5-5":{"draws":7,"losses":43,"wins":2},"claude-sonnet-5":{"draws":8,"losses":14,"wins":26},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":13,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"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":3,"losses":22,"wins":23},"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":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":12,"losses":20,"wins":52},"google/gemini-3.6-flash":{"draws":17,"losses":33,"wins":42},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":21},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":19},"gpt-4.1":{"draws":1,"losses":6,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":14,"wins":23},"gpt-5.4":{"draws":11,"losses":15,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":32},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":13},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":8,"losses":36,"wins":4},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"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":0,"losses":0,"wins":2},"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":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":16,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":2},"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":9,"wins":31},"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":2,"losses":8,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"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":30,"losses":57,"wins":71},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":7,"losses":19,"wins":20},"thinkingmachines/inkling":{"draws":8,"losses":11,"wins":45},"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":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":10,"losses":27,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":13,"losses":13,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":20,"losses":27,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":36},"claude-fable-5":{"draws":3,"losses":10,"wins":35},"claude-fable-5-1":{"draws":4,"losses":24,"wins":26},"claude-haiku-5-5":{"draws":5,"losses":8,"wins":33},"claude-opus-4-5":{"draws":3,"losses":11,"wins":64},"claude-opus-4-8":{"draws":3,"losses":10,"wins":31},"claude-opus-5":{"draws":12,"losses":25,"wins":45},"claude-opus-5-5":{"draws":6,"losses":27,"wins":19},"claude-sonnet-5":{"draws":1,"losses":6,"wins":41},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":61},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":6,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":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":5,"losses":8,"wins":35},"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":6,"losses":8,"wins":46},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":69},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":26},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":6,"wins":36},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":4,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":3,"losses":7,"wins":34},"gpt-5.6-luna":{"draws":1,"losses":6,"wins":41},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":37},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":37},"gpt-6-astra":{"draws":4,"losses":32,"wins":12},"gpt-6-luna":{"draws":6,"losses":4,"wins":38},"gpt-6-sol":{"draws":3,"losses":9,"wins":20},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":31},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":34},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":40},"meta/muse-spark-open":{"draws":2,"losses":7,"wins":37},"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":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":7,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":18,"wins":21},"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":6,"wins":36},"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":20,"wins":125},"stealth/space-bunny-alpha":{"draws":0,"losses":4,"wins":34},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":36},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":55},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":45},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":37},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":12,"wins":25},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":5,"losses":13,"wins":78},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":34},"z-ai/glm-5.3-flashx":{"draws":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":6,"losses":17,"wins":31},"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":13,"wins":62},"claude-opus-5-5":{"draws":5,"losses":21,"wins":26},"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":1,"losses":0,"wins":71},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":5,"wins":42},"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":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":46},"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":1,"losses":4,"wins":55},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":84},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":82},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":4,"losses":5,"wins":37},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":1,"losses":5,"wins":38},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":38},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":44},"gpt-6-astra":{"draws":8,"losses":15,"wins":25},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":4,"wins":39},"gpt-6.1-sol":{"draws":0,"losses":7,"wins":25},"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":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":51},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":47},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":4,"losses":4,"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":10},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":7,"wins":34},"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":2,"wins":40},"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":1,"losses":3,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":30},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"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":5,"wins":151},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":8},"unbiased/pareto-26.10-preview":{"draws":1,"losses":6,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":46},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.7":{"draws":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":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":6,"losses":3,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":2,"wins":43},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":42}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":11,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":27,"wins":0},"claude-opus-4-5":{"draws":28,"losses":30,"wins":2},"claude-opus-4-8":{"draws":10,"losses":24,"wins":2},"claude-opus-5":{"draws":11,"losses":45,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":12,"losses":23,"wins":1},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":23,"losses":26,"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":16,"losses":18,"wins":2},"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":21,"wins":2},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":5},"gemini-4-argon":{"draws":4,"losses":32,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":18,"losses":27,"wins":1},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":7},"google/gemini-3.6-flash":{"draws":26,"losses":40,"wins":2},"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":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":12,"losses":16,"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":13,"losses":17,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":12,"losses":22,"wins":2},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":2},"gpt-6-sol":{"draws":4,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":0},"inception/mercury-3":{"draws":12,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":13,"losses":10,"wins":7},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":6},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-open":{"draws":9,"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":10,"losses":6,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":3},"o3":{"draws":9,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":9},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":2},"qwen/qwen3.8-max":{"draws":17,"losses":17,"wins":2},"qwen/qwen3.8-max-0902":{"draws":17,"losses":16,"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":32,"losses":57,"wins":11},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":1},"stepfun/step-3.7-flash":{"draws":8,"losses":13,"wins":5},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"tencent/hy4-preview":{"draws":14,"losses":18,"wins":2},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":7},"thinkingmachines/inkling-small":{"draws":16,"losses":13,"wins":7},"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":12,"losses":22,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":29,"losses":27,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":32,"losses":34,"wins":6},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":2}},"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},"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":0,"wins":2},"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":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":1},"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":8,"losses":2,"wins":18},"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":0,"losses":2,"wins":2},"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":6,"losses":1,"wins":9},"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":15,"losses":8,"wins":15},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":17,"wins":8},"claude-opus-4-5":{"draws":28,"losses":27,"wins":13},"claude-opus-4-8":{"draws":12,"losses":18,"wins":8},"claude-opus-5":{"draws":8,"losses":66,"wins":6},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":15,"losses":18,"wins":9},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":12},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":11,"wins":21},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":17,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":14,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":28,"wins":4},"elorian/glimpse":{"draws":5,"losses":12,"wins":7},"fireworks/ember-1":{"draws":14,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":8},"gemini-4-argon":{"draws":5,"losses":36,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":18,"losses":23,"wins":11},"google/gemini-3.5-flash-lite":{"draws":29,"losses":21,"wins":22},"google/gemini-3.6-flash":{"draws":29,"losses":30,"wins":21},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":6},"google/gemma-4-31b-it":{"draws":15,"losses":4,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":16,"losses":14,"wins":8},"gpt-5.4":{"draws":11,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":17,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":15},"gpt-5.5":{"draws":21,"losses":16,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":20,"losses":15,"wins":5},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":8},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":9},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":7,"wins":18},"meta/muse-glimmer-30b":{"draws":15,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":14,"losses":20,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":20,"wins":11},"meta/muse-wonder":{"draws":12,"losses":25,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":8},"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":14,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":11,"wins":4},"o3":{"draws":11,"losses":27,"wins":16},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":12},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":14,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"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":35,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":16,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":23},"thinkingmachines/inkling-small":{"draws":20,"losses":3,"wins":19},"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":12,"losses":26,"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":26,"losses":10,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":4,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.2":{"draws":41,"losses":28,"wins":15},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":10}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":29},"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":19},"claude-opus-4-5":{"draws":18,"losses":18,"wins":42},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":16,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":19,"wins":20},"elorian/glimpse":{"draws":5,"losses":9,"wins":12},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"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":10,"losses":17,"wins":33},"google/gemini-3.5-flash-lite":{"draws":16,"losses":15,"wins":53},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":18,"wins":23},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":18},"gpt-4.1":{"draws":7,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":6,"losses":5,"wins":31},"gpt-5.4":{"draws":9,"losses":20,"wins":17},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":27},"gpt-5.5":{"draws":8,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":15},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":24},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":11,"losses":11,"wins":26},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":18},"inception/mercury-3":{"draws":7,"losses":4,"wins":21},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":28},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":15},"meta/muse-spark-1.3":{"draws":6,"losses":21,"wins":21},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":20},"meta/muse-wonder":{"draws":9,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":12,"wins":23},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":37,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":14},"o3":{"draws":6,"losses":21,"wins":39},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":34},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":21},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":25},"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":30,"losses":57,"wins":71},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":24},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":29},"unbiased/pareto-26.10":{"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":10,"losses":22,"wins":16},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":52},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":21},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":33},"claude-fable-5":{"draws":6,"losses":21,"wins":21},"claude-fable-5-1":{"draws":4,"losses":41,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":12,"losses":11,"wins":55},"claude-opus-4-8":{"draws":7,"losses":10,"wins":27},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":1,"losses":42,"wins":9},"claude-sonnet-5":{"draws":6,"losses":8,"wins":34},"claude-sonnet-5-5":{"draws":5,"losses":19,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":62},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":11,"wins":29},"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":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":11,"losses":21,"wins":60},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":22},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":2,"wins":31},"gpt-5.4":{"draws":11,"losses":13,"wins":22},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":6,"losses":12,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":33},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":28},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":31},"gpt-6-astra":{"draws":5,"losses":36,"wins":7},"gpt-6-luna":{"draws":6,"losses":6,"wins":36},"gpt-6-sol":{"draws":8,"losses":27,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":27},"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":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":31},"meta/muse-spark-1.2":{"draws":6,"losses":11,"wins":29},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":24},"meta/muse-spark-open":{"draws":5,"losses":9,"wins":32},"meta/muse-wonder":{"draws":8,"losses":21,"wins":19},"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":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":30,"wins":10},"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":6,"losses":2,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":3,"wins":17},"o3":{"draws":3,"losses":9,"wins":54},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":33},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":36},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":22},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":12,"wins":30},"qwen/qwen3.8-max-0902":{"draws":11,"losses":15,"wins":22},"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":23,"losses":31,"wins":104},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":29},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":53},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":42},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.6":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":24,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":10,"losses":15,"wins":71},"z-ai/glm-5.3":{"draws":10,"losses":16,"wins":20},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":29}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":25},"claude-fable-5":{"draws":2,"losses":26,"wins":14},"claude-fable-5-1":{"draws":1,"losses":38,"wins":9},"claude-haiku-5-5":{"draws":2,"losses":20,"wins":18},"claude-opus-4-5":{"draws":9,"losses":16,"wins":43},"claude-opus-4-8":{"draws":4,"losses":15,"wins":19},"claude-opus-5":{"draws":2,"losses":53,"wins":15},"claude-opus-5-5":{"draws":3,"losses":33,"wins":10},"claude-sonnet-5":{"draws":4,"losses":10,"wins":28},"claude-sonnet-5-5":{"draws":4,"losses":17,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":5,"losses":8,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":18,"wins":18},"elorian/glimpse":{"draws":2,"losses":12,"wins":10},"fireworks/ember-1":{"draws":3,"losses":15,"wins":24},"gemini-3.1-pro-preview":{"draws":3,"losses":11,"wins":28},"gemini-4-argon":{"draws":3,"losses":30,"wins":9},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":7,"losses":15,"wins":32},"google/gemini-3.5-flash-lite":{"draws":5,"losses":14,"wins":57},"google/gemini-3.6-flash":{"draws":6,"losses":30,"wins":46},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":24},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":18},"gpt-4.1":{"draws":1,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":4,"losses":8,"wins":26},"gpt-5.4":{"draws":6,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":33},"gpt-5.5":{"draws":3,"losses":13,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":26},"gpt-5.6-sol":{"draws":4,"losses":18,"wins":20},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":26},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":6,"losses":13,"wins":23},"gpt-6-sol":{"draws":3,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":21},"inception/mercury-3":{"draws":1,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":1,"losses":4,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":33},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":5,"losses":11,"wins":24},"meta/muse-spark-1.3":{"draws":3,"losses":15,"wins":24},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":14},"meta/muse-wonder":{"draws":6,"losses":18,"wins":18},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":20},"minimax/minimax-m3.1-flash":{"draws":5,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":2,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":16,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":32,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":15},"o3":{"draws":3,"losses":10,"wins":51},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":28},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":34},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":16,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":19},"qwen/qwen3.8-flash":{"draws":4,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":5,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":5,"losses":16,"wins":21},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":9,"wins":23},"stealth/ox-alpha":{"draws":17,"losses":39,"wins":86},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":4,"losses":15,"wins":23},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":41},"thinkingmachines/inkling-small":{"draws":4,"losses":6,"wins":32},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":19,"wins":20},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":16},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":6,"losses":11,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":9,"losses":21,"wins":54},"z-ai/glm-5.3":{"draws":1,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":3,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":5,"losses":16,"wins":21}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":35},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":5,"losses":35,"wins":14},"claude-haiku-5-5":{"draws":6,"losses":6,"wins":34},"claude-opus-4-5":{"draws":9,"losses":9,"wins":60},"claude-opus-4-8":{"draws":9,"losses":8,"wins":27},"claude-opus-5":{"draws":11,"losses":34,"wins":37},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":6,"losses":5,"wins":37},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":62},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":5,"wins":31},"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":9,"losses":7,"wins":32},"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":6,"wins":47},"google/gemini-3.5-flash-lite":{"draws":8,"losses":5,"wins":71},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":73},"google/gemini-3.8-flash":{"draws":9,"losses":12,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":43},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":30},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":31},"gpt-6-astra":{"draws":6,"losses":33,"wins":9},"gpt-6-luna":{"draws":7,"losses":5,"wins":36},"gpt-6-sol":{"draws":4,"losses":23,"wins":21},"gpt-6.1-sol":{"draws":9,"losses":26,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":8,"losses":1,"wins":23},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":40},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":1,"losses":10,"wins":35},"meta/muse-spark-1.3":{"draws":6,"losses":6,"wins":36},"meta/muse-spark-open":{"draws":6,"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":11},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":19},"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":7,"losses":1,"wins":34},"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":6,"losses":10,"wins":32},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":25},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":32},"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":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":52},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":40},"unbiased/pareto-26.10":{"draws":4,"losses":10,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":33},"x-ai/grok-4.6":{"draws":14,"losses":7,"wins":27},"x-ai/grok-4.7":{"draws":6,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":2,"losses":16,"wins":28},"z-ai/glm-5.3-flash":{"draws":11,"losses":10,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":6,"wins":33}},"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":19,"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},"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},"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":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":33,"wins":5},"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":10,"losses":11,"wins":13},"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},"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":27},"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":3,"losses":9,"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":8,"losses":25,"wins":15},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":22,"losses":22,"wins":34},"claude-opus-4-8":{"draws":7,"losses":14,"wins":23},"claude-opus-5":{"draws":13,"losses":57,"wins":12},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":14,"losses":18,"wins":16},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":14,"wins":19},"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":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash-lite":{"draws":17,"losses":14,"wins":53},"google/gemini-3.6-flash":{"draws":14,"losses":30,"wins":48},"google/gemini-3.8-flash":{"draws":14,"losses":15,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":6,"wins":25},"gpt-5.4":{"draws":15,"losses":18,"wins":13},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":31},"gpt-5.5":{"draws":10,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":17},"gpt-6-astra":{"draws":7,"losses":36,"wins":5},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":8,"losses":35,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":21,"wins":20},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-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":3,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":36,"wins":5},"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":12,"losses":9,"wins":21},"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":50,"losses":53,"wins":55},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":2,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":18,"losses":7,"wins":39},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"unbiased/pareto-26.10-preview":{"draws":3,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":16,"losses":17,"wins":15},"x-ai/grok-4.7":{"draws":9,"losses":20,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":8,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":18,"wins":49},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":18}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":11,"wins":10},"claude-fable-5":{"draws":13,"losses":25,"wins":4},"claude-fable-5-1":{"draws":2,"losses":45,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":21,"losses":37,"wins":10},"claude-opus-4-8":{"draws":11,"losses":24,"wins":3},"claude-opus-5":{"draws":11,"losses":53,"wins":6},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":19,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":25,"losses":17,"wins":20},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":2},"elorian/glimpse":{"draws":5,"losses":12,"wins":5},"fireworks/ember-1":{"draws":12,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":8},"gemini-4-argon":{"draws":1,"losses":39,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":26,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":27,"wins":17},"google/gemini-3.6-flash":{"draws":28,"losses":44,"wins":8},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":4},"google/gemma-4-31b-it":{"draws":11,"losses":10,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":16,"wins":8},"gpt-5.4":{"draws":14,"losses":22,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":20,"wins":11},"gpt-5.5":{"draws":14,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":19,"wins":4},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":2},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":5},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":22,"wins":5},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":7,"wins":11},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":16,"wins":12},"meta/muse-glimmer-30b":{"draws":18,"losses":13,"wins":5},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":3},"meta/muse-spark-open":{"draws":10,"losses":24,"wins":6},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":9},"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-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":38,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":11,"wins":2},"o3":{"draws":14,"losses":33,"wins":9},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":15,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"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":38,"losses":78,"wins":26},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":22,"wins":14},"thinkingmachines/inkling-small":{"draws":19,"losses":17,"wins":6},"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":12,"losses":26,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":17,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":34,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":24,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":17},"claude-fable-5":{"draws":6,"losses":24,"wins":12},"claude-fable-5-1":{"draws":0,"losses":41,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":16,"wins":14},"claude-opus-4-5":{"draws":19,"losses":23,"wins":26},"claude-opus-4-8":{"draws":8,"losses":17,"wins":13},"claude-opus-5":{"draws":11,"losses":53,"wins":16},"claude-opus-5-5":{"draws":2,"losses":41,"wins":3},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":27},"deepseek/deepseek-v4-pro":{"draws":10,"losses":11,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":21,"wins":13},"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":16,"losses":14,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":11,"wins":34},"google/gemini-3.6-flash":{"draws":16,"losses":32,"wins":32},"google/gemini-3.8-flash":{"draws":8,"losses":18,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":10},"gpt-4.1":{"draws":3,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":15,"wins":18},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":16},"gpt-5.5":{"draws":9,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":15,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":25,"wins":13},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":17},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":12,"losses":9,"wins":21},"gpt-6-sol":{"draws":4,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":10},"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":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":6,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":15},"meta/muse-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":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":32,"wins":6},"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":8,"losses":16,"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":0},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10":{"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":22,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":22,"losses":12,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":5},"z-ai/glm-5.2":{"draws":24,"losses":24,"wins":36},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":15},"z-ai/glm-5.3-flash":{"draws":11,"losses":17,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":16,"wins":15}},"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},"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":0,"losses":0,"wins":2},"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":2,"losses":3,"wins":41},"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":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":13,"wins":14},"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":40},"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":0,"wins":4},"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":0,"losses":2,"wins":24},"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},"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},"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-k2.7-code":{"draws":0,"losses":2,"wins":0},"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":4},"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},"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":3,"wins":1},"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":25,"losses":12,"wins":13},"claude-fable-5":{"draws":14,"losses":38,"wins":2},"claude-fable-5-1":{"draws":4,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":16,"losses":31,"wins":7},"claude-opus-4-5":{"draws":38,"losses":42,"wins":10},"claude-opus-4-8":{"draws":15,"losses":32,"wins":7},"claude-opus-5":{"draws":14,"losses":82,"wins":2},"claude-opus-5-5":{"draws":2,"losses":59,"wins":1},"claude-sonnet-5":{"draws":25,"losses":22,"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":38,"losses":24,"wins":20},"deepseek/deepseek-v4-pro":{"draws":19,"losses":23,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":21,"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":24,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":25,"losses":17,"wins":12},"gemini-4-argon":{"draws":6,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":25,"losses":28,"wins":15},"google/gemini-3.5-flash-lite":{"draws":39,"losses":28,"wins":27},"google/gemini-3.6-flash":{"draws":42,"losses":50,"wins":8},"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":10,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":24,"wins":5},"gpt-5.4":{"draws":18,"losses":30,"wins":2},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":21,"losses":25,"wins":16},"gpt-5.5":{"draws":25,"losses":22,"wins":1},"gpt-5.6-luna":{"draws":27,"losses":16,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":2},"gpt-5.6-terra":{"draws":25,"losses":22,"wins":3},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":19,"losses":28,"wins":7},"gpt-6-sol":{"draws":6,"losses":46,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":25,"losses":8,"wins":9},"inception/mercury-3":{"draws":16,"losses":17,"wins":5},"inclusionai/ling-3.0-flash":{"draws":23,"losses":5,"wins":8},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":14,"wins":21},"meta/muse-glimmer-30b":{"draws":28,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":15,"losses":32,"wins":5},"meta/muse-spark-1.3":{"draws":17,"losses":36,"wins":1},"meta/muse-spark-open":{"draws":12,"losses":35,"wins":3},"meta/muse-wonder":{"draws":20,"losses":33,"wins":1},"minimax/minimax-m3":{"draws":11,"losses":8,"wins":13},"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":19,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":21,"losses":22,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":47,"wins":0},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":4},"o3":{"draws":19,"losses":42,"wins":13},"openai/gpt-oss-120b":{"draws":25,"losses":10,"wins":13},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":20,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":17,"losses":16,"wins":3},"qwen/qwen3.8-max":{"draws":27,"losses":23,"wins":4},"qwen/qwen3.8-max-0902":{"draws":28,"losses":22,"wins":4},"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":55,"losses":82,"wins":13},"stealth/space-bunny-alpha":{"draws":20,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":20,"losses":27,"wins":3},"thinkingmachines/inkling":{"draws":25,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":27,"losses":13,"wins":14},"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":16,"losses":37,"wins":1},"x-ai/grok-4.6":{"draws":25,"losses":24,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":46,"losses":22,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":20,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":56,"losses":40,"wins":12},"z-ai/glm-5.3":{"draws":13,"losses":36,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":36,"wins":57},"claude-fable-5":{"draws":4,"losses":92,"wins":18},"claude-fable-5-1":{"draws":0,"losses":117,"wins":7},"claude-haiku-5-5":{"draws":11,"losses":57,"wins":44},"claude-opus-4-5":{"draws":13,"losses":119,"wins":56},"claude-opus-4-8":{"draws":7,"losses":66,"wins":37},"claude-opus-5":{"draws":6,"losses":156,"wins":10},"claude-opus-5-5":{"draws":2,"losses":122,"wins":2},"claude-sonnet-5":{"draws":7,"losses":52,"wins":55},"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":14,"losses":54,"wins":112},"deepseek/deepseek-v4-pro":{"draws":3,"losses":55,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":64,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":58,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":73,"wins":37},"elorian/glimpse":{"draws":4,"losses":33,"wins":23},"fireworks/ember-1":{"draws":8,"losses":70,"wins":36},"gemini-3.1-pro-preview":{"draws":11,"losses":45,"wins":58},"gemini-4-argon":{"draws":0,"losses":108,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":82},"google/gemini-3.5-flash":{"draws":8,"losses":89,"wins":53},"google/gemini-3.5-flash-lite":{"draws":13,"losses":65,"wins":128},"google/gemini-3.6-flash":{"draws":13,"losses":133,"wins":76},"google/gemini-3.8-flash":{"draws":5,"losses":78,"wins":31},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":46},"gpt-4.1":{"draws":4,"losses":18,"wins":16},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":2,"losses":61,"wins":43},"gpt-5.4":{"draws":1,"losses":84,"wins":29},"gpt-5.4-mini":{"draws":9,"losses":18,"wins":49},"gpt-5.4-nano":{"draws":5,"losses":67,"wins":66},"gpt-5.5":{"draws":13,"losses":65,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":44,"wins":56},"gpt-5.6-sol":{"draws":5,"losses":88,"wins":21},"gpt-5.6-terra":{"draws":12,"losses":52,"wins":42},"gpt-6-astra":{"draws":4,"losses":109,"wins":1},"gpt-6-luna":{"draws":15,"losses":62,"wins":37},"gpt-6-sol":{"draws":2,"losses":100,"wins":12},"gpt-6.1-sol":{"draws":0,"losses":107,"wins":7},"inception/mercury-2.5-preview":{"draws":9,"losses":11,"wins":56},"inception/mercury-3":{"draws":5,"losses":44,"wins":25},"inclusionai/ling-3.0-flash":{"draws":10,"losses":16,"wins":54},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":40,"wins":88},"meta/muse-glimmer-30b":{"draws":10,"losses":20,"wins":68},"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":18,"wins":47},"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":6,"losses":8,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":13,"wins":15},"moonshotai/kimi-k3":{"draws":7,"losses":53,"wins":46},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":96,"wins":14},"nex-agi/nex-n2-pro":{"draws":3,"losses":15,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":9,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":28,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":30,"wins":21},"o3":{"draws":10,"losses":77,"wins":83},"openai/gpt-oss-120b":{"draws":6,"losses":21,"wins":73},"poolside/laguna-s-2.1":{"draws":11,"losses":41,"wins":62},"qwen/qwen3.7-max":{"draws":10,"losses":29,"wins":35},"qwen/qwen3.7-plus":{"draws":2,"losses":17,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":67,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":43,"wins":38},"qwen/qwen3.8-flash":{"draws":6,"losses":38,"wins":32},"qwen/qwen3.8-max":{"draws":13,"losses":61,"wins":40},"qwen/qwen3.8-max-0902":{"draws":13,"losses":55,"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":26,"losses":174,"wins":144},"stealth/space-bunny-alpha":{"draws":7,"losses":36,"wins":49},"stepfun/step-3.7-flash":{"draws":8,"losses":32,"wins":58},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":23,"wins":28},"tencent/hy4-preview":{"draws":11,"losses":65,"wins":38},"thinkingmachines/inkling":{"draws":12,"losses":34,"wins":108},"thinkingmachines/inkling-small":{"draws":12,"losses":30,"wins":72},"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":14,"losses":69,"wins":31},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":3,"losses":12,"wins":23},"xiaomi/mimo-v2.5":{"draws":16,"losses":34,"wins":130},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":25,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":43,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":51,"wins":21},"z-ai/glm-5.2":{"draws":21,"losses":96,"wins":111},"z-ai/glm-5.3":{"draws":4,"losses":80,"wins":24},"z-ai/glm-5.3-flash":{"draws":3,"losses":57,"wins":54},"z-ai/glm-5.3-flashx":{"draws":7,"losses":68,"wins":39}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":11},"claude-fable-5":{"draws":10,"losses":25,"wins":7},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":26,"wins":4},"claude-opus-4-5":{"draws":19,"losses":31,"wins":18},"claude-opus-4-8":{"draws":13,"losses":17,"wins":8},"claude-opus-5":{"draws":12,"losses":56,"wins":2},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":11,"losses":25,"wins":6},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":17,"wins":23},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":26,"wins":7},"elorian/glimpse":{"draws":7,"losses":9,"wins":6},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":13,"wins":15},"gemini-4-argon":{"draws":2,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":19,"wins":18},"google/gemini-3.5-flash-lite":{"draws":21,"losses":20,"wins":33},"google/gemini-3.6-flash":{"draws":23,"losses":45,"wins":12},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":18,"wins":9},"gpt-5.4":{"draws":10,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":16},"gpt-5.5":{"draws":14,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":22,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":18,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":18,"wins":11},"gpt-6-sol":{"draws":7,"losses":34,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":12},"inception/mercury-3":{"draws":7,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":18,"wins":17},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":15},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":10,"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-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":34,"wins":2},"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":14,"losses":7,"wins":15},"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":14,"losses":7,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":27,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":10},"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":34,"losses":74,"wins":34},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":21,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":16,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":11,"wins":16},"unbiased/pareto-26.10":{"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":10,"losses":27,"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":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":13,"losses":26,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":1,"wins":32},"claude-fable-5":{"draws":12,"losses":13,"wins":23},"claude-fable-5-1":{"draws":5,"losses":45,"wins":4},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":25},"claude-opus-4-5":{"draws":23,"losses":7,"wins":48},"claude-opus-4-8":{"draws":8,"losses":6,"wins":30},"claude-opus-5":{"draws":13,"losses":52,"wins":17},"claude-opus-5-5":{"draws":4,"losses":37,"wins":11},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":9,"losses":16,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":16,"losses":5,"wins":51},"deepseek/deepseek-v4-pro":{"draws":11,"losses":4,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":14,"wins":24},"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":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":10,"wins":39},"google/gemini-3.5-flash-lite":{"draws":18,"losses":5,"wins":61},"google/gemini-3.6-flash":{"draws":22,"losses":19,"wins":51},"google/gemini-3.8-flash":{"draws":12,"losses":14,"wins":22},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":10,"losses":6,"wins":26},"gpt-5.4":{"draws":7,"losses":11,"wins":28},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":1,"wins":39},"gpt-5.5":{"draws":11,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":8,"losses":17,"wins":23},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":1,"losses":42,"wins":5},"gpt-6-luna":{"draws":12,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":33,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":11,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":12,"losses":11,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":11,"wins":28},"meta/muse-spark-open":{"draws":11,"losses":10,"wins":25},"meta/muse-wonder":{"draws":8,"losses":16,"wins":24},"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-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":31,"wins":9},"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":10,"losses":2,"wins":30},"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":5,"wins":22},"qwen/qwen3.8-27b":{"draws":13,"losses":3,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":19},"qwen/qwen3.8-max":{"draws":14,"losses":9,"wins":25},"qwen/qwen3.8-max-0902":{"draws":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":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":12,"losses":11,"wins":23},"thinkingmachines/inkling":{"draws":19,"losses":2,"wins":43},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"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":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":27,"losses":13,"wins":56},"z-ai/glm-5.3":{"draws":11,"losses":19,"wins":16},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":28},"z-ai/glm-5.3-flashx":{"draws":16,"losses":10,"wins":22}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":24},"claude-fable-5":{"draws":3,"losses":22,"wins":11},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":14,"wins":18},"claude-opus-4-5":{"draws":7,"losses":15,"wins":38},"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":5,"losses":10,"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":4,"losses":9,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":23,"wins":11},"elorian/glimpse":{"draws":2,"losses":7,"wins":11},"fireworks/ember-1":{"draws":4,"losses":11,"wins":21},"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":2,"wins":23},"google/gemini-3.5-flash":{"draws":3,"losses":13,"wins":32},"google/gemini-3.5-flash-lite":{"draws":5,"losses":8,"wins":53},"google/gemini-3.6-flash":{"draws":7,"losses":26,"wins":37},"google/gemini-3.8-flash":{"draws":3,"losses":17,"wins":16},"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":1,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":3,"losses":12,"wins":25},"gpt-5.5":{"draws":4,"losses":15,"wins":15},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":10},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":16},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":4,"losses":13,"wins":19},"gpt-6-sol":{"draws":4,"losses":24,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":22},"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":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":35},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":27},"meta/muse-spark-1.2":{"draws":1,"losses":12,"wins":21},"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":2,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":4,"losses":16,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":5,"wins":13},"o3":{"draws":2,"losses":19,"wins":39},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":2,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":6,"losses":13,"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":16,"losses":35,"wins":51},"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":2,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":33},"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":6,"losses":16,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":3,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":9},"z-ai/glm-5.2":{"draws":12,"losses":21,"wins":39},"z-ai/glm-5.3":{"draws":8,"losses":21,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":11,"wins":21},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":17}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":23,"losses":21,"wins":34},"claude-opus-4-8":{"draws":5,"losses":22,"wins":17},"claude-opus-5":{"draws":7,"losses":64,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":13,"losses":14,"wins":21},"claude-sonnet-5-5":{"draws":7,"losses":23,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":13,"losses":15,"wins":44},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"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":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"gemini-4-argon":{"draws":6,"losses":38,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":16,"losses":22,"wins":22},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":18,"losses":37,"wins":37},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":14,"wins":17},"gpt-5.4":{"draws":8,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":27},"gpt-5.5":{"draws":13,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":30},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":20,"losses":10,"wins":16},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":22},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":22},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":36},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":15},"meta/muse-spark-open":{"draws":3,"losses":22,"wins":21},"meta/muse-wonder":{"draws":9,"losses":27,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":16},"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":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":38,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":8,"losses":24,"wins":34},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":9,"wins":25},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":15},"qwen/qwen3.8-27b":{"draws":9,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":18},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":16},"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":37,"losses":63,"wins":58},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":2,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":18,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":13,"losses":10,"wins":25},"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":19,"wins":20},"x-ai/grok-4.6":{"draws":13,"losses":17,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":11},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":25,"losses":8,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":16},"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":29,"losses":30,"wins":37},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":11},"z-ai/glm-5.3-flash":{"draws":13,"losses":12,"wins":23},"z-ai/glm-5.3-flashx":{"draws":17,"losses":15,"wins":16}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":33},"claude-fable-5":{"draws":10,"losses":16,"wins":22},"claude-fable-5-1":{"draws":3,"losses":37,"wins":14},"claude-haiku-5-5":{"draws":10,"losses":9,"wins":27},"claude-opus-4-5":{"draws":14,"losses":12,"wins":52},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":8,"losses":44,"wins":30},"claude-opus-5-5":{"draws":8,"losses":35,"wins":9},"claude-sonnet-5":{"draws":12,"losses":7,"wins":29},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":53},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":9,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":16,"wins":20},"elorian/glimpse":{"draws":6,"losses":5,"wins":15},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":6,"wins":30},"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":7,"wins":41},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":67},"google/gemini-3.6-flash":{"draws":19,"losses":15,"wins":58},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":30},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":22},"gpt-4.1":{"draws":5,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":10,"losses":4,"wins":28},"gpt-5.4":{"draws":12,"losses":13,"wins":21},"gpt-5.4-mini":{"draws":11,"losses":1,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":14,"losses":9,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":7,"wins":32},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":8,"wins":29},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":31},"meta/muse-spark-open":{"draws":6,"losses":8,"wins":32},"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":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":11},"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":32,"losses":40,"wins":86},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":8,"wins":28},"thinkingmachines/inkling":{"draws":11,"losses":4,"wins":49},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"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":22,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":19,"losses":12,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":18},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":24},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"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},"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":0,"losses":0,"wins":2},"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":11,"losses":18,"wins":17},"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":6,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":14,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":39,"wins":3},"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":6,"wins":31},"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":0,"losses":2,"wins":2},"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":4,"losses":6,"wins":16},"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":14,"losses":19,"wins":107},"claude-fable-5":{"draws":15,"losses":78,"wins":57},"claude-fable-5-1":{"draws":19,"losses":135,"wins":18},"claude-haiku-5-5":{"draws":17,"losses":43,"wins":80},"claude-opus-4-5":{"draws":27,"losses":50,"wins":163},"claude-opus-4-8":{"draws":19,"losses":33,"wins":78},"claude-opus-5":{"draws":36,"losses":167,"wins":55},"claude-opus-5-5":{"draws":9,"losses":131,"wins":22},"claude-sonnet-5":{"draws":14,"losses":31,"wins":105},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":74},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":50},"deepseek/deepseek-v4-flash":{"draws":15,"losses":22,"wins":185},"deepseek/deepseek-v4-pro":{"draws":13,"losses":33,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":31,"wins":92},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":41,"wins":91},"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":35,"wins":95},"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":8,"losses":6,"wins":80},"google/gemini-3.5-flash":{"draws":20,"losses":39,"wins":127},"google/gemini-3.5-flash-lite":{"draws":20,"losses":32,"wins":212},"google/gemini-3.6-flash":{"draws":30,"losses":77,"wins":183},"google/gemini-3.8-flash":{"draws":15,"losses":57,"wins":78},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":69},"gpt-4.1":{"draws":8,"losses":9,"wins":33},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":14},"gpt-5":{"draws":11,"losses":30,"wins":93},"gpt-5.4":{"draws":19,"losses":47,"wins":80},"gpt-5.4-mini":{"draws":15,"losses":11,"wins":74},"gpt-5.4-nano":{"draws":7,"losses":35,"wins":100},"gpt-5.5":{"draws":18,"losses":41,"wins":81},"gpt-5.6-luna":{"draws":23,"losses":22,"wins":105},"gpt-5.6-sol":{"draws":16,"losses":70,"wins":64},"gpt-5.6-terra":{"draws":21,"losses":38,"wins":85},"gpt-6-astra":{"draws":15,"losses":121,"wins":14},"gpt-6-luna":{"draws":20,"losses":29,"wins":101},"gpt-6-sol":{"draws":18,"losses":91,"wins":41},"gpt-6.1-sol":{"draws":17,"losses":116,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":10,"wins":73},"inception/mercury-3":{"draws":8,"losses":26,"wins":64},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":92},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":13,"losses":19,"wins":132},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":114},"meta/muse-spark-1.2":{"draws":18,"losses":27,"wins":99},"meta/muse-spark-1.3":{"draws":18,"losses":49,"wins":83},"meta/muse-spark-open":{"draws":12,"losses":50,"wins":84},"meta/muse-wonder":{"draws":12,"losses":76,"wins":62},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":66},"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":4,"losses":7,"wins":23},"moonshotai/kimi-k3":{"draws":17,"losses":39,"wins":88},"moonshotai/kimi-k3.1-pro":{"draws":21,"losses":99,"wins":20},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":65},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":19,"wins":86},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":11,"wins":48},"o3":{"draws":9,"losses":41,"wins":154},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":112},"poolside/laguna-s-2.1":{"draws":16,"losses":17,"wins":115},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":67},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":59},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":44,"wins":87},"qwen/qwen3.8-27b":{"draws":8,"losses":22,"wins":76},"qwen/qwen3.8-flash":{"draws":8,"losses":24,"wins":68},"qwen/qwen3.8-max":{"draws":21,"losses":32,"wins":97},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":87},"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":52,"losses":129,"wins":307},"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":5,"wins":5},"tencent/hy3-preview":{"draws":13,"losses":11,"wins":54},"tencent/hy4-preview":{"draws":20,"losses":50,"wins":76},"thinkingmachines/inkling":{"draws":22,"losses":23,"wins":161},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":126},"unbiased/pareto-26.10":{"draws":3,"losses":46,"wins":1},"unbiased/pareto-26.10-preview":{"draws":10,"losses":35,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":33},"x-ai/grok-4.5":{"draws":14,"losses":63,"wins":73},"x-ai/grok-4.6":{"draws":29,"losses":56,"wins":65},"x-ai/grok-4.7":{"draws":9,"losses":77,"wins":42},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":44},"xiaomi/mimo-v2.5":{"draws":23,"losses":18,"wins":175},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":13,"wins":67},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":22,"wins":64},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":46},"z-ai/glm-5.2":{"draws":33,"losses":48,"wins":219},"z-ai/glm-5.3":{"draws":17,"losses":63,"wins":64},"z-ai/glm-5.3-flash":{"draws":16,"losses":43,"wins":91},"z-ai/glm-5.3-flashx":{"draws":19,"losses":49,"wins":82}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":15},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":1,"losses":37,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":11},"claude-opus-4-5":{"draws":18,"losses":27,"wins":15},"claude-opus-4-8":{"draws":8,"losses":15,"wins":13},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":6,"losses":13,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":28},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":14,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":6},"elorian/glimpse":{"draws":2,"losses":11,"wins":7},"fireworks/ember-1":{"draws":6,"losses":17,"wins":13},"gemini-3.1-pro-preview":{"draws":7,"losses":11,"wins":18},"gemini-4-argon":{"draws":1,"losses":31,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":17},"google/gemini-3.5-flash-lite":{"draws":16,"losses":16,"wins":34},"google/gemini-3.6-flash":{"draws":15,"losses":33,"wins":22},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":8},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":6,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":12,"wins":15},"gpt-5.4":{"draws":3,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":11,"losses":15,"wins":8},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":8,"losses":13,"wins":13},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":1,"losses":27,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":12},"inception/mercury-3":{"draws":3,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":19},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":15},"meta/muse-spark-open":{"draws":5,"losses":22,"wins":9},"meta/muse-wonder":{"draws":5,"losses":24,"wins":7},"minimax/minimax-m3":{"draws":3,"losses":2,"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":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":29,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":14,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":9},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":20},"poolside/laguna-s-2.1":{"draws":4,"losses":9,"wins":19},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":14,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":9,"losses":17,"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":20,"losses":46,"wins":36},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":15},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":24},"thinkingmachines/inkling-small":{"draws":8,"losses":6,"wins":22},"unbiased/pareto-26.10":{"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":8,"losses":21,"wins":7},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":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":4,"losses":37,"wins":9},"claude-opus-4-8":{"draws":2,"losses":23,"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":5,"losses":29,"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":4,"losses":24,"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":4,"losses":24,"wins":2},"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":5,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":2,"losses":28,"wins":10},"google/gemini-3.5-flash-lite":{"draws":6,"losses":32,"wins":16},"google/gemini-3.6-flash":{"draws":3,"losses":49,"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":2,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":25,"wins":13},"gpt-5.5":{"draws":4,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":17,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":20,"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},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"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":2,"losses":0,"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":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":12,"wins":4},"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":6,"wins":2},"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":4,"losses":18,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":12,"wins":2},"o3":{"draws":3,"losses":41,"wins":12},"openai/gpt-oss-120b":{"draws":2,"losses":12,"wins":12},"poolside/laguna-s-2.1":{"draws":2,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":13,"wins":3},"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":3,"losses":26,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":6},"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":3,"losses":10,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":12,"wins":21},"thinkingmachines/inkling-small":{"draws":3,"losses":17,"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":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":8,"losses":26,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":15,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":5,"losses":42,"wins":13},"z-ai/glm-5.3":{"draws":2,"losses":26,"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":12,"losses":12,"wins":14},"claude-fable-5":{"draws":12,"losses":25,"wins":5},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":18,"wins":13},"claude-opus-4-5":{"draws":23,"losses":29,"wins":18},"claude-opus-4-8":{"draws":10,"losses":22,"wins":10},"claude-opus-5":{"draws":13,"losses":55,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":21,"wins":26},"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":10,"losses":21,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":6},"elorian/glimpse":{"draws":6,"losses":9,"wins":7},"fireworks/ember-1":{"draws":13,"losses":21,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":16,"wins":14},"gemini-4-argon":{"draws":3,"losses":38,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":9,"wins":15},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":21,"losses":19,"wins":34},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":21},"gpt-5.5":{"draws":17,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":15,"wins":10},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":12},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":8,"wins":11},"inception/mercury-3":{"draws":8,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":15,"wins":21},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":8,"losses":24,"wins":8},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":11},"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":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":4},"o3":{"draws":10,"losses":24,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":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":14,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"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":35,"losses":59,"wins":24},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":11,"losses":17,"wins":12},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":30},"thinkingmachines/inkling-small":{"draws":12,"losses":11,"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":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":29,"wins":3},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":21,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":33,"wins":29},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":8},"z-ai/glm-5.3-flashx":{"draws":6,"losses":27,"wins":9}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":2,"wins":26},"claude-fable-5":{"draws":11,"losses":19,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":21,"losses":14,"wins":43},"claude-opus-4-8":{"draws":12,"losses":11,"wins":21},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":14,"losses":4,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":6,"wins":44},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":5,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":8,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":17,"wins":24},"elorian/glimpse":{"draws":2,"losses":9,"wins":15},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":5,"wins":38},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":51},"google/gemini-3.6-flash":{"draws":24,"losses":24,"wins":44},"google/gemini-3.8-flash":{"draws":11,"losses":13,"wins":24},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":17,"losses":7,"wins":18},"gpt-5.4":{"draws":12,"losses":14,"wins":20},"gpt-5.4-mini":{"draws":13,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":14,"losses":10,"wins":20},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":20,"wins":22},"gpt-5.6-terra":{"draws":15,"losses":7,"wins":24},"gpt-6-astra":{"draws":5,"losses":40,"wins":3},"gpt-6-luna":{"draws":13,"losses":8,"wins":27},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":1,"wins":16},"inception/mercury-3":{"draws":7,"losses":8,"wins":17},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":16,"losses":0,"wins":26},"meta/muse-spark-1.2":{"draws":4,"losses":14,"wins":28},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":27},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":5,"losses":16,"wins":21},"mistralai/mistral-large-4-0":{"draws":11,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":34,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":12},"o3":{"draws":14,"losses":14,"wins":38},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":18,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":26},"qwen/qwen3.8-27b":{"draws":10,"losses":5,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":25},"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":36,"losses":26,"wins":96},"stealth/space-bunny-alpha":{"draws":10,"losses":4,"wins":24},"stepfun/step-3.7-flash":{"draws":10,"losses":4,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":7,"losses":5,"wins":18},"thinkingmachines/inkling":{"draws":19,"losses":9,"wins":36},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10":{"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":18,"losses":15,"wins":15},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":28,"losses":0,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":24,"losses":8,"wins":64},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":12},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":32,"wins":20},"claude-fable-5":{"draws":13,"losses":66,"wins":5},"claude-fable-5-1":{"draws":2,"losses":92,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":43,"wins":9},"claude-opus-4-5":{"draws":44,"losses":71,"wins":21},"claude-opus-4-8":{"draws":19,"losses":46,"wins":11},"claude-opus-5":{"draws":21,"losses":119,"wins":10},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":28,"losses":45,"wins":11},"claude-sonnet-5-5":{"draws":19,"losses":47,"wins":18},"cohere/north-mini-code":{"draws":7,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":44,"losses":29,"wins":55},"deepseek/deepseek-v4-pro":{"draws":24,"losses":39,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":33,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":43,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":50,"wins":13},"elorian/glimpse":{"draws":9,"losses":25,"wins":12},"fireworks/ember-1":{"draws":26,"losses":46,"wins":12},"gemini-3.1-pro-preview":{"draws":29,"losses":35,"wins":20},"gemini-4-argon":{"draws":8,"losses":73,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":30},"google/gemini-3.5-flash":{"draws":28,"losses":49,"wins":27},"google/gemini-3.5-flash-lite":{"draws":46,"losses":48,"wins":50},"google/gemini-3.6-flash":{"draws":44,"losses":83,"wins":33},"google/gemini-3.8-flash":{"draws":28,"losses":47,"wins":9},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":36,"wins":21},"gpt-5.4":{"draws":21,"losses":44,"wins":15},"gpt-5.4-mini":{"draws":23,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":34},"gpt-5.5":{"draws":24,"losses":42,"wins":12},"gpt-5.6-luna":{"draws":30,"losses":34,"wins":20},"gpt-5.6-sol":{"draws":13,"losses":62,"wins":9},"gpt-5.6-terra":{"draws":24,"losses":39,"wins":17},"gpt-6-astra":{"draws":6,"losses":76,"wins":2},"gpt-6-luna":{"draws":23,"losses":41,"wins":20},"gpt-6-sol":{"draws":8,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":74,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":27,"losses":10,"wins":19},"inception/mercury-3":{"draws":20,"losses":21,"wins":17},"inclusionai/ling-3.0-flash":{"draws":25,"losses":10,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":23,"losses":28,"wins":39},"meta/muse-glimmer-30b":{"draws":26,"losses":23,"wins":27},"meta/muse-spark-1.2":{"draws":22,"losses":49,"wins":11},"meta/muse-spark-1.3":{"draws":14,"losses":61,"wins":9},"meta/muse-spark-open":{"draws":17,"losses":55,"wins":8},"meta/muse-wonder":{"draws":24,"losses":52,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":21},"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":17,"losses":7,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":24,"losses":41,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":71,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":21,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":10},"o3":{"draws":25,"losses":59,"wins":32},"openai/gpt-oss-120b":{"draws":23,"losses":19,"wins":34},"poolside/laguna-s-2.1":{"draws":29,"losses":31,"wins":26},"qwen/qwen3.7-max":{"draws":16,"losses":25,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":15,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":8},"qwen/qwen3.8-27b":{"draws":19,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":24,"wins":11},"qwen/qwen3.8-max":{"draws":27,"losses":39,"wins":18},"qwen/qwen3.8-max-0902":{"draws":26,"losses":44,"wins":14},"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":71,"losses":156,"wins":55},"stealth/space-bunny-alpha":{"draws":21,"losses":23,"wins":22},"stepfun/step-3.7-flash":{"draws":19,"losses":17,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":20,"wins":11},"tencent/hy4-preview":{"draws":19,"losses":45,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":32},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":38},"unbiased/pareto-26.10":{"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":26,"losses":51,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":58,"wins":5},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":46,"losses":40,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":25,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":40,"wins":7},"z-ai/glm-5.2":{"draws":45,"losses":74,"wins":49},"z-ai/glm-5.3":{"draws":18,"losses":53,"wins":9},"z-ai/glm-5.3-flash":{"draws":19,"losses":50,"wins":15},"z-ai/glm-5.3-flashx":{"draws":22,"losses":50,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":17,"wins":11},"claude-fable-5":{"draws":9,"losses":34,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":30,"wins":5},"claude-opus-4-5":{"draws":30,"losses":30,"wins":18},"claude-opus-4-8":{"draws":13,"losses":25,"wins":6},"claude-opus-5":{"draws":13,"losses":67,"wins":2},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":14,"losses":24,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":24,"wins":22},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":23,"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":15,"losses":23,"wins":10},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"gemini-4-argon":{"draws":4,"losses":44,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":18,"losses":30,"wins":12},"google/gemini-3.5-flash-lite":{"draws":27,"losses":21,"wins":36},"google/gemini-3.6-flash":{"draws":32,"losses":46,"wins":14},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":19,"wins":7},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":18,"losses":13,"wins":17},"gpt-5.5":{"draws":20,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":21,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":11},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":5,"wins":12},"inception/mercury-3":{"draws":10,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":11,"wins":20},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":15,"losses":28,"wins":5},"meta/muse-spark-open":{"draws":10,"losses":28,"wins":8},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":8},"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":11,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":41,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":3},"o3":{"draws":15,"losses":31,"wins":20},"openai/gpt-oss-120b":{"draws":18,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":18,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":12,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"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":41,"losses":93,"wins":24},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":9,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":16,"losses":25,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":16,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":15},"unbiased/pareto-26.10":{"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":17,"losses":23,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":17,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":18,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":23,"wins":4},"z-ai/glm-5.2":{"draws":36,"losses":35,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":35,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":27,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":10},"claude-fable-5":{"draws":0,"losses":14,"wins":4},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":0,"losses":20,"wins":10},"claude-opus-4-8":{"draws":0,"losses":15,"wins":3},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":0,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":0,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":0,"losses":15,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":12,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":14,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":15,"wins":3},"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},"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},"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":3,"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":1,"losses":5,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":6,"wins":2},"o3":{"draws":2,"losses":22,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":14,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.8-flash":{"draws":0,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":11,"wins":7},"qwen/qwen3.8-max-0902":{"draws":0,"losses":15,"wins":3},"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},"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":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":12,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":0,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":15,"wins":3}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":1,"wins":33},"claude-fable-5":{"draws":5,"losses":18,"wins":25},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":18,"losses":20,"wins":40},"claude-opus-4-8":{"draws":11,"losses":15,"wins":18},"claude-opus-5":{"draws":11,"losses":55,"wins":16},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"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":14,"losses":8,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":12,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":16,"wins":26},"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":12,"wins":28},"gemini-4-argon":{"draws":1,"losses":37,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":6,"losses":18,"wins":36},"google/gemini-3.5-flash-lite":{"draws":16,"losses":17,"wins":51},"google/gemini-3.6-flash":{"draws":14,"losses":30,"wins":48},"google/gemini-3.8-flash":{"draws":4,"losses":16,"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":9,"losses":9,"wins":24},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":11,"losses":13,"wins":20},"gpt-5.6-luna":{"draws":7,"losses":13,"wins":28},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":1,"losses":41,"wins":6},"gpt-6-luna":{"draws":6,"losses":15,"wins":27},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":11,"wins":27},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":23},"meta/muse-spark-open":{"draws":8,"losses":13,"wins":25},"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":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":6,"losses":12,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":9},"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":10,"losses":1,"wins":31},"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":30,"losses":51,"wins":77},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":9,"losses":16,"wins":21},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":5,"losses":7,"wins":36},"unbiased/pareto-26.10":{"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":12,"losses":9,"wins":11},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":13},"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":6,"losses":20,"wins":22},"z-ai/glm-5.3-flashx":{"draws":4,"losses":20,"wins":24}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":28},"claude-fable-5":{"draws":12,"losses":15,"wins":21},"claude-fable-5-1":{"draws":4,"losses":36,"wins":14},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":18},"claude-opus-4-5":{"draws":17,"losses":18,"wins":43},"claude-opus-4-8":{"draws":9,"losses":13,"wins":22},"claude-opus-5":{"draws":10,"losses":48,"wins":23},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":9,"losses":8,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":25},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":17,"losses":4,"wins":51},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":13,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":19,"wins":19},"elorian/glimpse":{"draws":6,"losses":7,"wins":13},"fireworks/ember-1":{"draws":12,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"gemini-4-argon":{"draws":9,"losses":29,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":10,"wins":36},"google/gemini-3.5-flash-lite":{"draws":19,"losses":10,"wins":55},"google/gemini-3.6-flash":{"draws":18,"losses":28,"wins":46},"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":11,"losses":3,"wins":28},"gpt-5.4":{"draws":11,"losses":12,"wins":23},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":17},"gpt-5.4-nano":{"draws":10,"losses":7,"wins":31},"gpt-5.5":{"draws":14,"losses":6,"wins":24},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":32},"gpt-5.6-sol":{"draws":8,"losses":15,"wins":25},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":33},"gpt-6-astra":{"draws":4,"losses":36,"wins":8},"gpt-6-luna":{"draws":10,"losses":11,"wins":27},"gpt-6-sol":{"draws":2,"losses":36,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inception/mercury-3":{"draws":9,"losses":3,"wins":20},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":7,"losses":11,"wins":28},"meta/muse-spark-1.3":{"draws":11,"losses":18,"wins":19},"meta/muse-spark-open":{"draws":7,"losses":13,"wins":26},"meta/muse-wonder":{"draws":11,"losses":20,"wins":17},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":24},"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":5,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":31,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":3,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":15,"losses":16,"wins":35},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":31},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":20,"wins":22},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":20},"qwen/qwen3.8-flash":{"draws":12,"losses":2,"wins":18},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":23},"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":45,"losses":44,"wins":69},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":17,"losses":8,"wins":21},"thinkingmachines/inkling":{"draws":20,"losses":6,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":2,"losses":12,"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":13,"losses":14,"wins":21},"x-ai/grok-4.6":{"draws":12,"losses":5,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":4,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":22,"losses":15,"wins":59},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":9,"losses":16,"wins":23},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":37},"claude-fable-5":{"draws":0,"losses":12,"wins":30},"claude-fable-5-1":{"draws":1,"losses":29,"wins":16},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":36},"claude-opus-4-5":{"draws":1,"losses":5,"wins":62},"claude-opus-4-8":{"draws":3,"losses":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":6,"wins":36},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"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":8,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":4,"wins":36},"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":1,"wins":49},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":71},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":67},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":3,"wins":32},"gpt-5.4":{"draws":2,"losses":8,"wins":30},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":43},"gpt-5.5":{"draws":3,"losses":9,"wins":26},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":37},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":30,"wins":8},"gpt-6-luna":{"draws":0,"losses":6,"wins":36},"gpt-6-sol":{"draws":1,"losses":13,"wins":28},"gpt-6.1-sol":{"draws":2,"losses":23,"wins":17},"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":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":34},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":35},"meta/muse-spark-1.3":{"draws":3,"losses":6,"wins":33},"meta/muse-spark-open":{"draws":0,"losses":6,"wins":34},"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-k2.7-code":{"draws":0,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":17,"wins":20},"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":2,"wins":36},"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":4,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":30},"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":6,"losses":16,"wins":118},"stealth/space-bunny-alpha":{"draws":0,"losses":5,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":32},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":49},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":39},"unbiased/pareto-26.10":{"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":9,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":4,"losses":9,"wins":71},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":30},"z-ai/glm-5.3-flash":{"draws":2,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"wins":33}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":7,"wins":6},"claude-fable-5":{"draws":10,"losses":20,"wins":0},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":1},"claude-opus-4-5":{"draws":28,"losses":19,"wins":3},"claude-opus-4-8":{"draws":11,"losses":16,"wins":3},"claude-opus-5":{"draws":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":23,"losses":13,"wins":10},"deepseek/deepseek-v4-pro":{"draws":15,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"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":15,"losses":11,"wins":4},"gemini-3.1-pro-preview":{"draws":15,"losses":10,"wins":5},"gemini-4-argon":{"draws":3,"losses":27,"wins":0},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":19,"losses":15,"wins":4},"google/gemini-3.5-flash-lite":{"draws":28,"losses":15,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":23,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":16,"wins":2},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":3},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":10,"wins":2},"gpt-5.4":{"draws":8,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":4},"gpt-5.5":{"draws":15,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":20,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":9,"wins":2},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":18,"losses":10,"wins":2},"gpt-6-sol":{"draws":5,"losses":23,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":0,"wins":7},"inception/mercury-3":{"draws":12,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":6},"meta/muse-glimmer-30b":{"draws":19,"losses":3,"wins":2},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":0},"meta/muse-spark-open":{"draws":11,"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":13,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":8,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":26,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":1},"o3":{"draws":13,"losses":17,"wins":8},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":2},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":9,"wins":3},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.8-flash":{"draws":14,"losses":6,"wins":0},"qwen/qwen3.8-max":{"draws":16,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":18,"losses":8,"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":35,"losses":37,"wins":10},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":22,"losses":8,"wins":6},"thinkingmachines/inkling-small":{"draws":19,"losses":6,"wins":5},"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":14,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":7},"z-ai/glm-5.3":{"draws":11,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":3},"z-ai/glm-5.3-flashx":{"draws":15,"losses":14,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":11,"losses":28,"wins":9},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":19,"losses":34,"wins":25},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":18,"losses":61,"wins":3},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":8,"losses":22,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":27,"losses":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":18,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":24,"wins":13},"elorian/glimpse":{"draws":3,"losses":13,"wins":10},"fireworks/ember-1":{"draws":11,"losses":19,"wins":18},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"gemini-4-argon":{"draws":7,"losses":41,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":18,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":18,"wins":37},"google/gemini-3.6-flash":{"draws":24,"losses":45,"wins":23},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4":{"draws":14,"losses":26,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":13,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":24,"losses":17,"wins":5},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":16},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":20},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":24,"wins":13},"meta/muse-spark-1.3":{"draws":6,"losses":32,"wins":10},"meta/muse-spark-open":{"draws":11,"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":9,"losses":5,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":19,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":15,"losses":29,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"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":48,"losses":76,"wins":34},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":18,"losses":18,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":20},"unbiased/pareto-26.10":{"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":14,"losses":25,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":34,"losses":14,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":29,"losses":27,"wins":24},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":34},"claude-fable-5":{"draws":4,"losses":7,"wins":31},"claude-fable-5-1":{"draws":2,"losses":35,"wins":11},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":32},"claude-opus-4-5":{"draws":5,"losses":4,"wins":59},"claude-opus-4-8":{"draws":5,"losses":5,"wins":28},"claude-opus-5":{"draws":6,"losses":25,"wins":39},"claude-opus-5-5":{"draws":2,"losses":32,"wins":12},"claude-sonnet-5":{"draws":5,"losses":2,"wins":35},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":57},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":2,"wins":37},"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":6,"losses":5,"wins":31},"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":5,"losses":4,"wins":43},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":69},"google/gemini-3.6-flash":{"draws":9,"losses":8,"wins":63},"google/gemini-3.8-flash":{"draws":7,"losses":5,"wins":30},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":21},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":3,"wins":33},"gpt-5.4":{"draws":5,"losses":2,"wins":33},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":26},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":35},"gpt-5.5":{"draws":3,"losses":3,"wins":32},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":31},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":31},"gpt-6-astra":{"draws":8,"losses":27,"wins":7},"gpt-6-luna":{"draws":5,"losses":1,"wins":36},"gpt-6-sol":{"draws":7,"losses":17,"wins":18},"gpt-6.1-sol":{"draws":8,"losses":23,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":28},"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":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":44},"meta/muse-glimmer-30b":{"draws":9,"losses":0,"wins":27},"meta/muse-spark-1.2":{"draws":5,"losses":3,"wins":32},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-open":{"draws":3,"losses":3,"wins":34},"meta/muse-wonder":{"draws":5,"losses":8,"wins":29},"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":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":16,"wins":14},"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":2,"losses":0,"wins":34},"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":15,"losses":12,"wins":115},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":29},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":20},"tencent/hy4-preview":{"draws":3,"losses":3,"wins":34},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":45},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":38},"unbiased/pareto-26.10":{"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":5,"losses":6,"wins":31},"x-ai/grok-4.7":{"draws":5,"losses":13,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":5,"wins":17},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":70},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":5,"wins":31},"z-ai/glm-5.3-flashx":{"draws":5,"losses":2,"wins":35}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":15,"wins":26},"claude-fable-5":{"draws":5,"losses":24,"wins":19},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":7,"losses":17,"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":11,"losses":53,"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":6,"losses":21,"wins":45},"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":7,"losses":17,"wins":24},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":22},"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":3,"losses":20,"wins":37},"google/gemini-3.5-flash-lite":{"draws":11,"losses":19,"wins":54},"google/gemini-3.6-flash":{"draws":6,"losses":34,"wins":52},"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},"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":5,"losses":11,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":9,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":7,"wins":32},"meta/muse-spark-1.2":{"draws":3,"losses":20,"wins":23},"meta/muse-spark-1.3":{"draws":6,"losses":14,"wins":28},"meta/muse-spark-open":{"draws":4,"losses":20,"wins":22},"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":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":5},"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":14,"wins":24},"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":6,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":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":0,"losses":8,"wins":18},"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":6,"losses":7,"wins":31},"claude-fable-5":{"draws":7,"losses":16,"wins":25},"claude-fable-5-1":{"draws":5,"losses":43,"wins":6},"claude-haiku-5-5":{"draws":7,"losses":12,"wins":27},"claude-opus-4-5":{"draws":9,"losses":13,"wins":56},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":6,"losses":20,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":31},"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":10,"wins":34},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":27},"gemini-4-argon":{"draws":2,"losses":35,"wins":11},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":10,"wins":43},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":58},"google/gemini-3.6-flash":{"draws":21,"losses":21,"wins":50},"google/gemini-3.8-flash":{"draws":2,"losses":16,"wins":30},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":5,"wins":26},"gpt-5.4":{"draws":5,"losses":11,"wins":30},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"gpt-5.5":{"draws":10,"losses":12,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":18,"wins":25},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":28},"gpt-6-astra":{"draws":3,"losses":39,"wins":6},"gpt-6-luna":{"draws":7,"losses":10,"wins":31},"gpt-6-sol":{"draws":5,"losses":24,"wins":19},"gpt-6.1-sol":{"draws":10,"losses":32,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":27},"inception/mercury-3":{"draws":4,"losses":8,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":42},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":27},"meta/muse-spark-open":{"draws":7,"losses":11,"wins":28},"meta/muse-wonder":{"draws":11,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"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":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":39,"wins":6},"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":11,"losses":3,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":5,"losses":13,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":28},"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":19,"losses":33,"wins":106},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":26},"thinkingmachines/inkling":{"draws":7,"losses":9,"wins":48},"thinkingmachines/inkling-small":{"draws":8,"losses":6,"wins":34},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":7,"losses":15,"wins":26},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":5,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":14},"z-ai/glm-5.2":{"draws":20,"losses":14,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":5,"wins":17}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":12},"claude-fable-5":{"draws":6,"losses":26,"wins":10},"claude-fable-5-1":{"draws":2,"losses":42,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":17},"claude-opus-4-5":{"draws":21,"losses":22,"wins":25},"claude-opus-4-8":{"draws":9,"losses":15,"wins":14},"claude-opus-5":{"draws":11,"losses":52,"wins":11},"claude-opus-5-5":{"draws":2,"losses":39,"wins":5},"claude-sonnet-5":{"draws":14,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":19,"losses":18,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":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":9,"losses":18,"wins":15},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":21,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":21,"wins":33},"google/gemini-3.6-flash":{"draws":17,"losses":39,"wins":24},"google/gemini-3.8-flash":{"draws":9,"losses":23,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":8,"losses":10,"wins":18},"gpt-5.4":{"draws":9,"losses":19,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":22},"gpt-5.5":{"draws":12,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":10},"gpt-6-astra":{"draws":2,"losses":35,"wins":5},"gpt-6-luna":{"draws":11,"losses":15,"wins":16},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":10,"wins":9},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":13,"wins":22},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":23,"wins":11},"meta/muse-spark-open":{"draws":8,"losses":20,"wins":12},"meta/muse-wonder":{"draws":13,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":12},"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":3,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":34,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":8,"wins":16},"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":14,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":14,"wins":14},"qwen/qwen3.8-max-0902":{"draws":8,"losses":25,"wins":9},"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":70,"wins":37},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":12,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":10,"wins":20},"unbiased/pareto-26.10":{"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":5,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":23,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":6,"losses":22,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":10}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":29},"claude-fable-5":{"draws":6,"losses":12,"wins":14},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":16,"losses":11,"wins":51},"claude-opus-4-8":{"draws":11,"losses":8,"wins":25},"claude-opus-5":{"draws":14,"losses":45,"wins":23},"claude-opus-5-5":{"draws":4,"losses":39,"wins":9},"claude-sonnet-5":{"draws":7,"losses":10,"wins":31},"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":4,"wins":53},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":11,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":13,"wins":23},"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":11,"losses":7,"wins":30},"gemini-4-argon":{"draws":5,"losses":32,"wins":11},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":56},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":43},"google/gemini-3.8-flash":{"draws":7,"losses":15,"wins":26},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":18},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":8,"wins":28},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":37},"gpt-5.5":{"draws":11,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":21,"wins":25},"gpt-5.6-terra":{"draws":15,"losses":5,"wins":26},"gpt-6-astra":{"draws":1,"losses":38,"wins":9},"gpt-6-luna":{"draws":12,"losses":7,"wins":29},"gpt-6-sol":{"draws":8,"losses":25,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inception/mercury-3":{"draws":8,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":6,"wins":40},"meta/muse-glimmer-30b":{"draws":6,"losses":5,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":11,"losses":16,"wins":21},"meta/muse-spark-open":{"draws":7,"losses":10,"wins":29},"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":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":7,"losses":10,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":29,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"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":6,"losses":10,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":10,"wins":23},"qwen/qwen3.8-27b":{"draws":7,"losses":5,"wins":22},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":26},"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":27,"losses":47,"wins":84},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":10,"losses":7,"wins":29},"thinkingmachines/inkling":{"draws":15,"losses":4,"wins":45},"thinkingmachines/inkling-small":{"draws":8,"losses":8,"wins":32},"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":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":12,"losses":19,"wins":17},"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":15,"losses":2,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":9,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":17},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":5,"losses":23,"wins":18},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":26},"z-ai/glm-5.3-flashx":{"draws":10,"losses":15,"wins":23}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":42},"claude-fable-5":{"draws":4,"losses":10,"wins":34},"claude-fable-5-1":{"draws":4,"losses":24,"wins":10},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":6,"losses":7,"wins":65},"claude-opus-4-8":{"draws":4,"losses":5,"wins":35},"claude-opus-5":{"draws":6,"losses":37,"wins":39},"claude-opus-5-5":{"draws":5,"losses":34,"wins":13},"claude-sonnet-5":{"draws":4,"losses":3,"wins":41},"claude-sonnet-5-5":{"draws":2,"losses":11,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":67},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":39},"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":4,"losses":2,"wins":42},"gemini-4-argon":{"draws":4,"losses":21,"wins":23},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":52},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":12,"wins":71},"google/gemini-3.8-flash":{"draws":1,"losses":8,"wins":39},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":0,"wins":39},"gpt-5.4":{"draws":6,"losses":5,"wins":35},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":3,"losses":10,"wins":31},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":41},"gpt-5.6-sol":{"draws":4,"losses":8,"wins":36},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":37},"gpt-6-astra":{"draws":5,"losses":34,"wins":9},"gpt-6-luna":{"draws":6,"losses":5,"wins":37},"gpt-6-sol":{"draws":6,"losses":13,"wins":29},"gpt-6.1-sol":{"draws":5,"losses":29,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":2,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":46},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":36},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":39},"meta/muse-spark-1.3":{"draws":3,"losses":7,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":8,"wins":34},"meta/muse-wonder":{"draws":3,"losses":14,"wins":31},"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":3,"losses":1,"wins":26},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":16,"wins":22},"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":0,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":21},"o3":{"draws":3,"losses":5,"wins":58},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":43},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":26},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":43},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"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":14,"wins":134},"stealth/space-bunny-alpha":{"draws":1,"losses":2,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":38},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":59},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":8},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":38},"x-ai/grok-4.6":{"draws":4,"losses":10,"wins":34},"x-ai/grok-4.7":{"draws":2,"losses":15,"wins":25},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":2,"wins":25},"z-ai/glm-5.2":{"draws":10,"losses":4,"wins":82},"z-ai/glm-5.3":{"draws":4,"losses":8,"wins":34},"z-ai/glm-5.3-flash":{"draws":2,"losses":8,"wins":38},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"wins":39}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":26},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":9},"claude-opus-4-5":{"draws":22,"losses":19,"wins":37},"claude-opus-4-8":{"draws":6,"losses":20,"wins":18},"claude-opus-5":{"draws":15,"losses":56,"wins":11},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":21},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":6,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":11,"wins":20},"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":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":25,"losses":32,"wins":35},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":15},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":24},"gpt-5.5":{"draws":19,"losses":10,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":17,"losses":11,"wins":20},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":38,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":37},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":23},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-spark-open":{"draws":4,"losses":19,"wins":23},"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":7,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":37,"wins":7},"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":10,"losses":9,"wins":23},"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":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":17},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":43},"thinkingmachines/inkling-small":{"draws":9,"losses":5,"wins":34},"unbiased/pareto-26.10":{"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":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":24,"losses":21,"wins":51},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":16,"wins":20}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":7,"losses":33,"wins":8},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":19,"losses":15,"wins":28},"claude-opus-4-8":{"draws":12,"losses":17,"wins":15},"claude-opus-5":{"draws":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":21,"wins":16},"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":13,"wins":45},"google/gemini-3.6-flash":{"draws":24,"losses":39,"wins":29},"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":12,"losses":13,"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":18,"losses":17,"wins":9},"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":5,"losses":40,"wins":3},"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},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":26,"wins":15},"meta/muse-spark-open":{"draws":13,"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-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":22},"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":13,"losses":20,"wins":15},"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":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":15},"thinkingmachines/inkling":{"draws":16,"losses":12,"wins":36},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"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":13,"losses":24,"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":6,"losses":9,"wins":11},"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":10,"losses":24,"wins":14},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":7,"wins":20},"claude-fable-5":{"draws":14,"losses":26,"wins":8},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":27,"losses":24,"wins":27},"claude-opus-4-8":{"draws":5,"losses":15,"wins":8},"claude-opus-5":{"draws":9,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":16,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":28,"losses":12,"wins":32},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":15,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":19,"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":18,"losses":15,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":20,"losses":18,"wins":22},"google/gemini-3.5-flash-lite":{"draws":32,"losses":8,"wins":44},"google/gemini-3.6-flash":{"draws":25,"losses":42,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":11},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":11,"wins":14},"gpt-5.4":{"draws":17,"losses":19,"wins":10},"gpt-5.4-mini":{"draws":11,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":21,"losses":11,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":15,"wins":14},"gpt-6-astra":{"draws":1,"losses":45,"wins":2},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":46,"wins":1},"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":12,"wins":9},"inclusionai/ling-3.0-flash":{"draws":17,"losses":0,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":24},"meta/muse-glimmer-30b":{"draws":18,"losses":6,"wins":18},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":13},"meta/muse-spark-1.3":{"draws":11,"losses":22,"wins":15},"meta/muse-spark-open":{"draws":13,"losses":20,"wins":13},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"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":12,"losses":2,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":0},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":6,"wins":8},"o3":{"draws":14,"losses":20,"wins":32},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":19},"qwen/qwen3.7-max":{"draws":14,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":17,"losses":6,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":15,"wins":14},"stealth/ox-alpha":{"draws":41,"losses":73,"wins":44},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":16,"losses":20,"wins":10},"thinkingmachines/inkling":{"draws":24,"losses":12,"wins":28},"thinkingmachines/inkling-small":{"draws":21,"losses":3,"wins":24},"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":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":19,"wins":15},"x-ai/grok-4.6":{"draws":15,"losses":22,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":29,"losses":8,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":3,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":41,"losses":21,"wins":34},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":22,"wins":15}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":59},"claude-fable-5":{"draws":13,"losses":23,"wins":48},"claude-fable-5-1":{"draws":6,"losses":69,"wins":21},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":51},"claude-opus-4-5":{"draws":27,"losses":8,"wins":101},"claude-opus-4-8":{"draws":12,"losses":12,"wins":52},"claude-opus-5":{"draws":18,"losses":61,"wins":53},"claude-opus-5-5":{"draws":8,"losses":59,"wins":25},"claude-sonnet-5":{"draws":11,"losses":9,"wins":64},"claude-sonnet-5-5":{"draws":9,"losses":32,"wins":43},"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":8,"losses":13,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":55},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":20,"wins":53},"elorian/glimpse":{"draws":8,"losses":9,"wins":31},"fireworks/ember-1":{"draws":9,"losses":16,"wins":59},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":61},"gemini-4-argon":{"draws":11,"losses":46,"wins":27},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":40},"google/gemini-3.5-flash":{"draws":13,"losses":6,"wins":85},"google/gemini-3.5-flash-lite":{"draws":22,"losses":10,"wins":112},"google/gemini-3.6-flash":{"draws":18,"losses":24,"wins":118},"google/gemini-3.8-flash":{"draws":9,"losses":18,"wins":57},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":35},"gpt-4.1":{"draws":3,"losses":1,"wins":24},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":5,"wins":61},"gpt-5.4":{"draws":10,"losses":15,"wins":55},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":39},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":67},"gpt-5.5":{"draws":10,"losses":21,"wins":49},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":64},"gpt-5.6-sol":{"draws":17,"losses":20,"wins":47},"gpt-5.6-terra":{"draws":11,"losses":8,"wins":61},"gpt-6-astra":{"draws":4,"losses":61,"wins":19},"gpt-6-luna":{"draws":16,"losses":8,"wins":60},"gpt-6-sol":{"draws":12,"losses":31,"wins":41},"gpt-6.1-sol":{"draws":6,"losses":51,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":40},"inception/mercury-3":{"draws":5,"losses":6,"wins":45},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":47},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":68},"meta/muse-glimmer-30b":{"draws":4,"losses":9,"wins":67},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":58},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":54},"meta/muse-spark-open":{"draws":11,"losses":13,"wins":56},"meta/muse-wonder":{"draws":9,"losses":32,"wins":43},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":40},"minimax/minimax-m3.1-flash":{"draws":11,"losses":7,"wins":54},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":40},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k3":{"draws":11,"losses":10,"wins":63},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":34,"wins":38},"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":8,"losses":1,"wins":63},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":26},"o3":{"draws":9,"losses":9,"wins":90},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":66},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":74},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":37},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":11,"wins":55},"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":13,"losses":5,"wins":66},"qwen/qwen3.8-max-0902":{"draws":14,"losses":14,"wins":56},"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":44,"losses":29,"wins":211},"stealth/space-bunny-alpha":{"draws":14,"losses":4,"wins":50},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":51},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":34},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":62},"thinkingmachines/inkling":{"draws":18,"losses":4,"wins":94},"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":2,"losses":18,"wins":8},"upstage/solar-mini4":{"draws":4,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":12,"losses":14,"wins":58},"x-ai/grok-4.6":{"draws":15,"losses":17,"wins":51},"x-ai/grok-4.7":{"draws":6,"losses":42,"wins":28},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":20},"xiaomi/mimo-v2.5":{"draws":30,"losses":6,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":38},"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":11,"losses":23,"wins":46},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":57},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":59}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":50},"claude-fable-5":{"draws":3,"losses":2,"wins":49},"claude-fable-5-1":{"draws":5,"losses":19,"wins":36},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":50},"claude-opus-4-5":{"draws":4,"losses":1,"wins":83},"claude-opus-4-8":{"draws":2,"losses":2,"wins":46},"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":1,"wins":53},"claude-sonnet-5-5":{"draws":5,"losses":9,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":80},"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":4,"wins":49},"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":1,"wins":67},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":94},"google/gemini-3.6-flash":{"draws":2,"losses":9,"wins":91},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":50},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":32},"gpt-4.1":{"draws":0,"losses":0,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":47},"gpt-5.4":{"draws":1,"losses":5,"wins":46},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":35},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":55},"gpt-5.5":{"draws":2,"losses":0,"wins":48},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":51},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":47},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":50},"gpt-6-astra":{"draws":4,"losses":24,"wins":26},"gpt-6-luna":{"draws":0,"losses":1,"wins":53},"gpt-6-sol":{"draws":4,"losses":13,"wins":37},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":38},"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":4},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":58},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":48},"meta/muse-spark-1.2":{"draws":1,"losses":1,"wins":50},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":54},"meta/muse-spark-open":{"draws":0,"losses":0,"wins":52},"meta/muse-wonder":{"draws":2,"losses":7,"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":2,"losses":3,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":51},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":15,"wins":31},"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":1,"wins":49},"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":0,"losses":0,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":0,"wins":53},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":33},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":5,"wins":48},"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":5,"losses":2,"wins":167},"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":4,"wins":47},"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":6,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":49},"x-ai/grok-4.6":{"draws":1,"losses":1,"wins":52},"x-ai/grok-4.7":{"draws":2,"losses":5,"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":30},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":34},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":107},"z-ai/glm-5.3":{"draws":2,"losses":5,"wins":45},"z-ai/glm-5.3-flash":{"draws":4,"losses":3,"wins":47},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":50}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":5,"wins":23},"claude-fable-5":{"draws":9,"losses":34,"wins":5},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":26,"losses":29,"wins":23},"claude-opus-4-8":{"draws":13,"losses":21,"wins":10},"claude-opus-5":{"draws":9,"losses":60,"wins":13},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":10,"losses":15,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":24,"losses":13,"wins":35},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":32,"wins":5},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":12,"losses":21,"wins":15},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"gemini-4-argon":{"draws":4,"losses":42,"wins":2},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":24,"wins":17},"google/gemini-3.5-flash-lite":{"draws":28,"losses":22,"wins":34},"google/gemini-3.6-flash":{"draws":27,"losses":50,"wins":15},"google/gemini-3.8-flash":{"draws":14,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":10,"wins":20},"gpt-5.4":{"draws":11,"losses":27,"wins":8},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":16,"wins":20},"gpt-5.5":{"draws":20,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":23,"losses":14,"wins":9},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inception/mercury-3":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":25},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":14,"losses":24,"wins":10},"meta/muse-spark-open":{"draws":9,"losses":28,"wins":9},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"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":14,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":22,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":40,"wins":1},"nex-agi/nex-n2-pro":{"draws":11,"losses":2,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":8},"o3":{"draws":10,"losses":32,"wins":24},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":19,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":5,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":22,"wins":9},"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":36,"losses":93,"wins":29},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":18,"losses":22,"wins":6},"thinkingmachines/inkling":{"draws":22,"losses":11,"wins":31},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":20},"unbiased/pareto-26.10":{"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":24,"wins":12},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":36,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":32,"losses":13,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":29,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":15,"losses":26,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":22,"losses":22,"wins":34},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"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":21,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":16,"wins":20},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"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":21,"losses":40,"wins":31},"google/gemini-3.8-flash":{"draws":6,"losses":24,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":14,"losses":18,"wins":14},"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":6,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":1,"losses":44,"wins":3},"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":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"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":0,"losses":0,"wins":2},"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":10,"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-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":40,"wins":3},"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":11,"losses":7,"wins":24},"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":13,"losses":13,"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":22,"wins":12},"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":21,"wins":17},"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":33,"losses":70,"wins":55},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":5,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.7":{"draws":8,"losses":26,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":23,"wins":44},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":13,"wins":12},"claude-fable-5":{"draws":6,"losses":28,"wins":2},"claude-fable-5-1":{"draws":0,"losses":41,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":20,"wins":7},"claude-opus-4-5":{"draws":6,"losses":44,"wins":8},"claude-opus-4-8":{"draws":7,"losses":23,"wins":2},"claude-opus-5":{"draws":6,"losses":48,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":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":12,"losses":20,"wins":20},"deepseek/deepseek-v4-pro":{"draws":5,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":1},"elorian/glimpse":{"draws":3,"losses":12,"wins":5},"fireworks/ember-1":{"draws":8,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":7,"losses":17,"wins":12},"gemini-4-argon":{"draws":0,"losses":34,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":11},"google/gemini-3.5-flash":{"draws":8,"losses":29,"wins":9},"google/gemini-3.5-flash-lite":{"draws":22,"losses":24,"wins":20},"google/gemini-3.6-flash":{"draws":14,"losses":47,"wins":9},"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":4,"losses":6,"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":6,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":20,"wins":11},"gpt-5.5":{"draws":8,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":17,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":29,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":6},"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},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":3,"losses":22,"wins":9},"meta/muse-spark-1.3":{"draws":2,"losses":32,"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":4,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":34,"wins":0},"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":7,"losses":12,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":13,"wins":2},"o3":{"draws":5,"losses":36,"wins":13},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":11},"poolside/laguna-s-2.1":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"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":27,"wins":4},"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":85,"wins":22},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":4},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":4},"thinkingmachines/inkling":{"draws":15,"losses":20,"wins":13},"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":8,"losses":25,"wins":3},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":13,"losses":18,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":35,"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":36,"losses":49,"wins":35},"claude-fable-5":{"draws":22,"losses":103,"wins":7},"claude-fable-5-1":{"draws":4,"losses":141,"wins":1},"claude-haiku-5-5":{"draws":33,"losses":75,"wins":20},"claude-opus-4-5":{"draws":64,"losses":115,"wins":37},"claude-opus-4-8":{"draws":31,"losses":78,"wins":15},"claude-opus-5":{"draws":21,"losses":191,"wins":10},"claude-opus-5-5":{"draws":6,"losses":135,"wins":3},"claude-sonnet-5":{"draws":39,"losses":71,"wins":22},"claude-sonnet-5-5":{"draws":27,"losses":87,"wins":18},"cohere/north-mini-code":{"draws":10,"losses":21,"wins":19},"deepseek/deepseek-v4-flash":{"draws":49,"losses":57,"wins":52},"deepseek/deepseek-v4-pro":{"draws":29,"losses":67,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":63,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":79,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":93,"wins":15},"elorian/glimpse":{"draws":15,"losses":39,"wins":16},"fireworks/ember-1":{"draws":39,"losses":74,"wins":19},"gemini-3.1-pro-preview":{"draws":36,"losses":66,"wins":30},"gemini-4-argon":{"draws":5,"losses":123,"wins":4},"google/gemini-3.1-flash-lite":{"draws":28,"losses":20,"wins":44},"google/gemini-3.5-flash":{"draws":34,"losses":99,"wins":33},"google/gemini-3.5-flash-lite":{"draws":67,"losses":83,"wins":80},"google/gemini-3.6-flash":{"draws":57,"losses":155,"wins":40},"google/gemini-3.8-flash":{"draws":23,"losses":97,"wins":12},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":27},"gpt-4.1":{"draws":14,"losses":23,"wins":7},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":36,"losses":55,"wins":25},"gpt-5.4":{"draws":30,"losses":78,"wins":18},"gpt-5.4-mini":{"draws":32,"losses":34,"wins":22},"gpt-5.4-nano":{"draws":28,"losses":61,"wins":51},"gpt-5.5":{"draws":42,"losses":66,"wins":12},"gpt-5.6-luna":{"draws":52,"losses":55,"wins":25},"gpt-5.6-sol":{"draws":17,"losses":109,"wins":6},"gpt-5.6-terra":{"draws":38,"losses":73,"wins":15},"gpt-6-astra":{"draws":4,"losses":124,"wins":4},"gpt-6-luna":{"draws":35,"losses":71,"wins":26},"gpt-6-sol":{"draws":18,"losses":105,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":122,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":38,"losses":22,"wins":34},"inception/mercury-3":{"draws":23,"losses":46,"wins":21},"inclusionai/ling-3.0-flash":{"draws":36,"losses":25,"wins":33},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":35,"losses":53,"wins":56},"meta/muse-glimmer-30b":{"draws":43,"losses":30,"wins":41},"meta/muse-spark-1.2":{"draws":32,"losses":76,"wins":18},"meta/muse-spark-1.3":{"draws":26,"losses":91,"wins":15},"meta/muse-spark-open":{"draws":24,"losses":86,"wins":16},"meta/muse-wonder":{"draws":23,"losses":93,"wins":16},"minimax/minimax-m3":{"draws":19,"losses":25,"wins":30},"minimax/minimax-m3.1-flash":{"draws":27,"losses":56,"wins":31},"mistralai/mistral-large-4-0":{"draws":28,"losses":43,"wins":11},"mistralai/mistral-medium-3-5":{"draws":30,"losses":20,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":16,"wins":8},"moonshotai/kimi-k3":{"draws":39,"losses":67,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":118,"wins":2},"nex-agi/nex-n2-pro":{"draws":16,"losses":24,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":39,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":26,"wins":17},"o3":{"draws":22,"losses":125,"wins":43},"openai/gpt-oss-120b":{"draws":39,"losses":39,"wins":38},"poolside/laguna-s-2.1":{"draws":40,"losses":46,"wins":42},"qwen/qwen3.7-max":{"draws":27,"losses":30,"wins":23},"qwen/qwen3.7-plus":{"draws":19,"losses":25,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":76,"wins":16},"qwen/qwen3.8-27b":{"draws":22,"losses":52,"wins":20},"qwen/qwen3.8-flash":{"draws":25,"losses":42,"wins":21},"qwen/qwen3.8-max":{"draws":41,"losses":70,"wins":21},"qwen/qwen3.8-max-0902":{"draws":38,"losses":77,"wins":17},"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":99,"losses":250,"wins":67},"stealth/space-bunny-alpha":{"draws":34,"losses":52,"wins":18},"stepfun/step-3.7-flash":{"draws":21,"losses":35,"wins":40},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":27,"losses":26,"wins":19},"tencent/hy4-preview":{"draws":32,"losses":76,"wins":18},"thinkingmachines/inkling":{"draws":50,"losses":67,"wins":57},"thinkingmachines/inkling-small":{"draws":48,"losses":33,"wins":51},"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":21,"losses":94,"wins":17},"x-ai/grok-4.6":{"draws":32,"losses":91,"wins":9},"x-ai/grok-4.7":{"draws":12,"losses":98,"wins":8},"x-ai/grok-build-0.1":{"draws":16,"losses":12,"wins":16},"xiaomi/mimo-v2.5":{"draws":64,"losses":72,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":33,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":54,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":63,"wins":13},"z-ai/glm-5.2":{"draws":87,"losses":115,"wins":62},"z-ai/glm-5.3":{"draws":27,"losses":91,"wins":8},"z-ai/glm-5.3-flash":{"draws":27,"losses":77,"wins":28},"z-ai/glm-5.3-flashx":{"draws":34,"losses":78,"wins":20}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":27},"claude-fable-5":{"draws":8,"losses":27,"wins":13},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":20,"losses":20,"wins":38},"claude-opus-4-8":{"draws":9,"losses":19,"wins":16},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":14},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":19,"wins":39},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":22,"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":19,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"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":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":14,"losses":22,"wins":48},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":42},"google/gemini-3.8-flash":{"draws":6,"losses":27,"wins":15},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":24},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":28},"gpt-5.5":{"draws":9,"losses":20,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":15},"gpt-5.6-terra":{"draws":10,"losses":14,"wins":22},"gpt-6-astra":{"draws":4,"losses":37,"wins":7},"gpt-6-luna":{"draws":10,"losses":20,"wins":18},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":9,"losses":10,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":8,"losses":23,"wins":17},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":11},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"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":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":19,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":5},"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":5,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":9},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":8,"losses":11,"wins":27},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":16},"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":7,"losses":14,"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":36,"losses":65,"wins":57},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":7,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":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":23,"wins":15},"x-ai/grok-4.6":{"draws":7,"losses":26,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":28,"losses":23,"wins":45},"z-ai/glm-5.3":{"draws":5,"losses":27,"wins":14},"z-ai/glm-5.3-flash":{"draws":8,"losses":23,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":17}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":13,"wins":18},"claude-fable-5":{"draws":7,"losses":31,"wins":10},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":10,"losses":24,"wins":12},"claude-opus-4-5":{"draws":24,"losses":29,"wins":25},"claude-opus-4-8":{"draws":12,"losses":16,"wins":16},"claude-opus-5":{"draws":10,"losses":62,"wins":10},"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":27,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":20,"losses":19,"wins":33},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":12},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":13,"losses":24,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":16,"losses":27,"wins":17},"google/gemini-3.5-flash-lite":{"draws":26,"losses":18,"wins":40},"google/gemini-3.6-flash":{"draws":22,"losses":46,"wins":24},"google/gemini-3.8-flash":{"draws":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":14,"wins":23},"gpt-5.5":{"draws":13,"losses":15,"wins":16},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":33,"wins":9},"gpt-5.6-terra":{"draws":13,"losses":20,"wins":13},"gpt-6-astra":{"draws":1,"losses":47,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":15},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":17},"inception/mercury-3":{"draws":11,"losses":10,"wins":11},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":15,"losses":13,"wins":24},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":8,"losses":26,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":24,"wins":13},"meta/muse-spark-open":{"draws":8,"losses":28,"wins":10},"meta/muse-wonder":{"draws":13,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"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":7,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":11,"losses":23,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":19},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":20,"losses":19,"wins":9},"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":42,"losses":66,"wins":50},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":18},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":14,"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":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":10,"losses":27,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":13,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":34,"losses":31,"wins":31},"z-ai/glm-5.3":{"draws":12,"losses":25,"wins":9},"z-ai/glm-5.3-flash":{"draws":5,"losses":29,"wins":14},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":6,"wins":22},"claude-fable-5":{"draws":12,"losses":24,"wins":12},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":18,"wins":13},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":11,"losses":11,"wins":22},"claude-opus-5":{"draws":18,"losses":51,"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":28,"losses":5,"wins":39},"deepseek/deepseek-v4-pro":{"draws":11,"losses":14,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":11,"wins":14},"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":16,"losses":12,"wins":20},"gemini-4-argon":{"draws":8,"losses":35,"wins":5},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":18},"google/gemini-3.5-flash":{"draws":20,"losses":16,"wins":24},"google/gemini-3.5-flash-lite":{"draws":33,"losses":7,"wins":44},"google/gemini-3.6-flash":{"draws":29,"losses":34,"wins":29},"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":14,"losses":10,"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":10,"wins":20},"gpt-5.5":{"draws":14,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":20,"losses":8,"wins":20},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":12,"wins":17},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":17,"losses":10,"wins":21},"gpt-6-sol":{"draws":7,"losses":30,"wins":11},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"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":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":28},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":20},"meta/muse-spark-1.2":{"draws":15,"losses":13,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":18},"meta/muse-spark-open":{"draws":13,"losses":13,"wins":20},"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":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":12,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":30,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":5,"wins":10},"o3":{"draws":15,"losses":16,"wins":35},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":5,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":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":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":20,"losses":13,"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":37,"losses":60,"wins":61},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":25},"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":31,"losses":6,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":8,"losses":17,"wins":23},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":16}},"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":5,"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},"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":0,"losses":0,"wins":2},"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":8,"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":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":9},"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":8,"losses":2,"wins":32},"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":0,"losses":2,"wins":2},"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":3,"losses":2,"wins":21},"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},"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":0,"wins":2},"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":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":15,"losses":7,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":28,"wins":11},"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":10,"losses":3,"wins":29},"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":0,"losses":0,"wins":4},"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":4,"losses":5,"wins":17},"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":14,"losses":5,"wins":25},"claude-fable-5":{"draws":12,"losses":31,"wins":5},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":29,"losses":21,"wins":28},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":24,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":27,"wins":7},"elorian/glimpse":{"draws":7,"losses":7,"wins":12},"fireworks/ember-1":{"draws":9,"losses":7,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":23},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":34,"losses":9,"wins":41},"google/gemini-3.6-flash":{"draws":29,"losses":28,"wins":35},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":8,"wins":22},"gpt-5.4":{"draws":12,"losses":20,"wins":14},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":15,"losses":9,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":26,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":11,"wins":22},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"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":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":17,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":21,"losses":16,"wins":11},"meta/muse-spark-open":{"draws":10,"losses":18,"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":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":3},"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":17,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"o3":{"draws":13,"losses":16,"wins":37},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":23},"poolside/laguna-s-2.1":{"draws":17,"losses":7,"wins":22},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":13,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":12,"wins":21},"qwen/qwen3.8-max-0902":{"draws":19,"losses":19,"wins":10},"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":48,"losses":51,"wins":59},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":24,"losses":3,"wins":37},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":25},"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":11,"losses":20,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":7,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":43},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":9},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":18}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":13,"losses":26,"wins":9},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":26,"losses":34,"wins":18},"claude-opus-4-8":{"draws":16,"losses":22,"wins":6},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":19,"losses":15,"wins":14},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":21,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":14,"losses":24,"wins":10},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":10},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":15,"losses":32,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":24,"wins":25},"google/gemini-3.6-flash":{"draws":22,"losses":47,"wins":23},"google/gemini-3.8-flash":{"draws":12,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":5,"wins":9},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":12,"wins":13},"gpt-5.4":{"draws":12,"losses":22,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":19},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":12,"wins":17},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":17,"wins":13},"gpt-6-sol":{"draws":4,"losses":39,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":5,"wins":10},"inception/mercury-3":{"draws":11,"losses":16,"wins":5},"inclusionai/ling-3.0-flash":{"draws":18,"losses":2,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":21,"losses":3,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":12},"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":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":24,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":6},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":7},"o3":{"draws":17,"losses":28,"wins":21},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":15,"losses":21,"wins":12},"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":46,"losses":73,"wins":39},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10":{"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":9,"losses":25,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":35,"wins":26},"z-ai/glm-5.3":{"draws":9,"losses":30,"wins":7},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"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},"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":0,"wins":2},"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":4,"losses":10,"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":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":24,"wins":14},"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":3,"wins":35},"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":0,"losses":1,"wins":3},"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":25},"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":12,"losses":14,"wins":8},"claude-fable-5":{"draws":4,"losses":30,"wins":2},"claude-fable-5-1":{"draws":1,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":4},"claude-opus-4-5":{"draws":14,"losses":44,"wins":2},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":7,"losses":46,"wins":5},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":2},"claude-sonnet-5-5":{"draws":8,"losses":22,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":18,"losses":27,"wins":9},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":28,"wins":1},"elorian/glimpse":{"draws":7,"losses":11,"wins":2},"fireworks/ember-1":{"draws":4,"losses":27,"wins":5},"gemini-3.1-pro-preview":{"draws":7,"losses":19,"wins":10},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":9,"wins":7},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":10},"google/gemini-3.5-flash-lite":{"draws":18,"losses":28,"wins":20},"google/gemini-3.6-flash":{"draws":16,"losses":46,"wins":8},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":7},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":20,"wins":2},"gpt-5.4":{"draws":7,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":3},"gpt-5.4-nano":{"draws":11,"losses":20,"wins":9},"gpt-5.5":{"draws":11,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":33,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":19,"wins":3},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":3},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":5},"inception/mercury-3":{"draws":3,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":20,"wins":13},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":22,"wins":5},"meta/muse-spark-1.3":{"draws":5,"losses":30,"wins":1},"meta/muse-spark-open":{"draws":7,"losses":29,"wins":0},"meta/muse-wonder":{"draws":5,"losses":30,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":6},"minimax/minimax-m3.1-flash":{"draws":8,"losses":20,"wins":4},"mistralai/mistral-large-4-0":{"draws":7,"losses":15,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":9,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":35,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":13,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":12,"wins":2},"o3":{"draws":11,"losses":45,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":17,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":27,"wins":1},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":23,"wins":0},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":0},"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":6,"losses":18,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":23,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":12},"unbiased/pareto-26.10":{"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":9,"losses":27,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":23,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":14,"losses":47,"wins":11},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":24,"wins":4},"z-ai/glm-5.3-flashx":{"draws":11,"losses":22,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":19},"claude-opus-4-5":{"draws":22,"losses":16,"wins":40},"claude-opus-4-8":{"draws":7,"losses":15,"wins":22},"claude-opus-5":{"draws":8,"losses":65,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":8,"losses":12,"wins":28},"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":20,"losses":10,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":8,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":17},"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":11,"losses":11,"wins":26},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":8,"losses":13,"wins":23},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":62},"google/gemini-3.6-flash":{"draws":19,"losses":34,"wins":39},"google/gemini-3.8-flash":{"draws":7,"losses":25,"wins":16},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":7,"losses":12,"wins":23},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":10,"losses":20,"wins":14},"gpt-5.6-luna":{"draws":18,"losses":8,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":14},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":20},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":33},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":9,"losses":24,"wins":15},"meta/muse-spark-open":{"draws":10,"losses":15,"wins":21},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"minimax/minimax-m3.1-flash":{"draws":10,"losses":8,"wins":23},"mistralai/mistral-large-4-0":{"draws":8,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":3},"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":8,"losses":7,"wins":27},"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":8,"losses":3,"wins":35},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":18},"qwen/qwen3.8-max-0902":{"draws":13,"losses":17,"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":26,"losses":56,"wins":76},"stealth/space-bunny-alpha":{"draws":10,"losses":5,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":17},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":39},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":29},"unbiased/pareto-26.10":{"draws":3,"losses":12,"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":9,"losses":17,"wins":22},"x-ai/grok-4.6":{"draws":14,"losses":24,"wins":10},"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":24,"losses":11,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":8,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":20,"wins":55},"z-ai/glm-5.3":{"draws":10,"losses":19,"wins":17},"z-ai/glm-5.3-flash":{"draws":6,"losses":21,"wins":21},"z-ai/glm-5.3-flashx":{"draws":15,"losses":17,"wins":16}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":34,"wins":18},"claude-fable-5":{"draws":16,"losses":63,"wins":5},"claude-fable-5-1":{"draws":8,"losses":85,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":48,"wins":12},"claude-opus-4-5":{"draws":49,"losses":74,"wins":13},"claude-opus-4-8":{"draws":23,"losses":52,"wins":1},"claude-opus-5":{"draws":22,"losses":113,"wins":9},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":26,"losses":46,"wins":12},"claude-sonnet-5-5":{"draws":15,"losses":57,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":14,"wins":7},"deepseek/deepseek-v4-flash":{"draws":41,"losses":53,"wins":30},"deepseek/deepseek-v4-pro":{"draws":21,"losses":37,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":44,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":45,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":60,"wins":9},"elorian/glimpse":{"draws":12,"losses":28,"wins":6},"fireworks/ember-1":{"draws":32,"losses":42,"wins":10},"gemini-3.1-pro-preview":{"draws":33,"losses":37,"wins":14},"gemini-4-argon":{"draws":7,"losses":77,"wins":0},"google/gemini-3.1-flash-lite":{"draws":18,"losses":13,"wins":25},"google/gemini-3.5-flash":{"draws":23,"losses":60,"wins":23},"google/gemini-3.5-flash-lite":{"draws":41,"losses":46,"wins":35},"google/gemini-3.6-flash":{"draws":47,"losses":95,"wins":20},"google/gemini-3.8-flash":{"draws":17,"losses":63,"wins":4},"google/gemma-4-31b-it":{"draws":20,"losses":14,"wins":14},"gpt-4.1":{"draws":11,"losses":14,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":23,"losses":34,"wins":17},"gpt-5.4":{"draws":22,"losses":51,"wins":9},"gpt-5.4-mini":{"draws":21,"losses":24,"wins":11},"gpt-5.4-nano":{"draws":20,"losses":34,"wins":30},"gpt-5.5":{"draws":31,"losses":40,"wins":7},"gpt-5.6-luna":{"draws":29,"losses":40,"wins":15},"gpt-5.6-sol":{"draws":12,"losses":69,"wins":3},"gpt-5.6-terra":{"draws":26,"losses":48,"wins":6},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":26,"losses":40,"wins":18},"gpt-6-sol":{"draws":14,"losses":61,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":78,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":22,"wins":14},"inception/mercury-3":{"draws":17,"losses":28,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":37,"wins":27},"meta/muse-glimmer-30b":{"draws":31,"losses":20,"wins":23},"meta/muse-spark-1.2":{"draws":20,"losses":51,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":62,"wins":7},"meta/muse-spark-open":{"draws":13,"losses":62,"wins":7},"meta/muse-wonder":{"draws":15,"losses":63,"wins":6},"minimax/minimax-m3":{"draws":11,"losses":15,"wins":18},"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":20,"losses":12,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":31,"losses":41,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":68,"wins":1},"nex-agi/nex-n2-pro":{"draws":11,"losses":15,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":29,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":24,"wins":4},"o3":{"draws":18,"losses":86,"wins":14},"openai/gpt-oss-120b":{"draws":24,"losses":30,"wins":18},"poolside/laguna-s-2.1":{"draws":26,"losses":41,"wins":15},"qwen/qwen3.7-max":{"draws":15,"losses":24,"wins":9},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":50,"wins":6},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":30,"wins":4},"qwen/qwen3.8-max":{"draws":28,"losses":46,"wins":10},"qwen/qwen3.8-max-0902":{"draws":25,"losses":53,"wins":6},"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":66,"losses":178,"wins":38},"stealth/space-bunny-alpha":{"draws":20,"losses":35,"wins":11},"stepfun/step-3.7-flash":{"draws":17,"losses":30,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":22,"wins":8},"tencent/hy4-preview":{"draws":25,"losses":45,"wins":12},"thinkingmachines/inkling":{"draws":30,"losses":49,"wins":35},"thinkingmachines/inkling-small":{"draws":26,"losses":24,"wins":34},"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":23,"losses":54,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":58,"wins":7},"x-ai/grok-build-0.1":{"draws":13,"losses":12,"wins":3},"xiaomi/mimo-v2.5":{"draws":39,"losses":56,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":37,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":44,"wins":6},"z-ai/glm-5.2":{"draws":59,"losses":76,"wins":33},"z-ai/glm-5.3":{"draws":18,"losses":59,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":14},"z-ai/glm-5.3-flashx":{"draws":21,"losses":53,"wins":10}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":13,"wins":47},"claude-fable-5":{"draws":14,"losses":43,"wins":27},"claude-fable-5-1":{"draws":8,"losses":80,"wins":8},"claude-haiku-5-5":{"draws":15,"losses":29,"wins":36},"claude-opus-4-5":{"draws":40,"losses":27,"wins":69},"claude-opus-4-8":{"draws":16,"losses":22,"wins":38},"claude-opus-5":{"draws":14,"losses":90,"wins":36},"claude-opus-5-5":{"draws":5,"losses":71,"wins":12},"claude-sonnet-5":{"draws":20,"losses":23,"wins":41},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":39},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":25},"deepseek/deepseek-v4-flash":{"draws":26,"losses":15,"wins":83},"deepseek/deepseek-v4-pro":{"draws":18,"losses":25,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":18,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":24,"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":20,"losses":32,"wins":32},"gemini-3.1-pro-preview":{"draws":15,"losses":25,"wins":44},"gemini-4-argon":{"draws":5,"losses":61,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":47},"google/gemini-3.5-flash":{"draws":21,"losses":31,"wins":54},"google/gemini-3.5-flash-lite":{"draws":41,"losses":25,"wins":84},"google/gemini-3.6-flash":{"draws":26,"losses":47,"wins":63},"google/gemini-3.8-flash":{"draws":15,"losses":37,"wins":32},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":28},"gpt-4.1":{"draws":7,"losses":4,"wins":17},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":14,"losses":15,"wins":45},"gpt-5.4":{"draws":16,"losses":32,"wins":34},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":31},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":59},"gpt-5.5":{"draws":17,"losses":31,"wins":30},"gpt-5.6-luna":{"draws":23,"losses":14,"wins":47},"gpt-5.6-sol":{"draws":11,"losses":47,"wins":26},"gpt-5.6-terra":{"draws":24,"losses":15,"wins":41},"gpt-6-astra":{"draws":6,"losses":72,"wins":6},"gpt-6-luna":{"draws":21,"losses":23,"wins":40},"gpt-6-sol":{"draws":8,"losses":51,"wins":25},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":36},"inception/mercury-3":{"draws":14,"losses":11,"wins":27},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":41},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":65},"meta/muse-glimmer-30b":{"draws":17,"losses":11,"wins":46},"meta/muse-spark-1.2":{"draws":15,"losses":27,"wins":38},"meta/muse-spark-1.3":{"draws":7,"losses":40,"wins":37},"meta/muse-spark-open":{"draws":19,"losses":28,"wins":35},"meta/muse-wonder":{"draws":13,"losses":43,"wins":28},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":32},"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":11,"losses":4,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":2,"wins":11},"moonshotai/kimi-k3":{"draws":19,"losses":25,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":60,"wins":14},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":8,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":5,"wins":22},"o3":{"draws":14,"losses":25,"wins":81},"openai/gpt-oss-120b":{"draws":21,"losses":6,"wins":45},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":48},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":30},"qwen/qwen3.7-plus":{"draws":11,"losses":3,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":25,"wins":39},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":34},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":27},"qwen/qwen3.8-max":{"draws":20,"losses":27,"wins":37},"qwen/qwen3.8-max-0902":{"draws":16,"losses":30,"wins":38},"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":55,"losses":103,"wins":126},"stealth/space-bunny-alpha":{"draws":19,"losses":9,"wins":40},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":43},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":13,"losses":9,"wins":22},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":36},"thinkingmachines/inkling":{"draws":27,"losses":17,"wins":72},"thinkingmachines/inkling-small":{"draws":19,"losses":11,"wins":54},"unbiased/pareto-26.10":{"draws":2,"losses":24,"wins":2},"unbiased/pareto-26.10-preview":{"draws":3,"losses":22,"wins":3},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":18,"losses":30,"wins":36},"x-ai/grok-4.6":{"draws":21,"losses":35,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":46,"wins":22},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":20},"xiaomi/mimo-v2.5":{"draws":35,"losses":10,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":18,"wins":26},"z-ai/glm-5.2":{"draws":38,"losses":46,"wins":84},"z-ai/glm-5.3":{"draws":13,"losses":46,"wins":21},"z-ai/glm-5.3-flash":{"draws":8,"losses":43,"wins":33},"z-ai/glm-5.3-flashx":{"draws":15,"losses":30,"wins":39}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":8,"losses":15,"wins":25},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":30,"losses":10,"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":20,"wins":18},"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":13,"losses":12,"wins":19},"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":17,"losses":13,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":9,"wins":25},"gemini-4-argon":{"draws":12,"losses":33,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":14,"wins":32},"google/gemini-3.5-flash-lite":{"draws":23,"losses":3,"wins":58},"google/gemini-3.6-flash":{"draws":25,"losses":24,"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":11,"losses":12,"wins":19},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":27},"gpt-5.5":{"draws":23,"losses":12,"wins":9},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":14,"losses":10,"wins":22},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":14,"losses":14,"wins":20},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":0,"wins":20},"inception/mercury-3":{"draws":9,"losses":9,"wins":14},"inclusionai/ling-3.0-flash":{"draws":12,"losses":0,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":17,"losses":3,"wins":22},"meta/muse-spark-1.2":{"draws":10,"losses":24,"wins":12},"meta/muse-spark-1.3":{"draws":15,"losses":14,"wins":19},"meta/muse-spark-open":{"draws":9,"losses":19,"wins":18},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"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":11,"losses":0,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":10,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":32,"wins":9},"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":17,"losses":0,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":7,"wins":13},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":25},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":14,"wins":19},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":22},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":13,"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":39,"losses":40,"wins":79},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":14,"wins":18},"thinkingmachines/inkling":{"draws":23,"losses":4,"wins":37},"thinkingmachines/inkling-small":{"draws":15,"losses":4,"wins":29},"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":15,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":3,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"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":31,"losses":15,"wins":50},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":12,"losses":14,"wins":22}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":13,"wins":17},"claude-fable-5":{"draws":11,"losses":30,"wins":7},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":28,"wins":6},"claude-opus-4-5":{"draws":28,"losses":37,"wins":13},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":13,"losses":62,"wins":7},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":10},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":34,"losses":24,"wins":14},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"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":17,"losses":20,"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":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":31,"wins":24},"google/gemini-3.6-flash":{"draws":28,"losses":49,"wins":15},"google/gemini-3.8-flash":{"draws":10,"losses":31,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":6},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":17,"wins":8},"gpt-5.4":{"draws":17,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":17,"losses":20,"wins":11},"gpt-5.5":{"draws":19,"losses":20,"wins":5},"gpt-5.6-luna":{"draws":20,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":38,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":5,"losses":41,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":15,"wins":16},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":6},"meta/muse-spark-open":{"draws":12,"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":4},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":1},"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":24,"losses":8,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":15,"losses":34,"wins":17},"openai/gpt-oss-120b":{"draws":17,"losses":17,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":14,"wins":14},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":16,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":21,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":9},"thinkingmachines/inkling":{"draws":25,"losses":17,"wins":22},"thinkingmachines/inkling-small":{"draws":19,"losses":13,"wins":16},"unbiased/pareto-26.10":{"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":10,"losses":29,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":34,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":31,"wins":22},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":15,"losses":24,"wins":9}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":15,"wins":16},"claude-fable-5":{"draws":7,"losses":27,"wins":8},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":15,"losses":31,"wins":22},"claude-opus-4-8":{"draws":8,"losses":21,"wins":9},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":13,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":6,"losses":27,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":15,"losses":17,"wins":30},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":12},"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":9,"losses":22,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":12},"gemini-4-argon":{"draws":3,"losses":33,"wins":6},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":27,"wins":16},"google/gemini-3.5-flash-lite":{"draws":19,"losses":26,"wins":31},"google/gemini-3.6-flash":{"draws":10,"losses":45,"wins":27},"google/gemini-3.8-flash":{"draws":7,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":11},"gpt-4.1":{"draws":3,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":6},"gpt-5.4":{"draws":7,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":21,"wins":15},"gpt-5.5":{"draws":12,"losses":15,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":3,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":10,"losses":19,"wins":13},"gpt-6-sol":{"draws":2,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":15},"inception/mercury-3":{"draws":1,"losses":20,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":10,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":28},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":13},"meta/muse-spark-1.2":{"draws":6,"losses":23,"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":4,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":13,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":9,"losses":24,"wins":31},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":9},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":27,"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":33,"losses":61,"wins":48},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":13,"losses":14,"wins":31},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":22},"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":10,"losses":26,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":20,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":29,"losses":28,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":8},"z-ai/glm-5.3-flash":{"draws":7,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":25},"claude-fable-5":{"draws":12,"losses":23,"wins":13},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":15},"claude-opus-4-5":{"draws":25,"losses":14,"wins":39},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":6,"losses":63,"wins":13},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":17,"losses":20,"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":16,"losses":17,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":23,"wins":15},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":14,"losses":16,"wins":18},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":21,"wins":28},"google/gemini-3.5-flash-lite":{"draws":23,"losses":15,"wins":46},"google/gemini-3.6-flash":{"draws":21,"losses":39,"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":10,"losses":2,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":30},"gpt-5.5":{"draws":10,"losses":18,"wins":16},"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":13,"losses":13,"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":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":9,"losses":9,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":30},"meta/muse-glimmer-30b":{"draws":15,"losses":4,"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":8,"losses":24,"wins":14},"meta/muse-wonder":{"draws":15,"losses":20,"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":3,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":13,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":6},"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":12,"losses":6,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":26},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"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":44,"losses":53,"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"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":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":16,"wins":19},"x-ai/grok-4.6":{"draws":16,"losses":17,"wins":15},"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":4,"losses":8,"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":9,"losses":21,"wins":18}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":21,"losses":29,"wins":28},"claude-opus-4-8":{"draws":11,"losses":14,"wins":19},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":24,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":18,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":32,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":14,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":18},"gemini-4-argon":{"draws":6,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":24},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":42},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":25},"google/gemini-3.8-flash":{"draws":8,"losses":28,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":9,"wins":24},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":22,"losses":14,"wins":8},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":11},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":17,"wins":10},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":16},"inception/mercury-3":{"draws":8,"losses":18,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":7,"wins":29},"meta/muse-glimmer-30b":{"draws":19,"losses":0,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":28,"wins":10},"meta/muse-spark-open":{"draws":9,"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":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":6},"o3":{"draws":10,"losses":28,"wins":28},"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":9,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"wins":13},"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":34,"losses":75,"wins":49},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":20,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":11,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"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":13,"losses":24,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":31,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":13,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":37,"losses":29,"wins":30},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":26,"wins":26},"claude-fable-5":{"draws":8,"losses":54,"wins":10},"claude-fable-5-1":{"draws":2,"losses":76,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":38,"wins":24},"claude-opus-4-5":{"draws":32,"losses":47,"wins":41},"claude-opus-4-8":{"draws":11,"losses":42,"wins":19},"claude-opus-5":{"draws":12,"losses":91,"wins":13},"claude-opus-5-5":{"draws":2,"losses":76,"wins":2},"claude-sonnet-5":{"draws":10,"losses":38,"wins":24},"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":23,"losses":38,"wins":51},"deepseek/deepseek-v4-pro":{"draws":7,"losses":37,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":31,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":37,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":46,"wins":16},"elorian/glimpse":{"draws":5,"losses":18,"wins":15},"fireworks/ember-1":{"draws":16,"losses":35,"wins":21},"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":12,"losses":49,"wins":33},"google/gemini-3.5-flash-lite":{"draws":18,"losses":57,"wins":53},"google/gemini-3.6-flash":{"draws":23,"losses":82,"wins":33},"google/gemini-3.8-flash":{"draws":11,"losses":46,"wins":15},"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":9,"losses":28,"wins":27},"gpt-5.4":{"draws":7,"losses":44,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":25},"gpt-5.4-nano":{"draws":6,"losses":26,"wins":28},"gpt-5.5":{"draws":15,"losses":32,"wins":19},"gpt-5.6-luna":{"draws":13,"losses":30,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":56,"wins":10},"gpt-5.6-terra":{"draws":9,"losses":35,"wins":24},"gpt-6-astra":{"draws":0,"losses":70,"wins":2},"gpt-6-luna":{"draws":14,"losses":30,"wins":28},"gpt-6-sol":{"draws":12,"losses":56,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":67,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":33},"inception/mercury-3":{"draws":11,"losses":21,"wins":16},"inclusionai/ling-3.0-flash":{"draws":13,"losses":18,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":22,"wins":52},"meta/muse-glimmer-30b":{"draws":13,"losses":23,"wins":26},"meta/muse-spark-1.2":{"draws":11,"losses":32,"wins":25},"meta/muse-spark-1.3":{"draws":13,"losses":38,"wins":21},"meta/muse-spark-open":{"draws":11,"losses":42,"wins":17},"meta/muse-wonder":{"draws":7,"losses":55,"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":8,"losses":7,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":8},"moonshotai/kimi-k3":{"draws":16,"losses":31,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":63,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":25,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":14,"wins":15},"o3":{"draws":8,"losses":45,"wins":65},"openai/gpt-oss-120b":{"draws":11,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":9,"losses":27,"wins":32},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":20},"qwen/qwen3.7-plus":{"draws":9,"losses":14,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":39,"wins":15},"qwen/qwen3.8-27b":{"draws":7,"losses":24,"wins":21},"qwen/qwen3.8-flash":{"draws":9,"losses":23,"wins":16},"qwen/qwen3.8-max":{"draws":18,"losses":37,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":37,"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":32,"losses":100,"wins":70},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":34},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":41,"wins":20},"thinkingmachines/inkling":{"draws":17,"losses":29,"wins":48},"thinkingmachines/inkling-small":{"draws":21,"losses":18,"wins":33},"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":37,"wins":21},"x-ai/grok-4.6":{"draws":9,"losses":51,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":51,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":13},"xiaomi/mimo-v2.5":{"draws":26,"losses":35,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":17,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":25,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":31,"wins":11},"z-ai/glm-5.2":{"draws":29,"losses":55,"wins":60},"z-ai/glm-5.3":{"draws":7,"losses":47,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":39,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":40,"wins":20}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":9,"wins":16},"claude-fable-5":{"draws":11,"losses":24,"wins":13},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":20,"losses":19,"wins":7},"claude-opus-4-5":{"draws":37,"losses":17,"wins":24},"claude-opus-4-8":{"draws":13,"losses":12,"wins":19},"claude-opus-5":{"draws":12,"losses":57,"wins":13},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":19,"losses":9,"wins":20},"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":25,"losses":11,"wins":36},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":17},"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":13,"losses":13,"wins":22},"gemini-4-argon":{"draws":2,"losses":41,"wins":5},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":18,"losses":17,"wins":25},"google/gemini-3.5-flash-lite":{"draws":34,"losses":15,"wins":35},"google/gemini-3.6-flash":{"draws":27,"losses":33,"wins":32},"google/gemini-3.8-flash":{"draws":15,"losses":20,"wins":13},"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":14,"losses":10,"wins":18},"gpt-5.4":{"draws":12,"losses":18,"wins":16},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":17},"gpt-5.5":{"draws":11,"losses":8,"wins":9},"gpt-5.6-luna":{"draws":19,"losses":7,"wins":22},"gpt-5.6-sol":{"draws":11,"losses":21,"wins":16},"gpt-5.6-terra":{"draws":17,"losses":12,"wins":17},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":21,"losses":10,"wins":17},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":14},"inception/mercury-3":{"draws":10,"losses":8,"wins":14},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":16,"losses":11,"wins":25},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":18},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":18},"meta/muse-spark-open":{"draws":11,"losses":20,"wins":15},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"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":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":6},"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":16,"losses":4,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":9},"o3":{"draws":14,"losses":19,"wins":33},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":13,"losses":9,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":11},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"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":45,"losses":66,"wins":47},"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":1,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":13},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":15,"wins":29},"thinkingmachines/inkling-small":{"draws":18,"losses":9,"wins":21},"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":21,"wins":19},"x-ai/grok-4.6":{"draws":15,"losses":20,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":9,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":7,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":40,"losses":18,"wins":38},"z-ai/glm-5.3":{"draws":15,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":14,"losses":20,"wins":14}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":14,"wins":15},"claude-fable-5":{"draws":12,"losses":33,"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":30,"wins":20},"claude-opus-4-8":{"draws":12,"losses":25,"wins":7},"claude-opus-5":{"draws":8,"losses":63,"wins":11},"claude-opus-5-5":{"draws":6,"losses":46,"wins":0},"claude-sonnet-5":{"draws":19,"losses":18,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":29},"deepseek/deepseek-v4-pro":{"draws":16,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":22,"wins":7},"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":18,"losses":15,"wins":15},"gemini-4-argon":{"draws":5,"losses":41,"wins":2},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":18,"losses":28,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":19,"wins":35},"google/gemini-3.6-flash":{"draws":32,"losses":42,"wins":18},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":16,"wins":11},"gpt-5.4":{"draws":14,"losses":25,"wins":7},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":18,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":8,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":12},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":18,"losses":18,"wins":12},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":3,"wins":12},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":24},"meta/muse-glimmer-30b":{"draws":19,"losses":6,"wins":17},"meta/muse-spark-1.2":{"draws":13,"losses":21,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":26,"wins":10},"meta/muse-spark-open":{"draws":9,"losses":26,"wins":11},"meta/muse-wonder":{"draws":9,"losses":34,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":13},"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":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":23,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":2},"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":20,"losses":8,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":9,"wins":6},"o3":{"draws":15,"losses":23,"wins":28},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":18},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":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":18,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":19,"losses":21,"wins":8},"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":52,"losses":71,"wins":35},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":27,"wins":6},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":31},"thinkingmachines/inkling-small":{"draws":21,"losses":8,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":16,"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":13,"losses":26,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":9,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":21,"wins":6},"z-ai/glm-5.2":{"draws":33,"losses":34,"wins":29},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":22,"wins":10}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":30},"claude-fable-5":{"draws":7,"losses":23,"wins":18},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":17,"losses":14,"wins":47},"claude-opus-4-8":{"draws":3,"losses":17,"wins":24},"claude-opus-5":{"draws":12,"losses":53,"wins":17},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":25},"elorian/glimpse":{"draws":2,"losses":7,"wins":17},"fireworks/ember-1":{"draws":7,"losses":12,"wins":29},"gemini-3.1-pro-preview":{"draws":3,"losses":17,"wins":28},"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":6,"losses":15,"wins":39},"google/gemini-3.5-flash-lite":{"draws":11,"losses":9,"wins":64},"google/gemini-3.6-flash":{"draws":11,"losses":27,"wins":54},"google/gemini-3.8-flash":{"draws":5,"losses":20,"wins":23},"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":10,"losses":13,"wins":21},"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":12,"losses":6,"wins":28},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":5,"losses":7,"wins":20},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":35},"meta/muse-spark-1.2":{"draws":4,"losses":16,"wins":26},"meta/muse-spark-1.3":{"draws":9,"losses":16,"wins":23},"meta/muse-spark-open":{"draws":8,"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":1,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":11,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":30,"wins":8},"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":33},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":15},"o3":{"draws":7,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":37},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":29},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":21},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":29},"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":25,"losses":38,"wins":95},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":15,"wins":25},"thinkingmachines/inkling":{"draws":8,"losses":8,"wins":48},"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":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":18},"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":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":15,"wins":70},"z-ai/glm-5.3":{"draws":10,"losses":15,"wins":21},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":26}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":11,"wins":21},"claude-fable-5":{"draws":12,"losses":28,"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":24,"wins":31},"claude-opus-4-8":{"draws":9,"losses":21,"wins":14},"claude-opus-5":{"draws":8,"losses":69,"wins":5},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":15,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":24,"losses":11,"wins":37},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":14,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":13,"wins":16},"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":20,"wins":17},"gemini-3.1-pro-preview":{"draws":14,"losses":16,"wins":18},"gemini-4-argon":{"draws":7,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":20,"wins":28},"google/gemini-3.5-flash-lite":{"draws":24,"losses":14,"wins":46},"google/gemini-3.6-flash":{"draws":23,"losses":42,"wins":27},"google/gemini-3.8-flash":{"draws":14,"losses":16,"wins":18},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":9,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":10,"wins":25},"gpt-5.4":{"draws":11,"losses":22,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":15,"wins":24},"gpt-5.5":{"draws":15,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":10},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":6,"losses":37,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":43,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":12,"wins":29},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":25,"wins":14},"meta/muse-spark-open":{"draws":10,"losses":20,"wins":16},"meta/muse-wonder":{"draws":13,"losses":25,"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":7,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":21,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":8},"o3":{"draws":12,"losses":24,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"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":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":13},"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":43,"losses":66,"wins":49},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":25},"unbiased/pareto-26.10":{"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":13,"losses":23,"wins":12},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":22,"losses":5,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":35,"losses":23,"wins":38},"z-ai/glm-5.3":{"draws":10,"losses":30,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":22,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":19,"wins":17}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":41},"claude-fable-5":{"draws":4,"losses":7,"wins":37},"claude-fable-5-1":{"draws":6,"losses":19,"wins":29},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":41},"claude-opus-4-5":{"draws":6,"losses":2,"wins":70},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":9,"losses":24,"wins":49},"claude-opus-5-5":{"draws":4,"losses":24,"wins":24},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":3,"wins":41},"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":5,"losses":2,"wins":41},"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":3,"losses":4,"wins":53},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":82},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":80},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":1,"wins":37},"gpt-5.4":{"draws":1,"losses":6,"wins":39},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":47},"gpt-5.5":{"draws":1,"losses":3,"wins":40},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":42},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":37},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":4,"losses":21,"wins":7},"gpt-6-luna":{"draws":4,"losses":5,"wins":39},"gpt-6-sol":{"draws":6,"losses":7,"wins":35},"gpt-6.1-sol":{"draws":7,"losses":19,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"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":2},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":49},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":3,"losses":1,"wins":42},"meta/muse-spark-1.3":{"draws":7,"losses":4,"wins":37},"meta/muse-spark-open":{"draws":1,"losses":1,"wins":44},"meta/muse-wonder":{"draws":3,"losses":6,"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-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":12,"wins":30},"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":39},"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":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":45},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":28},"qwen/qwen3.8-max":{"draws":5,"losses":0,"wins":43},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"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":11,"losses":8,"wins":139},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":2,"losses":1,"wins":43},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":60},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"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":3,"losses":5,"wins":40},"x-ai/grok-4.6":{"draws":4,"losses":6,"wins":38},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":29},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":71},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":5,"losses":3,"wins":38},"z-ai/glm-5.3-flash":{"draws":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":16,"losses":14,"wins":14},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":23,"wins":9},"claude-opus-4-5":{"draws":30,"losses":33,"wins":15},"claude-opus-4-8":{"draws":9,"losses":24,"wins":11},"claude-opus-5":{"draws":18,"losses":58,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":14,"losses":22,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":32,"losses":13,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"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":15,"losses":18,"wins":15},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"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":27,"losses":25,"wins":32},"google/gemini-3.6-flash":{"draws":28,"losses":50,"wins":14},"google/gemini-3.8-flash":{"draws":19,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":15,"wins":10},"gpt-5.4":{"draws":14,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":20},"gpt-5.5":{"draws":22,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":15,"wins":17},"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},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":5,"wins":11},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":13,"wins":26},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":23,"wins":8},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":11},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":12},"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":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":16,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":8},"o3":{"draws":15,"losses":20,"wins":31},"openai/gpt-oss-120b":{"draws":14,"losses":11,"wins":17},"poolside/laguna-s-2.1":{"draws":16,"losses":13,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":11,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":16,"losses":19,"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":38,"losses":76,"wins":44},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10":{"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":14,"losses":31,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":31,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":27,"wins":10}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":34},"claude-fable-5":{"draws":8,"losses":11,"wins":29},"claude-fable-5-1":{"draws":8,"losses":36,"wins":10},"claude-haiku-5-5":{"draws":13,"losses":5,"wins":28},"claude-opus-4-5":{"draws":17,"losses":4,"wins":57},"claude-opus-4-8":{"draws":10,"losses":7,"wins":27},"claude-opus-5":{"draws":10,"losses":36,"wins":36},"claude-opus-5-5":{"draws":6,"losses":33,"wins":13},"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":7,"wins":30},"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":5,"wins":36},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":39},"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":10,"losses":3,"wins":47},"google/gemini-3.5-flash-lite":{"draws":22,"losses":4,"wins":58},"google/gemini-3.6-flash":{"draws":12,"losses":16,"wins":64},"google/gemini-3.8-flash":{"draws":9,"losses":7,"wins":32},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":32},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":34},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":27},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":32},"gpt-6-astra":{"draws":9,"losses":29,"wins":10},"gpt-6-luna":{"draws":8,"losses":9,"wins":31},"gpt-6-sol":{"draws":5,"losses":13,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":45},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":31},"meta/muse-spark-1.3":{"draws":11,"losses":6,"wins":31},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":36},"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":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":29,"wins":13},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"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":8,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":8,"wins":35},"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":23,"losses":20,"wins":115},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":7,"wins":32},"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":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":33},"x-ai/grok-4.6":{"draws":7,"losses":9,"wins":32},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":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":14,"wins":25},"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":3,"losses":9,"wins":36},"claude-fable-5-1":{"draws":2,"losses":22,"wins":30},"claude-haiku-5-5":{"draws":5,"losses":4,"wins":37},"claude-opus-4-5":{"draws":2,"losses":5,"wins":71},"claude-opus-4-8":{"draws":2,"losses":5,"wins":37},"claude-opus-5":{"draws":13,"losses":26,"wins":43},"claude-opus-5-5":{"draws":4,"losses":28,"wins":20},"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":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"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":3,"losses":3,"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":4,"losses":5,"wins":51},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":78},"google/gemini-3.6-flash":{"draws":5,"losses":6,"wins":81},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":38},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":2,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":30},"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":4,"wins":41},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":41},"gpt-6-astra":{"draws":5,"losses":26,"wins":17},"gpt-6-luna":{"draws":1,"losses":1,"wins":46},"gpt-6-sol":{"draws":5,"losses":10,"wins":33},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":3,"losses":6,"wins":37},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":38},"meta/muse-spark-open":{"draws":0,"losses":5,"wins":41},"meta/muse-wonder":{"draws":7,"losses":11,"wins":30},"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-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":16,"wins":27},"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":42},"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":3,"losses":1,"wins":24},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":29},"qwen/qwen3.8-max":{"draws":4,"losses":4,"wins":40},"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":13,"losses":9,"wins":136},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":44},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10":{"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":5,"wins":40},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":21},"z-ai/glm-5.2":{"draws":11,"losses":5,"wins":80},"z-ai/glm-5.3":{"draws":8,"losses":7,"wins":31},"z-ai/glm-5.3-flash":{"draws":5,"losses":5,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":38}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"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},"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},"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":0,"wins":1},"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},"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":13,"losses":12,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":4,"losses":36,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":25,"wins":1},"claude-opus-4-5":{"draws":21,"losses":38,"wins":1},"claude-opus-4-8":{"draws":11,"losses":24,"wins":1},"claude-opus-5":{"draws":6,"losses":50,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":25,"losses":21,"wins":8},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":2},"elorian/glimpse":{"draws":4,"losses":13,"wins":1},"fireworks/ember-1":{"draws":16,"losses":20,"wins":0},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":4},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":15,"losses":26,"wins":5},"google/gemini-3.5-flash-lite":{"draws":27,"losses":29,"wins":8},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":2},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":2},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":2},"gpt-5.4":{"draws":14,"losses":20,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":3},"gpt-5.5":{"draws":14,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":5},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":0},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":5,"losses":30,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":16,"wins":11},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":25,"wins":1},"meta/muse-spark-open":{"draws":9,"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":12,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":32,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":2},"o3":{"draws":15,"losses":34,"wins":3},"openai/gpt-oss-120b":{"draws":15,"losses":14,"wins":3},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":1},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":2},"qwen/qwen3.8-max-0902":{"draws":15,"losses":16,"wins":5},"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":33,"losses":65,"wins":4},"stealth/space-bunny-alpha":{"draws":13,"losses":13,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":19,"wins":7},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":7},"unbiased/pareto-26.10":{"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":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":29,"losses":25,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":41,"wins":4},"z-ai/glm-5.3":{"draws":12,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":2}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":6},"claude-fable-5":{"draws":4,"losses":8,"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":2,"wins":20},"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":8},"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":11},"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},"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":3,"wins":13},"meta/muse-glimmer-30b":{"draws":4,"losses":1,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":6,"wins":7},"meta/muse-spark-1.3":{"draws":4,"losses":7,"wins":7},"meta/muse-spark-open":{"draws":1,"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":2,"losses":1,"wins":3},"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":6,"losses":4,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":7},"o3":{"draws":1,"losses":7,"wins":16},"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":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":6,"losses":2,"wins":10},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":11,"losses":16,"wins":23},"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":1},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":6},"tencent/hy4-preview":{"draws":1,"losses":7,"wins":8},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":13},"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":5,"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":1,"losses":1,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":9},"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":3,"losses":4,"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":4,"losses":31,"wins":1},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":1},"claude-opus-4-5":{"draws":24,"losses":24,"wins":12},"claude-opus-4-8":{"draws":10,"losses":26,"wins":0},"claude-opus-5":{"draws":9,"losses":43,"wins":2},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":20,"wins":18},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":28,"wins":1},"elorian/glimpse":{"draws":7,"losses":9,"wins":4},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":5},"gemini-4-argon":{"draws":1,"losses":33,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":11,"losses":28,"wins":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":32,"wins":13},"google/gemini-3.6-flash":{"draws":22,"losses":40,"wins":8},"google/gemini-3.8-flash":{"draws":9,"losses":26,"wins":1},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":16,"wins":4},"gpt-5.4":{"draws":7,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":14},"gpt-5.5":{"draws":10,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":23,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":9,"losses":21,"wins":6},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":11},"inception/mercury-3":{"draws":10,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":7,"wins":5},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":10,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":6},"meta/muse-spark-1.3":{"draws":1,"losses":30,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":25,"wins":3},"meta/muse-wonder":{"draws":9,"losses":27,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"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-k2.7-code":{"draws":2,"losses":6,"wins":2},"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":10,"losses":9,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":5},"o3":{"draws":4,"losses":37,"wins":11},"openai/gpt-oss-120b":{"draws":9,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":7,"losses":15,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"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":21,"losses":66,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":16,"wins":7},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":8},"unbiased/pareto-26.10":{"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":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":35,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":3},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":29,"wins":19},"claude-fable-5":{"draws":8,"losses":53,"wins":11},"claude-fable-5-1":{"draws":5,"losses":73,"wins":3},"claude-haiku-5-5":{"draws":15,"losses":44,"wins":11},"claude-opus-4-5":{"draws":29,"losses":71,"wins":18},"claude-opus-4-8":{"draws":16,"losses":41,"wins":11},"claude-opus-5":{"draws":11,"losses":92,"wins":13},"claude-opus-5-5":{"draws":5,"losses":71,"wins":4},"claude-sonnet-5":{"draws":17,"losses":43,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":47,"wins":17},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":33,"losses":41,"wins":32},"deepseek/deepseek-v4-pro":{"draws":14,"losses":38,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":34,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":41,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":48,"wins":13},"elorian/glimpse":{"draws":11,"losses":17,"wins":10},"fireworks/ember-1":{"draws":14,"losses":42,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":35,"wins":24},"gemini-4-argon":{"draws":5,"losses":61,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":14,"wins":31},"google/gemini-3.5-flash":{"draws":18,"losses":56,"wins":18},"google/gemini-3.5-flash-lite":{"draws":29,"losses":52,"wins":49},"google/gemini-3.6-flash":{"draws":30,"losses":87,"wins":21},"google/gemini-3.8-flash":{"draws":15,"losses":45,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":15,"wins":18},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":19,"losses":32,"wins":11},"gpt-5.4":{"draws":13,"losses":42,"wins":15},"gpt-5.4-mini":{"draws":14,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":39,"wins":22},"gpt-5.5":{"draws":11,"losses":41,"wins":14},"gpt-5.6-luna":{"draws":22,"losses":29,"wins":21},"gpt-5.6-sol":{"draws":11,"losses":53,"wins":8},"gpt-5.6-terra":{"draws":18,"losses":33,"wins":17},"gpt-6-astra":{"draws":3,"losses":67,"wins":2},"gpt-6-luna":{"draws":14,"losses":40,"wins":18},"gpt-6-sol":{"draws":4,"losses":63,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":63,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":12,"wins":23},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":18,"wins":25},"meta/muse-glimmer-30b":{"draws":17,"losses":21,"wins":24},"meta/muse-spark-1.2":{"draws":13,"losses":39,"wins":16},"meta/muse-spark-1.3":{"draws":14,"losses":46,"wins":12},"meta/muse-spark-open":{"draws":12,"losses":49,"wins":9},"meta/muse-wonder":{"draws":11,"losses":51,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":12,"wins":18},"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":17,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":9,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":40,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":63,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":13,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":20,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":13,"wins":11},"o3":{"draws":13,"losses":62,"wins":31},"openai/gpt-oss-120b":{"draws":19,"losses":13,"wins":32},"poolside/laguna-s-2.1":{"draws":17,"losses":21,"wins":28},"qwen/qwen3.7-max":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":42,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":21,"losses":42,"wins":9},"qwen/qwen3.8-max-0902":{"draws":9,"losses":53,"wins":10},"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":49,"losses":141,"wins":38},"stealth/space-bunny-alpha":{"draws":18,"losses":24,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":40,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":34,"wins":33},"thinkingmachines/inkling-small":{"draws":20,"losses":22,"wins":30},"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":48,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":46,"wins":12},"x-ai/grok-4.7":{"draws":3,"losses":57,"wins":2},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":7},"xiaomi/mimo-v2.5":{"draws":40,"losses":36,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":25,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":37,"wins":6},"z-ai/glm-5.2":{"draws":37,"losses":72,"wins":35},"z-ai/glm-5.3":{"draws":14,"losses":52,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":47,"wins":14},"z-ai/glm-5.3-flashx":{"draws":18,"losses":46,"wins":8}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":10,"losses":36,"wins":2},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":28,"wins":4},"claude-opus-4-5":{"draws":28,"losses":39,"wins":11},"claude-opus-4-8":{"draws":12,"losses":27,"wins":5},"claude-opus-5":{"draws":4,"losses":70,"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":33,"losses":27,"wins":12},"deepseek/deepseek-v4-pro":{"draws":14,"losses":23,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":26,"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":14,"losses":28,"wins":6},"gemini-3.1-pro-preview":{"draws":21,"losses":22,"wins":5},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":19,"losses":35,"wins":6},"google/gemini-3.5-flash-lite":{"draws":39,"losses":31,"wins":14},"google/gemini-3.6-flash":{"draws":29,"losses":56,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":19,"wins":9},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":21,"wins":16},"gpt-5.5":{"draws":12,"losses":23,"wins":9},"gpt-5.6-luna":{"draws":19,"losses":20,"wins":9},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":16,"losses":27,"wins":5},"gpt-6-sol":{"draws":10,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":9,"wins":8},"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":2,"losses":0,"wins":0},"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":11,"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":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":39,"wins":0},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":14,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":11,"wins":3},"o3":{"draws":15,"losses":45,"wins":6},"openai/gpt-oss-120b":{"draws":21,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":14,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":8,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":32,"wins":2},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":15,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":25,"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":39,"losses":104,"wins":15},"stealth/space-bunny-alpha":{"draws":14,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":13,"losses":31,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":18},"thinkingmachines/inkling-small":{"draws":19,"losses":14,"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":8,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":34,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":31,"losses":23,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":16,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":41,"losses":40,"wins":15},"z-ai/glm-5.3":{"draws":9,"losses":33,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"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":9,"losses":8,"wins":21},"claude-fable-5":{"draws":8,"losses":22,"wins":12},"claude-fable-5-1":{"draws":2,"losses":40,"wins":6},"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":11,"losses":12,"wins":15},"claude-opus-5":{"draws":10,"losses":54,"wins":16},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":12,"losses":10,"wins":20},"claude-sonnet-5-5":{"draws":13,"losses":17,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":4,"wins":40},"deepseek/deepseek-v4-pro":{"draws":7,"losses":14,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":19},"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":13,"wins":18},"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":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":12,"wins":29},"google/gemini-3.5-flash-lite":{"draws":18,"losses":7,"wins":47},"google/gemini-3.6-flash":{"draws":13,"losses":26,"wins":41},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":24},"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":9,"losses":8,"wins":21},"gpt-5.4":{"draws":9,"losses":16,"wins":15},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":24},"gpt-5.5":{"draws":8,"losses":15,"wins":17},"gpt-5.6-luna":{"draws":13,"losses":6,"wins":23},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":14},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":17},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":12,"losses":7,"wins":23},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":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":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":28},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":13},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":21},"meta/muse-spark-open":{"draws":10,"losses":14,"wins":16},"meta/muse-wonder":{"draws":8,"losses":18,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":20},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":32,"wins":5},"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":11,"losses":2,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":11},"o3":{"draws":8,"losses":14,"wins":32},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":25},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":16},"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":39,"losses":60,"wins":43},"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":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":16,"wins":16},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":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":11,"losses":19,"wins":12},"x-ai/grok-4.6":{"draws":10,"losses":20,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":16,"losses":4,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":15,"losses":19,"wins":50},"z-ai/glm-5.3":{"draws":7,"losses":21,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":21},"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":6,"wins":31},"claude-fable-5":{"draws":7,"losses":22,"wins":19},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":4,"losses":19,"wins":23},"claude-opus-4-5":{"draws":13,"losses":13,"wins":52},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":8,"losses":50,"wins":24},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":12,"losses":8,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":56},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":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":11,"losses":14,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"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":9,"wins":43},"google/gemini-3.5-flash-lite":{"draws":12,"losses":8,"wins":64},"google/gemini-3.6-flash":{"draws":18,"losses":26,"wins":48},"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":8,"losses":15,"wins":23},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":35},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"gpt-6-luna":{"draws":5,"losses":10,"wins":33},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":35,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"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":0,"losses":0,"wins":2},"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":8,"losses":16,"wins":22},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":14},"meta/muse-spark-open":{"draws":7,"losses":12,"wins":27},"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":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":40,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":31},"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":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":12,"wins":26},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":52},"thinkingmachines/inkling-small":{"draws":8,"losses":4,"wins":36},"unbiased/pareto-26.10":{"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":2,"losses":2,"wins":22},"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":7},"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},"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":0,"losses":0,"wins":2},"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":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":2},"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":16,"losses":2,"wins":24},"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":0,"losses":2,"wins":2},"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":9,"losses":2,"wins":15},"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":9,"losses":16,"wins":23},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":11,"wins":27},"claude-opus-4-5":{"draws":11,"losses":22,"wins":45},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":7,"losses":53,"wins":22},"claude-opus-5-5":{"draws":5,"losses":37,"wins":10},"claude-sonnet-5":{"draws":8,"losses":13,"wins":27},"claude-sonnet-5-5":{"draws":6,"losses":23,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":48},"deepseek/deepseek-v4-pro":{"draws":7,"losses":12,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"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":2,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":59},"google/gemini-3.6-flash":{"draws":16,"losses":29,"wins":47},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":28},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":19},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":36},"gpt-5.5":{"draws":11,"losses":14,"wins":19},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":30},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":21},"gpt-5.6-terra":{"draws":3,"losses":16,"wins":27},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":9,"losses":14,"wins":25},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":33,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":33},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":15,"wins":24},"meta/muse-spark-open":{"draws":7,"losses":17,"wins":22},"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":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":11},"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":8,"losses":6,"wins":28},"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":5,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":23},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":27},"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":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":42},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":31},"unbiased/pareto-26.10":{"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":2,"losses":9,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":15,"wins":14},"z-ai/glm-5.2":{"draws":23,"losses":15,"wins":58},"z-ai/glm-5.3":{"draws":9,"losses":17,"wins":20},"z-ai/glm-5.3-flash":{"draws":8,"losses":12,"wins":28},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":17,"wins":7},"claude-fable-5":{"draws":9,"losses":32,"wins":1},"claude-fable-5-1":{"draws":1,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":31,"wins":5},"claude-opus-4-5":{"draws":20,"losses":47,"wins":3},"claude-opus-4-8":{"draws":12,"losses":28,"wins":2},"claude-opus-5":{"draws":7,"losses":60,"wins":3},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":21,"losses":26,"wins":17},"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":11,"losses":23,"wins":8},"gemini-4-argon":{"draws":1,"losses":40,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":15,"wins":8},"google/gemini-3.5-flash":{"draws":14,"losses":31,"wins":9},"google/gemini-3.5-flash-lite":{"draws":19,"losses":37,"wins":18},"google/gemini-3.6-flash":{"draws":19,"losses":51,"wins":10},"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":6,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":22,"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":14,"losses":21,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":3},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":12,"losses":24,"wins":6},"gpt-6-sol":{"draws":7,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":10,"wins":8},"inception/mercury-3":{"draws":7,"losses":21,"wins":0},"inclusionai/ling-3.0-flash":{"draws":11,"losses":11,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":27,"wins":13},"meta/muse-glimmer-30b":{"draws":12,"losses":16,"wins":8},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":33,"wins":2},"meta/muse-spark-open":{"draws":9,"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":10,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"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":3,"losses":10,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":21,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":3},"o3":{"draws":7,"losses":44,"wins":11},"openai/gpt-oss-120b":{"draws":12,"losses":16,"wins":8},"poolside/laguna-s-2.1":{"draws":8,"losses":22,"wins":8},"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":12,"losses":23,"wins":7},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":4},"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":21,"losses":87,"wins":10},"stealth/space-bunny-alpha":{"draws":8,"losses":22,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":12,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":13,"wins":1},"tencent/hy4-preview":{"draws":9,"losses":29,"wins":2},"thinkingmachines/inkling":{"draws":14,"losses":31,"wins":9},"thinkingmachines/inkling-small":{"draws":13,"losses":13,"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":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":21,"losses":34,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":14,"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":24,"losses":50,"wins":10},"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":12,"losses":28,"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},"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":0,"losses":0,"wins":2},"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":5,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":5},"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":19},"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":3,"wins":1},"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":2,"losses":8,"wins":14},"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":11,"losses":8,"wins":13},"claude-fable-5":{"draws":6,"losses":24,"wins":6},"claude-fable-5-1":{"draws":2,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":17,"losses":28,"wins":15},"claude-opus-4-8":{"draws":10,"losses":19,"wins":7},"claude-opus-5":{"draws":6,"losses":58,"wins":4},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":11,"losses":8,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":11,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":15,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":13,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":2},"elorian/glimpse":{"draws":4,"losses":9,"wins":7},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":16},"google/gemini-3.5-flash-lite":{"draws":16,"losses":14,"wins":32},"google/gemini-3.6-flash":{"draws":20,"losses":33,"wins":15},"google/gemini-3.8-flash":{"draws":5,"losses":13,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":6,"losses":21,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":13},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":17},"gpt-5.5":{"draws":12,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":24,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":11},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":13,"losses":13,"wins":10},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":14},"inception/mercury-3":{"draws":6,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":15},"meta/muse-spark-open":{"draws":7,"losses":21,"wins":6},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":13},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":32,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":8},"o3":{"draws":5,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":11,"wins":13},"stealth/ox-alpha":{"draws":24,"losses":49,"wins":29},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":28},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":23,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":11,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":24,"wins":31},"z-ai/glm-5.3":{"draws":10,"losses":20,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":12,"wins":13}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":21},"claude-fable-5":{"draws":15,"losses":31,"wins":2},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":11},"claude-opus-4-5":{"draws":29,"losses":26,"wins":23},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":15,"losses":59,"wins":8},"claude-opus-5-5":{"draws":2,"losses":44,"wins":6},"claude-sonnet-5":{"draws":17,"losses":13,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":13,"wins":41},"deepseek/deepseek-v4-pro":{"draws":10,"losses":15,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":9},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":17,"losses":20,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"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":17,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":24,"losses":16,"wins":44},"google/gemini-3.6-flash":{"draws":27,"losses":40,"wins":25},"google/gemini-3.8-flash":{"draws":13,"losses":30,"wins":5},"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":12,"losses":14,"wins":16},"gpt-5.4":{"draws":10,"losses":29,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":24},"gpt-5.5":{"draws":18,"losses":15,"wins":11},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":8},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":15},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":18,"losses":15,"wins":15},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":12,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":8,"wins":29},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":24,"wins":12},"meta/muse-spark-open":{"draws":10,"losses":23,"wins":13},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"minimax/minimax-m3.1-flash":{"draws":12,"losses":16,"wins":14},"mistralai/mistral-large-4-0":{"draws":14,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":11,"losses":24,"wins":31},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":17},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":19,"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":39,"losses":66,"wins":53},"stealth/space-bunny-alpha":{"draws":16,"losses":7,"wins":15},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"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":12,"losses":24,"wins":12},"x-ai/grok-4.6":{"draws":20,"losses":20,"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":10,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":35},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":16,"losses":23,"wins":9}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":3,"wins":25},"claude-fable-5":{"draws":5,"losses":9,"wins":28},"claude-fable-5-1":{"draws":5,"losses":28,"wins":13},"claude-haiku-5-5":{"draws":6,"losses":7,"wins":29},"claude-opus-4-5":{"draws":14,"losses":3,"wins":53},"claude-opus-4-8":{"draws":5,"losses":6,"wins":31},"claude-opus-5":{"draws":10,"losses":36,"wins":24},"claude-opus-5-5":{"draws":2,"losses":31,"wins":13},"claude-sonnet-5":{"draws":6,"losses":2,"wins":34},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":25},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":8,"losses":0,"wins":57},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":10,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":7,"wins":30},"elorian/glimpse":{"draws":1,"losses":3,"wins":18},"fireworks/ember-1":{"draws":6,"losses":3,"wins":33},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":33},"gemini-4-argon":{"draws":4,"losses":24,"wins":15},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":45},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":64},"google/gemini-3.6-flash":{"draws":12,"losses":12,"wins":57},"google/gemini-3.8-flash":{"draws":4,"losses":7,"wins":31},"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":1,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":2,"wins":28},"gpt-5.4":{"draws":6,"losses":6,"wins":28},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":2,"wins":39},"gpt-5.5":{"draws":4,"losses":7,"wins":27},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":38},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":27},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":36},"gpt-6-astra":{"draws":2,"losses":30,"wins":10},"gpt-6-luna":{"draws":5,"losses":2,"wins":35},"gpt-6-sol":{"draws":4,"losses":11,"wins":27},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":24},"inception/mercury-3":{"draws":5,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":28},"meta/muse-spark-1.2":{"draws":6,"losses":3,"wins":31},"meta/muse-spark-1.3":{"draws":4,"losses":2,"wins":36},"meta/muse-spark-open":{"draws":4,"losses":3,"wins":33},"meta/muse-wonder":{"draws":5,"losses":13,"wins":24},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":4,"losses":1,"wins":31},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":16,"wins":9},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":16},"o3":{"draws":5,"losses":3,"wins":54},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":30},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":22},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":1,"wins":35},"qwen/qwen3.8-27b":{"draws":5,"losses":0,"wins":25},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":25},"qwen/qwen3.8-max":{"draws":5,"losses":5,"wins":32},"qwen/qwen3.8-max-0902":{"draws":7,"losses":3,"wins":32},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":4,"wins":27},"stealth/ox-alpha":{"draws":22,"losses":5,"wins":91},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":17},"tencent/hy4-preview":{"draws":3,"losses":2,"wins":35},"thinkingmachines/inkling":{"draws":9,"losses":0,"wins":46},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":37},"unbiased/pareto-26.10":{"draws":2,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":9,"losses":4,"wins":29},"x-ai/grok-4.6":{"draws":5,"losses":8,"wins":29},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":24},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":9,"losses":0,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":2,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":6,"wins":15},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":66},"z-ai/glm-5.3":{"draws":5,"losses":10,"wins":25},"z-ai/glm-5.3-flash":{"draws":5,"losses":6,"wins":31},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":33}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":21,"wins":4},"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":45,"wins":1},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":6,"losses":21,"wins":3},"claude-sonnet-5-5":{"draws":3,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":9,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":25,"wins":16},"deepseek/deepseek-v4-pro":{"draws":2,"losses":24,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":28,"wins":1},"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":4,"losses":21,"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":5,"losses":30,"wins":3},"google/gemini-3.5-flash-lite":{"draws":5,"losses":38,"wins":11},"google/gemini-3.6-flash":{"draws":2,"losses":54,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":28,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":4},"gpt-4.1":{"draws":0,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":22,"wins":5},"gpt-5.4":{"draws":4,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":11,"wins":6},"gpt-5.4-nano":{"draws":3,"losses":18,"wins":11},"gpt-5.5":{"draws":1,"losses":26,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":21,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":26,"wins":1},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":23,"wins":5},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":10,"wins":8},"inception/mercury-3":{"draws":0,"losses":19,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":11,"wins":7},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":5,"losses":17,"wins":4},"meta/muse-spark-1.2":{"draws":1,"losses":25,"wins":2},"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":1,"losses":10,"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":2,"losses":12,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":28,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":19,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":9,"wins":3},"o3":{"draws":1,"losses":46,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":9,"losses":21,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":9,"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":14,"losses":85,"wins":9},"stealth/space-bunny-alpha":{"draws":3,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":25,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":23,"wins":11},"thinkingmachines/inkling-small":{"draws":4,"losses":19,"wins":7},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":6,"wins":1},"x-ai/grok-4.5":{"draws":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":2,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":18,"wins":1},"z-ai/glm-5.2":{"draws":15,"losses":40,"wins":5},"z-ai/glm-5.3":{"draws":3,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":26,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":27,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":8},"claude-fable-5":{"draws":6,"losses":21,"wins":3},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":16,"wins":7},"claude-opus-4-5":{"draws":22,"losses":19,"wins":9},"claude-opus-4-8":{"draws":6,"losses":23,"wins":1},"claude-opus-5":{"draws":4,"losses":41,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":9,"losses":12,"wins":9},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":17,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":14,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":21,"wins":5},"elorian/glimpse":{"draws":2,"losses":11,"wins":3},"fireworks/ember-1":{"draws":11,"losses":14,"wins":5},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":6},"gemini-4-argon":{"draws":1,"losses":27,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":13},"google/gemini-3.5-flash":{"draws":9,"losses":24,"wins":5},"google/gemini-3.5-flash-lite":{"draws":16,"losses":18,"wins":16},"google/gemini-3.6-flash":{"draws":14,"losses":31,"wins":11},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":4},"gpt-4.1":{"draws":4,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":12,"wins":7},"gpt-5.4":{"draws":5,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":13},"gpt-5.5":{"draws":10,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":8},"gpt-6-astra":{"draws":3,"losses":26,"wins":1},"gpt-6-luna":{"draws":13,"losses":11,"wins":6},"gpt-6-sol":{"draws":2,"losses":26,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":10},"inception/mercury-3":{"draws":9,"losses":10,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":10,"wins":14},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":7},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":16,"wins":7},"meta/muse-spark-open":{"draws":6,"losses":17,"wins":5},"meta/muse-wonder":{"draws":7,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":25,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":2,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":2},"o3":{"draws":8,"losses":27,"wins":11},"openai/gpt-oss-120b":{"draws":9,"losses":13,"wins":4},"poolside/laguna-s-2.1":{"draws":13,"losses":8,"wins":7},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":11,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":2},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":17,"wins":4},"stealth/ox-alpha":{"draws":20,"losses":41,"wins":21},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":13,"wins":13},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":12},"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":2,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":18,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":14,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":4},"z-ai/glm-5.2":{"draws":27,"losses":19,"wins":14},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.3-flash":{"draws":6,"losses":12,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":9}},"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},"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":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":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":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":20,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":40,"wins":4},"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":9,"losses":8,"wins":25},"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":0,"losses":2,"wins":2},"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":5,"losses":6,"wins":15},"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":16,"losses":27,"wins":17},"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":16,"wins":10},"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":9,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":8,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":16,"losses":13,"wins":37},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":24},"google/gemini-3.8-flash":{"draws":2,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":13},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":15,"wins":13},"gpt-5.4":{"draws":6,"losses":21,"wins":9},"gpt-5.4-mini":{"draws":5,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":3,"losses":16,"wins":21},"gpt-5.5":{"draws":10,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":2,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":19,"wins":8},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":6,"losses":16,"wins":14},"gpt-6-sol":{"draws":6,"losses":27,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":17},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":25},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":19,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":24,"wins":7},"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":6,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":12},"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":12,"losses":7,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":5},"o3":{"draws":6,"losses":22,"wins":20},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":25},"poolside/laguna-s-2.1":{"draws":3,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":3,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":7},"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":15,"losses":61,"wins":26},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":29},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":9},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":17,"losses":9,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":27,"wins":29},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":12},"z-ai/glm-5.3-flashx":{"draws":3,"losses":23,"wins":10}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":14,"wins":13},"claude-fable-5":{"draws":12,"losses":35,"wins":1},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":31,"wins":3},"claude-opus-4-5":{"draws":28,"losses":41,"wins":9},"claude-opus-4-8":{"draws":14,"losses":29,"wins":1},"claude-opus-5":{"draws":12,"losses":65,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":15,"losses":27,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":29,"losses":22,"wins":21},"deepseek/deepseek-v4-pro":{"draws":14,"losses":23,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":27,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":35,"wins":4},"elorian/glimpse":{"draws":4,"losses":15,"wins":7},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":16,"losses":22,"wins":10},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":8,"wins":14},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":30,"wins":24},"google/gemini-3.6-flash":{"draws":29,"losses":52,"wins":11},"google/gemini-3.8-flash":{"draws":11,"losses":36,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":7,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":22,"wins":5},"gpt-5.4":{"draws":16,"losses":28,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":18},"gpt-5.5":{"draws":19,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":17,"losses":27,"wins":2},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":16,"losses":24,"wins":8},"gpt-6-sol":{"draws":6,"losses":39,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":17,"losses":7,"wins":10},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":24,"wins":11},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":12},"meta/muse-spark-1.2":{"draws":13,"losses":29,"wins":4},"meta/muse-spark-1.3":{"draws":13,"losses":32,"wins":3},"meta/muse-spark-open":{"draws":11,"losses":32,"wins":3},"meta/muse-wonder":{"draws":10,"losses":36,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":10,"wins":6},"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":13,"losses":7,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":26,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":41,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":13,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":2},"o3":{"draws":11,"losses":50,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":5},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":31,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":19,"losses":27,"wins":2},"qwen/qwen3.8-max-0902":{"draws":16,"losses":31,"wins":1},"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":42,"losses":102,"wins":14},"stealth/space-bunny-alpha":{"draws":14,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":15,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":12,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":6},"thinkingmachines/inkling":{"draws":20,"losses":24,"wins":20},"thinkingmachines/inkling-small":{"draws":19,"losses":14,"wins":15},"unbiased/pareto-26.10":{"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":18,"losses":29,"wins":1},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":26,"losses":25,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":21,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":24,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":44,"wins":17},"z-ai/glm-5.3":{"draws":10,"losses":34,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":35,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":30,"wins":8}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":23,"wins":15},"claude-fable-5":{"draws":17,"losses":42,"wins":7},"claude-fable-5-1":{"draws":5,"losses":66,"wins":1},"claude-haiku-5-5":{"draws":19,"losses":31,"wins":12},"claude-opus-4-5":{"draws":42,"losses":52,"wins":12},"claude-opus-4-8":{"draws":23,"losses":30,"wins":5},"claude-opus-5":{"draws":19,"losses":97,"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":15,"losses":40,"wins":11},"cohere/north-mini-code":{"draws":8,"losses":12,"wins":4},"deepseek/deepseek-v4-flash":{"draws":42,"losses":32,"wins":24},"deepseek/deepseek-v4-pro":{"draws":22,"losses":22,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":28,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":28,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":43,"wins":7},"elorian/glimpse":{"draws":11,"losses":18,"wins":5},"fireworks/ember-1":{"draws":29,"losses":28,"wins":9},"gemini-3.1-pro-preview":{"draws":24,"losses":29,"wins":13},"gemini-4-argon":{"draws":6,"losses":58,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":8,"wins":15},"google/gemini-3.5-flash":{"draws":23,"losses":46,"wins":11},"google/gemini-3.5-flash-lite":{"draws":46,"losses":33,"wins":35},"google/gemini-3.6-flash":{"draws":41,"losses":69,"wins":14},"google/gemini-3.8-flash":{"draws":14,"losses":46,"wins":6},"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":2,"wins":1},"gpt-5":{"draws":21,"losses":26,"wins":11},"gpt-5.4":{"draws":16,"losses":37,"wins":9},"gpt-5.4-mini":{"draws":18,"losses":17,"wins":9},"gpt-5.4-nano":{"draws":21,"losses":24,"wins":21},"gpt-5.5":{"draws":22,"losses":28,"wins":10},"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":26,"losses":31,"wins":5},"gpt-6-astra":{"draws":5,"losses":61,"wins":0},"gpt-6-luna":{"draws":23,"losses":34,"wins":9},"gpt-6-sol":{"draws":12,"losses":51,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":61,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":12,"wins":10},"inception/mercury-3":{"draws":19,"losses":22,"wins":5},"inclusionai/ling-3.0-flash":{"draws":23,"losses":9,"wins":12},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":27,"wins":21},"meta/muse-glimmer-30b":{"draws":29,"losses":11,"wins":18},"meta/muse-spark-1.2":{"draws":18,"losses":43,"wins":3},"meta/muse-spark-1.3":{"draws":20,"losses":39,"wins":7},"meta/muse-spark-open":{"draws":17,"losses":39,"wins":6},"meta/muse-wonder":{"draws":12,"losses":48,"wins":6},"minimax/minimax-m3":{"draws":13,"losses":10,"wins":13},"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":20,"losses":8,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":25,"losses":36,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":52,"wins":0},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":18,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":4},"o3":{"draws":17,"losses":44,"wins":21},"openai/gpt-oss-120b":{"draws":30,"losses":22,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":13},"qwen/qwen3.7-max":{"draws":18,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":38,"wins":5},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":7},"qwen/qwen3.8-max":{"draws":24,"losses":32,"wins":10},"qwen/qwen3.8-max-0902":{"draws":24,"losses":37,"wins":5},"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":67,"losses":135,"wins":28},"stealth/space-bunny-alpha":{"draws":19,"losses":20,"wins":11},"stepfun/step-3.7-flash":{"draws":16,"losses":15,"wins":11},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":13,"wins":8},"tencent/hy4-preview":{"draws":20,"losses":32,"wins":10},"thinkingmachines/inkling":{"draws":36,"losses":26,"wins":26},"thinkingmachines/inkling-small":{"draws":27,"losses":12,"wins":27},"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":16,"losses":44,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":46,"wins":4},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":41,"losses":27,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":9,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":30,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":59,"losses":48,"wins":25},"z-ai/glm-5.3":{"draws":18,"losses":40,"wins":6},"z-ai/glm-5.3-flash":{"draws":17,"losses":37,"wins":12},"z-ai/glm-5.3-flashx":{"draws":27,"losses":31,"wins":8}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":6,"wins":17},"claude-fable-5":{"draws":7,"losses":27,"wins":8},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":12},"claude-opus-4-5":{"draws":22,"losses":28,"wins":20},"claude-opus-4-8":{"draws":14,"losses":17,"wins":11},"claude-opus-5":{"draws":9,"losses":52,"wins":9},"claude-opus-5-5":{"draws":1,"losses":45,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":10},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":32,"losses":9,"wins":23},"deepseek/deepseek-v4-pro":{"draws":14,"losses":18,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":12,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":29,"wins":5},"elorian/glimpse":{"draws":3,"losses":11,"wins":8},"fireworks/ember-1":{"draws":13,"losses":17,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":16},"gemini-4-argon":{"draws":4,"losses":33,"wins":5},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":17},"google/gemini-3.5-flash":{"draws":19,"losses":18,"wins":17},"google/gemini-3.5-flash-lite":{"draws":25,"losses":20,"wins":29},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":10},"gpt-4.1":{"draws":8,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":14,"wins":6},"gpt-5.4":{"draws":8,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":20},"gpt-5.5":{"draws":13,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":11,"losses":18,"wins":11},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":11,"losses":19,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":13},"inception/mercury-3":{"draws":9,"losses":10,"wins":9},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":24},"meta/muse-glimmer-30b":{"draws":15,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":11},"meta/muse-spark-open":{"draws":7,"losses":21,"wins":12},"meta/muse-wonder":{"draws":6,"losses":33,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"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":12,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":19,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":8,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":10},"o3":{"draws":16,"losses":22,"wins":24},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":16},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"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":31,"losses":56,"wins":31},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":17,"losses":6,"wins":31},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10":{"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":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":13,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":33,"wins":26},"z-ai/glm-5.3":{"draws":10,"losses":21,"wins":9},"z-ai/glm-5.3-flash":{"draws":15,"losses":15,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":17,"wins":12}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":13},"claude-fable-5":{"draws":6,"losses":25,"wins":5},"claude-fable-5-1":{"draws":0,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":22,"wins":7},"claude-opus-4-5":{"draws":15,"losses":24,"wins":21},"claude-opus-4-8":{"draws":8,"losses":20,"wins":8},"claude-opus-5":{"draws":9,"losses":48,"wins":1},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":19,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":15},"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":9,"losses":16,"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":6,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":9,"losses":21,"wins":16},"google/gemini-3.5-flash-lite":{"draws":17,"losses":15,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":19},"google/gemini-3.8-flash":{"draws":8,"losses":24,"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":8,"losses":16,"wins":8},"gpt-5.4":{"draws":4,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":11,"wins":22},"gpt-5.5":{"draws":15,"losses":13,"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":16,"losses":9,"wins":9},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":10},"gpt-6-sol":{"draws":3,"losses":27,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":30,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":15},"inception/mercury-3":{"draws":7,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":10,"wins":23},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":10},"meta/muse-spark-1.2":{"draws":6,"losses":23,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":18,"wins":9},"meta/muse-spark-open":{"draws":7,"losses":20,"wins":7},"meta/muse-wonder":{"draws":11,"losses":25,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":5,"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":8,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":11,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":6,"wins":8},"o3":{"draws":7,"losses":27,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":11,"losses":11,"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":20,"losses":60,"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":29},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":18},"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":13,"losses":19,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":23,"losses":26,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":17,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":9}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":12,"losses":32,"wins":4},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":22,"wins":8},"claude-opus-4-5":{"draws":35,"losses":27,"wins":16},"claude-opus-4-8":{"draws":16,"losses":20,"wins":8},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"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":30,"losses":15,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":29,"wins":10},"elorian/glimpse":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":26,"losses":20,"wins":2},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":17},"google/gemini-3.5-flash":{"draws":19,"losses":26,"wins":15},"google/gemini-3.5-flash-lite":{"draws":34,"losses":21,"wins":29},"google/gemini-3.6-flash":{"draws":29,"losses":45,"wins":18},"google/gemini-3.8-flash":{"draws":11,"losses":28,"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":17,"losses":14,"wins":11},"gpt-5.4":{"draws":10,"losses":27,"wins":9},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":17,"losses":15,"wins":16},"gpt-5.5":{"draws":17,"losses":18,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":21,"losses":13,"wins":12},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":20,"losses":2,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":13,"wins":24},"meta/muse-glimmer-30b":{"draws":25,"losses":2,"wins":15},"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":25,"wins":9},"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":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":16,"losses":22,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":8,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":8,"wins":6},"o3":{"draws":14,"losses":28,"wins":24},"openai/gpt-oss-120b":{"draws":20,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":14,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-27b":{"draws":15,"losses":11,"wins":8},"qwen/qwen3.8-flash":{"draws":13,"losses":12,"wins":7},"qwen/qwen3.8-max":{"draws":20,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":20,"losses":24,"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":52,"losses":72,"wins":34},"stealth/space-bunny-alpha":{"draws":18,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":18,"losses":6,"wins":24},"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":29,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":36,"losses":16,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":47,"losses":31,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":33,"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":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":9},"claude-opus-4-5":{"draws":26,"losses":14,"wins":28},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":14,"losses":51,"wins":5},"claude-opus-5-5":{"draws":2,"losses":39,"wins":1},"claude-sonnet-5":{"draws":14,"losses":14,"wins":14},"claude-sonnet-5-5":{"draws":6,"losses":28,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":14},"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":11,"losses":14,"wins":17},"gemini-4-argon":{"draws":3,"losses":36,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":17,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":39,"wins":21},"google/gemini-3.8-flash":{"draws":6,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":13},"gpt-5.4":{"draws":10,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":20},"gpt-5.5":{"draws":17,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":6},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":5,"losses":32,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":4,"wins":13},"inception/mercury-3":{"draws":11,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":10},"meta/muse-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":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":0},"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":12,"losses":6,"wins":16},"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":14,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":15,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":8},"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":61,"wins":41},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":15,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":21,"losses":8,"wins":29},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":19},"unbiased/pareto-26.10":{"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":26,"losses":9,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":6}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":14,"losses":17,"wins":17},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":24,"losses":13,"wins":41},"claude-opus-4-8":{"draws":19,"losses":11,"wins":14},"claude-opus-5":{"draws":10,"losses":62,"wins":10},"claude-opus-5-5":{"draws":7,"losses":43,"wins":2},"claude-sonnet-5":{"draws":12,"losses":9,"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":21,"losses":6,"wins":45},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":15,"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":15,"losses":9,"wins":24},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"gemini-4-argon":{"draws":10,"losses":27,"wins":11},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":17,"losses":12,"wins":31},"google/gemini-3.5-flash-lite":{"draws":27,"losses":4,"wins":53},"google/gemini-3.6-flash":{"draws":22,"losses":28,"wins":42},"google/gemini-3.8-flash":{"draws":10,"losses":11,"wins":27},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":13},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":4,"wins":27},"gpt-5.4":{"draws":11,"losses":17,"wins":18},"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":10,"losses":25,"wins":13},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":21},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":6,"losses":28,"wins":14},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":32},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":10,"losses":15,"wins":21},"meta/muse-spark-1.3":{"draws":11,"losses":15,"wins":22},"meta/muse-spark-open":{"draws":10,"losses":10,"wins":26},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"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":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":8,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":32,"wins":11},"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":14,"losses":3,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":0,"wins":15},"o3":{"draws":7,"losses":12,"wins":47},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"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":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":11,"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":13,"losses":14,"wins":21},"qwen/qwen3.8-max-0902":{"draws":15,"losses":10,"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":40,"wins":78},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":13,"losses":10,"wins":23},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":37},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":25},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":17,"wins":17},"x-ai/grok-4.6":{"draws":18,"losses":17,"wins":13},"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":27,"losses":4,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":28,"losses":11,"wins":57},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":11},"z-ai/glm-5.3-flash":{"draws":6,"losses":14,"wins":28},"z-ai/glm-5.3-flashx":{"draws":11,"losses":16,"wins":21}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":8,"wins":19},"claude-fable-5":{"draws":6,"losses":30,"wins":12},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":27,"wins":12},"claude-opus-4-5":{"draws":25,"losses":16,"wins":37},"claude-opus-4-8":{"draws":11,"losses":20,"wins":13},"claude-opus-5":{"draws":15,"losses":60,"wins":7},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":15,"losses":13,"wins":20},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":10,"wins":40},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":13,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":18,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":29,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"gemini-4-argon":{"draws":0,"losses":46,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":20},"google/gemini-3.5-flash-lite":{"draws":30,"losses":14,"wins":40},"google/gemini-3.6-flash":{"draws":30,"losses":41,"wins":21},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":8,"wins":20},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":27},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":20,"losses":14,"wins":12},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":15,"losses":14,"wins":19},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":13,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":16,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":21},"meta/muse-spark-1.3":{"draws":10,"losses":30,"wins":8},"meta/muse-spark-open":{"draws":13,"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":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":2},"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":14,"losses":6,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":13,"losses":19,"wins":34},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":13,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":14},"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":39,"losses":61,"wins":58},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":19,"losses":13,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":15,"wins":21},"unbiased/pareto-26.10":{"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":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":15,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":33,"losses":23,"wins":40},"z-ai/glm-5.3":{"draws":13,"losses":24,"wins":9},"z-ai/glm-5.3-flash":{"draws":10,"losses":22,"wins":16},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":12,"wins":22},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":11},"claude-opus-4-5":{"draws":24,"losses":39,"wins":15},"claude-opus-4-8":{"draws":13,"losses":24,"wins":7},"claude-opus-5":{"draws":15,"losses":58,"wins":9},"claude-opus-5-5":{"draws":6,"losses":45,"wins":1},"claude-sonnet-5":{"draws":13,"losses":15,"wins":20},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":24,"losses":15,"wins":33},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":28,"wins":9},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":12,"losses":21,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":15,"losses":25,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":26,"wins":32},"google/gemini-3.6-flash":{"draws":19,"losses":51,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":29,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":16,"wins":15},"gpt-5.4":{"draws":7,"losses":27,"wins":12},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":14,"losses":19,"wins":15},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":14,"wins":32},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":23,"wins":11},"meta/muse-spark-open":{"draws":13,"losses":27,"wins":6},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":6,"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":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":42,"wins":2},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":10,"wins":4},"o3":{"draws":11,"losses":29,"wins":26},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":21},"poolside/laguna-s-2.1":{"draws":18,"losses":13,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":19,"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":36,"losses":75,"wins":47},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":24,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":24},"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":13,"losses":25,"wins":10},"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":28,"losses":17,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":10,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":6},"z-ai/glm-5.2":{"draws":34,"losses":29,"wins":33},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":22,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"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},"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":0,"losses":1,"wins":1},"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":5,"losses":32,"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":7,"wins":2},"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":10,"losses":17,"wins":13},"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":0,"losses":2,"wins":2},"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":14,"wins":7},"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":24,"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},"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":0,"losses":0,"wins":2},"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":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":3},"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":9,"losses":6,"wins":21},"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":0,"losses":2,"wins":2},"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":1,"losses":9,"wins":12},"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":34,"losses":33,"wins":77},"claude-fable-5":{"draws":30,"losses":91,"wins":35},"claude-fable-5-1":{"draws":7,"losses":166,"wins":9},"claude-haiku-5-5":{"draws":31,"losses":59,"wins":52},"claude-opus-4-5":{"draws":73,"losses":75,"wins":98},"claude-opus-4-8":{"draws":31,"losses":50,"wins":47},"claude-opus-5":{"draws":48,"losses":190,"wins":42},"claude-opus-5-5":{"draws":19,"losses":144,"wins":5},"claude-sonnet-5":{"draws":40,"losses":43,"wins":73},"claude-sonnet-5-5":{"draws":37,"losses":70,"wins":49},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":47},"deepseek/deepseek-v4-flash":{"draws":56,"losses":47,"wins":125},"deepseek/deepseek-v4-pro":{"draws":33,"losses":46,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":49,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":62,"wins":52},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":81,"wins":47},"elorian/glimpse":{"draws":20,"losses":30,"wins":38},"fireworks/ember-1":{"draws":38,"losses":62,"wins":56},"gemini-3.1-pro-preview":{"draws":37,"losses":48,"wins":71},"gemini-4-argon":{"draws":16,"losses":125,"wins":15},"google/gemini-3.1-flash-lite":{"draws":18,"losses":14,"wins":54},"google/gemini-3.5-flash":{"draws":41,"losses":63,"wins":84},"google/gemini-3.5-flash-lite":{"draws":61,"losses":58,"wins":151},"google/gemini-3.6-flash":{"draws":79,"losses":124,"wins":97},"google/gemini-3.8-flash":{"draws":38,"losses":75,"wins":43},"google/gemma-4-31b-it":{"draws":18,"losses":17,"wins":51},"gpt-4.1":{"draws":12,"losses":9,"wins":31},"gpt-4.1-nano":{"draws":13,"losses":1,"wins":10},"gpt-5":{"draws":30,"losses":45,"wins":65},"gpt-5.4":{"draws":38,"losses":59,"wins":53},"gpt-5.4-mini":{"draws":29,"losses":18,"wins":57},"gpt-5.4-nano":{"draws":30,"losses":36,"wins":70},"gpt-5.5":{"draws":42,"losses":55,"wins":49},"gpt-5.6-luna":{"draws":51,"losses":31,"wins":74},"gpt-5.6-sol":{"draws":24,"losses":103,"wins":29},"gpt-5.6-terra":{"draws":42,"losses":39,"wins":69},"gpt-6-astra":{"draws":9,"losses":141,"wins":6},"gpt-6-luna":{"draws":38,"losses":56,"wins":62},"gpt-6-sol":{"draws":23,"losses":115,"wins":18},"gpt-6.1-sol":{"draws":15,"losses":133,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":35,"losses":11,"wins":56},"inception/mercury-3":{"draws":29,"losses":32,"wins":43},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":72},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":30,"losses":26,"wins":112},"meta/muse-glimmer-30b":{"draws":31,"losses":21,"wins":90},"meta/muse-spark-1.2":{"draws":36,"losses":57,"wins":59},"meta/muse-spark-1.3":{"draws":36,"losses":69,"wins":51},"meta/muse-spark-open":{"draws":31,"losses":76,"wins":43},"meta/muse-wonder":{"draws":37,"losses":76,"wins":43},"minimax/minimax-m3":{"draws":18,"losses":17,"wins":45},"minimax/minimax-m3.1-flash":{"draws":27,"losses":42,"wins":69},"mistralai/mistral-large-4-0":{"draws":33,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":19,"losses":18,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":16},"moonshotai/kimi-k3":{"draws":40,"losses":63,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":116,"wins":7},"nex-agi/nex-n2-pro":{"draws":19,"losses":13,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":9,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":17,"wins":69},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":19,"wins":32},"o3":{"draws":27,"losses":71,"wins":94},"openai/gpt-oss-120b":{"draws":31,"losses":24,"wins":87},"poolside/laguna-s-2.1":{"draws":36,"losses":31,"wins":93},"qwen/qwen3.7-max":{"draws":23,"losses":22,"wins":39},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":62,"wins":50},"qwen/qwen3.8-27b":{"draws":23,"losses":41,"wins":42},"qwen/qwen3.8-flash":{"draws":29,"losses":36,"wins":39},"qwen/qwen3.8-max":{"draws":50,"losses":50,"wins":56},"qwen/qwen3.8-max-0902":{"draws":35,"losses":72,"wins":49},"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":99,"losses":246,"wins":205},"stealth/space-bunny-alpha":{"draws":33,"losses":30,"wins":59},"stepfun/step-3.7-flash":{"draws":14,"losses":22,"wins":70},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":12,"wins":43},"tencent/hy4-preview":{"draws":33,"losses":68,"wins":49},"thinkingmachines/inkling":{"draws":54,"losses":45,"wins":117},"thinkingmachines/inkling-small":{"draws":40,"losses":36,"wins":80},"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":38,"losses":69,"wins":49},"x-ai/grok-4.6":{"draws":43,"losses":65,"wins":48},"x-ai/grok-4.7":{"draws":16,"losses":98,"wins":18},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":61,"losses":31,"wins":116},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":35,"wins":42},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":51,"wins":37},"z-ai/glm-5.2":{"draws":82,"losses":79,"wins":151},"z-ai/glm-5.3":{"draws":31,"losses":88,"wins":33},"z-ai/glm-5.3-flash":{"draws":30,"losses":76,"wins":50},"z-ai/glm-5.3-flashx":{"draws":24,"losses":78,"wins":54}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":6},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":18,"wins":8},"claude-opus-4-5":{"draws":21,"losses":23,"wins":24},"claude-opus-4-8":{"draws":11,"losses":22,"wins":5},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":1,"losses":41,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":9,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":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":13,"losses":18,"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":16,"losses":29,"wins":29},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":15},"gpt-5.4":{"draws":12,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":15},"gpt-5.5":{"draws":10,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":20,"wins":5},"gpt-6-sol":{"draws":9,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":15},"inception/mercury-3":{"draws":9,"losses":10,"wins":7},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":14},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":19,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":31,"wins":4},"meta/muse-spark-open":{"draws":10,"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":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":36,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":11,"wins":8},"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":8,"losses":15,"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":18,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"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":8,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":16},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":18,"wins":21},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10":{"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":20,"wins":10},"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":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":11},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":23},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":13},"claude-fable-5":{"draws":2,"losses":30,"wins":4},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":23,"wins":7},"claude-opus-4-5":{"draws":10,"losses":32,"wins":16},"claude-opus-4-8":{"draws":3,"losses":19,"wins":10},"claude-opus-5":{"draws":2,"losses":54,"wins":2},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":7,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":3,"losses":23,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":13,"losses":24,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":19,"wins":9},"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":23,"wins":28},"google/gemini-3.6-flash":{"draws":9,"losses":45,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":9},"gpt-4.1":{"draws":1,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":25,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":22,"wins":12},"gpt-5.5":{"draws":8,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":19,"wins":7},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":6,"losses":21,"wins":9},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":7,"wins":11},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":14,"wins":19},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":14},"meta/muse-spark-1.2":{"draws":0,"losses":27,"wins":7},"meta/muse-spark-1.3":{"draws":3,"losses":24,"wins":9},"meta/muse-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-k2.7-code":{"draws":0,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":20,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":34,"wins":0},"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":10,"losses":13,"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":14,"losses":12,"wins":12},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":24,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"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":88,"wins":19},"stealth/space-bunny-alpha":{"draws":4,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":7},"thinkingmachines/inkling":{"draws":11,"losses":19,"wins":20},"thinkingmachines/inkling-small":{"draws":10,"losses":11,"wins":15},"unbiased/pareto-26.10":{"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":6,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":18,"losses":37,"wins":17},"z-ai/glm-5.3":{"draws":3,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":6,"losses":24,"wins":6}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":4},"claude-fable-5":{"draws":0,"losses":1,"wins":5},"claude-fable-5-1":{"draws":0,"losses":4,"wins":2},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":0,"wins":10},"claude-opus-4-8":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":5,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":4},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":2,"wins":4},"elorian/glimpse":{"draws":0,"losses":2,"wins":2},"fireworks/ember-1":{"draws":0,"losses":2,"wins":4},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":4},"gemini-4-argon":{"draws":0,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":9},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":0,"losses":0,"wins":6},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":8},"gpt-5.5":{"draws":0,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":6},"gpt-6-astra":{"draws":0,"losses":2,"wins":4},"gpt-6-luna":{"draws":0,"losses":1,"wins":5},"gpt-6-sol":{"draws":1,"losses":2,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":4,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inception/mercury-3":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":5},"meta/muse-spark-open":{"draws":0,"losses":1,"wins":5},"meta/muse-wonder":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":10},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":1,"wins":5},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":0,"losses":1,"wins":15},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":6},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":11},"z-ai/glm-5.3":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.3-flash":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":6}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":6,"wins":25},"claude-fable-5":{"draws":3,"losses":28,"wins":11},"claude-fable-5-1":{"draws":1,"losses":44,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":22},"claude-opus-4-5":{"draws":13,"losses":14,"wins":41},"claude-opus-4-8":{"draws":7,"losses":13,"wins":18},"claude-opus-5":{"draws":2,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":35,"wins":7},"claude-sonnet-5":{"draws":11,"losses":12,"wins":19},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":40},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":19,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"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":15,"wins":19},"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":6,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":31},"google/gemini-3.5-flash-lite":{"draws":12,"losses":15,"wins":49},"google/gemini-3.6-flash":{"draws":9,"losses":38,"wins":35},"google/gemini-3.8-flash":{"draws":9,"losses":13,"wins":20},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":13,"wins":19},"gpt-5.4":{"draws":4,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":34},"gpt-5.5":{"draws":10,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":5,"losses":17,"wins":20},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":20},"gpt-6-astra":{"draws":2,"losses":38,"wins":2},"gpt-6-luna":{"draws":8,"losses":10,"wins":24},"gpt-6-sol":{"draws":3,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":18},"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":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":6,"losses":14,"wins":20},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":22},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":12},"meta/muse-wonder":{"draws":6,"losses":19,"wins":17},"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":1,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":12},"o3":{"draws":5,"losses":13,"wins":46},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":24},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":6,"losses":18,"wins":18},"qwen/qwen3.8-max-0902":{"draws":6,"losses":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":56,"wins":55},"stealth/space-bunny-alpha":{"draws":9,"losses":8,"wins":17},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":11},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":29},"unbiased/pareto-26.10":{"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":20,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":10,"losses":8,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3":{"draws":4,"losses":29,"wins":7},"z-ai/glm-5.3-flash":{"draws":2,"losses":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":10,"losses":19,"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":16,"losses":32,"wins":18},"google/gemini-3.6-flash":{"draws":14,"losses":54,"wins":4},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":7},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":23,"wins":2},"gpt-5.4":{"draws":9,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":20,"wins":10},"gpt-5.5":{"draws":13,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":21,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":22,"wins":3},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":10,"losses":24,"wins":2},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":8,"wins":10},"inception/mercury-3":{"draws":7,"losses":12,"wins":1},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":23,"wins":7},"meta/muse-glimmer-30b":{"draws":9,"losses":17,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":31,"wins":1},"meta/muse-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":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":6},"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":77,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":25,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":19,"wins":8},"thinkingmachines/inkling-small":{"draws":11,"losses":13,"wins":12},"unbiased/pareto-26.10":{"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":8,"losses":27,"wins":1},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":29,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":15,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":43,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":2,"losses":31,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":1}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":16,"wins":12},"claude-fable-5":{"draws":12,"losses":32,"wins":4},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":3},"claude-opus-4-5":{"draws":23,"losses":47,"wins":8},"claude-opus-4-8":{"draws":13,"losses":27,"wins":4},"claude-opus-5":{"draws":13,"losses":64,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":16,"losses":25,"wins":7},"claude-sonnet-5-5":{"draws":11,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":31,"losses":27,"wins":14},"deepseek/deepseek-v4-pro":{"draws":11,"losses":27,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":24,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":25,"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":15,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":6},"gemini-4-argon":{"draws":4,"losses":41,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":10,"wins":12},"google/gemini-3.5-flash":{"draws":15,"losses":32,"wins":13},"google/gemini-3.5-flash-lite":{"draws":30,"losses":39,"wins":15},"google/gemini-3.6-flash":{"draws":26,"losses":51,"wins":15},"google/gemini-3.8-flash":{"draws":13,"losses":27,"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":13,"losses":21,"wins":8},"gpt-5.4":{"draws":14,"losses":27,"wins":5},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":25,"wins":10},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":15,"losses":22,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":12,"losses":28,"wins":8},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"inception/mercury-3":{"draws":8,"losses":20,"wins":4},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":24,"wins":16},"meta/muse-glimmer-30b":{"draws":18,"losses":16,"wins":8},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":10},"meta/muse-spark-1.3":{"draws":8,"losses":35,"wins":5},"meta/muse-spark-open":{"draws":8,"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":12,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":42,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":17,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":12,"losses":44,"wins":10},"openai/gpt-oss-120b":{"draws":14,"losses":20,"wins":8},"poolside/laguna-s-2.1":{"draws":16,"losses":24,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":31,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":26,"wins":8},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"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":46,"losses":90,"wins":22},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":28,"wins":4},"thinkingmachines/inkling":{"draws":21,"losses":32,"wins":11},"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":13,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":26,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":35,"losses":44,"wins":17},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":33,"wins":5},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":7,"wins":5},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":10,"wins":2},"claude-opus-4-5":{"draws":1,"losses":18,"wins":1},"claude-opus-4-8":{"draws":0,"losses":12,"wins":0},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":1,"losses":10,"wins":1},"claude-sonnet-5-5":{"draws":0,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":11,"wins":3},"deepseek/deepseek-v4-pro":{"draws":1,"losses":9,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":10,"wins":1},"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},"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},"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":1,"wins":1},"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":7,"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":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":8,"losses":25,"wins":15},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":21},"claude-opus-4-5":{"draws":19,"losses":19,"wins":40},"claude-opus-4-8":{"draws":7,"losses":15,"wins":22},"claude-opus-5":{"draws":13,"losses":54,"wins":15},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":12,"losses":11,"wins":25},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":51},"deepseek/deepseek-v4-pro":{"draws":8,"losses":12,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":20,"wins":17},"elorian/glimpse":{"draws":5,"losses":9,"wins":12},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":27},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":18,"losses":14,"wins":52},"google/gemini-3.6-flash":{"draws":23,"losses":28,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":15,"wins":25},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":18},"gpt-4.1":{"draws":5,"losses":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":14,"losses":17,"wins":15},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":27},"gpt-5.5":{"draws":13,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":15,"losses":8,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":15,"losses":7,"wins":24},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":11,"losses":14,"wins":23},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"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":2},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":36},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":10,"wins":25},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":21},"meta/muse-spark-open":{"draws":8,"losses":16,"wins":22},"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":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":30,"wins":7},"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":7,"losses":3,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":7,"losses":17,"wins":42},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"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":15,"wins":25},"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":31,"losses":46,"wins":81},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":22},"thinkingmachines/inkling":{"draws":19,"losses":5,"wins":40},"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":8,"wins":16},"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":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":12,"wins":14},"z-ai/glm-5.2":{"draws":25,"losses":15,"wins":56},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":15,"wins":25},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":2,"wins":37},"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":12,"wins":51},"claude-opus-4-8":{"draws":10,"losses":10,"wins":24},"claude-opus-5":{"draws":11,"losses":50,"wins":21},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":7,"losses":15,"wins":26},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":57},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":4,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":12,"wins":23},"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":18,"wins":56},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":22},"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":3,"wins":30},"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":1,"wins":43},"gpt-5.5":{"draws":8,"losses":13,"wins":23},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":14,"wins":24},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":7,"losses":2,"wins":39},"gpt-6-sol":{"draws":8,"losses":25,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":26},"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":0,"losses":0,"wins":2},"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":8,"losses":6,"wins":32},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":26},"meta/muse-spark-open":{"draws":9,"losses":7,"wins":30},"meta/muse-wonder":{"draws":10,"losses":16,"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":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":32,"wins":9},"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":10,"losses":0,"wins":32},"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":9,"wins":29},"qwen/qwen3.8-27b":{"draws":7,"losses":3,"wins":24},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":19},"qwen/qwen3.8-max":{"draws":12,"losses":6,"wins":30},"qwen/qwen3.8-max-0902":{"draws":11,"losses":8,"wins":29},"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":27,"wins":101},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":8,"losses":7,"wins":31},"thinkingmachines/inkling":{"draws":19,"losses":3,"wins":42},"thinkingmachines/inkling-small":{"draws":9,"losses":2,"wins":37},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":9,"wins":25},"x-ai/grok-4.6":{"draws":12,"losses":7,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":17},"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":1,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":8,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":16},"z-ai/glm-5.2":{"draws":20,"losses":9,"wins":67},"z-ai/glm-5.3":{"draws":8,"losses":20,"wins":18},"z-ai/glm-5.3-flash":{"draws":12,"losses":11,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":36},"claude-fable-5":{"draws":1,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":31,"wins":15},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":36},"claude-opus-4-5":{"draws":2,"losses":2,"wins":64},"claude-opus-4-8":{"draws":2,"losses":5,"wins":31},"claude-opus-5":{"draws":9,"losses":26,"wins":45},"claude-opus-5-5":{"draws":6,"losses":28,"wins":12},"claude-sonnet-5":{"draws":3,"losses":4,"wins":35},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":29},"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":5,"losses":5,"wins":32},"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":2,"losses":6,"wins":44},"google/gemini-3.5-flash-lite":{"draws":6,"losses":8,"wins":58},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":70},"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":5,"losses":1,"wins":34},"gpt-5.5":{"draws":0,"losses":8,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":30},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":35},"gpt-6-astra":{"draws":5,"losses":28,"wins":9},"gpt-6-luna":{"draws":3,"losses":1,"wins":38},"gpt-6-sol":{"draws":3,"losses":15,"wins":24},"gpt-6.1-sol":{"draws":2,"losses":26,"wins":14},"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":0,"losses":0,"wins":2},"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":1,"losses":5,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":33},"meta/muse-spark-open":{"draws":2,"losses":4,"wins":34},"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":2,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":35},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":17,"wins":18},"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":1,"losses":0,"wins":35},"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":13,"losses":14,"wins":115},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":30},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":1,"losses":8,"wins":31},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":51},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":39},"unbiased/pareto-26.10":{"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":10,"wins":13},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":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":16,"losses":18,"wins":10},"claude-fable-5":{"draws":10,"losses":32,"wins":6},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":39,"wins":12},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":15,"losses":64,"wins":3},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":26,"wins":19},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"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":17,"losses":19,"wins":12},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":33,"wins":8},"google/gemini-3.5-flash-lite":{"draws":33,"losses":27,"wins":24},"google/gemini-3.6-flash":{"draws":31,"losses":56,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":18,"wins":9},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":24,"wins":14},"gpt-5.5":{"draws":23,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":24,"wins":5},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":8},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":10,"losses":28,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":10,"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":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":37,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":9,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":13,"losses":38,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":21,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":15,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":9},"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":38,"losses":101,"wins":19},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":26},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":14},"unbiased/pareto-26.10":{"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":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":33,"losses":19,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":42,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":35,"wins":13},"claude-fable-5":{"draws":18,"losses":68,"wins":4},"claude-fable-5-1":{"draws":7,"losses":90,"wins":3},"claude-haiku-5-5":{"draws":28,"losses":52,"wins":10},"claude-opus-4-5":{"draws":57,"losses":73,"wins":20},"claude-opus-4-8":{"draws":33,"losses":51,"wins":6},"claude-opus-5":{"draws":24,"losses":123,"wins":15},"claude-opus-5-5":{"draws":5,"losses":89,"wins":4},"claude-sonnet-5":{"draws":37,"losses":38,"wins":15},"claude-sonnet-5-5":{"draws":23,"losses":55,"wins":12},"cohere/north-mini-code":{"draws":9,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":53,"losses":38,"wins":43},"deepseek/deepseek-v4-pro":{"draws":30,"losses":40,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":40,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":49,"wins":10},"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":35,"losses":37,"wins":18},"gemini-4-argon":{"draws":6,"losses":83,"wins":1},"google/gemini-3.1-flash-lite":{"draws":23,"losses":13,"wins":28},"google/gemini-3.5-flash":{"draws":36,"losses":59,"wins":19},"google/gemini-3.5-flash-lite":{"draws":55,"losses":47,"wins":54},"google/gemini-3.6-flash":{"draws":59,"losses":100,"wins":11},"google/gemini-3.8-flash":{"draws":25,"losses":58,"wins":7},"google/gemma-4-31b-it":{"draws":28,"losses":15,"wins":13},"gpt-4.1":{"draws":14,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":25,"losses":35,"wins":16},"gpt-5.4":{"draws":26,"losses":48,"wins":10},"gpt-5.4-mini":{"draws":25,"losses":23,"wins":12},"gpt-5.4-nano":{"draws":24,"losses":38,"wins":30},"gpt-5.5":{"draws":32,"losses":45,"wins":5},"gpt-5.6-luna":{"draws":39,"losses":33,"wins":18},"gpt-5.6-sol":{"draws":17,"losses":72,"wins":1},"gpt-5.6-terra":{"draws":32,"losses":48,"wins":6},"gpt-6-astra":{"draws":4,"losses":85,"wins":1},"gpt-6-luna":{"draws":36,"losses":41,"wins":13},"gpt-6-sol":{"draws":16,"losses":69,"wins":5},"gpt-6.1-sol":{"draws":8,"losses":80,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":36,"losses":10,"wins":24},"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":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":31,"wins":32},"meta/muse-glimmer-30b":{"draws":31,"losses":27,"wins":22},"meta/muse-spark-1.2":{"draws":29,"losses":51,"wins":8},"meta/muse-spark-1.3":{"draws":26,"losses":56,"wins":8},"meta/muse-spark-open":{"draws":25,"losses":54,"wins":5},"meta/muse-wonder":{"draws":26,"losses":60,"wins":4},"minimax/minimax-m3":{"draws":21,"losses":16,"wins":15},"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":27,"losses":8,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":31,"losses":43,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":78,"wins":1},"nex-agi/nex-n2-pro":{"draws":11,"losses":14,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":32,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":18,"wins":10},"o3":{"draws":22,"losses":79,"wins":17},"openai/gpt-oss-120b":{"draws":31,"losses":24,"wins":23},"poolside/laguna-s-2.1":{"draws":23,"losses":30,"wins":27},"qwen/qwen3.7-max":{"draws":22,"losses":25,"wins":7},"qwen/qwen3.7-plus":{"draws":21,"losses":17,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":44,"wins":7},"qwen/qwen3.8-27b":{"draws":21,"losses":34,"wins":7},"qwen/qwen3.8-flash":{"draws":24,"losses":22,"wins":14},"qwen/qwen3.8-max":{"draws":36,"losses":44,"wins":10},"qwen/qwen3.8-max-0902":{"draws":31,"losses":46,"wins":13},"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":75,"losses":144,"wins":35},"stealth/space-bunny-alpha":{"draws":32,"losses":29,"wins":13},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":19},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":13},"tencent/hy4-preview":{"draws":27,"losses":47,"wins":10},"thinkingmachines/inkling":{"draws":43,"losses":31,"wins":42},"thinkingmachines/inkling-small":{"draws":37,"losses":29,"wins":24},"unbiased/pareto-26.10":{"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":26,"losses":57,"wins":7},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":6},"x-ai/grok-build-0.1":{"draws":15,"losses":8,"wins":7},"xiaomi/mimo-v2.5":{"draws":58,"losses":36,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":20,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":34,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":38,"wins":4},"z-ai/glm-5.2":{"draws":68,"losses":78,"wins":34},"z-ai/glm-5.3":{"draws":24,"losses":61,"wins":1},"z-ai/glm-5.3-flash":{"draws":27,"losses":52,"wins":11},"z-ai/glm-5.3-flashx":{"draws":35,"losses":50,"wins":5}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":16},"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":10},"claude-opus-4-5":{"draws":14,"losses":24,"wins":22},"claude-opus-4-8":{"draws":7,"losses":20,"wins":9},"claude-opus-5":{"draws":8,"losses":46,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":3,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":12,"wins":27},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":12,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":23,"wins":10},"elorian/glimpse":{"draws":3,"losses":9,"wins":8},"fireworks/ember-1":{"draws":10,"losses":14,"wins":12},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":15},"gemini-4-argon":{"draws":0,"losses":33,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":20,"losses":16,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":37,"wins":17},"google/gemini-3.8-flash":{"draws":6,"losses":23,"wins":7},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":12},"gpt-4.1":{"draws":3,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":9},"gpt-5.4":{"draws":5,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":13,"wins":22},"gpt-5.5":{"draws":8,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":8},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":8,"losses":16,"wins":12},"gpt-6-sol":{"draws":4,"losses":29,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":4,"wins":15},"inception/mercury-3":{"draws":3,"losses":13,"wins":6},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":14},"meta/muse-spark-1.2":{"draws":2,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":5,"losses":20,"wins":11},"meta/muse-spark-open":{"draws":7,"losses":22,"wins":7},"meta/muse-wonder":{"draws":3,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":10},"minimax/minimax-m3.1-flash":{"draws":5,"losses":12,"wins":15},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":30,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":8,"wins":7},"o3":{"draws":7,"losses":22,"wins":31},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":16},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":17,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":14},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":12},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":14,"wins":12},"stealth/ox-alpha":{"draws":15,"losses":52,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":10,"wins":30},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":16},"x-ai/grok-4.6":{"draws":7,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":0,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":20,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":23,"wins":10},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":11}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":32},"claude-fable-5":{"draws":5,"losses":25,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":9,"losses":20,"wins":17},"claude-opus-4-5":{"draws":11,"losses":18,"wins":49},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":8,"losses":63,"wins":11},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":6,"losses":10,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":23,"wins":23},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":50},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":22,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":26,"wins":16},"elorian/glimpse":{"draws":2,"losses":9,"wins":15},"fireworks/ember-1":{"draws":3,"losses":18,"wins":27},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"gemini-4-argon":{"draws":1,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":18,"wins":33},"google/gemini-3.5-flash-lite":{"draws":14,"losses":10,"wins":60},"google/gemini-3.6-flash":{"draws":8,"losses":35,"wins":49},"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":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":9,"wins":28},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":29},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":11,"losses":11,"wins":26},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":7,"losses":16,"wins":23},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":8,"losses":13,"wins":27},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":25},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":9,"wins":32},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":21,"wins":19},"meta/muse-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":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":34,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":6,"wins":13},"o3":{"draws":9,"losses":15,"wins":42},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":16,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":13},"qwen/qwen3.8-max":{"draws":6,"losses":19,"wins":23},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":25},"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":22,"losses":61,"wins":75},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":13,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":13,"losses":1,"wins":34},"unbiased/pareto-26.10":{"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":8,"losses":19,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":12,"losses":20,"wins":64},"z-ai/glm-5.3":{"draws":7,"losses":28,"wins":11},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":24},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":38},"claude-fable-5":{"draws":2,"losses":15,"wins":31},"claude-fable-5-1":{"draws":9,"losses":38,"wins":7},"claude-haiku-5-5":{"draws":4,"losses":11,"wins":31},"claude-opus-4-5":{"draws":11,"losses":8,"wins":59},"claude-opus-4-8":{"draws":2,"losses":13,"wins":29},"claude-opus-5":{"draws":16,"losses":39,"wins":27},"claude-opus-5-5":{"draws":4,"losses":39,"wins":9},"claude-sonnet-5":{"draws":0,"losses":9,"wins":39},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":9,"wins":60},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":26},"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":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":72},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":64},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":33},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":26},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":8,"wins":32},"gpt-5.4":{"draws":5,"losses":14,"wins":27},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":25},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":40},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":40},"gpt-5.6-sol":{"draws":9,"losses":14,"wins":25},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":30},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":9,"losses":10,"wins":29},"gpt-6-sol":{"draws":8,"losses":21,"wins":19},"gpt-6.1-sol":{"draws":8,"losses":27,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"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":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":43},"meta/muse-glimmer-30b":{"draws":0,"losses":7,"wins":35},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":35},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":3,"losses":15,"wins":28},"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":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":19,"wins":17},"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":5,"losses":5,"wins":32},"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":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":30},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":43},"unbiased/pareto-26.10":{"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":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":9,"losses":11,"wins":28},"x-ai/grok-4.7":{"draws":1,"losses":25,"wins":16},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":7,"losses":9,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":13},"z-ai/glm-5.2":{"draws":9,"losses":15,"wins":72},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":26},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":30}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":16,"wins":44},"claude-fable-5":{"draws":21,"losses":60,"wins":15},"claude-fable-5-1":{"draws":10,"losses":95,"wins":3},"claude-haiku-5-5":{"draws":23,"losses":40,"wins":29},"claude-opus-4-5":{"draws":55,"losses":45,"wins":56},"claude-opus-4-8":{"draws":27,"losses":37,"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":52,"wins":25},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":54,"losses":30,"wins":60},"deepseek/deepseek-v4-pro":{"draws":33,"losses":29,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":35,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":22,"losses":54,"wins":20},"elorian/glimpse":{"draws":13,"losses":23,"wins":16},"fireworks/ember-1":{"draws":30,"losses":40,"wins":26},"gemini-3.1-pro-preview":{"draws":32,"losses":29,"wins":35},"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":39,"losses":35,"wins":46},"google/gemini-3.5-flash-lite":{"draws":63,"losses":32,"wins":73},"google/gemini-3.6-flash":{"draws":43,"losses":78,"wins":63},"google/gemini-3.8-flash":{"draws":23,"losses":49,"wins":24},"google/gemma-4-31b-it":{"draws":25,"losses":8,"wins":23},"gpt-4.1":{"draws":13,"losses":5,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":31,"losses":25,"wins":28},"gpt-5.4":{"draws":27,"losses":39,"wins":26},"gpt-5.4-mini":{"draws":31,"losses":9,"wins":24},"gpt-5.4-nano":{"draws":29,"losses":26,"wins":41},"gpt-5.5":{"draws":37,"losses":37,"wins":14},"gpt-5.6-luna":{"draws":43,"losses":19,"wins":34},"gpt-5.6-sol":{"draws":12,"losses":60,"wins":24},"gpt-5.6-terra":{"draws":40,"losses":28,"wins":24},"gpt-6-astra":{"draws":8,"losses":82,"wins":6},"gpt-6-luna":{"draws":31,"losses":35,"wins":30},"gpt-6-sol":{"draws":12,"losses":72,"wins":12},"gpt-6.1-sol":{"draws":15,"losses":78,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":32,"losses":3,"wins":33},"inception/mercury-3":{"draws":22,"losses":24,"wins":18},"inclusionai/ling-3.0-flash":{"draws":37,"losses":5,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":23,"wins":51},"meta/muse-glimmer-30b":{"draws":38,"losses":14,"wins":32},"meta/muse-spark-1.2":{"draws":24,"losses":45,"wins":23},"meta/muse-spark-1.3":{"draws":23,"losses":46,"wins":27},"meta/muse-spark-open":{"draws":22,"losses":46,"wins":24},"meta/muse-wonder":{"draws":26,"losses":52,"wins":18},"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":24,"losses":6,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":12},"moonshotai/kimi-k3":{"draws":35,"losses":30,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":73,"wins":8},"nex-agi/nex-n2-pro":{"draws":20,"losses":2,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":17,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":13,"wins":16},"o3":{"draws":24,"losses":50,"wins":58},"openai/gpt-oss-120b":{"draws":39,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":44,"losses":15,"wins":33},"qwen/qwen3.7-max":{"draws":21,"losses":11,"wins":24},"qwen/qwen3.7-plus":{"draws":16,"losses":9,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":39,"wins":26},"qwen/qwen3.8-27b":{"draws":22,"losses":19,"wins":27},"qwen/qwen3.8-flash":{"draws":17,"losses":28,"wins":19},"qwen/qwen3.8-max":{"draws":28,"losses":38,"wins":30},"qwen/qwen3.8-max-0902":{"draws":32,"losses":42,"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":82,"losses":144,"wins":90},"stealth/space-bunny-alpha":{"draws":31,"losses":19,"wins":26},"stepfun/step-3.7-flash":{"draws":18,"losses":7,"wins":43},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":21},"thinkingmachines/inkling":{"draws":40,"losses":28,"wins":60},"thinkingmachines/inkling-small":{"draws":35,"losses":12,"wins":49},"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":27,"losses":50,"wins":19},"x-ai/grok-4.7":{"draws":9,"losses":60,"wins":15},"x-ai/grok-build-0.1":{"draws":16,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":57,"losses":18,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":10,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":31,"wins":15},"z-ai/glm-5.2":{"draws":66,"losses":38,"wins":56},"z-ai/glm-5.3":{"draws":20,"losses":55,"wins":17},"z-ai/glm-5.3-flash":{"draws":26,"losses":42,"wins":28},"z-ai/glm-5.3-flashx":{"draws":31,"losses":40,"wins":25}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":5,"wins":29},"claude-fable-5":{"draws":9,"losses":17,"wins":22},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":28},"claude-opus-4-5":{"draws":15,"losses":5,"wins":58},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":13,"losses":53,"wins":16},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":7,"losses":14,"wins":27},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":56},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":5,"wins":35},"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":8,"losses":9,"wins":31},"gemini-4-argon":{"draws":5,"losses":32,"wins":11},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":43},"google/gemini-3.5-flash-lite":{"draws":11,"losses":3,"wins":70},"google/gemini-3.6-flash":{"draws":19,"losses":19,"wins":54},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":5,"losses":8,"wins":29},"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":13,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":9,"losses":22,"wins":17},"gpt-5.6-terra":{"draws":14,"losses":4,"wins":28},"gpt-6-astra":{"draws":7,"losses":39,"wins":2},"gpt-6-luna":{"draws":10,"losses":7,"wins":31},"gpt-6-sol":{"draws":6,"losses":23,"wins":19},"gpt-6.1-sol":{"draws":11,"losses":29,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":7,"losses":7,"wins":18},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":34},"meta/muse-spark-1.2":{"draws":6,"losses":13,"wins":27},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":26},"meta/muse-spark-open":{"draws":5,"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":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":4,"losses":17,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":28,"wins":15},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"o3":{"draws":7,"losses":8,"wins":51},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":32},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":29},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":18},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":30},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":32},"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":21,"losses":38,"wins":99},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":4,"losses":12,"wins":30},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":41},"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":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":11,"losses":14,"wins":23},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":15,"losses":1,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":17,"losses":14,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":8,"wins":13},"z-ai/glm-5.3-flash":{"draws":12,"losses":9,"wins":27},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":6,"wins":27},"claude-fable-5":{"draws":9,"losses":22,"wins":17},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":20,"losses":12,"wins":46},"claude-opus-4-8":{"draws":8,"losses":12,"wins":24},"claude-opus-5":{"draws":9,"losses":55,"wins":18},"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":18,"losses":6,"wins":48},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":12,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":19},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":8,"losses":13,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":10,"wins":26},"gemini-4-argon":{"draws":6,"losses":35,"wins":7},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":36},"google/gemini-3.5-flash-lite":{"draws":17,"losses":5,"wins":62},"google/gemini-3.6-flash":{"draws":16,"losses":21,"wins":55},"google/gemini-3.8-flash":{"draws":10,"losses":21,"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":8,"losses":9,"wins":25},"gpt-5.4":{"draws":8,"losses":20,"wins":18},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":33},"gpt-5.5":{"draws":9,"losses":14,"wins":21},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":20},"gpt-5.6-terra":{"draws":13,"losses":11,"wins":22},"gpt-6-astra":{"draws":5,"losses":38,"wins":5},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":24},"inception/mercury-3":{"draws":4,"losses":10,"wins":18},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":6,"losses":18,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":14,"wins":23},"meta/muse-spark-open":{"draws":9,"losses":13,"wins":24},"meta/muse-wonder":{"draws":7,"losses":23,"wins":18},"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":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":15,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":31,"wins":11},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":11},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":14,"wins":21},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":18},"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":28,"losses":47,"wins":83},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":15,"wins":25},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":11,"losses":3,"wins":34},"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":11,"losses":16,"wins":21},"x-ai/grok-4.7":{"draws":7,"losses":22,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":3,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":25,"losses":10,"wins":61},"z-ai/glm-5.3":{"draws":10,"losses":21,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":23}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"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":10,"losses":15,"wins":23},"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":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"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":5,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":19,"wins":26},"google/gemini-3.5-flash-lite":{"draws":15,"losses":26,"wins":43},"google/gemini-3.6-flash":{"draws":17,"losses":40,"wins":35},"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":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":17,"wins":14},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":12,"losses":17,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":12,"losses":17,"wins":19},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":21},"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":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":10,"losses":22,"wins":14},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"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":5,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":4,"losses":31,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"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":32,"losses":64,"wins":62},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":12},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":28},"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":14,"losses":22,"wins":12},"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":26,"losses":10,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":43},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":19,"wins":19},"z-ai/glm-5.3-flashx":{"draws":12,"losses":15,"wins":5}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":5},"claude-fable-5":{"draws":5,"losses":34,"wins":3},"claude-fable-5-1":{"draws":0,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":30,"wins":3},"claude-opus-4-5":{"draws":20,"losses":38,"wins":10},"claude-opus-4-8":{"draws":7,"losses":31,"wins":0},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":10,"losses":28,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":21,"losses":25,"wins":16},"deepseek/deepseek-v4-pro":{"draws":11,"losses":26,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":33,"wins":5},"elorian/glimpse":{"draws":4,"losses":14,"wins":6},"fireworks/ember-1":{"draws":10,"losses":26,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":24,"wins":7},"gemini-4-argon":{"draws":0,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":10,"losses":33,"wins":11},"google/gemini-3.5-flash-lite":{"draws":22,"losses":35,"wins":19},"google/gemini-3.6-flash":{"draws":19,"losses":54,"wins":9},"google/gemini-3.8-flash":{"draws":9,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":11,"losses":18,"wins":9},"gpt-5.4":{"draws":10,"losses":26,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":15},"gpt-5.5":{"draws":14,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":20,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":26,"wins":4},"gpt-6-astra":{"draws":1,"losses":40,"wins":1},"gpt-6-luna":{"draws":13,"losses":22,"wins":7},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":11},"inception/mercury-3":{"draws":3,"losses":19,"wins":4},"inclusionai/ling-3.0-flash":{"draws":14,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":18,"wins":14},"meta/muse-glimmer-30b":{"draws":16,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":30,"wins":4},"meta/muse-wonder":{"draws":5,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":9},"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":11,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":14,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":3},"o3":{"draws":15,"losses":38,"wins":11},"openai/gpt-oss-120b":{"draws":11,"losses":16,"wins":9},"poolside/laguna-s-2.1":{"draws":13,"losses":18,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":11,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":28,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":6},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":2},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":4},"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":26,"losses":97,"wins":19},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":6},"stepfun/step-3.7-flash":{"draws":10,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":3},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":18},"thinkingmachines/inkling-small":{"draws":16,"losses":11,"wins":15},"unbiased/pareto-26.10":{"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":11,"losses":27,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":23,"losses":24,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":37,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":29,"wins":6}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":5,"losses":18,"wins":9},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":7,"losses":15,"wins":24},"claude-opus-4-5":{"draws":19,"losses":16,"wins":43},"claude-opus-4-8":{"draws":12,"losses":15,"wins":17},"claude-opus-5":{"draws":16,"losses":54,"wins":12},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":12,"losses":11,"wins":25},"claude-sonnet-5-5":{"draws":14,"losses":22,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":16,"losses":7,"wins":49},"deepseek/deepseek-v4-pro":{"draws":14,"losses":10,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":16},"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":10,"losses":21,"wins":17},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":14,"losses":13,"wins":19},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":10,"losses":3,"wins":35},"gpt-5.5":{"draws":16,"losses":10,"wins":18},"gpt-5.6-luna":{"draws":15,"losses":6,"wins":27},"gpt-5.6-sol":{"draws":8,"losses":24,"wins":16},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":4,"losses":36,"wins":8},"gpt-6-luna":{"draws":12,"losses":9,"wins":27},"gpt-6-sol":{"draws":8,"losses":31,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":13,"losses":4,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":35},"meta/muse-glimmer-30b":{"draws":11,"losses":1,"wins":30},"meta/muse-spark-1.2":{"draws":9,"losses":15,"wins":22},"meta/muse-spark-1.3":{"draws":8,"losses":19,"wins":21},"meta/muse-spark-open":{"draws":13,"losses":10,"wins":23},"meta/muse-wonder":{"draws":11,"losses":22,"wins":15},"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":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":15,"losses":9,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":5},"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":8,"losses":5,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":0,"wins":14},"o3":{"draws":7,"losses":10,"wins":49},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":13,"losses":8,"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":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":23},"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":35,"losses":51,"wins":72},"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":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":4,"wins":10},"tencent/hy4-preview":{"draws":7,"losses":17,"wins":22},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":31},"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":20,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":1,"losses":28,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":9,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":28,"losses":18,"wins":50},"z-ai/glm-5.3":{"draws":8,"losses":28,"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":3,"losses":2,"wins":39},"claude-fable-5":{"draws":5,"losses":5,"wins":38},"claude-fable-5-1":{"draws":2,"losses":26,"wins":10},"claude-haiku-5-5":{"draws":2,"losses":6,"wins":38},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":4,"losses":2,"wins":38},"claude-opus-5":{"draws":13,"losses":23,"wins":46},"claude-opus-5-5":{"draws":4,"losses":27,"wins":21},"claude-sonnet-5":{"draws":5,"losses":2,"wins":41},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":31},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":70},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":42},"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":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":3,"losses":2,"wins":43},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":45},"gemini-4-argon":{"draws":7,"losses":19,"wins":22},"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":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":3,"wins":80},"google/gemini-3.8-flash":{"draws":3,"losses":4,"wins":41},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":1,"wins":39},"gpt-5.4":{"draws":3,"losses":8,"wins":35},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":2,"losses":6,"wins":36},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":37},"gpt-5.6-terra":{"draws":5,"losses":0,"wins":41},"gpt-6-astra":{"draws":4,"losses":31,"wins":13},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":7,"losses":14,"wins":27},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":38},"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":0,"losses":4,"wins":42},"meta/muse-wonder":{"draws":6,"losses":10,"wins":32},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":39},"mistralai/mistral-large-4-0":{"draws":1,"losses":1,"wins":28},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":6,"losses":3,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":19,"wins":24},"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":2,"losses":0,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":18},"o3":{"draws":2,"losses":3,"wins":61},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":39},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":44},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":1,"wins":40},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":29},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":28},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":43},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"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":14,"losses":11,"wins":133},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":5,"wins":37},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":60},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":5,"losses":3,"wins":40},"x-ai/grok-4.6":{"draws":2,"losses":7,"wins":39},"x-ai/grok-4.7":{"draws":3,"losses":16,"wins":23},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":22},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":85},"z-ai/glm-5.3":{"draws":4,"losses":10,"wins":32},"z-ai/glm-5.3-flash":{"draws":6,"losses":2,"wins":40},"z-ai/glm-5.3-flashx":{"draws":6,"losses":5,"wins":37}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":18,"wins":7},"claude-opus-4-5":{"draws":30,"losses":32,"wins":16},"claude-opus-4-8":{"draws":15,"losses":27,"wins":2},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":22,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":30,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"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":20,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":30,"losses":49,"wins":13},"google/gemini-3.8-flash":{"draws":13,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":14,"wins":11},"gpt-5.4":{"draws":18,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":13},"gpt-5.5":{"draws":22,"losses":15,"wins":7},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":18,"wins":11},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":14},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":10,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":23,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":12,"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":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":19,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":1},"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":20,"losses":11,"wins":11},"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":21,"losses":17,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-max-0902":{"draws":19,"losses":23,"wins":6},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":29,"wins":4},"thinkingmachines/inkling":{"draws":28,"losses":14,"wins":22},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10":{"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":26,"wins":6},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":30,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":21,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":34,"wins":27},"z-ai/glm-5.3":{"draws":10,"losses":34,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":17,"wins":13},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":15,"losses":19,"wins":12},"claude-opus-4-5":{"draws":24,"losses":18,"wins":20},"claude-opus-4-8":{"draws":11,"losses":23,"wins":10},"claude-opus-5":{"draws":16,"losses":59,"wins":7},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":17,"losses":21,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":15},"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":12,"losses":19,"wins":17},"gemini-4-argon":{"draws":3,"losses":43,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":19},"google/gemini-3.5-flash-lite":{"draws":28,"losses":20,"wins":36},"google/gemini-3.6-flash":{"draws":29,"losses":41,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":22,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":13,"wins":15},"gpt-5.4":{"draws":12,"losses":21,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":22,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":15,"wins":9},"gpt-6-astra":{"draws":2,"losses":40,"wins":6},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":5,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":15,"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":2,"wins":8},"moonshotai/kimi-k3":{"draws":19,"losses":15,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":34,"wins":2},"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":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":7,"wins":6},"o3":{"draws":10,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":19},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"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":46,"losses":76,"wins":36},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":24,"losses":11,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":25},"unbiased/pareto-26.10":{"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":19,"wins":16},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":31,"wins":7}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":19},"claude-fable-5":{"draws":7,"losses":29,"wins":6},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":15},"claude-opus-4-5":{"draws":24,"losses":19,"wins":27},"claude-opus-4-8":{"draws":6,"losses":16,"wins":6},"claude-opus-5":{"draws":13,"losses":49,"wins":8},"claude-opus-5-5":{"draws":1,"losses":40,"wins":5},"claude-sonnet-5":{"draws":12,"losses":14,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":12},"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":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":10,"losses":23,"wins":21},"google/gemini-3.5-flash-lite":{"draws":24,"losses":10,"wins":40},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":22},"google/gemini-3.8-flash":{"draws":8,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":13},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":14,"wins":12},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":23},"gpt-5.5":{"draws":11,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":13},"gpt-6-astra":{"draws":2,"losses":36,"wins":4},"gpt-6-luna":{"draws":9,"losses":16,"wins":17},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":16},"inception/mercury-3":{"draws":9,"losses":6,"wins":13},"inclusionai/ling-3.0-flash":{"draws":11,"losses":0,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":9,"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":9,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"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":7,"wins":25},"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":14,"losses":7,"wins":17},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":16,"wins":12},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":15},"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":19,"losses":64,"wins":35},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":13,"losses":7,"wins":34},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":22},"unbiased/pareto-26.10":{"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":12,"losses":23,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":23,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":12,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":23,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":22,"wins":14}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":8,"wins":57},"claude-fable-5":{"draws":23,"losses":23,"wins":38},"claude-fable-5-1":{"draws":11,"losses":63,"wins":20},"claude-haiku-5-5":{"draws":19,"losses":14,"wins":47},"claude-opus-4-5":{"draws":35,"losses":21,"wins":80},"claude-opus-4-8":{"draws":18,"losses":11,"wins":47},"claude-opus-5":{"draws":22,"losses":68,"wins":36},"claude-opus-5-5":{"draws":13,"losses":64,"wins":15},"claude-sonnet-5":{"draws":17,"losses":18,"wins":49},"claude-sonnet-5-5":{"draws":15,"losses":33,"wins":36},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":23,"losses":12,"wins":89},"deepseek/deepseek-v4-pro":{"draws":14,"losses":15,"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":14,"wins":55},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":55},"gemini-4-argon":{"draws":13,"losses":45,"wins":26},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":42},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":71},"google/gemini-3.5-flash-lite":{"draws":25,"losses":16,"wins":105},"google/gemini-3.6-flash":{"draws":36,"losses":41,"wins":83},"google/gemini-3.8-flash":{"draws":16,"losses":24,"wins":44},"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":12,"losses":6,"wins":64},"gpt-5.5":{"draws":17,"losses":15,"wins":46},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":60},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":49},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":58},"gpt-6-astra":{"draws":11,"losses":58,"wins":15},"gpt-6-luna":{"draws":20,"losses":9,"wins":55},"gpt-6-sol":{"draws":14,"losses":37,"wins":33},"gpt-6.1-sol":{"draws":13,"losses":53,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":42},"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":0,"losses":0,"wins":4},"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":16,"losses":16,"wins":50},"meta/muse-spark-1.3":{"draws":16,"losses":23,"wins":45},"meta/muse-spark-open":{"draws":11,"losses":21,"wins":48},"meta/muse-wonder":{"draws":15,"losses":27,"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":3,"losses":2,"wins":17},"moonshotai/kimi-k3":{"draws":19,"losses":22,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":51,"wins":21},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":3,"wins":25},"o3":{"draws":15,"losses":5,"wins":88},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":52},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":62},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":50},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":34},"qwen/qwen3.8-max":{"draws":21,"losses":19,"wins":44},"qwen/qwen3.8-max-0902":{"draws":17,"losses":19,"wins":48},"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":69,"losses":68,"wins":145},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":44},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":33},"tencent/hy4-preview":{"draws":15,"losses":15,"wins":50},"thinkingmachines/inkling":{"draws":22,"losses":18,"wins":74},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":63},"unbiased/pareto-26.10":{"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":16,"losses":16,"wins":52},"x-ai/grok-4.6":{"draws":16,"losses":23,"wins":45},"x-ai/grok-4.7":{"draws":8,"losses":38,"wins":28},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":19},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":16,"wins":27},"z-ai/glm-5.2":{"draws":41,"losses":13,"wins":114},"z-ai/glm-5.3":{"draws":15,"losses":32,"wins":33},"z-ai/glm-5.3-flash":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3-flashx":{"draws":17,"losses":24,"wins":43}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":7,"losses":15,"wins":32},"claude-fable-5-1":{"draws":7,"losses":38,"wins":15},"claude-haiku-5-5":{"draws":12,"losses":7,"wins":33},"claude-opus-4-5":{"draws":16,"losses":15,"wins":57},"claude-opus-4-8":{"draws":9,"losses":14,"wins":27},"claude-opus-5":{"draws":17,"losses":50,"wins":27},"claude-opus-5-5":{"draws":1,"losses":33,"wins":10},"claude-sonnet-5":{"draws":11,"losses":10,"wins":33},"claude-sonnet-5-5":{"draws":7,"losses":16,"wins":31},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":66},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":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":11,"wins":35},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":41},"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":9,"losses":7,"wins":52},"google/gemini-3.5-flash-lite":{"draws":17,"losses":1,"wins":76},"google/gemini-3.6-flash":{"draws":19,"losses":9,"wins":74},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":27},"gpt-4.1":{"draws":5,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":4,"wins":35},"gpt-5.4":{"draws":9,"losses":4,"wins":39},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":48},"gpt-5.5":{"draws":11,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":10,"losses":12,"wins":32},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":42},"gpt-6-astra":{"draws":8,"losses":34,"wins":12},"gpt-6-luna":{"draws":13,"losses":1,"wins":40},"gpt-6-sol":{"draws":7,"losses":26,"wins":21},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":30},"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":0,"losses":0,"wins":4},"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":10,"losses":5,"wins":37},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":36},"meta/muse-spark-open":{"draws":10,"losses":12,"wins":30},"meta/muse-wonder":{"draws":6,"losses":20,"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":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":29,"wins":21},"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":4,"losses":1,"wins":45},"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":4,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":31},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":12,"losses":5,"wins":37},"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":39,"losses":25,"wins":110},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":11,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":15,"losses":0,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":46},"unbiased/pareto-26.10":{"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":12,"wins":30},"x-ai/grok-4.6":{"draws":13,"losses":13,"wins":28},"x-ai/grok-4.7":{"draws":8,"losses":22,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":2,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":17,"losses":10,"wins":81},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":29},"z-ai/glm-5.3-flash":{"draws":7,"losses":6,"wins":41},"z-ai/glm-5.3-flashx":{"draws":10,"losses":6,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":16},"claude-fable-5":{"draws":9,"losses":33,"wins":6},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":28,"losses":31,"wins":19},"claude-opus-4-8":{"draws":13,"losses":23,"wins":8},"claude-opus-5":{"draws":12,"losses":61,"wins":9},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":8,"losses":15,"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":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":17,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":13},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":15,"losses":29,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":21,"wins":38},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":28,"wins":10},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":18,"wins":11},"gpt-5.4":{"draws":13,"losses":25,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":12,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":21},"gpt-5.5":{"draws":17,"losses":21,"wins":6},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":18,"losses":20,"wins":8},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":0,"losses":45,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":16,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":26,"wins":7},"meta/muse-spark-open":{"draws":13,"losses":26,"wins":7},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"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":10,"losses":2,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":11,"losses":27,"wins":28},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":22,"wins":9},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"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":37,"losses":82,"wins":39},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":23,"wins":9},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10":{"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":27,"wins":10},"x-ai/grok-4.6":{"draws":15,"losses":26,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":17,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":18,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":9},"z-ai/glm-5.2":{"draws":26,"losses":33,"wins":37},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flashx":{"draws":14,"losses":27,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":18,"wins":18},"claude-fable-5":{"draws":9,"losses":31,"wins":8},"claude-fable-5-1":{"draws":0,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":22,"wins":15},"claude-opus-4-5":{"draws":18,"losses":34,"wins":26},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":12,"losses":62,"wins":8},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":15},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":21,"wins":30},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":25,"wins":10},"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":8,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":21},"google/gemini-3.5-flash-lite":{"draws":21,"losses":21,"wins":42},"google/gemini-3.6-flash":{"draws":21,"losses":53,"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":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":23},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":11,"losses":27,"wins":10},"gpt-6-sol":{"draws":4,"losses":42,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":17},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":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":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":43,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":14,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":10},"o3":{"draws":8,"losses":30,"wins":28},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":25,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":28,"wins":9},"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":42,"losses":90,"wins":26},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":28,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":24},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":18},"unbiased/pareto-26.10":{"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":9,"losses":30,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":16,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":19,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":27,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":27,"wins":10}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":10,"wins":2},"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":3,"losses":27,"wins":0},"claude-opus-4-8":{"draws":2,"losses":15,"wins":1},"claude-opus-5":{"draws":0,"losses":32,"wins":0},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":15,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":9,"losses":14,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":12,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":1},"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},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":14,"wins":4},"meta/muse-glimmer-30b":{"draws":6,"losses":9,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":18,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":16,"wins":0},"meta/muse-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-k2.7-code":{"draws":0,"losses":6,"wins":0},"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":8,"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":13,"wins":8},"thinkingmachines/inkling-small":{"draws":6,"losses":9,"wins":3},"unbiased/pareto-26.10":{"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":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":25,"wins":1},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":13,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":13,"wins":15},"claude-fable-5":{"draws":8,"losses":34,"wins":0},"claude-fable-5-1":{"draws":1,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":4},"claude-opus-4-5":{"draws":22,"losses":35,"wins":11},"claude-opus-4-8":{"draws":8,"losses":26,"wins":4},"claude-opus-5":{"draws":8,"losses":60,"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":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":18},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":32,"wins":4},"elorian/glimpse":{"draws":4,"losses":12,"wins":6},"fireworks/ember-1":{"draws":13,"losses":17,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":10},"gemini-4-argon":{"draws":0,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":22,"losses":25,"wins":25},"google/gemini-3.6-flash":{"draws":15,"losses":57,"wins":8},"google/gemini-3.8-flash":{"draws":6,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":2,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":24,"wins":8},"gpt-5.4":{"draws":7,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":16,"wins":18},"gpt-5.5":{"draws":9,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":22,"wins":6},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":15},"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":0,"wins":1},"meituan/longcat-2.0":{"draws":11,"losses":16,"wins":19},"meta/muse-glimmer-30b":{"draws":16,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":5,"losses":28,"wins":7},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":6},"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":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":21,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":36,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":11,"wins":6},"o3":{"draws":10,"losses":33,"wins":19},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":10},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":12},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":11,"losses":23,"wins":8},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"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":29,"losses":80,"wins":31},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":9,"losses":24,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":20},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":17},"unbiased/pareto-26.10":{"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":31,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":38,"wins":19},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":13,"losses":22,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":29,"wins":5}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":9},"claude-fable-5":{"draws":8,"losses":24,"wins":4},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":14,"wins":7},"claude-opus-4-5":{"draws":18,"losses":33,"wins":7},"claude-opus-4-8":{"draws":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":18,"losses":10,"wins":24},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":17,"wins":9},"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":12,"losses":18,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"gemini-4-argon":{"draws":3,"losses":32,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":10,"losses":23,"wins":13},"google/gemini-3.5-flash-lite":{"draws":22,"losses":21,"wins":21},"google/gemini-3.6-flash":{"draws":24,"losses":35,"wins":11},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":13,"wins":8},"gpt-5.4":{"draws":6,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":13,"losses":17,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":16,"losses":11,"wins":7},"gpt-6-astra":{"draws":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},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":7},"inception/mercury-3":{"draws":5,"losses":11,"wins":6},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":11},"meta/muse-spark-1.2":{"draws":4,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-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":8,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":27,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":5},"o3":{"draws":8,"losses":24,"wins":20},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"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":33,"losses":62,"wins":31},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":18,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":20},"thinkingmachines/inkling-small":{"draws":15,"losses":11,"wins":10},"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":15,"losses":20,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":23,"losses":12,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":24,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":5,"losses":26,"wins":5},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":4}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":9},"claude-fable-5":{"draws":6,"losses":26,"wins":4},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":3},"claude-opus-4-5":{"draws":20,"losses":29,"wins":9},"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":13,"losses":16,"wins":7},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":19},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":14,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"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":11,"losses":19,"wins":6},"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":10,"losses":3,"wins":11},"google/gemini-3.5-flash":{"draws":12,"losses":27,"wins":7},"google/gemini-3.5-flash-lite":{"draws":25,"losses":23,"wins":16},"google/gemini-3.6-flash":{"draws":17,"losses":39,"wins":14},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":20,"wins":6},"gpt-5.4":{"draws":8,"losses":21,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":14},"gpt-5.5":{"draws":9,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":25,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":20,"wins":5},"gpt-6-astra":{"draws":2,"losses":33,"wins":1},"gpt-6-luna":{"draws":9,"losses":16,"wins":11},"gpt-6-sol":{"draws":3,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":4,"wins":10},"inception/mercury-3":{"draws":5,"losses":14,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":12,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":12,"wins":13},"meta/muse-glimmer-30b":{"draws":9,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":7},"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":7,"losses":22,"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":6,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":13,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":28,"wins":1},"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":8,"losses":6,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":4},"o3":{"draws":8,"losses":22,"wins":22},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":9},"poolside/laguna-s-2.1":{"draws":9,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"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":7,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":9,"losses":19,"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":68,"wins":22},"stealth/space-bunny-alpha":{"draws":9,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":11,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":10},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"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":9,"losses":19,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":16,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":11,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":29,"losses":21,"wins":22},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":25,"wins":6}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":11,"losses":32,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":29,"losses":34,"wins":15},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":14,"losses":63,"wins":5},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":20,"losses":25,"wins":3},"claude-sonnet-5-5":{"draws":14,"losses":31,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":19,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":31,"wins":5},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":16,"losses":27,"wins":5},"gemini-3.1-pro-preview":{"draws":15,"losses":24,"wins":9},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":16,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":17,"losses":33,"wins":10},"google/gemini-3.5-flash-lite":{"draws":30,"losses":38,"wins":16},"google/gemini-3.6-flash":{"draws":28,"losses":53,"wins":11},"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":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":12,"losses":16,"wins":14},"gpt-5.4":{"draws":17,"losses":27,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":20,"wins":15},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":17,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":18,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":17,"losses":24,"wins":7},"gpt-6-sol":{"draws":9,"losses":32,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":12},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":19,"losses":5,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":20,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":31,"wins":9},"meta/muse-spark-open":{"draws":10,"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":13,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":20,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":11,"wins":4},"o3":{"draws":16,"losses":34,"wins":16},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":22,"losses":15,"wins":9},"qwen/qwen3.7-max":{"draws":11,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":14,"losses":12,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"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":42,"losses":82,"wins":33},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":14,"wins":26},"thinkingmachines/inkling-small":{"draws":15,"losses":16,"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":11,"losses":32,"wins":5},"x-ai/grok-4.6":{"draws":14,"losses":29,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":28,"losses":20,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":12,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":30,"wins":7},"z-ai/glm-5.3-flashx":{"draws":14,"losses":30,"wins":4}},"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},"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":0,"losses":0,"wins":2},"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":11,"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":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":17,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":3},"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":10,"losses":5,"wins":27},"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":2,"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":8,"wins":14},"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":16},"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},"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":0,"losses":0,"wins":2},"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":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":19,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":28,"wins":0},"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":5,"losses":4,"wins":15},"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":2,"wins":2},"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":2,"losses":9,"wins":5},"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":14,"losses":17,"wins":13},"claude-fable-5":{"draws":13,"losses":34,"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":31,"losses":31,"wins":16},"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":21,"wins":12},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":25,"losses":25,"wins":22},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":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":7,"losses":6,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":31,"wins":10},"google/gemini-3.5-flash-lite":{"draws":32,"losses":32,"wins":20},"google/gemini-3.6-flash":{"draws":32,"losses":42,"wins":18},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":19,"wins":8},"gpt-5.4":{"draws":17,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"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":18,"losses":20,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":13,"losses":23,"wins":12},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":3,"wins":12},"inception/mercury-3":{"draws":13,"losses":18,"wins":1},"inclusionai/ling-3.0-flash":{"draws":20,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":13,"wins":22},"meta/muse-glimmer-30b":{"draws":18,"losses":9,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":7},"meta/muse-spark-1.3":{"draws":8,"losses":31,"wins":9},"meta/muse-spark-open":{"draws":10,"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":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":17,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":0},"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":18,"losses":14,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"o3":{"draws":18,"losses":28,"wins":20},"openai/gpt-oss-120b":{"draws":19,"losses":13,"wins":10},"poolside/laguna-s-2.1":{"draws":22,"losses":14,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":21,"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":18,"losses":18,"wins":12},"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":45,"losses":89,"wins":24},"stealth/space-bunny-alpha":{"draws":12,"losses":14,"wins":12},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":18,"losses":19,"wins":9},"thinkingmachines/inkling":{"draws":22,"losses":21,"wins":21},"thinkingmachines/inkling-small":{"draws":18,"losses":11,"wins":19},"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":14,"losses":27,"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":10,"losses":11,"wins":5},"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":37,"losses":36,"wins":23},"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":18,"wins":12},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":26,"wins":7},"claude-opus-4-5":{"draws":25,"losses":45,"wins":8},"claude-opus-4-8":{"draws":12,"losses":29,"wins":3},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":10,"wins":4},"deepseek/deepseek-v4-flash":{"draws":27,"losses":26,"wins":19},"deepseek/deepseek-v4-pro":{"draws":14,"losses":24,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":23,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":24,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":36,"wins":4},"elorian/glimpse":{"draws":5,"losses":16,"wins":5},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":4},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":10,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":33,"losses":30,"wins":21},"google/gemini-3.6-flash":{"draws":33,"losses":53,"wins":6},"google/gemini-3.8-flash":{"draws":11,"losses":36,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":19,"losses":18,"wins":5},"gpt-5.4":{"draws":14,"losses":29,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":17},"gpt-5.5":{"draws":18,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":21,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":40,"wins":2},"gpt-5.6-terra":{"draws":21,"losses":22,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":12,"wins":7},"inception/mercury-3":{"draws":12,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":23,"wins":13},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":28,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":35,"wins":4},"meta/muse-spark-open":{"draws":12,"losses":33,"wins":1},"meta/muse-wonder":{"draws":8,"losses":38,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"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":15,"losses":5,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":40,"wins":1},"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":16,"losses":14,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":12,"losses":47,"wins":7},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":19,"losses":19,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":28,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-max-0902":{"draws":15,"losses":30,"wins":3},"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":36,"losses":107,"wins":15},"stealth/space-bunny-alpha":{"draws":15,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":11,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":25,"losses":24,"wins":15},"thinkingmachines/inkling-small":{"draws":19,"losses":16,"wins":13},"unbiased/pareto-26.10":{"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":16,"losses":31,"wins":1},"x-ai/grok-4.7":{"draws":4,"losses":35,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":28,"losses":28,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":40,"wins":18},"z-ai/glm-5.3":{"draws":10,"losses":35,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":29,"wins":4},"z-ai/glm-5.3-flashx":{"draws":13,"losses":31,"wins":4}},"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},"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":0,"losses":0,"wins":2},"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":6,"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":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":2,"losses":6,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":26,"wins":17},"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":3,"losses":0,"wins":39},"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":0,"losses":1,"wins":3},"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":1,"losses":3,"wins":22},"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":7,"losses":15,"wins":4},"claude-fable-5":{"draws":2,"losses":27,"wins":1},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":25,"wins":0},"claude-opus-4-5":{"draws":12,"losses":36,"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":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":6,"losses":21,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":29,"wins":6},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":20,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"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":7,"losses":40,"wins":5},"google/gemini-3.6-flash":{"draws":12,"losses":44,"wins":2},"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":5,"losses":21,"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":7,"losses":22,"wins":7},"gpt-5.5":{"draws":6,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":20,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":21,"wins":1},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":7,"losses":19,"wins":4},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":5},"inception/mercury-3":{"draws":8,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":12,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":25,"wins":3},"meta/muse-glimmer-30b":{"draws":8,"losses":12,"wins":4},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":0},"meta/muse-spark-open":{"draws":4,"losses":23,"wins":1},"meta/muse-wonder":{"draws":3,"losses":26,"wins":1},"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":4,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"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":6,"losses":20,"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":17,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":21,"wins":0},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-max":{"draws":8,"losses":22,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":0},"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},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":0},"thinkingmachines/inkling":{"draws":12,"losses":20,"wins":8},"thinkingmachines/inkling-small":{"draws":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":2,"losses":16,"wins":0},"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":43,"wins":5},"z-ai/glm-5.3":{"draws":4,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":30,"wins":25},"claude-fable-5":{"draws":16,"losses":62,"wins":6},"claude-fable-5-1":{"draws":3,"losses":91,"wins":0},"claude-haiku-5-5":{"draws":18,"losses":45,"wins":19},"claude-opus-4-5":{"draws":39,"losses":72,"wins":27},"claude-opus-4-8":{"draws":21,"losses":51,"wins":8},"claude-opus-5":{"draws":15,"losses":116,"wins":9},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":29,"losses":33,"wins":22},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":35,"losses":42,"wins":49},"deepseek/deepseek-v4-pro":{"draws":22,"losses":34,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":36,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":43,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":60,"wins":10},"elorian/glimpse":{"draws":7,"losses":26,"wins":13},"fireworks/ember-1":{"draws":29,"losses":41,"wins":14},"gemini-3.1-pro-preview":{"draws":24,"losses":38,"wins":22},"gemini-4-argon":{"draws":2,"losses":79,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":10,"wins":34},"google/gemini-3.5-flash":{"draws":16,"losses":50,"wins":14},"google/gemini-3.5-flash-lite":{"draws":45,"losses":63,"wins":42},"google/gemini-3.6-flash":{"draws":44,"losses":84,"wins":34},"google/gemini-3.8-flash":{"draws":22,"losses":55,"wins":7},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":20},"gpt-4.1":{"draws":10,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":21,"losses":33,"wins":20},"gpt-5.4":{"draws":11,"losses":56,"wins":15},"gpt-5.4-mini":{"draws":22,"losses":17,"wins":17},"gpt-5.4-nano":{"draws":17,"losses":33,"wins":38},"gpt-5.5":{"draws":28,"losses":39,"wins":11},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":70,"wins":7},"gpt-5.6-terra":{"draws":29,"losses":38,"wins":13},"gpt-6-astra":{"draws":3,"losses":79,"wins":2},"gpt-6-luna":{"draws":29,"losses":34,"wins":21},"gpt-6-sol":{"draws":14,"losses":64,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":79,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":13,"wins":23},"inception/mercury-3":{"draws":13,"losses":29,"wins":12},"inclusionai/ling-3.0-flash":{"draws":24,"losses":9,"wins":27},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":25,"wins":47},"meta/muse-glimmer-30b":{"draws":30,"losses":17,"wins":27},"meta/muse-spark-1.2":{"draws":17,"losses":49,"wins":14},"meta/muse-spark-1.3":{"draws":17,"losses":55,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":62,"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":18,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":29,"losses":34,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":74,"wins":4},"nex-agi/nex-n2-pro":{"draws":13,"losses":11,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":21,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":21,"wins":12},"o3":{"draws":23,"losses":57,"wins":46},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":23},"poolside/laguna-s-2.1":{"draws":27,"losses":23,"wins":28},"qwen/qwen3.7-max":{"draws":16,"losses":23,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":48,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":35,"wins":15},"qwen/qwen3.8-flash":{"draws":19,"losses":24,"wins":13},"qwen/qwen3.8-max":{"draws":28,"losses":35,"wins":21},"qwen/qwen3.8-max-0902":{"draws":25,"losses":46,"wins":13},"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":52,"losses":164,"wins":44},"stealth/space-bunny-alpha":{"draws":23,"losses":27,"wins":18},"stepfun/step-3.7-flash":{"draws":13,"losses":17,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":26,"losses":47,"wins":9},"thinkingmachines/inkling":{"draws":26,"losses":37,"wins":49},"thinkingmachines/inkling-small":{"draws":28,"losses":22,"wins":34},"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":23,"losses":54,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":12},"xiaomi/mimo-v2.5":{"draws":48,"losses":37,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":34,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":59,"losses":70,"wins":39},"z-ai/glm-5.3":{"draws":13,"losses":62,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":57,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":30},"claude-fable-5":{"draws":17,"losses":61,"wins":12},"claude-fable-5-1":{"draws":6,"losses":93,"wins":1},"claude-haiku-5-5":{"draws":18,"losses":53,"wins":17},"claude-opus-4-5":{"draws":48,"losses":55,"wins":45},"claude-opus-4-8":{"draws":25,"losses":50,"wins":11},"claude-opus-5":{"draws":18,"losses":122,"wins":12},"claude-opus-5-5":{"draws":4,"losses":93,"wins":1},"claude-sonnet-5":{"draws":26,"losses":44,"wins":20},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":44,"losses":38,"wins":54},"deepseek/deepseek-v4-pro":{"draws":23,"losses":33,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":37,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":45,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":62,"wins":15},"elorian/glimpse":{"draws":15,"losses":21,"wins":12},"fireworks/ember-1":{"draws":28,"losses":36,"wins":26},"gemini-3.1-pro-preview":{"draws":33,"losses":32,"wins":25},"gemini-4-argon":{"draws":2,"losses":82,"wins":6},"google/gemini-3.1-flash-lite":{"draws":18,"losses":9,"wins":37},"google/gemini-3.5-flash":{"draws":29,"losses":53,"wins":32},"google/gemini-3.5-flash-lite":{"draws":45,"losses":35,"wins":48},"google/gemini-3.6-flash":{"draws":51,"losses":76,"wins":45},"google/gemini-3.8-flash":{"draws":18,"losses":64,"wins":8},"google/gemma-4-31b-it":{"draws":20,"losses":9,"wins":25},"gpt-4.1":{"draws":9,"losses":6,"wins":15},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":23,"losses":32,"wins":23},"gpt-5.4":{"draws":21,"losses":51,"wins":14},"gpt-5.4-mini":{"draws":19,"losses":18,"wins":23},"gpt-5.4-nano":{"draws":19,"losses":34,"wins":41},"gpt-5.5":{"draws":33,"losses":37,"wins":12},"gpt-5.6-luna":{"draws":27,"losses":28,"wins":35},"gpt-5.6-sol":{"draws":10,"losses":69,"wins":11},"gpt-5.6-terra":{"draws":27,"losses":34,"wins":25},"gpt-6-astra":{"draws":5,"losses":85,"wins":0},"gpt-6-luna":{"draws":31,"losses":35,"wins":24},"gpt-6-sol":{"draws":13,"losses":68,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":83,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":28},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":22,"wins":51},"meta/muse-glimmer-30b":{"draws":35,"losses":14,"wins":29},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":22},"meta/muse-spark-1.3":{"draws":21,"losses":53,"wins":16},"meta/muse-spark-open":{"draws":18,"losses":51,"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":20,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":19,"losses":9,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":28,"losses":39,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":75,"wins":1},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":3,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":18,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":18,"wins":10},"o3":{"draws":22,"losses":54,"wins":52},"openai/gpt-oss-120b":{"draws":24,"losses":24,"wins":30},"poolside/laguna-s-2.1":{"draws":26,"losses":27,"wins":31},"qwen/qwen3.7-max":{"draws":17,"losses":20,"wins":17},"qwen/qwen3.7-plus":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":41,"wins":19},"qwen/qwen3.8-27b":{"draws":13,"losses":31,"wins":20},"qwen/qwen3.8-flash":{"draws":17,"losses":24,"wins":19},"qwen/qwen3.8-max":{"draws":28,"losses":39,"wins":23},"qwen/qwen3.8-max-0902":{"draws":25,"losses":47,"wins":18},"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":146,"wins":66},"stealth/space-bunny-alpha":{"draws":25,"losses":19,"wins":28},"stepfun/step-3.7-flash":{"draws":19,"losses":11,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":19,"wins":10},"tencent/hy4-preview":{"draws":24,"losses":43,"wins":19},"thinkingmachines/inkling":{"draws":37,"losses":31,"wins":50},"thinkingmachines/inkling-small":{"draws":30,"losses":20,"wins":40},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":12},"x-ai/grok-4.5":{"draws":23,"losses":47,"wins":20},"x-ai/grok-4.6":{"draws":20,"losses":55,"wins":15},"x-ai/grok-4.7":{"draws":9,"losses":59,"wins":12},"x-ai/grok-build-0.1":{"draws":13,"losses":5,"wins":12},"xiaomi/mimo-v2.5":{"draws":46,"losses":37,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":36,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":65,"losses":57,"wins":58},"z-ai/glm-5.3":{"draws":13,"losses":66,"wins":7},"z-ai/glm-5.3-flash":{"draws":16,"losses":53,"wins":21},"z-ai/glm-5.3-flashx":{"draws":26,"losses":44,"wins":20}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":28,"wins":30},"claude-fable-5":{"draws":22,"losses":63,"wins":11},"claude-fable-5-1":{"draws":6,"losses":100,"wins":2},"claude-haiku-5-5":{"draws":28,"losses":47,"wins":17},"claude-opus-4-5":{"draws":54,"losses":63,"wins":39},"claude-opus-4-8":{"draws":26,"losses":40,"wins":22},"claude-opus-5":{"draws":18,"losses":129,"wins":17},"claude-opus-5-5":{"draws":4,"losses":99,"wins":1},"claude-sonnet-5":{"draws":31,"losses":42,"wins":23},"claude-sonnet-5-5":{"draws":19,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":48,"losses":37,"wins":59},"deepseek/deepseek-v4-pro":{"draws":29,"losses":39,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":40,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":40,"wins":22},"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":34,"losses":35,"wins":27},"gemini-4-argon":{"draws":7,"losses":86,"wins":3},"google/gemini-3.1-flash-lite":{"draws":25,"losses":10,"wins":29},"google/gemini-3.5-flash":{"draws":32,"losses":65,"wins":23},"google/gemini-3.5-flash-lite":{"draws":61,"losses":51,"wins":56},"google/gemini-3.6-flash":{"draws":40,"losses":85,"wins":27},"google/gemini-3.8-flash":{"draws":24,"losses":59,"wins":13},"google/gemma-4-31b-it":{"draws":23,"losses":11,"wins":22},"gpt-4.1":{"draws":12,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":3},"gpt-5":{"draws":27,"losses":40,"wins":17},"gpt-5.4":{"draws":22,"losses":48,"wins":22},"gpt-5.4-mini":{"draws":23,"losses":17,"wins":24},"gpt-5.4-nano":{"draws":24,"losses":36,"wins":36},"gpt-5.5":{"draws":36,"losses":37,"wins":15},"gpt-5.6-luna":{"draws":38,"losses":27,"wins":31},"gpt-5.6-sol":{"draws":14,"losses":73,"wins":9},"gpt-5.6-terra":{"draws":37,"losses":35,"wins":20},"gpt-6-astra":{"draws":8,"losses":88,"wins":0},"gpt-6-luna":{"draws":34,"losses":31,"wins":31},"gpt-6-sol":{"draws":13,"losses":76,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":90,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":5,"wins":30},"inception/mercury-3":{"draws":17,"losses":28,"wins":19},"inclusionai/ling-3.0-flash":{"draws":36,"losses":11,"wins":21},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":27,"wins":48},"meta/muse-glimmer-30b":{"draws":41,"losses":16,"wins":27},"meta/muse-spark-1.2":{"draws":22,"losses":52,"wins":18},"meta/muse-spark-1.3":{"draws":25,"losses":54,"wins":17},"meta/muse-spark-open":{"draws":19,"losses":51,"wins":22},"meta/muse-wonder":{"draws":16,"losses":68,"wins":12},"minimax/minimax-m3":{"draws":15,"losses":11,"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":29,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":6},"moonshotai/kimi-k3":{"draws":30,"losses":42,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":77,"wins":1},"nex-agi/nex-n2-pro":{"draws":16,"losses":5,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":17,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":22,"wins":10},"o3":{"draws":25,"losses":75,"wins":32},"openai/gpt-oss-120b":{"draws":36,"losses":18,"wins":30},"poolside/laguna-s-2.1":{"draws":37,"losses":25,"wins":30},"qwen/qwen3.7-max":{"draws":19,"losses":21,"wins":16},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":44,"wins":20},"qwen/qwen3.8-27b":{"draws":18,"losses":33,"wins":17},"qwen/qwen3.8-flash":{"draws":27,"losses":22,"wins":15},"qwen/qwen3.8-max":{"draws":30,"losses":44,"wins":22},"qwen/qwen3.8-max-0902":{"draws":32,"losses":41,"wins":23},"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":86,"losses":159,"wins":71},"stealth/space-bunny-alpha":{"draws":25,"losses":26,"wins":25},"stepfun/step-3.7-flash":{"draws":19,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":18},"tencent/hy4-preview":{"draws":24,"losses":54,"wins":14},"thinkingmachines/inkling":{"draws":43,"losses":24,"wins":61},"thinkingmachines/inkling-small":{"draws":39,"losses":29,"wins":28},"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":29,"losses":57,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":70,"wins":11},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":15},"xiaomi/mimo-v2.5":{"draws":61,"losses":34,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":17,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":34,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":13},"z-ai/glm-5.2":{"draws":72,"losses":77,"wins":43},"z-ai/glm-5.3":{"draws":20,"losses":66,"wins":6},"z-ai/glm-5.3-flash":{"draws":22,"losses":58,"wins":16},"z-ai/glm-5.3-flashx":{"draws":27,"losses":48,"wins":21}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":8,"losses":31,"wins":9},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":17},"claude-opus-4-5":{"draws":30,"losses":15,"wins":33},"claude-opus-4-8":{"draws":11,"losses":18,"wins":15},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":27,"wins":13},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":13,"losses":18,"wins":17},"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":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":19,"losses":8,"wins":57},"google/gemini-3.6-flash":{"draws":25,"losses":29,"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":10,"losses":6,"wins":32},"gpt-5.5":{"draws":15,"losses":13,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":6,"losses":27,"wins":15},"gpt-5.6-terra":{"draws":18,"losses":11,"wins":17},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":16,"losses":14,"wins":18},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":39,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":34},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":18,"wins":17},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-spark-open":{"draws":13,"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":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":13,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":3},"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":15,"losses":3,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":2,"wins":13},"o3":{"draws":9,"losses":16,"wins":41},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"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":15,"losses":14,"wins":19},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"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":66,"wins":55},"stealth/space-bunny-alpha":{"draws":14,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"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":24,"wins":14},"x-ai/grok-4.6":{"draws":15,"losses":21,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":28,"losses":2,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":25,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":18}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":7},"claude-fable-5":{"draws":7,"losses":28,"wins":1},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":22,"wins":3},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":8,"losses":47,"wins":3},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":5,"losses":23,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":24,"losses":22,"wins":8},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"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":13,"losses":19,"wins":4},"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":17,"losses":24,"wins":5},"google/gemini-3.5-flash-lite":{"draws":26,"losses":27,"wins":11},"google/gemini-3.6-flash":{"draws":23,"losses":40,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":15,"wins":1},"gpt-5.4":{"draws":11,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":11,"wins":4},"gpt-5.4-nano":{"draws":9,"losses":23,"wins":6},"gpt-5.5":{"draws":11,"losses":20,"wins":1},"gpt-5.6-luna":{"draws":14,"losses":16,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":0},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":8},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":20,"wins":10},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":23,"wins":2},"meta/muse-spark-open":{"draws":8,"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":4,"losses":6,"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":16,"losses":10,"wins":8},"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":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":8},"unbiased/pareto-26.10":{"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":8,"losses":12,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":0},"z-ai/glm-5.2":{"draws":26,"losses":39,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":3},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":32,"losses":29,"wins":17},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":16,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":16,"wins":34},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"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":19,"wins":16},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":28,"losses":27,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":47,"wins":20},"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":15,"wins":16},"gpt-5.4":{"draws":11,"losses":24,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":10,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":27},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":15,"losses":23,"wins":8},"meta/muse-spark-1.3":{"draws":17,"losses":27,"wins":4},"meta/muse-spark-open":{"draws":7,"losses":27,"wins":11},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"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":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":42,"wins":2},"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":18,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":7},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":20},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":24,"wins":7},"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":19,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"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":41,"losses":80,"wins":37},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":27},"thinkingmachines/inkling-small":{"draws":15,"losses":13,"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":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":30,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":35,"losses":38,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":28,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":0},"elorian/glimpse":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":9,"losses":8,"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":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-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":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":0},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"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":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10":{"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":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":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":16,"losses":25,"wins":17},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":7,"losses":57,"wins":4},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":8,"losses":24,"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":17,"losses":19,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":13,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"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":12,"losses":14,"wins":10},"gemini-4-argon":{"draws":0,"losses":35,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":7,"losses":23,"wins":14},"google/gemini-3.5-flash-lite":{"draws":12,"losses":17,"wins":31},"google/gemini-3.6-flash":{"draws":14,"losses":31,"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":8,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":18},"gpt-5.5":{"draws":11,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":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},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":8,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":5,"losses":26,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":5,"losses":25,"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":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":19,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":28,"wins":5},"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":9,"losses":5,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":8,"wins":7},"o3":{"draws":6,"losses":21,"wins":23},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":6},"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":8,"losses":20,"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":22,"losses":70,"wins":32},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":16,"wins":11},"thinkingmachines/inkling":{"draws":9,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":15},"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":4,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":11,"losses":12,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":9},"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":17,"losses":27,"wins":28},"z-ai/glm-5.3":{"draws":4,"losses":25,"wins":5},"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":21,"wins":13},"claude-opus-4-5":{"draws":27,"losses":28,"wins":23},"claude-opus-4-8":{"draws":13,"losses":16,"wins":15},"claude-opus-5":{"draws":15,"losses":61,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":15,"wins":34},"deepseek/deepseek-v4-pro":{"draws":9,"losses":19,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":21,"wins":12},"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":12,"losses":18,"wins":18},"gemini-4-argon":{"draws":3,"losses":42,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":10,"losses":23,"wins":27},"google/gemini-3.5-flash-lite":{"draws":23,"losses":20,"wins":41},"google/gemini-3.6-flash":{"draws":19,"losses":45,"wins":28},"google/gemini-3.8-flash":{"draws":11,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":17,"wins":17},"gpt-5.4":{"draws":7,"losses":22,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":17},"gpt-5.4-nano":{"draws":7,"losses":16,"wins":25},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":16,"losses":20,"wins":10},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":20,"losses":14,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":10,"losses":14,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":24,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":29,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":22,"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":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":37,"wins":4},"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":16,"losses":4,"wins":22},"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":15,"losses":11,"wins":20},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":10},"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":9,"losses":12,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":18,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":18},"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":38,"losses":80,"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":11,"wins":34},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10":{"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":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":21,"losses":12,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":28,"losses":29,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":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":21,"losses":18,"wins":5},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":30,"wins":2},"claude-opus-4-5":{"draws":36,"losses":35,"wins":7},"claude-opus-4-8":{"draws":11,"losses":30,"wins":3},"claude-opus-5":{"draws":21,"losses":57,"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":32,"losses":27,"wins":13},"deepseek/deepseek-v4-pro":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":25,"wins":2},"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":22,"losses":23,"wins":3},"gemini-3.1-pro-preview":{"draws":21,"losses":20,"wins":7},"gemini-4-argon":{"draws":7,"losses":41,"wins":0},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":23,"losses":32,"wins":5},"google/gemini-3.5-flash-lite":{"draws":31,"losses":37,"wins":16},"google/gemini-3.6-flash":{"draws":34,"losses":53,"wins":5},"google/gemini-3.8-flash":{"draws":15,"losses":32,"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":18,"losses":21,"wins":3},"gpt-5.4":{"draws":16,"losses":30,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":16,"losses":24,"wins":8},"gpt-5.5":{"draws":18,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":21,"losses":20,"wins":5},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":22,"losses":23,"wins":3},"gpt-6-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":18,"losses":9,"wins":7},"inception/mercury-3":{"draws":13,"losses":16,"wins":3},"inclusionai/ling-3.0-flash":{"draws":21,"losses":9,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":23,"wins":8},"meta/muse-glimmer-30b":{"draws":24,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":16,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":37,"wins":1},"meta/muse-spark-open":{"draws":14,"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":14,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":0},"nex-agi/nex-n2-pro":{"draws":9,"losses":9,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":14,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":0},"o3":{"draws":16,"losses":43,"wins":7},"openai/gpt-oss-120b":{"draws":21,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":23,"losses":18,"wins":5},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":26,"losses":16,"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":57,"losses":88,"wins":13},"stealth/space-bunny-alpha":{"draws":16,"losses":22,"wins":0},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":3},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":0},"thinkingmachines/inkling":{"draws":25,"losses":26,"wins":13},"thinkingmachines/inkling-small":{"draws":24,"losses":17,"wins":7},"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":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":26,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":21,"wins":1},"z-ai/glm-5.2":{"draws":50,"losses":41,"wins":5},"z-ai/glm-5.3":{"draws":15,"losses":30,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":27,"wins":7},"z-ai/glm-5.3-flashx":{"draws":15,"losses":32,"wins":1}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":28,"wins":22},"claude-fable-5":{"draws":11,"losses":58,"wins":3},"claude-fable-5-1":{"draws":1,"losses":75,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":38,"wins":15},"claude-opus-4-5":{"draws":32,"losses":63,"wins":23},"claude-opus-4-8":{"draws":14,"losses":42,"wins":12},"claude-opus-5":{"draws":12,"losses":105,"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":30,"losses":43,"wins":41},"deepseek/deepseek-v4-pro":{"draws":11,"losses":30,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":33,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":35,"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":22,"losses":35,"wins":15},"gemini-4-argon":{"draws":0,"losses":68,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":13,"wins":25},"google/gemini-3.5-flash":{"draws":18,"losses":56,"wins":16},"google/gemini-3.5-flash-lite":{"draws":33,"losses":49,"wins":42},"google/gemini-3.6-flash":{"draws":28,"losses":83,"wins":25},"google/gemini-3.8-flash":{"draws":18,"losses":45,"wins":9},"google/gemma-4-31b-it":{"draws":15,"losses":10,"wins":17},"gpt-4.1":{"draws":7,"losses":9,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":11,"losses":36,"wins":17},"gpt-5.4":{"draws":8,"losses":47,"wins":13},"gpt-5.4-mini":{"draws":17,"losses":15,"wins":16},"gpt-5.4-nano":{"draws":14,"losses":24,"wins":22},"gpt-5.5":{"draws":18,"losses":32,"wins":14},"gpt-5.6-luna":{"draws":22,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":5,"losses":60,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":37,"wins":14},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":16,"losses":42,"wins":14},"gpt-6-sol":{"draws":8,"losses":56,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":67,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":9,"wins":23},"inception/mercury-3":{"draws":15,"losses":25,"wins":12},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":29,"wins":33},"meta/muse-glimmer-30b":{"draws":18,"losses":19,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":37,"wins":19},"meta/muse-spark-1.3":{"draws":12,"losses":52,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":52,"wins":7},"meta/muse-wonder":{"draws":5,"losses":55,"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":8,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":9,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":18,"losses":37,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":64,"wins":0},"nex-agi/nex-n2-pro":{"draws":10,"losses":14,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":20,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":15,"wins":9},"o3":{"draws":12,"losses":58,"wins":38},"openai/gpt-oss-120b":{"draws":24,"losses":24,"wins":16},"poolside/laguna-s-2.1":{"draws":28,"losses":28,"wins":20},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":41,"wins":12},"qwen/qwen3.8-27b":{"draws":15,"losses":25,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":26,"wins":10},"qwen/qwen3.8-max":{"draws":15,"losses":37,"wins":20},"qwen/qwen3.8-max-0902":{"draws":22,"losses":35,"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":47,"losses":123,"wins":52},"stealth/space-bunny-alpha":{"draws":13,"losses":27,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":21,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":46,"wins":8},"thinkingmachines/inkling":{"draws":25,"losses":40,"wins":29},"thinkingmachines/inkling-small":{"draws":24,"losses":23,"wins":25},"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":16,"losses":47,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":44,"wins":13},"x-ai/grok-4.7":{"draws":10,"losses":54,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":11},"xiaomi/mimo-v2.5":{"draws":30,"losses":39,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":20,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":25,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":42,"losses":66,"wins":36},"z-ai/glm-5.3":{"draws":12,"losses":49,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":46,"wins":14},"z-ai/glm-5.3-flashx":{"draws":18,"losses":39,"wins":15}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":12},"claude-fable-5":{"draws":13,"losses":22,"wins":7},"claude-fable-5-1":{"draws":2,"losses":43,"wins":3},"claude-haiku-5-5":{"draws":17,"losses":17,"wins":6},"claude-opus-4-5":{"draws":36,"losses":21,"wins":11},"claude-opus-4-8":{"draws":18,"losses":16,"wins":4},"claude-opus-5":{"draws":14,"losses":65,"wins":1},"claude-opus-5-5":{"draws":7,"losses":39,"wins":0},"claude-sonnet-5":{"draws":22,"losses":10,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":31,"losses":9,"wins":22},"deepseek/deepseek-v4-pro":{"draws":20,"losses":12,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":20,"wins":8},"elorian/glimpse":{"draws":5,"losses":8,"wins":11},"fireworks/ember-1":{"draws":15,"losses":18,"wins":9},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":11},"gemini-4-argon":{"draws":4,"losses":38,"wins":0},"google/gemini-3.1-flash-lite":{"draws":13,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":18,"losses":21,"wins":13},"google/gemini-3.5-flash-lite":{"draws":37,"losses":13,"wins":22},"google/gemini-3.6-flash":{"draws":26,"losses":40,"wins":14},"google/gemini-3.8-flash":{"draws":19,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":8},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":12,"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":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":11,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":16,"losses":15,"wins":11},"gpt-6-sol":{"draws":10,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":9},"inception/mercury-3":{"draws":12,"losses":10,"wins":6},"inclusionai/ling-3.0-flash":{"draws":21,"losses":2,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":20,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":9,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":6},"meta/muse-spark-open":{"draws":10,"losses":25,"wins":5},"meta/muse-wonder":{"draws":17,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":7},"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":14,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":3,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":6,"wins":5},"o3":{"draws":16,"losses":18,"wins":20},"openai/gpt-oss-120b":{"draws":20,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":22,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":14,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":8},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":6},"qwen/qwen3.8-max":{"draws":17,"losses":15,"wins":10},"qwen/qwen3.8-max-0902":{"draws":19,"losses":18,"wins":5},"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":45,"losses":69,"wins":28},"stealth/space-bunny-alpha":{"draws":18,"losses":7,"wins":9},"stepfun/step-3.7-flash":{"draws":13,"losses":5,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":4},"thinkingmachines/inkling":{"draws":26,"losses":7,"wins":25},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"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":2,"wins":4},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":2},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":34,"losses":7,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":5},"z-ai/glm-5.2":{"draws":37,"losses":23,"wins":24},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":20,"wins":9},"z-ai/glm-5.3-flashx":{"draws":18,"losses":18,"wins":6}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":24,"wins":8},"claude-fable-5":{"draws":8,"losses":37,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":32,"wins":2},"claude-opus-4-5":{"draws":26,"losses":45,"wins":7},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":9,"losses":69,"wins":4},"claude-opus-5-5":{"draws":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":29,"losses":30,"wins":13},"deepseek/deepseek-v4-pro":{"draws":14,"losses":26,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":22,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":28,"wins":6},"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":27,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":26,"wins":10},"gemini-4-argon":{"draws":3,"losses":45,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":16,"wins":9},"google/gemini-3.5-flash":{"draws":11,"losses":43,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":43,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":62,"wins":5},"google/gemini-3.8-flash":{"draws":6,"losses":39,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":15,"wins":3},"gpt-4.1":{"draws":4,"losses":11,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":27,"wins":4},"gpt-5.4":{"draws":13,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":11,"losses":17,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":27,"wins":8},"gpt-5.5":{"draws":13,"losses":28,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":15,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":40,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":7},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":7},"gpt-6-sol":{"draws":9,"losses":37,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":13,"wins":5},"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":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":29,"wins":6},"meta/muse-glimmer-30b":{"draws":17,"losses":22,"wins":3},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":34,"wins":2},"meta/muse-spark-open":{"draws":11,"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":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":24,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":2},"o3":{"draws":8,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":26,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":31,"wins":0},"qwen/qwen3.8-27b":{"draws":11,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":29,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":31,"wins":3},"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":100,"wins":9},"stealth/space-bunny-alpha":{"draws":15,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":16,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":18,"wins":0},"tencent/hy4-preview":{"draws":12,"losses":30,"wins":4},"thinkingmachines/inkling":{"draws":22,"losses":26,"wins":16},"thinkingmachines/inkling-small":{"draws":18,"losses":23,"wins":7},"unbiased/pareto-26.10":{"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":15,"losses":32,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":36,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":35,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":25,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":53,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":34,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":4,"wins":28},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":4,"losses":22,"wins":20},"claude-opus-4-5":{"draws":21,"losses":13,"wins":44},"claude-opus-4-8":{"draws":9,"losses":21,"wins":14},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":9,"wins":25},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":14,"losses":11,"wins":47},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":16,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":21,"wins":13},"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":10,"losses":13,"wins":25},"gemini-4-argon":{"draws":4,"losses":40,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":18,"wins":32},"google/gemini-3.5-flash-lite":{"draws":21,"losses":10,"wins":53},"google/gemini-3.6-flash":{"draws":20,"losses":33,"wins":39},"google/gemini-3.8-flash":{"draws":10,"losses":23,"wins":15},"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":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"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},"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":7,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":7,"losses":23,"wins":18},"meta/muse-spark-open":{"draws":11,"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-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":42,"wins":3},"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":9,"losses":5,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":31},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":7,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":19},"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":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"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":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":21,"losses":26,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":21}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":8,"wins":17},"claude-fable-5":{"draws":13,"losses":28,"wins":1},"claude-fable-5-1":{"draws":4,"losses":43,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":5},"claude-opus-4-5":{"draws":30,"losses":28,"wins":10},"claude-opus-4-8":{"draws":16,"losses":19,"wins":3},"claude-opus-5":{"draws":11,"losses":51,"wins":8},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":20,"losses":15,"wins":7},"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":24,"losses":12,"wins":28},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":16,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":29,"wins":1},"elorian/glimpse":{"draws":7,"losses":13,"wins":4},"fireworks/ember-1":{"draws":16,"losses":24,"wins":2},"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":12,"losses":3,"wins":11},"google/gemini-3.5-flash":{"draws":22,"losses":24,"wins":6},"google/gemini-3.5-flash-lite":{"draws":28,"losses":22,"wins":22},"google/gemini-3.6-flash":{"draws":30,"losses":39,"wins":11},"google/gemini-3.8-flash":{"draws":14,"losses":24,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":17,"wins":6},"gpt-5.4":{"draws":10,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":15},"gpt-5.5":{"draws":21,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":11},"gpt-5.6-sol":{"draws":12,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":8},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":17,"losses":17,"wins":8},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":12},"inception/mercury-3":{"draws":13,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":14},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":14},"meta/muse-spark-1.2":{"draws":16,"losses":15,"wins":9},"meta/muse-spark-1.3":{"draws":13,"losses":20,"wins":9},"meta/muse-spark-open":{"draws":12,"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":10,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":4,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":6,"wins":4},"o3":{"draws":14,"losses":22,"wins":18},"openai/gpt-oss-120b":{"draws":18,"losses":1,"wins":17},"poolside/laguna-s-2.1":{"draws":23,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":15,"losses":12,"wins":3},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":21,"losses":11,"wins":10},"qwen/qwen3.8-max-0902":{"draws":19,"losses":17,"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":51,"losses":67,"wins":22},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":16,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":20},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":16},"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":16,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":31,"losses":9,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":10,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":3},"z-ai/glm-5.2":{"draws":44,"losses":22,"wins":18},"z-ai/glm-5.3":{"draws":13,"losses":23,"wins":4},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":13,"losses":24,"wins":5}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":35},"claude-fable-5":{"draws":5,"losses":9,"wins":34},"claude-fable-5-1":{"draws":6,"losses":27,"wins":21},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":38},"claude-opus-4-5":{"draws":8,"losses":7,"wins":63},"claude-opus-4-8":{"draws":5,"losses":7,"wins":32},"claude-opus-5":{"draws":10,"losses":24,"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":11,"wins":32},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":1,"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":5,"losses":1,"wins":42},"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":8,"losses":1,"wins":51},"google/gemini-3.5-flash-lite":{"draws":9,"losses":1,"wins":74},"google/gemini-3.6-flash":{"draws":12,"losses":6,"wins":74},"google/gemini-3.8-flash":{"draws":7,"losses":6,"wins":35},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":0,"wins":37},"gpt-5.4":{"draws":5,"losses":7,"wins":34},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":28},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":45},"gpt-5.5":{"draws":3,"losses":3,"wins":38},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":2,"wins":39},"gpt-5.6-terra":{"draws":10,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":17,"wins":11},"gpt-6-luna":{"draws":8,"losses":4,"wins":36},"gpt-6-sol":{"draws":3,"losses":15,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":23,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":45},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":39},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":35},"meta/muse-spark-open":{"draws":4,"losses":2,"wins":40},"meta/muse-wonder":{"draws":8,"losses":7,"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":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":19,"wins":22},"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":6,"losses":0,"wins":36},"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":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":9,"losses":1,"wins":22},"qwen/qwen3.8-max":{"draws":7,"losses":2,"wins":39},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":37},"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":9,"wins":130},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":33},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":1,"wins":38},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":56},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":9},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":35},"x-ai/grok-4.6":{"draws":7,"losses":6,"wins":35},"x-ai/grok-4.7":{"draws":5,"losses":9,"wins":28},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":13,"losses":7,"wins":76},"z-ai/glm-5.3":{"draws":10,"losses":4,"wins":32},"z-ai/glm-5.3-flash":{"draws":7,"losses":5,"wins":36},"z-ai/glm-5.3-flashx":{"draws":10,"losses":3,"wins":35}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":16},"claude-fable-5":{"draws":12,"losses":31,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":20,"wins":9},"claude-opus-4-5":{"draws":30,"losses":25,"wins":23},"claude-opus-4-8":{"draws":17,"losses":22,"wins":5},"claude-opus-5":{"draws":17,"losses":60,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":12,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":24,"losses":19,"wins":29},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":21,"wins":8},"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":22,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":21,"wins":9},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":22,"losses":23,"wins":15},"google/gemini-3.5-flash-lite":{"draws":40,"losses":15,"wins":29},"google/gemini-3.6-flash":{"draws":37,"losses":40,"wins":15},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":3,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":13,"wins":12},"gpt-5.4":{"draws":17,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":18,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":21,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":10,"losses":10,"wins":12},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inception/mercury-3":{"draws":10,"losses":12,"wins":10},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":12,"wins":20},"meta/muse-glimmer-30b":{"draws":21,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":5},"meta/muse-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":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":41,"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":23,"losses":5,"wins":14},"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":23,"losses":9,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":12},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":21,"losses":12,"wins":15},"unbiased/pareto-26.10":{"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":35,"losses":6,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":38,"losses":23,"wins":35},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":11}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":10,"losses":20,"wins":18},"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":10,"wins":53},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":11,"losses":59,"wins":12},"claude-opus-5-5":{"draws":2,"losses":42,"wins":8},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":21,"wins":19},"elorian/glimpse":{"draws":4,"losses":6,"wins":16},"fireworks/ember-1":{"draws":11,"losses":12,"wins":25},"gemini-3.1-pro-preview":{"draws":9,"losses":13,"wins":26},"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":11,"losses":15,"wins":34},"google/gemini-3.5-flash-lite":{"draws":12,"losses":9,"wins":63},"google/gemini-3.6-flash":{"draws":17,"losses":26,"wins":49},"google/gemini-3.8-flash":{"draws":9,"losses":18,"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":7,"losses":8,"wins":27},"gpt-5.4":{"draws":5,"losses":9,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":5,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":22,"wins":21},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":29},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":6,"wins":33},"gpt-6-sol":{"draws":4,"losses":20,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":10,"wins":28},"meta/muse-spark-open":{"draws":7,"losses":8,"wins":31},"meta/muse-wonder":{"draws":12,"losses":21,"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":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":5},"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":1,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":15},"o3":{"draws":4,"losses":4,"wins":58},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":10,"losses":3,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":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":25,"losses":33,"wins":100},"stealth/space-bunny-alpha":{"draws":9,"losses":4,"wins":25},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":27},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":1,"wins":17},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":33},"unbiased/pareto-26.10":{"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":13,"wins":23},"x-ai/grok-4.6":{"draws":11,"losses":17,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":22,"losses":15,"wins":59},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":7,"losses":22,"wins":19}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":32},"claude-fable-5":{"draws":4,"losses":18,"wins":26},"claude-fable-5-1":{"draws":4,"losses":36,"wins":14},"claude-haiku-5-5":{"draws":8,"losses":4,"wins":34},"claude-opus-4-5":{"draws":18,"losses":9,"wins":51},"claude-opus-4-8":{"draws":4,"losses":8,"wins":32},"claude-opus-5":{"draws":13,"losses":35,"wins":34},"claude-opus-5-5":{"draws":10,"losses":25,"wins":17},"claude-sonnet-5":{"draws":5,"losses":7,"wins":36},"claude-sonnet-5-5":{"draws":1,"losses":17,"wins":30},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":61},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":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":9,"losses":7,"wins":32},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"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":6,"losses":9,"wins":45},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":69},"google/gemini-3.8-flash":{"draws":12,"losses":8,"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":4,"wins":33},"gpt-5.4":{"draws":5,"losses":10,"wins":31},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":8,"losses":10,"wins":30},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":37},"gpt-6-astra":{"draws":5,"losses":35,"wins":8},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":1,"losses":23,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":31},"meta/muse-spark-1.3":{"draws":7,"losses":9,"wins":32},"meta/muse-spark-open":{"draws":7,"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":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":24,"wins":16},"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":8,"losses":4,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":18},"o3":{"draws":2,"losses":7,"wins":57},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":36},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":37},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":31},"qwen/qwen3.8-27b":{"draws":7,"losses":1,"wins":26},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":23},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":38},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"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":27,"losses":17,"wins":114},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":50},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"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":11,"losses":5,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":17},"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":6,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":4,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":15,"wins":24},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":34},"z-ai/glm-5.3-flashx":{"draws":12,"losses":8,"wins":28}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":10},"claude-fable-5":{"draws":8,"losses":17,"wins":5},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":3},"claude-opus-4-5":{"draws":23,"losses":20,"wins":5},"claude-opus-4-8":{"draws":11,"losses":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":15,"losses":12,"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":9,"losses":8,"wins":13},"gemini-4-argon":{"draws":3,"losses":27,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":10},"google/gemini-3.5-flash-lite":{"draws":19,"losses":11,"wins":24},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":8},"google/gemini-3.8-flash":{"draws":11,"losses":18,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":5},"gpt-5.4":{"draws":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":13,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":9,"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},"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},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":9},"meta/muse-spark-1.2":{"draws":11,"losses":11,"wins":6},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":4},"meta/muse-spark-open":{"draws":9,"losses":15,"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-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":1},"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":12,"losses":14,"wins":4},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":2},"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},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":12,"wins":3},"thinkingmachines/inkling":{"draws":17,"losses":5,"wins":18},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":10},"unbiased/pareto-26.10":{"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":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":20,"losses":15,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":23,"wins":9},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":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},"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":0,"losses":0,"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":30,"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":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":21,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":39,"wins":3},"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":15,"losses":12,"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":0,"losses":2,"wins":2},"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":6,"losses":12,"wins":8},"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":27,"losses":27,"wins":10},"claude-fable-5":{"draws":14,"losses":49,"wins":3},"claude-fable-5-1":{"draws":3,"losses":69,"wins":0},"claude-haiku-5-5":{"draws":21,"losses":37,"wins":4},"claude-opus-4-5":{"draws":35,"losses":64,"wins":7},"claude-opus-4-8":{"draws":19,"losses":39,"wins":0},"claude-opus-5":{"draws":17,"losses":89,"wins":6},"claude-opus-5-5":{"draws":5,"losses":73,"wins":0},"claude-sonnet-5":{"draws":24,"losses":38,"wins":4},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":3},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":45,"losses":33,"wins":24},"deepseek/deepseek-v4-pro":{"draws":24,"losses":24,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":29,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":28,"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":29,"losses":36,"wins":1},"gemini-3.1-pro-preview":{"draws":29,"losses":32,"wins":5},"gemini-4-argon":{"draws":6,"losses":58,"wins":2},"google/gemini-3.1-flash-lite":{"draws":18,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":26,"losses":51,"wins":5},"google/gemini-3.5-flash-lite":{"draws":45,"losses":47,"wins":22},"google/gemini-3.6-flash":{"draws":46,"losses":68,"wins":10},"google/gemini-3.8-flash":{"draws":21,"losses":44,"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":21,"losses":19,"wins":18},"gpt-5.4":{"draws":16,"losses":37,"wins":11},"gpt-5.4-mini":{"draws":21,"losses":17,"wins":6},"gpt-5.4-nano":{"draws":22,"losses":34,"wins":12},"gpt-5.5":{"draws":31,"losses":26,"wins":3},"gpt-5.6-luna":{"draws":37,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":1},"gpt-5.6-terra":{"draws":26,"losses":37,"wins":3},"gpt-6-astra":{"draws":3,"losses":62,"wins":1},"gpt-6-luna":{"draws":26,"losses":33,"wins":7},"gpt-6-sol":{"draws":10,"losses":50,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":63,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":13,"wins":8},"inception/mercury-3":{"draws":10,"losses":29,"wins":11},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":25,"wins":12},"meta/muse-glimmer-30b":{"draws":36,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":16,"losses":41,"wins":5},"meta/muse-spark-1.3":{"draws":15,"losses":47,"wins":4},"meta/muse-spark-open":{"draws":11,"losses":48,"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":16,"losses":14,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":23,"losses":33,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":53,"wins":0},"nex-agi/nex-n2-pro":{"draws":15,"losses":8,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":17,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":15,"wins":5},"o3":{"draws":25,"losses":53,"wins":10},"openai/gpt-oss-120b":{"draws":29,"losses":25,"wins":2},"poolside/laguna-s-2.1":{"draws":34,"losses":21,"wins":13},"qwen/qwen3.7-max":{"draws":22,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":39,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":9},"qwen/qwen3.8-flash":{"draws":18,"losses":25,"wins":1},"qwen/qwen3.8-max":{"draws":27,"losses":32,"wins":7},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"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":69,"losses":143,"wins":14},"stealth/space-bunny-alpha":{"draws":24,"losses":16,"wins":6},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":4},"tencent/hy4-preview":{"draws":29,"losses":33,"wins":2},"thinkingmachines/inkling":{"draws":31,"losses":36,"wins":17},"thinkingmachines/inkling-small":{"draws":33,"losses":18,"wins":15},"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":24,"losses":39,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":48,"wins":3},"x-ai/grok-build-0.1":{"draws":11,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":46,"losses":34,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":15,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":23,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":34,"wins":3},"z-ai/glm-5.2":{"draws":79,"losses":43,"wins":10},"z-ai/glm-5.3":{"draws":17,"losses":42,"wins":3},"z-ai/glm-5.3-flash":{"draws":23,"losses":33,"wins":10},"z-ai/glm-5.3-flashx":{"draws":25,"losses":35,"wins":6}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"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":0,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inception/mercury-3":{"draws":0,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":6,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":2},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":34,"wins":22},"claude-fable-5":{"draws":10,"losses":65,"wins":9},"claude-fable-5-1":{"draws":0,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":18,"losses":52,"wins":10},"claude-opus-4-5":{"draws":36,"losses":82,"wins":18},"claude-opus-4-8":{"draws":16,"losses":50,"wins":10},"claude-opus-5":{"draws":14,"losses":117,"wins":9},"claude-opus-5-5":{"draws":5,"losses":85,"wins":2},"claude-sonnet-5":{"draws":24,"losses":42,"wins":18},"claude-sonnet-5-5":{"draws":12,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":20},"deepseek/deepseek-v4-flash":{"draws":31,"losses":53,"wins":44},"deepseek/deepseek-v4-pro":{"draws":15,"losses":47,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":37,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":46,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":60,"wins":9},"elorian/glimpse":{"draws":6,"losses":30,"wins":10},"fireworks/ember-1":{"draws":26,"losses":48,"wins":10},"gemini-3.1-pro-preview":{"draws":24,"losses":39,"wins":21},"gemini-4-argon":{"draws":3,"losses":77,"wins":4},"google/gemini-3.1-flash-lite":{"draws":13,"losses":14,"wins":31},"google/gemini-3.5-flash":{"draws":17,"losses":68,"wins":21},"google/gemini-3.5-flash-lite":{"draws":45,"losses":69,"wins":34},"google/gemini-3.6-flash":{"draws":34,"losses":103,"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":6,"losses":17,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":13,"losses":41,"wins":22},"gpt-5.4":{"draws":19,"losses":53,"wins":10},"gpt-5.4-mini":{"draws":23,"losses":20,"wins":13},"gpt-5.4-nano":{"draws":13,"losses":46,"wins":29},"gpt-5.5":{"draws":29,"losses":36,"wins":13},"gpt-5.6-luna":{"draws":26,"losses":32,"wins":26},"gpt-5.6-sol":{"draws":9,"losses":69,"wins":6},"gpt-5.6-terra":{"draws":22,"losses":39,"wins":19},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":24,"losses":44,"wins":16},"gpt-6-sol":{"draws":7,"losses":69,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":76,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":16,"wins":19},"inception/mercury-3":{"draws":15,"losses":28,"wins":13},"inclusionai/ling-3.0-flash":{"draws":23,"losses":17,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":27,"wins":20},"meta/muse-glimmer-30b":{"draws":28,"losses":26,"wins":20},"meta/muse-spark-1.2":{"draws":15,"losses":54,"wins":11},"meta/muse-spark-1.3":{"draws":15,"losses":57,"wins":12},"meta/muse-spark-open":{"draws":16,"losses":57,"wins":9},"meta/muse-wonder":{"draws":20,"losses":54,"wins":10},"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":17,"losses":15,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":15,"wins":2},"moonshotai/kimi-k3":{"draws":24,"losses":41,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":69,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":15,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":26,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":23,"wins":5},"o3":{"draws":19,"losses":78,"wins":29},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":25},"poolside/laguna-s-2.1":{"draws":28,"losses":35,"wins":21},"qwen/qwen3.7-max":{"draws":15,"losses":22,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":19,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":50,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":37,"wins":10},"qwen/qwen3.8-flash":{"draws":16,"losses":27,"wins":13},"qwen/qwen3.8-max":{"draws":25,"losses":40,"wins":19},"qwen/qwen3.8-max-0902":{"draws":17,"losses":52,"wins":15},"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":57,"losses":183,"wins":42},"stealth/space-bunny-alpha":{"draws":21,"losses":35,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":22,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":22,"wins":13},"tencent/hy4-preview":{"draws":17,"losses":52,"wins":13},"thinkingmachines/inkling":{"draws":29,"losses":43,"wins":42},"thinkingmachines/inkling-small":{"draws":29,"losses":26,"wins":29},"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":22,"losses":52,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":64,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":10,"wins":10},"xiaomi/mimo-v2.5":{"draws":34,"losses":45,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":28,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":30,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":37,"wins":5},"z-ai/glm-5.2":{"draws":51,"losses":78,"wins":39},"z-ai/glm-5.3":{"draws":12,"losses":63,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":51,"wins":19},"z-ai/glm-5.3-flashx":{"draws":14,"losses":58,"wins":12}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":6},"claude-fable-5":{"draws":8,"losses":25,"wins":3},"claude-fable-5-1":{"draws":1,"losses":41,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":23,"wins":3},"claude-opus-4-5":{"draws":18,"losses":35,"wins":5},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":2,"losses":58,"wins":8},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":10,"losses":22,"wins":4},"claude-sonnet-5-5":{"draws":4,"losses":28,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":19,"losses":19,"wins":14},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":2},"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":8,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":12,"losses":29,"wins":5},"google/gemini-3.5-flash-lite":{"draws":21,"losses":27,"wins":16},"google/gemini-3.6-flash":{"draws":20,"losses":42,"wins":8},"google/gemini-3.8-flash":{"draws":10,"losses":21,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":10,"losses":17,"wins":7},"gpt-5.4":{"draws":8,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":11,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":15,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":13,"losses":12,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":4},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":12,"losses":19,"wins":5},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":6},"inception/mercury-3":{"draws":6,"losses":12,"wins":4},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":18,"wins":12},"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":8,"losses":25,"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":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":21,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":27,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":4},"o3":{"draws":8,"losses":31,"wins":13},"openai/gpt-oss-120b":{"draws":10,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":12,"losses":16,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":20,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"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":26,"losses":84,"wins":16},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":13,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":2},"thinkingmachines/inkling":{"draws":16,"losses":19,"wins":17},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"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":2,"wins":3},"x-ai/grok-4.5":{"draws":8,"losses":24,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":0},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":23,"losses":17,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":32,"losses":27,"wins":13},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":3},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":5}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":5,"losses":37,"wins":6},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":30,"wins":6},"claude-opus-4-5":{"draws":23,"losses":32,"wins":23},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":9,"losses":63,"wins":10},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":19,"wins":14},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":21,"wins":30},"deepseek/deepseek-v4-pro":{"draws":9,"losses":21,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":22,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":26,"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":22,"wins":13},"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":14,"losses":30,"wins":16},"google/gemini-3.5-flash-lite":{"draws":26,"losses":23,"wins":35},"google/gemini-3.6-flash":{"draws":24,"losses":50,"wins":18},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":18,"wins":15},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":10,"losses":23,"wins":11},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":20,"wins":13},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":18,"wins":22},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":6,"losses":18,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":26,"wins":10},"meta/muse-spark-open":{"draws":11,"losses":28,"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":11,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":22,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":2},"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":15,"losses":8,"wins":19},"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":18,"wins":6},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"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":37,"losses":86,"wins":35},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":15,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":7,"losses":26,"wins":13},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":21},"unbiased/pareto-26.10":{"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":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":30,"losses":32,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":9},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":10,"wins":17},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":29,"losses":30,"wins":19},"claude-opus-4-8":{"draws":13,"losses":26,"wins":5},"claude-opus-5":{"draws":12,"losses":64,"wins":6},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":19,"losses":17,"wins":12},"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":23,"losses":17,"wins":32},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":21,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":32,"wins":11},"elorian/glimpse":{"draws":6,"losses":13,"wins":7},"fireworks/ember-1":{"draws":18,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":15},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":27,"wins":16},"google/gemini-3.5-flash-lite":{"draws":24,"losses":23,"wins":37},"google/gemini-3.6-flash":{"draws":19,"losses":50,"wins":23},"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":8,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":20,"wins":13},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":18},"gpt-5.5":{"draws":17,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":21,"losses":15,"wins":12},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":15,"losses":22,"wins":9},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":8,"losses":39,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":2,"wins":15},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":12,"wins":23},"meta/muse-glimmer-30b":{"draws":22,"losses":9,"wins":11},"meta/muse-spark-1.2":{"draws":13,"losses":25,"wins":8},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":2},"meta/muse-spark-open":{"draws":10,"losses":31,"wins":5},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"minimax/minimax-m3.1-flash":{"draws":6,"losses":15,"wins":21},"mistralai/mistral-large-4-0":{"draws":12,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":24,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":41,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"o3":{"draws":11,"losses":33,"wins":22},"openai/gpt-oss-120b":{"draws":17,"losses":6,"wins":19},"poolside/laguna-s-2.1":{"draws":16,"losses":17,"wins":13},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":19,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":20,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":25,"wins":5},"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":39,"losses":85,"wins":34},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":5},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":21,"losses":10,"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":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":32,"wins":6},"x-ai/grok-4.6":{"draws":15,"losses":25,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":33,"losses":14,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":6},"z-ai/glm-5.2":{"draws":30,"losses":37,"wins":29},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":10,"losses":34,"wins":4},"z-ai/glm-5.3-flashx":{"draws":13,"losses":27,"wins":8}},"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":51},"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},"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":0,"losses":0,"wins":2},"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":2,"wins":8},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":0},"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":8,"wins":25},"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":0,"losses":2,"wins":2},"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":4,"losses":7,"wins":15},"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":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":4,"losses":39,"wins":11},"claude-haiku-5-5":{"draws":16,"losses":12,"wins":18},"claude-opus-4-5":{"draws":27,"losses":17,"wins":34},"claude-opus-4-8":{"draws":12,"losses":19,"wins":13},"claude-opus-5":{"draws":11,"losses":54,"wins":17},"claude-opus-5-5":{"draws":0,"losses":43,"wins":9},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":16},"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":11,"losses":11,"wins":26},"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":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":27,"losses":30,"wins":35},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":14},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":18,"losses":12,"wins":14},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":14},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":18,"losses":14,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":21},"inception/mercury-3":{"draws":11,"losses":11,"wins":9},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":32},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":16},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-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":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":32,"wins":8},"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":21,"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":11,"losses":0,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":4,"wins":17},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":17,"losses":12,"wins":19},"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":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":13},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":7,"wins":32},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":15,"wins":18},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":7,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":24,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":11,"losses":21,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":18,"wins":16}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":20,"wins":8},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":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":56,"wins":4},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":8,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":4,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":14,"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":6,"losses":22,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":16,"wins":29},"google/gemini-3.6-flash":{"draws":10,"losses":43,"wins":15},"google/gemini-3.8-flash":{"draws":4,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":2,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":7,"losses":16,"wins":11},"gpt-5.4":{"draws":4,"losses":17,"wins":13},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":19},"gpt-5.5":{"draws":8,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":18,"wins":10},"gpt-6-astra":{"draws":0,"losses":34,"wins":2},"gpt-6-luna":{"draws":9,"losses":18,"wins":9},"gpt-6-sol":{"draws":2,"losses":29,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":32,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":11},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":11,"wins":18},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":4,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":25,"wins":3},"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":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":23,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":32,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":19},"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":8,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":11},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":25,"wins":4},"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":65,"wins":30},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":25},"thinkingmachines/inkling-small":{"draws":8,"losses":7,"wins":21},"unbiased/pareto-26.10":{"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":27,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":10,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":17,"losses":25,"wins":30},"z-ai/glm-5.3":{"draws":5,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":10}},"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},"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},"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":12,"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":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":34,"wins":1},"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":13,"losses":7,"wins":14},"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},"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":4,"losses":12,"wins":6},"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":10,"losses":24,"wins":8},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":7},"claude-opus-4-5":{"draws":24,"losses":31,"wins":13},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":62,"wins":7},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":14,"losses":20,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":17,"wins":7},"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":19,"losses":20,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":15,"wins":22},"google/gemini-3.6-flash":{"draws":27,"losses":42,"wins":11},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":7},"gpt-4.1":{"draws":6,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":10,"wins":9},"gpt-5.4":{"draws":15,"losses":22,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":17},"gpt-5.5":{"draws":19,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":5},"gpt-5.6-terra":{"draws":21,"losses":10,"wins":9},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":6,"losses":31,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":8},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":13},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":9,"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-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":1},"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":16,"losses":9,"wins":11},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":19},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":14},"unbiased/pareto-26.10":{"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":7,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":7},"z-ai/glm-5.2":{"draws":42,"losses":19,"wins":23},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":15,"losses":18,"wins":9}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":8},"claude-fable-5":{"draws":7,"losses":33,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":23,"losses":43,"wins":2},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":11,"losses":57,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":13,"losses":27,"wins":2},"claude-sonnet-5-5":{"draws":7,"losses":32,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":28,"losses":25,"wins":9},"deepseek/deepseek-v4-pro":{"draws":9,"losses":25,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":23,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":23,"wins":3},"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":7,"losses":8,"wins":11},"google/gemini-3.5-flash":{"draws":14,"losses":34,"wins":4},"google/gemini-3.5-flash-lite":{"draws":22,"losses":37,"wins":15},"google/gemini-3.6-flash":{"draws":28,"losses":46,"wins":6},"google/gemini-3.8-flash":{"draws":8,"losses":32,"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":10,"losses":18,"wins":8},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":14,"losses":11,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":27,"wins":5},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":35,"wins":3},"gpt-5.6-terra":{"draws":12,"losses":25,"wins":3},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":25,"wins":2},"gpt-6-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":10,"wins":5},"inception/mercury-3":{"draws":8,"losses":18,"wins":2},"inclusionai/ling-3.0-flash":{"draws":15,"losses":7,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":19,"wins":11},"meta/muse-glimmer-30b":{"draws":17,"losses":14,"wins":5},"meta/muse-spark-1.2":{"draws":9,"losses":28,"wins":3},"meta/muse-spark-1.3":{"draws":7,"losses":34,"wins":1},"meta/muse-spark-open":{"draws":7,"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":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":28,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":39,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":15,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":3},"o3":{"draws":11,"losses":38,"wins":5},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":3},"poolside/laguna-s-2.1":{"draws":17,"losses":18,"wins":7},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":30,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":19,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":18,"wins":2},"qwen/qwen3.8-max":{"draws":11,"losses":27,"wins":4},"qwen/qwen3.8-max-0902":{"draws":15,"losses":25,"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":32,"losses":94,"wins":14},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":12,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":3},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":2},"thinkingmachines/inkling":{"draws":21,"losses":27,"wins":8},"thinkingmachines/inkling-small":{"draws":18,"losses":14,"wins":10},"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":13,"losses":25,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":14,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":2},"z-ai/glm-5.2":{"draws":36,"losses":41,"wins":7},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":23,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":31,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":6,"losses":29,"wins":13},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":28,"losses":17,"wins":33},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"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":17,"wins":19},"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":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"gemini-4-argon":{"draws":0,"losses":42,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":17,"losses":22,"wins":21},"google/gemini-3.5-flash-lite":{"draws":26,"losses":17,"wins":41},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":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":26,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":18},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"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":0,"losses":0,"wins":2},"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":12,"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":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":38,"wins":4},"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":15,"losses":5,"wins":22},"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":8,"wins":23},"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":15,"wins":21},"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":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":30},"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":20,"wins":16},"x-ai/grok-4.6":{"draws":7,"losses":27,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":9},"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":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":19,"wins":40},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":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},"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":0,"losses":0,"wins":2},"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":36},"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":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":10,"wins":16},"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":37},"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":0,"wins":4},"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":1,"losses":3,"wins":22},"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":15,"losses":15,"wins":8},"claude-fable-5":{"draws":9,"losses":31,"wins":2},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":7},"claude-opus-4-5":{"draws":24,"losses":32,"wins":12},"claude-opus-4-8":{"draws":13,"losses":22,"wins":3},"claude-opus-5":{"draws":3,"losses":63,"wins":4},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":18,"losses":16,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":20,"losses":26,"wins":16},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":4},"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":10,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":17,"losses":21,"wins":14},"google/gemini-3.5-flash-lite":{"draws":27,"losses":20,"wins":27},"google/gemini-3.6-flash":{"draws":24,"losses":41,"wins":15},"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":5,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":13,"losses":11,"wins":12},"gpt-5.4":{"draws":12,"losses":16,"wins":12},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":11},"gpt-5.5":{"draws":17,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":19,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":7},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":6,"wins":8},"inception/mercury-3":{"draws":10,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":17,"wins":17},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":11,"losses":25,"wins":6},"meta/muse-spark-open":{"draws":9,"losses":23,"wins":8},"meta/muse-wonder":{"draws":12,"losses":27,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":9},"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":12,"losses":10,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":33,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":7},"o3":{"draws":9,"losses":30,"wins":17},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":14},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":12},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":17,"losses":23,"wins":2},"qwen/qwen3.8-max-0902":{"draws":17,"losses":18,"wins":7},"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":45,"losses":76,"wins":21},"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":17,"wins":17},"thinkingmachines/inkling-small":{"draws":18,"losses":12,"wins":12},"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":15,"losses":24,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":28,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":42,"losses":30,"wins":12},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":23,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":4}},"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},"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":0,"losses":0,"wins":2},"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":4,"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":4,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":21,"wins":0},"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":7,"losses":6,"wins":7},"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":0,"losses":3,"wins":1},"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":3,"losses":2,"wins":7},"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":13,"losses":14,"wins":13},"claude-fable-5":{"draws":8,"losses":28,"wins":6},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":12},"claude-opus-4-5":{"draws":19,"losses":38,"wins":11},"claude-opus-4-8":{"draws":6,"losses":22,"wins":10},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"claude-opus-5-5":{"draws":2,"losses":43,"wins":1},"claude-sonnet-5":{"draws":11,"losses":18,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":13,"losses":30,"wins":19},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":21,"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":10,"losses":21,"wins":11},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":11},"gemini-4-argon":{"draws":2,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":11,"wins":12},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":12},"google/gemini-3.5-flash-lite":{"draws":27,"losses":24,"wins":25},"google/gemini-3.6-flash":{"draws":20,"losses":47,"wins":15},"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":13,"losses":16,"wins":9},"gpt-5.4":{"draws":13,"losses":25,"wins":4},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":21,"wins":16},"gpt-5.5":{"draws":18,"losses":19,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":12,"wins":7},"inception/mercury-3":{"draws":4,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":24,"wins":11},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":10},"meta/muse-spark-1.3":{"draws":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":5,"losses":10,"wins":7},"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":10,"losses":6,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":6},"o3":{"draws":12,"losses":32,"wins":20},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":14},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":12,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":22,"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":28,"losses":88,"wins":26},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":17,"losses":19,"wins":22},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":14},"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":13,"losses":26,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":34,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":19,"losses":22,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":21,"wins":3},"z-ai/glm-5.2":{"draws":25,"losses":31,"wins":28},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":5,"losses":26,"wins":11},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":7}},"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},"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":0,"losses":2,"wins":0},"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-k2.7-code":{"draws":2,"losses":2,"wins":2},"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":4,"wins":8},"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":0,"losses":3,"wins":1},"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":4,"wins":4},"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":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":19,"wins":10},"claude-opus-4-5":{"draws":18,"losses":38,"wins":22},"claude-opus-4-8":{"draws":14,"losses":22,"wins":8},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":31,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":14,"wins":33},"deepseek/deepseek-v4-pro":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"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":13,"losses":19,"wins":16},"gemini-4-argon":{"draws":1,"losses":47,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":25,"wins":16},"google/gemini-3.5-flash-lite":{"draws":28,"losses":20,"wins":36},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":23},"google/gemini-3.8-flash":{"draws":16,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":11,"wins":13},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":20,"wins":16},"gpt-5.5":{"draws":13,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":2,"losses":44,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":15},"inception/mercury-3":{"draws":8,"losses":19,"wins":5},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":27},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":27,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":29,"wins":7},"meta/muse-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":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":45,"wins":1},"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":17,"losses":9,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":7},"o3":{"draws":10,"losses":22,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":26,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"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":44,"losses":82,"wins":32},"stealth/space-bunny-alpha":{"draws":13,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":20,"losses":14,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":20},"unbiased/pareto-26.10":{"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":25,"losses":20,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":27,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":27,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":14,"losses":25,"wins":9},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":14,"wins":8},"claude-fable-5":{"draws":7,"losses":26,"wins":3},"claude-fable-5-1":{"draws":1,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":21,"wins":5},"claude-opus-4-5":{"draws":19,"losses":34,"wins":5},"claude-opus-4-8":{"draws":9,"losses":22,"wins":1},"claude-opus-5":{"draws":6,"losses":58,"wins":4},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":20},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":23,"wins":6},"elorian/glimpse":{"draws":3,"losses":12,"wins":5},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":6},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":11,"losses":24,"wins":9},"google/gemini-3.5-flash-lite":{"draws":17,"losses":25,"wins":18},"google/gemini-3.6-flash":{"draws":20,"losses":39,"wins":9},"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":11,"losses":16,"wins":7},"gpt-5.4":{"draws":7,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":13},"gpt-5.5":{"draws":11,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":34,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":21,"wins":3},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":12,"losses":17,"wins":7},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":7},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":15,"wins":10},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":11},"meta/muse-spark-1.2":{"draws":7,"losses":28,"wins":1},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":4},"meta/muse-spark-open":{"draws":6,"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":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":28,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"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":6,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":17,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":19,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":4},"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":32,"losses":81,"wins":11},"stealth/space-bunny-alpha":{"draws":6,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":25,"wins":14},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":16},"unbiased/pareto-26.10":{"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":9,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":19,"losses":19,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":32,"losses":28,"wins":12},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":17,"wins":25},"claude-fable-5":{"draws":9,"losses":49,"wins":14},"claude-fable-5-1":{"draws":0,"losses":79,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":30,"wins":23},"claude-opus-4-5":{"draws":34,"losses":56,"wins":26},"claude-opus-4-8":{"draws":14,"losses":38,"wins":12},"claude-opus-5":{"draws":8,"losses":111,"wins":7},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":18,"losses":34,"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":33,"losses":31,"wins":48},"deepseek/deepseek-v4-pro":{"draws":13,"losses":27,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":30,"wins":23},"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":18,"losses":37,"wins":17},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"gemini-4-argon":{"draws":2,"losses":69,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":9,"wins":28},"google/gemini-3.5-flash":{"draws":14,"losses":56,"wins":20},"google/gemini-3.5-flash-lite":{"draws":27,"losses":34,"wins":63},"google/gemini-3.6-flash":{"draws":34,"losses":68,"wins":36},"google/gemini-3.8-flash":{"draws":12,"losses":49,"wins":11},"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":17,"losses":23,"wins":28},"gpt-5.4":{"draws":15,"losses":43,"wins":12},"gpt-5.4-mini":{"draws":18,"losses":15,"wins":15},"gpt-5.4-nano":{"draws":16,"losses":28,"wins":34},"gpt-5.5":{"draws":25,"losses":30,"wins":13},"gpt-5.6-luna":{"draws":21,"losses":23,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":33,"wins":12},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":20,"losses":25,"wins":27},"gpt-6-sol":{"draws":10,"losses":54,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":12,"wins":18},"inception/mercury-3":{"draws":11,"losses":27,"wins":12},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":22,"wins":35},"meta/muse-glimmer-30b":{"draws":23,"losses":19,"wins":24},"meta/muse-spark-1.2":{"draws":11,"losses":43,"wins":16},"meta/muse-spark-1.3":{"draws":9,"losses":44,"wins":19},"meta/muse-spark-open":{"draws":8,"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":13,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":19,"losses":31,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":56,"wins":4},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":14,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":17,"wins":11},"o3":{"draws":17,"losses":54,"wins":39},"openai/gpt-oss-120b":{"draws":19,"losses":14,"wins":33},"poolside/laguna-s-2.1":{"draws":18,"losses":15,"wins":21},"qwen/qwen3.7-max":{"draws":14,"losses":18,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":42,"wins":10},"qwen/qwen3.8-27b":{"draws":11,"losses":23,"wins":16},"qwen/qwen3.8-flash":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-max":{"draws":22,"losses":27,"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":51,"losses":135,"wins":62},"stealth/space-bunny-alpha":{"draws":13,"losses":22,"wins":21},"stepfun/step-3.7-flash":{"draws":15,"losses":15,"wins":26},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":35,"wins":15},"thinkingmachines/inkling":{"draws":22,"losses":29,"wins":49},"thinkingmachines/inkling-small":{"draws":22,"losses":12,"wins":38},"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":20,"losses":42,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":30,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":16,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":33,"wins":13},"z-ai/glm-5.2":{"draws":52,"losses":48,"wins":44},"z-ai/glm-5.3":{"draws":7,"losses":52,"wins":9},"z-ai/glm-5.3-flash":{"draws":15,"losses":38,"wins":19},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":17,"wins":10},"claude-fable-5":{"draws":6,"losses":31,"wins":5},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":19,"wins":8},"claude-opus-4-5":{"draws":21,"losses":34,"wins":13},"claude-opus-4-8":{"draws":11,"losses":18,"wins":9},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":13,"losses":18,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":20,"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":13,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":13},"gemini-4-argon":{"draws":0,"losses":40,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":16,"losses":22,"wins":34},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":19,"wins":9},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":15,"losses":14,"wins":9},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":16},"gpt-5.5":{"draws":14,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":22,"wins":5},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":11,"losses":16,"wins":15},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":10},"inception/mercury-3":{"draws":6,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":13,"wins":21},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":25,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":6},"meta/muse-wonder":{"draws":5,"losses":28,"wins":9},"minimax/minimax-m3":{"draws":8,"losses":3,"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":12,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":31,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":9,"wins":6},"o3":{"draws":10,"losses":34,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":16,"losses":13,"wins":15},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-max":{"draws":18,"losses":17,"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":31,"losses":81,"wins":28},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":17,"losses":11,"wins":28},"thinkingmachines/inkling-small":{"draws":12,"losses":10,"wins":20},"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":13,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":14,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":30,"losses":27,"wins":27},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":7},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":5,"losses":35,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":28,"wins":1},"claude-opus-4-5":{"draws":25,"losses":28,"wins":7},"claude-opus-4-8":{"draws":8,"losses":25,"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":12,"losses":22,"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":18,"losses":36,"wins":10},"google/gemini-3.6-flash":{"draws":23,"losses":44,"wins":3},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":6},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":20,"wins":2},"gpt-5.4":{"draws":6,"losses":27,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":22,"wins":8},"gpt-5.5":{"draws":11,"losses":19,"wins":2},"gpt-5.6-luna":{"draws":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},"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},"meituan/longcat-2.0":{"draws":8,"losses":22,"wins":8},"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":8,"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":9,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"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":16,"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":18,"wins":2},"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},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":5},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":9},"thinkingmachines/inkling-small":{"draws":15,"losses":18,"wins":3},"unbiased/pareto-26.10":{"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":24,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":16,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":42,"wins":8},"z-ai/glm-5.3":{"draws":8,"losses":23,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":20},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":14},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":14,"losses":18,"wins":12},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"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":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":22,"wins":16},"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":12,"losses":17,"wins":19},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":18,"losses":19,"wins":23},"google/gemini-3.5-flash-lite":{"draws":28,"losses":16,"wins":40},"google/gemini-3.6-flash":{"draws":21,"losses":45,"wins":26},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":13},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":13,"wins":19},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":25},"gpt-5.5":{"draws":12,"losses":18,"wins":14},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":8},"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},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":22},"meta/muse-spark-1.3":{"draws":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":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":19,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":40,"wins":1},"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":14,"losses":4,"wins":24},"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":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":7},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":25,"wins":12},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"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":67,"wins":54},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":29},"unbiased/pareto-26.10":{"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":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":6,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":30,"losses":26,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":25,"wins":11}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":8},"claude-fable-5":{"draws":5,"losses":17,"wins":2},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":19,"wins":2},"claude-opus-4-8":{"draws":5,"losses":12,"wins":3},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":6,"losses":13,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":10,"wins":2},"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":9,"wins":7},"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":4,"losses":20,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":18,"wins":12},"google/gemini-3.6-flash":{"draws":14,"losses":26,"wins":6},"google/gemini-3.8-flash":{"draws":7,"losses":17,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":8,"wins":5},"gpt-5.4":{"draws":7,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":4},"gpt-5.5":{"draws":8,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":9,"losses":11,"wins":4},"gpt-6-sol":{"draws":7,"losses":16,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":21,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":8},"inception/mercury-3":{"draws":8,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":8},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":15,"wins":1},"meta/muse-spark-open":{"draws":4,"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-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":18,"wins":0},"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":9,"losses":8,"wins":3},"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":9,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":2},"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":15,"losses":14,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":20,"losses":22,"wins":6},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":2}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":31,"wins":2},"claude-opus-4-5":{"draws":31,"losses":40,"wins":7},"claude-opus-4-8":{"draws":12,"losses":30,"wins":2},"claude-opus-5":{"draws":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":23,"losses":24,"wins":25},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":32,"wins":8},"elorian/glimpse":{"draws":7,"losses":15,"wins":4},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":15,"losses":37,"wins":8},"google/gemini-3.5-flash-lite":{"draws":28,"losses":26,"wins":30},"google/gemini-3.6-flash":{"draws":33,"losses":53,"wins":6},"google/gemini-3.8-flash":{"draws":10,"losses":37,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":26,"wins":9},"gpt-5.4":{"draws":8,"losses":28,"wins":10},"gpt-5.4-mini":{"draws":13,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":17},"gpt-5.5":{"draws":18,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":22,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":25,"wins":10},"gpt-6-astra":{"draws":6,"losses":42,"wins":0},"gpt-6-luna":{"draws":14,"losses":25,"wins":9},"gpt-6-sol":{"draws":3,"losses":40,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":6,"wins":12},"inception/mercury-3":{"draws":8,"losses":17,"wins":7},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":17},"meta/muse-glimmer-30b":{"draws":21,"losses":12,"wins":9},"meta/muse-spark-1.2":{"draws":12,"losses":27,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":32,"wins":6},"meta/muse-spark-open":{"draws":9,"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":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":41,"wins":1},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":11,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":15,"losses":35,"wins":16},"openai/gpt-oss-120b":{"draws":12,"losses":17,"wins":13},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":28,"wins":4},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":0},"qwen/qwen3.8-max":{"draws":18,"losses":24,"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":43,"losses":89,"wins":26},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":30,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":18,"wins":23},"thinkingmachines/inkling-small":{"draws":19,"losses":14,"wins":15},"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":17,"losses":28,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":30,"losses":27,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":37,"losses":43,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":28,"wins":6},"z-ai/glm-5.3-flashx":{"draws":18,"losses":26,"wins":4}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":10,"losses":23,"wins":15},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":26,"losses":31,"wins":21},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":19,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":32,"losses":11,"wins":29},"deepseek/deepseek-v4-pro":{"draws":13,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":24,"wins":15},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":15,"losses":16,"wins":17},"gemini-4-argon":{"draws":3,"losses":39,"wins":6},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":24,"losses":16,"wins":20},"google/gemini-3.5-flash-lite":{"draws":32,"losses":21,"wins":31},"google/gemini-3.6-flash":{"draws":24,"losses":36,"wins":32},"google/gemini-3.8-flash":{"draws":10,"losses":20,"wins":18},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":15,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":15,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":31,"wins":9},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":13,"losses":19,"wins":16},"gpt-6-sol":{"draws":5,"losses":29,"wins":14},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":5,"wins":14},"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":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":24,"losses":8,"wins":20},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":12,"losses":18,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":20,"wins":16},"meta/muse-spark-open":{"draws":12,"losses":24,"wins":10},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"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":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":16,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":34,"wins":9},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":9},"o3":{"draws":16,"losses":20,"wins":30},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":17,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"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":49,"losses":67,"wins":42},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":14,"wins":17},"unbiased/pareto-26.10":{"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":20,"wins":16},"x-ai/grok-4.6":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":25,"losses":18,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":35,"losses":24,"wins":37},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":9,"losses":23,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":5,"wins":19},"claude-fable-5":{"draws":12,"losses":29,"wins":7},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":29,"losses":26,"wins":23},"claude-opus-4-8":{"draws":16,"losses":13,"wins":15},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":14,"wins":17},"claude-sonnet-5-5":{"draws":14,"losses":22,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":26,"losses":10,"wins":36},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":28,"wins":11},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":17,"losses":12,"wins":19},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":18},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":20,"losses":16,"wins":24},"google/gemini-3.5-flash-lite":{"draws":31,"losses":9,"wins":44},"google/gemini-3.6-flash":{"draws":36,"losses":31,"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":8,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":11,"wins":16},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":23},"gpt-5.5":{"draws":22,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":22,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":15,"wins":14},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":19,"losses":16,"wins":13},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":6,"wins":11},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":32},"meta/muse-glimmer-30b":{"draws":18,"losses":3,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":11,"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":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":9,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":2,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":9},"o3":{"draws":16,"losses":21,"wins":29},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"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":17,"losses":17,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":15,"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":42,"losses":61,"wins":55},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":21,"losses":2,"wins":25},"unbiased/pareto-26.10":{"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":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":33,"losses":9,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":45,"losses":16,"wins":35},"z-ai/glm-5.3":{"draws":15,"losses":25,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":17},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"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},"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":12,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":8},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"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":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":1},"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":13,"losses":6,"wins":17},"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":0,"losses":2,"wins":2},"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":7,"losses":6,"wins":9},"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":53,"losses":36,"wins":67},"claude-fable-5":{"draws":34,"losses":109,"wins":25},"claude-fable-5-1":{"draws":6,"losses":188,"wins":2},"claude-haiku-5-5":{"draws":48,"losses":71,"wins":33},"claude-opus-4-5":{"draws":99,"losses":90,"wins":75},"claude-opus-4-8":{"draws":34,"losses":70,"wins":32},"claude-opus-5":{"draws":47,"losses":223,"wins":24},"claude-opus-5-5":{"draws":18,"losses":157,"wins":1},"claude-sonnet-5":{"draws":53,"losses":60,"wins":55},"claude-sonnet-5-5":{"draws":37,"losses":90,"wins":41},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":34},"deepseek/deepseek-v4-flash":{"draws":94,"losses":62,"wins":90},"deepseek/deepseek-v4-pro":{"draws":58,"losses":53,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":50,"losses":67,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":51,"losses":77,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":37,"losses":92,"wins":39},"elorian/glimpse":{"draws":35,"losses":41,"wins":18},"fireworks/ember-1":{"draws":58,"losses":77,"wins":33},"gemini-3.1-pro-preview":{"draws":51,"losses":60,"wins":57},"gemini-4-argon":{"draws":13,"losses":147,"wins":8},"google/gemini-3.1-flash-lite":{"draws":27,"losses":8,"wins":57},"google/gemini-3.5-flash":{"draws":45,"losses":100,"wins":57},"google/gemini-3.5-flash-lite":{"draws":94,"losses":77,"wins":121},"google/gemini-3.6-flash":{"draws":88,"losses":158,"wins":80},"google/gemini-3.8-flash":{"draws":45,"losses":95,"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":53,"losses":56,"wins":41},"gpt-5.4":{"draws":57,"losses":77,"wins":28},"gpt-5.4-mini":{"draws":47,"losses":33,"wins":32},"gpt-5.4-nano":{"draws":42,"losses":51,"wins":53},"gpt-5.5":{"draws":61,"losses":60,"wins":35},"gpt-5.6-luna":{"draws":71,"losses":48,"wins":49},"gpt-5.6-sol":{"draws":32,"losses":113,"wins":23},"gpt-5.6-terra":{"draws":70,"losses":51,"wins":41},"gpt-6-astra":{"draws":11,"losses":156,"wins":1},"gpt-6-luna":{"draws":54,"losses":69,"wins":45},"gpt-6-sol":{"draws":20,"losses":134,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":152,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":48,"losses":13,"wins":47},"inception/mercury-3":{"draws":42,"losses":45,"wins":23},"inclusionai/ling-3.0-flash":{"draws":55,"losses":16,"wins":45},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":63,"losses":35,"wins":80},"meta/muse-glimmer-30b":{"draws":58,"losses":28,"wins":64},"meta/muse-spark-1.2":{"draws":52,"losses":65,"wins":45},"meta/muse-spark-1.3":{"draws":37,"losses":102,"wins":29},"meta/muse-spark-open":{"draws":42,"losses":87,"wins":33},"meta/muse-wonder":{"draws":44,"losses":101,"wins":23},"minimax/minimax-m3":{"draws":24,"losses":19,"wins":41},"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":39,"losses":15,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":10},"moonshotai/kimi-k3":{"draws":52,"losses":65,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":133,"wins":5},"nex-agi/nex-n2-pro":{"draws":33,"losses":11,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":14,"losses":10,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":24,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":27,"losses":24,"wins":21},"o3":{"draws":49,"losses":90,"wins":69},"openai/gpt-oss-120b":{"draws":64,"losses":28,"wins":58},"poolside/laguna-s-2.1":{"draws":66,"losses":42,"wins":62},"qwen/qwen3.7-max":{"draws":33,"losses":26,"wins":31},"qwen/qwen3.7-plus":{"draws":22,"losses":13,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":57,"losses":72,"wins":39},"qwen/qwen3.8-27b":{"draws":43,"losses":45,"wins":32},"qwen/qwen3.8-flash":{"draws":46,"losses":44,"wins":22},"qwen/qwen3.8-max":{"draws":54,"losses":76,"wins":38},"qwen/qwen3.8-max-0902":{"draws":54,"losses":74,"wins":40},"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":302,"wins":165},"stealth/space-bunny-alpha":{"draws":53,"losses":38,"wins":39},"stepfun/step-3.7-flash":{"draws":36,"losses":22,"wins":60},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":33,"losses":22,"wins":29},"tencent/hy4-preview":{"draws":49,"losses":81,"wins":32},"thinkingmachines/inkling":{"draws":88,"losses":52,"wins":96},"thinkingmachines/inkling-small":{"draws":70,"losses":29,"wins":69},"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":64,"losses":74,"wins":30},"x-ai/grok-4.7":{"draws":19,"losses":106,"wins":15},"x-ai/grok-build-0.1":{"draws":20,"losses":12,"wins":24},"xiaomi/mimo-v2.5":{"draws":87,"losses":47,"wins":88},"xiaomi/mimo-v2.5-pro":{"draws":32,"losses":28,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":26,"losses":54,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":64,"wins":22},"z-ai/glm-5.2":{"draws":135,"losses":97,"wins":104},"z-ai/glm-5.3":{"draws":34,"losses":107,"wins":21},"z-ai/glm-5.3-flash":{"draws":32,"losses":94,"wins":42},"z-ai/glm-5.3-flashx":{"draws":42,"losses":95,"wins":31}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":12,"losses":20,"wins":4},"claude-fable-5-1":{"draws":2,"losses":39,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":4},"claude-opus-4-5":{"draws":19,"losses":29,"wins":10},"claude-opus-4-8":{"draws":11,"losses":16,"wins":5},"claude-opus-5":{"draws":10,"losses":55,"wins":3},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":24,"losses":13,"wins":15},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":14,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":4},"fireworks/ember-1":{"draws":12,"losses":18,"wins":6},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":6},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":8},"google/gemini-3.5-flash-lite":{"draws":26,"losses":16,"wins":20},"google/gemini-3.6-flash":{"draws":20,"losses":41,"wins":7},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":5},"gpt-4.1":{"draws":5,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":12,"wins":7},"gpt-5.4":{"draws":15,"losses":13,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":12},"gpt-5.5":{"draws":20,"losses":13,"wins":1},"gpt-5.6-luna":{"draws":19,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":9},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":6},"gpt-6-sol":{"draws":6,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":8},"inception/mercury-3":{"draws":7,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":2},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":15},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":2},"meta/muse-spark-open":{"draws":9,"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":12,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":32,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":1,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":0,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":8,"wins":4},"o3":{"draws":12,"losses":25,"wins":7},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":11},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":5},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":2},"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":46,"losses":67,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":15},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":8},"unbiased/pareto-26.10":{"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":16,"losses":16,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":19,"wins":3},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":6}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":11,"losses":24,"wins":1},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":22,"wins":4},"claude-opus-4-5":{"draws":18,"losses":25,"wins":15},"claude-opus-4-8":{"draws":11,"losses":18,"wins":3},"claude-opus-5":{"draws":11,"losses":43,"wins":4},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":14,"losses":9,"wins":13},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":12,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":16,"wins":8},"elorian/glimpse":{"draws":5,"losses":9,"wins":6},"fireworks/ember-1":{"draws":14,"losses":15,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":11,"wins":8},"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":12,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":23,"losses":37,"wins":10},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":8},"gpt-4.1":{"draws":6,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":11,"wins":9},"gpt-5.4":{"draws":12,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":9},"gpt-5.5":{"draws":14,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":9},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":8},"gpt-6-astra":{"draws":6,"losses":30,"wins":0},"gpt-6-luna":{"draws":13,"losses":16,"wins":7},"gpt-6-sol":{"draws":9,"losses":24,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":14},"inception/mercury-3":{"draws":11,"losses":10,"wins":3},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":18},"meta/muse-glimmer-30b":{"draws":13,"losses":11,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":10,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":4},"meta/muse-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":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":31,"wins":0},"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":12,"losses":3,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":1},"o3":{"draws":11,"losses":20,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":23,"wins":2},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":9},"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":3,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":12},"unbiased/pareto-26.10":{"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":3,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":19},"z-ai/glm-5.3":{"draws":10,"losses":23,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":10},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":0},"fireworks/ember-1":{"draws":3,"losses":3,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":0,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inception/mercury-3":{"draws":0,"losses":5,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":6,"wins":0},"meta/muse-wonder":{"draws":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":1},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":8,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":2,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":2,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":1},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":9},"claude-fable-5":{"draws":10,"losses":20,"wins":6},"claude-fable-5-1":{"draws":5,"losses":32,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":13,"wins":7},"claude-opus-4-5":{"draws":23,"losses":23,"wins":12},"claude-opus-4-8":{"draws":10,"losses":16,"wins":6},"claude-opus-5":{"draws":13,"losses":50,"wins":9},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":17},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":10,"wins":6},"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":15,"losses":15,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":8},"gemini-4-argon":{"draws":1,"losses":33,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":10,"wins":24},"google/gemini-3.6-flash":{"draws":25,"losses":28,"wins":15},"google/gemini-3.8-flash":{"draws":17,"losses":16,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":11,"losses":10,"wins":11},"gpt-5.4":{"draws":17,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":16},"gpt-5.5":{"draws":16,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":6},"gpt-6-astra":{"draws":7,"losses":29,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":8},"gpt-6-sol":{"draws":10,"losses":24,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":5},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":6},"meta/muse-spark-open":{"draws":9,"losses":16,"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":10,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":26,"wins":2},"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":20,"losses":6,"wins":6},"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":16,"losses":12,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":6},"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":36,"losses":67,"wins":21},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling-small":{"draws":19,"losses":5,"wins":12},"unbiased/pareto-26.10":{"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":5,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":12,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":31,"losses":23,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":21,"wins":15},"claude-opus-4-5":{"draws":29,"losses":30,"wins":19},"claude-opus-4-8":{"draws":11,"losses":22,"wins":11},"claude-opus-5":{"draws":12,"losses":61,"wins":9},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":33},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":5,"losses":14,"wins":7},"fireworks/ember-1":{"draws":20,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"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":15,"losses":26,"wins":19},"google/gemini-3.5-flash-lite":{"draws":25,"losses":26,"wins":33},"google/gemini-3.6-flash":{"draws":28,"losses":41,"wins":23},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":10},"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":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":17,"wins":13},"gpt-5.4":{"draws":12,"losses":25,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":21},"gpt-5.5":{"draws":20,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":19,"losses":17,"wins":12},"gpt-6-sol":{"draws":9,"losses":36,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":10,"wins":27},"meta/muse-glimmer-30b":{"draws":20,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":25,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":26,"wins":11},"meta/muse-spark-open":{"draws":9,"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":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":16,"losses":17,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":7,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":11,"losses":34,"wins":21},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":20},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":13,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-max-0902":{"draws":16,"losses":22,"wins":10},"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":35,"losses":75,"wins":48},"stealth/space-bunny-alpha":{"draws":14,"losses":14,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":15,"wins":31},"thinkingmachines/inkling-small":{"draws":18,"losses":9,"wins":21},"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":17,"losses":24,"wins":7},"x-ai/grok-4.6":{"draws":17,"losses":25,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":12,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":31,"losses":28,"wins":37},"z-ai/glm-5.3":{"draws":9,"losses":30,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":13},"z-ai/glm-5.3-flashx":{"draws":14,"losses":22,"wins":12}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":22,"wins":19},"claude-fable-5":{"draws":16,"losses":49,"wins":7},"claude-fable-5-1":{"draws":5,"losses":77,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":43,"wins":12},"claude-opus-4-5":{"draws":40,"losses":52,"wins":24},"claude-opus-4-8":{"draws":18,"losses":37,"wins":9},"claude-opus-5":{"draws":17,"losses":98,"wins":15},"claude-opus-5-5":{"draws":6,"losses":70,"wins":0},"claude-sonnet-5":{"draws":24,"losses":34,"wins":14},"claude-sonnet-5-5":{"draws":15,"losses":42,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":10},"deepseek/deepseek-v4-flash":{"draws":37,"losses":37,"wins":30},"deepseek/deepseek-v4-pro":{"draws":19,"losses":33,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":23,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":31,"wins":15},"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":35,"wins":13},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"gemini-4-argon":{"draws":5,"losses":62,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":17,"wins":19},"google/gemini-3.5-flash":{"draws":22,"losses":50,"wins":18},"google/gemini-3.5-flash-lite":{"draws":30,"losses":53,"wins":45},"google/gemini-3.6-flash":{"draws":45,"losses":75,"wins":20},"google/gemini-3.8-flash":{"draws":13,"losses":49,"wins":10},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":10},"gpt-4.1":{"draws":5,"losses":10,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":34,"wins":16},"gpt-5.4":{"draws":19,"losses":40,"wins":11},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":15},"gpt-5.4-nano":{"draws":12,"losses":31,"wins":25},"gpt-5.5":{"draws":18,"losses":38,"wins":12},"gpt-5.6-luna":{"draws":24,"losses":30,"wins":18},"gpt-5.6-sol":{"draws":12,"losses":53,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":30,"wins":16},"gpt-6-astra":{"draws":3,"losses":68,"wins":1},"gpt-6-luna":{"draws":23,"losses":31,"wins":18},"gpt-6-sol":{"draws":13,"losses":56,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":65,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":14,"wins":15},"inception/mercury-3":{"draws":16,"losses":20,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":21,"losses":24,"wins":31},"meta/muse-glimmer-30b":{"draws":25,"losses":18,"wins":23},"meta/muse-spark-1.2":{"draws":19,"losses":31,"wins":20},"meta/muse-spark-1.3":{"draws":15,"losses":49,"wins":8},"meta/muse-spark-open":{"draws":15,"losses":41,"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":30,"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":3,"losses":10,"wins":5},"moonshotai/kimi-k3":{"draws":22,"losses":31,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":61,"wins":0},"nex-agi/nex-n2-pro":{"draws":10,"losses":7,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":22,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":8},"o3":{"draws":12,"losses":62,"wins":22},"openai/gpt-oss-120b":{"draws":16,"losses":23,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":28,"wins":23},"qwen/qwen3.7-max":{"draws":15,"losses":19,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":33,"wins":16},"qwen/qwen3.8-27b":{"draws":12,"losses":26,"wins":14},"qwen/qwen3.8-flash":{"draws":14,"losses":24,"wins":10},"qwen/qwen3.8-max":{"draws":26,"losses":31,"wins":15},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":12},"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":59,"losses":141,"wins":50},"stealth/space-bunny-alpha":{"draws":19,"losses":22,"wins":17},"stepfun/step-3.7-flash":{"draws":12,"losses":28,"wins":10},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":17,"wins":11},"tencent/hy4-preview":{"draws":24,"losses":37,"wins":9},"thinkingmachines/inkling":{"draws":30,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":26,"losses":21,"wins":25},"unbiased/pareto-26.10":{"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":34,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":50,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":43,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":23,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":29,"wins":5},"z-ai/glm-5.2":{"draws":51,"losses":55,"wins":38},"z-ai/glm-5.3":{"draws":15,"losses":44,"wins":9},"z-ai/glm-5.3-flash":{"draws":19,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":44,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":6,"losses":37,"wins":5},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":29,"wins":5},"claude-opus-4-5":{"draws":24,"losses":47,"wins":7},"claude-opus-4-8":{"draws":13,"losses":29,"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":17,"losses":24,"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":30,"losses":30,"wins":12},"deepseek/deepseek-v4-pro":{"draws":17,"losses":22,"wins":5},"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":15,"losses":29,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":26,"wins":6},"gemini-4-argon":{"draws":8,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.5-flash":{"draws":15,"losses":37,"wins":8},"google/gemini-3.5-flash-lite":{"draws":24,"losses":37,"wins":23},"google/gemini-3.6-flash":{"draws":25,"losses":50,"wins":17},"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":22,"losses":19,"wins":7},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":16,"losses":28,"wins":2},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":10,"wins":9},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":24,"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":12,"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":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":25,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":1},"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":12,"losses":19,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":3},"o3":{"draws":11,"losses":41,"wins":14},"openai/gpt-oss-120b":{"draws":16,"losses":18,"wins":8},"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":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":12,"losses":28,"wins":6},"thinkingmachines/inkling":{"draws":28,"losses":27,"wins":9},"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":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":32,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"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":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":31,"wins":9},"z-ai/glm-5.3-flashx":{"draws":9,"losses":33,"wins":6}},"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},"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":2},"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":2,"losses":2,"wins":42},"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":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":1,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":15,"wins":26},"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":40},"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":4},"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":0,"losses":1,"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":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"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":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":0,"losses":2,"wins":30},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"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":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":16,"wins":25},"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":41},"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":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"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":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"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":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":8,"losses":1,"wins":1},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":7,"losses":5,"wins":0},"claude-opus-5-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":5,"losses":1,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"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":11,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.5":{"draws":5,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":0},"gpt-6-astra":{"draws":2,"losses":4,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":0},"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":0,"losses":3,"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-k2.7-code":{"draws":0,"losses":2,"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},"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":11,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":1,"wins":0},"z-ai/glm-5.3-flashx":{"draws":5,"losses":1,"wins":0}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":20},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":18,"losses":12,"wins":18},"claude-sonnet-5-5":{"draws":15,"losses":20,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":18,"wins":18},"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":44,"wins":26},"google/gemini-3.8-flash":{"draws":12,"losses":20,"wins":16},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":16},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":18,"wins":16},"gpt-5.4":{"draws":9,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":27},"gpt-5.5":{"draws":11,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":32,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":18},"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":0,"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":12,"losses":20,"wins":14},"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":3,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":20,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":33,"wins":5},"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":14,"losses":7,"wins":21},"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":18,"wins":15},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"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":71,"wins":48},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"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":12,"losses":15,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":22,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":7},"z-ai/glm-5.3-flash":{"draws":6,"losses":29,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":7,"wins":17},"claude-fable-5":{"draws":14,"losses":29,"wins":5},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":13},"claude-opus-4-5":{"draws":27,"losses":23,"wins":28},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":16,"losses":61,"wins":5},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":20,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":13,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":26,"losses":14,"wins":32},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":26,"wins":6},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":18,"losses":23,"wins":7},"gemini-3.1-pro-preview":{"draws":20,"losses":14,"wins":14},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":21,"losses":19,"wins":20},"google/gemini-3.5-flash-lite":{"draws":31,"losses":18,"wins":35},"google/gemini-3.6-flash":{"draws":34,"losses":36,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":24,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":15,"losses":13,"wins":14},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":18},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":11},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":21,"losses":11,"wins":16},"gpt-6-sol":{"draws":10,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":7,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":5,"wins":13},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":18},"meta/muse-glimmer-30b":{"draws":22,"losses":3,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":14,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":14,"losses":23,"wins":9},"meta/muse-wonder":{"draws":20,"losses":26,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"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":15,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":10,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":41,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":6,"wins":8},"o3":{"draws":12,"losses":25,"wins":29},"openai/gpt-oss-120b":{"draws":20,"losses":6,"wins":16},"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":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":21,"losses":18,"wins":9},"qwen/qwen3.8-max-0902":{"draws":21,"losses":13,"wins":14},"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":61,"losses":72,"wins":25},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":20},"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":31,"losses":14,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":36,"losses":26,"wins":34},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":22,"wins":11},"z-ai/glm-5.3-flashx":{"draws":14,"losses":29,"wins":5}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":15,"wins":18},"claude-fable-5":{"draws":6,"losses":25,"wins":11},"claude-fable-5-1":{"draws":3,"losses":38,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":18},"claude-opus-4-5":{"draws":13,"losses":27,"wins":30},"claude-opus-4-8":{"draws":10,"losses":18,"wins":14},"claude-opus-5":{"draws":8,"losses":45,"wins":17},"claude-opus-5-5":{"draws":4,"losses":37,"wins":5},"claude-sonnet-5":{"draws":9,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":12,"losses":18,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":16,"losses":9,"wins":39},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":20},"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":14,"wins":22},"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":10,"losses":16,"wins":28},"google/gemini-3.5-flash-lite":{"draws":13,"losses":20,"wins":41},"google/gemini-3.6-flash":{"draws":10,"losses":37,"wins":33},"google/gemini-3.8-flash":{"draws":8,"losses":15,"wins":19},"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":8,"wins":28},"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":1,"losses":36,"wins":5},"gpt-6-luna":{"draws":7,"losses":13,"wins":22},"gpt-6-sol":{"draws":9,"losses":25,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"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":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":4,"losses":13,"wins":19},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":17},"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":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":17,"wins":16},"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":5,"losses":7,"wins":28},"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":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":21,"wins":11},"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":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":20,"wins":13},"x-ai/grok-4.6":{"draws":8,"losses":16,"wins":18},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":22,"losses":22,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":18,"wins":12},"z-ai/glm-5.3-flash":{"draws":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":25,"losses":38,"wins":33},"claude-fable-5":{"draws":14,"losses":86,"wins":2},"claude-fable-5-1":{"draws":5,"losses":105,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":64,"wins":20},"claude-opus-4-5":{"draws":45,"losses":91,"wins":32},"claude-opus-4-8":{"draws":18,"losses":65,"wins":15},"claude-opus-5":{"draws":23,"losses":137,"wins":6},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":29,"losses":55,"wins":18},"claude-sonnet-5-5":{"draws":15,"losses":74,"wins":13},"cohere/north-mini-code":{"draws":8,"losses":13,"wins":19},"deepseek/deepseek-v4-flash":{"draws":41,"losses":58,"wins":55},"deepseek/deepseek-v4-pro":{"draws":28,"losses":50,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":47,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":57,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":79,"wins":10},"elorian/glimpse":{"draws":13,"losses":33,"wins":8},"fireworks/ember-1":{"draws":27,"losses":54,"wins":21},"gemini-3.1-pro-preview":{"draws":24,"losses":52,"wins":26},"gemini-4-argon":{"draws":7,"losses":95,"wins":0},"google/gemini-3.1-flash-lite":{"draws":21,"losses":19,"wins":38},"google/gemini-3.5-flash":{"draws":28,"losses":77,"wins":27},"google/gemini-3.5-flash-lite":{"draws":41,"losses":75,"wins":68},"google/gemini-3.6-flash":{"draws":44,"losses":121,"wins":33},"google/gemini-3.8-flash":{"draws":23,"losses":68,"wins":11},"google/gemma-4-31b-it":{"draws":19,"losses":16,"wins":25},"gpt-4.1":{"draws":10,"losses":16,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":21,"losses":48,"wins":21},"gpt-5.4":{"draws":21,"losses":71,"wins":8},"gpt-5.4-mini":{"draws":19,"losses":26,"wins":23},"gpt-5.4-nano":{"draws":19,"losses":53,"wins":40},"gpt-5.5":{"draws":37,"losses":46,"wins":11},"gpt-5.6-luna":{"draws":33,"losses":43,"wins":26},"gpt-5.6-sol":{"draws":11,"losses":82,"wins":9},"gpt-5.6-terra":{"draws":27,"losses":61,"wins":8},"gpt-6-astra":{"draws":7,"losses":94,"wins":1},"gpt-6-luna":{"draws":25,"losses":63,"wins":14},"gpt-6-sol":{"draws":14,"losses":78,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":91,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":11,"wins":36},"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":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":42,"wins":43},"meta/muse-glimmer-30b":{"draws":30,"losses":32,"wins":26},"meta/muse-spark-1.2":{"draws":22,"losses":57,"wins":17},"meta/muse-spark-1.3":{"draws":19,"losses":72,"wins":11},"meta/muse-spark-open":{"draws":17,"losses":71,"wins":12},"meta/muse-wonder":{"draws":10,"losses":83,"wins":9},"minimax/minimax-m3":{"draws":11,"losses":19,"wins":26},"minimax/minimax-m3.1-flash":{"draws":16,"losses":49,"wins":27},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":12},"mistralai/mistral-medium-3-5":{"draws":18,"losses":15,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":9},"moonshotai/kimi-k3":{"draws":26,"losses":54,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":86,"wins":3},"nex-agi/nex-n2-pro":{"draws":14,"losses":12,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":29,"wins":38},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":22,"wins":13},"o3":{"draws":23,"losses":99,"wins":38},"openai/gpt-oss-120b":{"draws":22,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":26,"losses":42,"wins":28},"qwen/qwen3.7-max":{"draws":20,"losses":24,"wins":18},"qwen/qwen3.7-plus":{"draws":12,"losses":21,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":56,"wins":15},"qwen/qwen3.8-27b":{"draws":12,"losses":45,"wins":19},"qwen/qwen3.8-flash":{"draws":19,"losses":32,"wins":17},"qwen/qwen3.8-max":{"draws":24,"losses":53,"wins":25},"qwen/qwen3.8-max-0902":{"draws":34,"losses":57,"wins":11},"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":61,"losses":198,"wins":51},"stealth/space-bunny-alpha":{"draws":26,"losses":33,"wins":23},"stepfun/step-3.7-flash":{"draws":18,"losses":28,"wins":32},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":24,"wins":17},"tencent/hy4-preview":{"draws":27,"losses":65,"wins":8},"thinkingmachines/inkling":{"draws":31,"losses":43,"wins":64},"thinkingmachines/inkling-small":{"draws":29,"losses":27,"wins":46},"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":5,"losses":17,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":72,"wins":12},"x-ai/grok-4.6":{"draws":34,"losses":58,"wins":10},"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":39,"losses":43,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":32,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":44,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":6},"z-ai/glm-5.2":{"draws":64,"losses":91,"wins":49},"z-ai/glm-5.3":{"draws":12,"losses":81,"wins":3},"z-ai/glm-5.3-flash":{"draws":17,"losses":62,"wins":23},"z-ai/glm-5.3-flashx":{"draws":22,"losses":70,"wins":10}},"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":4,"losses":65,"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":5,"losses":23,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":23,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":25,"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":5,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":28,"wins":14},"google/gemini-3.5-flash-lite":{"draws":19,"losses":34,"wins":19},"google/gemini-3.6-flash":{"draws":15,"losses":51,"wins":14},"google/gemini-3.8-flash":{"draws":9,"losses":28,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":17,"wins":12},"gpt-5.4":{"draws":6,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":15,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":22,"wins":15},"gpt-5.5":{"draws":12,"losses":19,"wins":7},"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},"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":9,"losses":9,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"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":25,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":34,"wins":3},"meta/muse-spark-open":{"draws":7,"losses":29,"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":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":2},"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":12,"wins":14},"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":27,"wins":9},"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":9,"losses":23,"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":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":9,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":28},"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":1,"losses":6,"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":11,"losses":10,"wins":17},"claude-fable-5":{"draws":13,"losses":25,"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":22,"losses":27,"wins":19},"claude-opus-4-8":{"draws":10,"losses":16,"wins":12},"claude-opus-5":{"draws":8,"losses":56,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":10,"losses":15,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":15,"wins":31},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":6},"elorian/glimpse":{"draws":3,"losses":8,"wins":11},"fireworks/ember-1":{"draws":10,"losses":18,"wins":14},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"gemini-4-argon":{"draws":2,"losses":38,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":9,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":14,"losses":12,"wins":46},"google/gemini-3.6-flash":{"draws":15,"losses":41,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":1},"gpt-5":{"draws":11,"losses":17,"wins":10},"gpt-5.4":{"draws":14,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":15,"losses":10,"wins":21},"gpt-5.5":{"draws":19,"losses":15,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":5},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":14,"losses":19,"wins":9},"gpt-6-sol":{"draws":3,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":6},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":16},"inception/mercury-3":{"draws":9,"losses":16,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":9,"wins":23},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":30,"wins":7},"meta/muse-spark-open":{"draws":6,"losses":23,"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":7,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":17,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":5},"o3":{"draws":9,"losses":22,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":15,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":11},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":19,"wins":12},"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":10,"losses":10,"wins":12},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":16,"losses":13,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":8,"wins":22},"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":21,"wins":10},"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":25,"losses":4,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":30,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":9},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":9}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":6,"losses":32,"wins":10},"claude-fable-5-1":{"draws":4,"losses":46,"wins":4},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":12},"claude-opus-4-5":{"draws":28,"losses":24,"wins":26},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":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":19,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":19},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":27,"losses":43,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":15},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":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":12,"losses":21,"wins":11},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":30,"wins":10},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":15},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":10,"losses":17,"wins":21},"gpt-6-sol":{"draws":10,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"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":0,"losses":0,"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":9,"losses":18,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":10,"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":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":11},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":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":43,"losses":68,"wins":47},"stealth/space-bunny-alpha":{"draws":15,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":28},"unbiased/pareto-26.10":{"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":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":29,"losses":5,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":13,"wins":2},"z-ai/glm-5.2":{"draws":40,"losses":22,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":20,"wins":18},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":14}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":51,"losses":43,"wins":38},"claude-fable-5":{"draws":28,"losses":97,"wins":19},"claude-fable-5-1":{"draws":8,"losses":152,"wins":2},"claude-haiku-5-5":{"draws":28,"losses":84,"wins":26},"claude-opus-4-5":{"draws":75,"losses":105,"wins":54},"claude-opus-4-8":{"draws":35,"losses":74,"wins":23},"claude-opus-5":{"draws":32,"losses":193,"wins":21},"claude-opus-5-5":{"draws":9,"losses":142,"wins":5},"claude-sonnet-5":{"draws":46,"losses":64,"wins":34},"claude-sonnet-5-5":{"draws":28,"losses":89,"wins":27},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":36},"deepseek/deepseek-v4-flash":{"draws":70,"losses":52,"wins":94},"deepseek/deepseek-v4-pro":{"draws":45,"losses":53,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":47,"losses":45,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":50,"losses":66,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":95,"wins":20},"elorian/glimpse":{"draws":19,"losses":36,"wins":23},"fireworks/ember-1":{"draws":48,"losses":69,"wins":27},"gemini-3.1-pro-preview":{"draws":43,"losses":64,"wins":37},"gemini-4-argon":{"draws":11,"losses":123,"wins":10},"google/gemini-3.1-flash-lite":{"draws":18,"losses":16,"wins":62},"google/gemini-3.5-flash":{"draws":41,"losses":91,"wins":48},"google/gemini-3.5-flash-lite":{"draws":75,"losses":88,"wins":89},"google/gemini-3.6-flash":{"draws":85,"losses":127,"wins":64},"google/gemini-3.8-flash":{"draws":38,"losses":80,"wins":26},"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":35,"losses":54,"wins":37},"gpt-5.4":{"draws":35,"losses":75,"wins":28},"gpt-5.4-mini":{"draws":43,"losses":21,"wins":32},"gpt-5.4-nano":{"draws":32,"losses":53,"wins":59},"gpt-5.5":{"draws":51,"losses":57,"wins":24},"gpt-5.6-luna":{"draws":50,"losses":40,"wins":54},"gpt-5.6-sol":{"draws":19,"losses":108,"wins":17},"gpt-5.6-terra":{"draws":52,"losses":49,"wins":37},"gpt-6-astra":{"draws":7,"losses":134,"wins":3},"gpt-6-luna":{"draws":53,"losses":57,"wins":34},"gpt-6-sol":{"draws":26,"losses":105,"wins":13},"gpt-6.1-sol":{"draws":12,"losses":128,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":43,"losses":10,"wins":49},"inception/mercury-3":{"draws":34,"losses":41,"wins":21},"inclusionai/ling-3.0-flash":{"draws":47,"losses":16,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":43,"losses":34,"wins":79},"meta/muse-glimmer-30b":{"draws":59,"losses":22,"wins":45},"meta/muse-spark-1.2":{"draws":32,"losses":67,"wins":39},"meta/muse-spark-1.3":{"draws":29,"losses":85,"wins":30},"meta/muse-spark-open":{"draws":36,"losses":76,"wins":26},"meta/muse-wonder":{"draws":30,"losses":95,"wins":19},"minimax/minimax-m3":{"draws":26,"losses":19,"wins":33},"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":41,"losses":8,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":42,"losses":62,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":118,"wins":6},"nex-agi/nex-n2-pro":{"draws":28,"losses":11,"wins":33},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":8,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":30,"wins":44},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":25,"wins":19},"o3":{"draws":34,"losses":94,"wins":70},"openai/gpt-oss-120b":{"draws":42,"losses":33,"wins":51},"poolside/laguna-s-2.1":{"draws":49,"losses":47,"wins":42},"qwen/qwen3.7-max":{"draws":25,"losses":35,"wins":24},"qwen/qwen3.7-plus":{"draws":20,"losses":17,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":56,"wins":30},"qwen/qwen3.8-27b":{"draws":35,"losses":39,"wins":28},"qwen/qwen3.8-flash":{"draws":37,"losses":32,"wins":27},"qwen/qwen3.8-max":{"draws":50,"losses":57,"wins":37},"qwen/qwen3.8-max-0902":{"draws":50,"losses":65,"wins":29},"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":120,"losses":254,"wins":100},"stealth/space-bunny-alpha":{"draws":40,"losses":37,"wins":37},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":46},"stepfun/step-5-preview":{"draws":4,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":23,"wins":27},"tencent/hy4-preview":{"draws":34,"losses":79,"wins":25},"thinkingmachines/inkling":{"draws":60,"losses":48,"wins":84},"thinkingmachines/inkling-small":{"draws":51,"losses":36,"wins":57},"unbiased/pareto-26.10":{"draws":2,"losses":46,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":19},"x-ai/grok-4.5":{"draws":35,"losses":90,"wins":19},"x-ai/grok-4.6":{"draws":37,"losses":85,"wins":22},"x-ai/grok-4.7":{"draws":15,"losses":94,"wins":17},"x-ai/grok-build-0.1":{"draws":20,"losses":12,"wins":16},"xiaomi/mimo-v2.5":{"draws":75,"losses":58,"wins":89},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":32,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":53,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":56,"wins":18},"z-ai/glm-5.2":{"draws":85,"losses":85,"wins":70},"z-ai/glm-5.3":{"draws":33,"losses":93,"wins":12},"z-ai/glm-5.3-flash":{"draws":33,"losses":85,"wins":26},"z-ai/glm-5.3-flashx":{"draws":35,"losses":77,"wins":32}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":21},"claude-fable-5":{"draws":8,"losses":29,"wins":11},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":28,"losses":22,"wins":28},"claude-opus-4-8":{"draws":10,"losses":15,"wins":19},"claude-opus-5":{"draws":12,"losses":62,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":27,"losses":8,"wins":37},"deepseek/deepseek-v4-pro":{"draws":16,"losses":15,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":7,"losses":9,"wins":10},"fireworks/ember-1":{"draws":16,"losses":14,"wins":18},"gemini-3.1-pro-preview":{"draws":11,"losses":16,"wins":21},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":19,"losses":21,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":13,"wins":45},"google/gemini-3.6-flash":{"draws":24,"losses":33,"wins":35},"google/gemini-3.8-flash":{"draws":12,"losses":23,"wins":13},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":15,"losses":10,"wins":19},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":16},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":11,"losses":19,"wins":18},"gpt-6-sol":{"draws":8,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":7,"wins":29},"meta/muse-glimmer-30b":{"draws":10,"losses":10,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":18},"meta/muse-spark-open":{"draws":11,"losses":20,"wins":15},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":4,"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":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":36,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":10,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":13},"o3":{"draws":9,"losses":26,"wins":31},"openai/gpt-oss-120b":{"draws":17,"losses":3,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":22},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":13},"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":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":19,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":18,"wins":12},"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":46,"losses":68,"wins":44},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":20},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":24},"unbiased/pareto-26.10":{"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":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":32,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":27,"losses":3,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":36,"losses":21,"wins":39},"z-ai/glm-5.3":{"draws":5,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":14,"losses":18,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":21,"wins":13}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":8,"wins":21},"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":24,"wins":11},"claude-opus-4-5":{"draws":24,"losses":25,"wins":29},"claude-opus-4-8":{"draws":6,"losses":23,"wins":15},"claude-opus-5":{"draws":15,"losses":57,"wins":10},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":13,"losses":19,"wins":16},"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":30,"losses":16,"wins":26},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":29,"wins":8},"elorian/glimpse":{"draws":4,"losses":11,"wins":11},"fireworks/ember-1":{"draws":11,"losses":16,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":19,"wins":18},"gemini-4-argon":{"draws":6,"losses":38,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":10,"losses":26,"wins":24},"google/gemini-3.5-flash-lite":{"draws":23,"losses":23,"wins":38},"google/gemini-3.6-flash":{"draws":23,"losses":35,"wins":34},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":15},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":2,"losses":7,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":12,"wins":20},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":21},"gpt-5.5":{"draws":12,"losses":18,"wins":14},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":13,"losses":26,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":19},"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":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":13,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":18},"meta/muse-spark-open":{"draws":8,"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":11,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":3},"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":11,"losses":16,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":9,"losses":27,"wins":30},"openai/gpt-oss-120b":{"draws":12,"losses":10,"wins":20},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"wins":18},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":16},"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":16,"losses":20,"wins":12},"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":33,"losses":79,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":19,"losses":18,"wins":27},"thinkingmachines/inkling-small":{"draws":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":9,"losses":22,"wins":17},"x-ai/grok-4.6":{"draws":18,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":13,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"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":35,"losses":25,"wins":36},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":13,"losses":24,"wins":11}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":22,"losses":24,"wins":32},"claude-opus-4-8":{"draws":11,"losses":21,"wins":12},"claude-opus-5":{"draws":13,"losses":58,"wins":11},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":19,"losses":11,"wins":18},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":15,"losses":19,"wins":14},"gemini-3.1-pro-preview":{"draws":18,"losses":12,"wins":18},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":20,"losses":17,"wins":23},"google/gemini-3.5-flash-lite":{"draws":30,"losses":14,"wins":40},"google/gemini-3.6-flash":{"draws":30,"losses":34,"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":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":10,"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":19,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":17},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"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":0},"meituan/longcat-2.0":{"draws":15,"losses":9,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":10,"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":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":6},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":12,"losses":14,"wins":40},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":9,"wins":14},"qwen/qwen3.8-flash":{"draws":13,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"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":34,"losses":70,"wins":54},"stealth/space-bunny-alpha":{"draws":14,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":21,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":14,"losses":7,"wins":27},"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":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":1,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":12,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":35,"losses":24,"wins":37},"z-ai/glm-5.3":{"draws":12,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":10}}}}}