{"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":"2026-10-26T02:27:24Z","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":89.73915656706482,"highest":94.44100465618811,"medium":89.64961921867949,"none":85.12684582632687},"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":89.10507177707132,"score":89.10507177707132},"GB2-02":{"attempts":3,"playable":82.96418916904214,"score":82.96418916904214},"GB2-03":{"attempts":3,"playable":89.33935974529317,"score":89.33935974529317},"GB2-04":{"attempts":3,"playable":89.14063875254455,"score":89.14063875254455},"GB2-05":{"attempts":3,"playable":95.42288021642845,"score":95.42288021642845},"GB2-06":{"attempts":3,"playable":86.8694252634245,"score":86.8694252634245},"GB2-07":{"attempts":3,"playable":96.3563864921544,"score":96.3563864921544},"GB2-08":{"attempts":3,"playable":88.71530112056003,"score":88.71530112056003}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":97.26310618029666,"score":97.26310618029666},"GB2-02":{"attempts":1,"playable":95.28254216483235,"score":95.28254216483235},"GB2-03":{"attempts":1,"playable":97.71729001652737,"score":97.71729001652737},"GB2-04":{"attempts":1,"playable":92.61249312688841,"score":92.61249312688841},"GB2-05":{"attempts":1,"playable":98.93325735214952,"score":98.93325735214952},"GB2-06":{"attempts":1,"playable":86.99208992144212,"score":86.99208992144212},"GB2-07":{"attempts":1,"playable":97.81823072023141,"score":97.81823072023141},"GB2-08":{"attempts":1,"playable":88.909027767137,"score":88.909027767137}},"medium":{"GB2-01":{"attempts":1,"playable":76.89221681442544,"score":76.89221681442544},"GB2-02":{"attempts":1,"playable":80.9876563481334,"score":80.9876563481334},"GB2-03":{"attempts":1,"playable":94.79866348037507,"score":94.79866348037507},"GB2-04":{"attempts":1,"playable":91.41780283715886,"score":91.41780283715886},"GB2-05":{"attempts":1,"playable":93.07462175455832,"score":93.07462175455832},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":1,"playable":96.65952162760107,"score":96.65952162760107},"GB2-08":{"attempts":1,"playable":94.74947165976819,"score":94.74947165976819}},"none":{"GB2-01":{"attempts":1,"playable":93.15989233649182,"score":93.15989233649182},"GB2-02":{"attempts":1,"playable":72.62236899416067,"score":72.62236899416067},"GB2-03":{"attempts":1,"playable":75.50212573897703,"score":75.50212573897703},"GB2-04":{"attempts":1,"playable":83.39162029358637,"score":83.39162029358637},"GB2-05":{"attempts":1,"playable":94.26076154257755,"score":94.26076154257755},"GB2-06":{"attempts":1,"playable":84.99918664141589,"score":84.99918664141589},"GB2-07":{"attempts":1,"playable":94.5914071286307,"score":94.5914071286307},"GB2-08":{"attempts":1,"playable":82.48740393477489,"score":82.48740393477489}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:42Z","match_totals_all":{"draws":879,"losses":886,"wins":10499},"match_totals_tracks":{"highest":{"draws":96,"losses":188,"wins":3804},"medium":{"draws":268,"losses":309,"wins":3511},"none":{"draws":515,"losses":389,"wins":3184}},"model_slug":"gpt-6-astra","official_rank_by_reasoning":{"highest":2,"medium":2,"none":4},"overall":{"max":98.93325735214952,"mean":89.73915656706482,"min":72.62236899416067},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":97.26310618029666,"GB2-02":95.28254216483235,"GB2-03":97.71729001652737,"GB2-04":92.61249312688841,"GB2-05":98.93325735214952,"GB2-06":86.99208992144212,"GB2-07":97.81823072023141,"GB2-08":88.909027767137},"per_game_all":{"GB2-01":89.10507177707132,"GB2-02":82.96418916904214,"GB2-03":89.33935974529317,"GB2-04":89.14063875254455,"GB2-05":95.42288021642845,"GB2-06":86.8694252634245,"GB2-07":96.3563864921544,"GB2-08":88.71530112056003},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":154,"wins":1333},"GB2-02":{"draws":405,"losses":55,"wins":980},"GB2-03":{"draws":175,"losses":87,"wins":1220},"GB2-04":{"draws":161,"losses":91,"wins":1242},"GB2-05":{"draws":0,"losses":70,"wins":1520},"GB2-06":{"draws":77,"losses":181,"wins":1248},"GB2-07":{"draws":0,"losses":47,"wins":1543},"GB2-08":{"draws":0,"losses":201,"wins":1413}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":15,"wins":501},"GB2-02":{"draws":25,"losses":10,"wins":445},"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":29,"losses":58,"wins":415},"GB2-07":{"draws":0,"losses":8,"wins":522},"GB2-08":{"draws":0,"losses":66,"wins":472}},"medium":{"GB2-01":{"draws":37,"losses":111,"wins":368},"GB2-02":{"draws":159,"losses":17,"wins":304},"GB2-03":{"draws":5,"losses":25,"wins":464},"GB2-04":{"draws":44,"losses":23,"wins":431},"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":161,"losses":56,"wins":277},"GB2-04":{"draws":84,"losses":46,"wins":368},"GB2-05":{"draws":0,"losses":30,"wins":500},"GB2-06":{"draws":25,"losses":71,"wins":406},"GB2-07":{"draws":0,"losses":25,"wins":505},"GB2-08":{"draws":0,"losses":105,"wins":433}}},"per_game_raw_elo_all":{"GB2-01":2036.856172990388,"GB2-02":1846.4288328611008,"GB2-03":2101.082363755428,"GB2-04":1915.120041414236,"GB2-05":2599.1474030401637,"GB2-06":2094.3981341651106,"GB2-07":2540.7889523749654,"GB2-08":2141.5977260355276},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2278.952139988751,"GB2-02":2104.383342180453,"GB2-03":2409.485425321855,"GB2-04":1988.3985291147696,"GB2-05":2940.474339211618,"GB2-06":2096.29153331524,"GB2-07":2659.0241931141227,"GB2-08":2124.276681060836},"medium":{"GB2-01":1755.5119501945394,"GB2-02":1767.471459423531,"GB2-03":2196.9643603095296,"GB2-04":1955.634716282792,"GB2-05":2395.054730741312,"GB2-06":2136.948866428713,"GB2-07":2552.8943025353105,"GB2-08":2349.0046349166278},"none":{"GB2-01":2076.104428787874,"GB2-02":1667.4316969793183,"GB2-03":1696.7973056348999,"GB2-04":1801.3268788451471,"GB2-05":2461.9131391675596,"GB2-06":2049.9540027513794,"GB2-07":2410.448361475462,"GB2-08":1951.5118621291194}},"per_game_tracks":{"highest":{"GB2-01":97.26310618029666,"GB2-02":95.28254216483235,"GB2-03":97.71729001652737,"GB2-04":92.61249312688841,"GB2-05":98.93325735214952,"GB2-06":86.99208992144212,"GB2-07":97.81823072023141,"GB2-08":88.909027767137},"medium":{"GB2-01":76.89221681442544,"GB2-02":80.9876563481334,"GB2-03":94.79866348037507,"GB2-04":91.41780283715886,"GB2-05":93.07462175455832,"GB2-06":88.61699922741556,"GB2-07":96.65952162760107,"GB2-08":94.74947165976819},"none":{"GB2-01":93.15989233649182,"GB2-02":72.62236899416067,"GB2-03":75.50212573897703,"GB2-04":83.39162029358637,"GB2-05":94.26076154257755,"GB2-06":84.99918664141589,"GB2-07":94.5914071286307,"GB2-08":82.48740393477489}},"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":"2026-10-24T19:15:38Z","reasoning":{"highest":94.44100465618811,"medium":89.64961921867949,"none":85.12684582632687},"reasoning_agg":{"highest":{"max":98.93325735214952,"mean":94.44100465618811,"min":86.99208992144212},"medium":{"max":96.65952162760107,"mean":89.64961921867949,"min":76.89221681442544},"none":{"max":94.5914071286307,"mean":85.12684582632687,"min":72.62236899416067}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.314158829861242},"working_program_strength":{"all":89.73915656706482,"highest":94.44100465618811,"medium":89.64961921867949,"none":85.12684582632687}},{"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":3.0063079999999998},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.052792}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.006308},"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":17.677192}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292},"codegen_output_tokens":{"attempt_count":30,"output_max":149830,"output_mean":37334.40740740741,"output_min":2400,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":149830,"output_mean":94967.22222222222,"output_min":65515,"run_count":9},"medium":{"attempt_count":10,"output_max":31033,"output_mean":13777.666666666666,"output_min":6104,"run_count":9},"none":{"attempt_count":9,"output_max":3890,"output_mean":3258.3333333333335,"output_min":2400,"run_count":9}},"display_name":"Claude Opus 5.5","economics":{"all":88.76770154866954,"highest":95.14696610308756,"medium":92.95307801297679,"none":78.20306052994427},"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":89.76435656585477,"score":89.76435656585477},"GB2-02":{"attempts":3,"playable":90.66743868817797,"score":90.66743868817797},"GB2-03":{"attempts":3,"playable":80.8167274563028,"score":80.8167274563028},"GB2-04":{"attempts":3,"playable":84.51602833601972,"score":84.51602833601972},"GB2-05":{"attempts":3,"playable":93.29321053571618,"score":93.29321053571618},"GB2-06":{"attempts":3,"playable":89.7708078067045,"score":89.7708078067045},"GB2-07":{"attempts":3,"playable":94.3978209257494,"score":94.3978209257494},"GB2-08":{"attempts":5,"playable":86.91522207483105,"score":86.91522207483105}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.36451415389676,"score":84.36451415389676},"GB2-02":{"attempts":1,"playable":96.04425995743617,"score":96.04425995743617},"GB2-03":{"attempts":1,"playable":97.11633628095088,"score":97.11633628095088},"GB2-04":{"attempts":1,"playable":94.80532092654904,"score":94.80532092654904},"GB2-05":{"attempts":1,"playable":98.2460503822685,"score":98.2460503822685},"GB2-06":{"attempts":1,"playable":99.48374593708698,"score":99.48374593708698},"GB2-07":{"attempts":1,"playable":97.81823072023141,"score":97.81823072023141},"GB2-08":{"attempts":1,"playable":93.2972704662808,"score":93.2972704662808}},"medium":{"GB2-01":{"attempts":1,"playable":93.91877159812458,"score":93.91877159812458},"GB2-02":{"attempts":1,"playable":95.75873519610694,"score":95.75873519610694},"GB2-03":{"attempts":1,"playable":92.57125832418781,"score":92.57125832418781},"GB2-04":{"attempts":1,"playable":88.54928037127607,"score":88.54928037127607},"GB2-05":{"attempts":1,"playable":89.73340164958267,"score":89.73340164958267},"GB2-06":{"attempts":1,"playable":92.37059265200884,"score":92.37059265200884},"GB2-07":{"attempts":1,"playable":93.49401010142148,"score":93.49401010142148},"GB2-08":{"attempts":2,"playable":97.22857421110604,"score":97.22857421110604}},"none":{"GB2-01":{"attempts":1,"playable":91.00978394554295,"score":91.00978394554295},"GB2-02":{"attempts":1,"playable":80.19932091099078,"score":80.19932091099078},"GB2-03":{"attempts":1,"playable":52.762587763769716,"score":52.762587763769716},"GB2-04":{"attempts":1,"playable":70.19348371023403,"score":70.19348371023403},"GB2-05":{"attempts":1,"playable":91.90017957529739,"score":91.90017957529739},"GB2-06":{"attempts":1,"playable":77.45808483101766,"score":77.45808483101766},"GB2-07":{"attempts":1,"playable":91.8812219555953,"score":91.8812219555953},"GB2-08":{"attempts":2,"playable":70.21982154710635,"score":70.21982154710635}}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:23Z","match_totals_all":{"draws":940,"losses":1175,"wins":11225},"match_totals_tracks":{"highest":{"draws":79,"losses":163,"wins":3846},"medium":{"draws":128,"losses":252,"wins":4246},"none":{"draws":733,"losses":760,"wins":3133}},"model_slug":"claude-opus-5-5","official_rank_by_reasoning":{"highest":1,"medium":1,"none":7},"overall":{"max":99.48374593708698,"mean":88.76770154866954,"min":52.762587763769716},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.36451415389676,"GB2-02":96.04425995743617,"GB2-03":97.11633628095088,"GB2-04":94.80532092654904,"GB2-05":98.2460503822685,"GB2-06":99.48374593708698,"GB2-07":97.81823072023141,"GB2-08":93.2972704662808},"per_game_all":{"GB2-01":89.76435656585477,"GB2-02":90.66743868817797,"GB2-03":80.8167274563028,"GB2-04":84.51602833601972,"GB2-05":93.29321053571618,"GB2-06":89.7708078067045,"GB2-07":94.3978209257494,"GB2-08":86.91522207483105},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":145,"wins":1338},"GB2-02":{"draws":148,"losses":65,"wins":1227},"GB2-03":{"draws":351,"losses":132,"wins":999},"GB2-04":{"draws":313,"losses":87,"wins":1094},"GB2-05":{"draws":0,"losses":108,"wins":1482},"GB2-06":{"draws":51,"losses":142,"wins":1313},"GB2-07":{"draws":0,"losses":79,"wins":1511},"GB2-08":{"draws":12,"losses":417,"wins":2261}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":85,"wins":422},"GB2-02":{"draws":25,"losses":6,"wins":449},"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":0,"losses":0,"wins":502},"GB2-07":{"draws":0,"losses":8,"wins":522},"GB2-08":{"draws":0,"losses":39,"wins":499}},"medium":{"GB2-01":{"draws":35,"losses":18,"wins":463},"GB2-02":{"draws":14,"losses":13,"wins":453},"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":15,"losses":35,"wins":452},"GB2-07":{"draws":0,"losses":31,"wins":499},"GB2-08":{"draws":0,"losses":29,"wins":1047}},"none":{"GB2-01":{"draws":21,"losses":42,"wins":453},"GB2-02":{"draws":109,"losses":46,"wins":325},"GB2-03":{"draws":326,"losses":90,"wins":78},"GB2-04":{"draws":229,"losses":42,"wins":227},"GB2-05":{"draws":0,"losses":44,"wins":486},"GB2-06":{"draws":36,"losses":107,"wins":359},"GB2-07":{"draws":0,"losses":40,"wins":490},"GB2-08":{"draws":12,"losses":349,"wins":715}}},"per_game_raw_elo_all":{"GB2-01":1994.0007399753733,"GB2-02":2009.0951187952776,"GB2-03":1965.4916760000772,"GB2-04":1866.1476630802354,"GB2-05":2462.844934702697,"GB2-06":2342.490149441263,"GB2-07":2423.3137176783766,"GB2-08":2170.6914460904845},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1867.9455023411629,"GB2-02":2142.8587070806193,"GB2-03":2353.4199519677736,"GB2-04":2062.7327324292587,"GB2-05":2816.051486361429,"GB2-06":2886.0352406480743,"GB2-07":2659.024193114123,"GB2-08":2280.913726321405},"medium":{"GB2-01":2103.521267973436,"GB2-02":2127.7403512751134,"GB2-03":2090.869958215492,"GB2-04":1890.420279415069,"GB2-05":2237.06953937912,"GB2-06":2247.6382772247325,"GB2-07":2347.0302978762957,"GB2-08":2540.774299200761},"none":{"GB2-01":2010.535449611522,"GB2-02":1756.6862980301,"GB2-03":1452.1851178169666,"GB2-04":1645.2899773963784,"GB2-05":2335.4137783675424,"GB2-06":1893.7969304509822,"GB2-07":2263.8866620447116,"GB2-08":1690.3863127492878}},"per_game_tracks":{"highest":{"GB2-01":84.36451415389676,"GB2-02":96.04425995743617,"GB2-03":97.11633628095088,"GB2-04":94.80532092654904,"GB2-05":98.2460503822685,"GB2-06":99.48374593708698,"GB2-07":97.81823072023141,"GB2-08":93.2972704662808},"medium":{"GB2-01":93.91877159812458,"GB2-02":95.75873519610694,"GB2-03":92.57125832418781,"GB2-04":88.54928037127607,"GB2-05":89.73340164958267,"GB2-06":92.37059265200884,"GB2-07":93.49401010142148,"GB2-08":97.22857421110604},"none":{"GB2-01":91.00978394554295,"GB2-02":80.19932091099078,"GB2-03":52.762587763769716,"GB2-04":70.19348371023403,"GB2-05":91.90017957529739,"GB2-06":77.45808483101766,"GB2-07":91.8812219555953,"GB2-08":70.21982154710635}},"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":"2026-10-24T19:20:59Z","reasoning":{"highest":95.14696610308756,"medium":92.95307801297679,"none":78.20306052994427},"reasoning_agg":{"highest":{"max":99.48374593708698,"mean":95.14696610308756,"min":84.36451415389676},"medium":{"max":97.22857421110604,"mean":92.95307801297679,"min":88.54928037127607},"none":{"max":91.90017957529739,"mean":78.20306052994427,"min":52.762587763769716}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.943905573143297},"working_program_strength":{"all":88.76770154866954,"highest":95.14696610308756,"medium":92.95307801297679,"none":78.20306052994427}},{"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":48.73911793121369},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276067},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.339052010326091}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609},"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":48.73911793121369}},"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":64.31171957781584},"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":88.60004874346238,"highest":94.36682200330814,"medium":84.83104488902094,"none":86.60227933805807},"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":85.09349334712874,"score":85.09349334712874},"GB2-02":{"attempts":3,"playable":89.96597587922939,"score":89.96597587922939},"GB2-03":{"attempts":4,"playable":93.65659197143766,"score":93.65659197143766},"GB2-04":{"attempts":4,"playable":75.59904252153194,"score":75.59904252153194},"GB2-05":{"attempts":3,"playable":91.23667517816655,"score":91.23667517816655},"GB2-06":{"attempts":3,"playable":90.19592678809134,"score":90.19592678809134},"GB2-07":{"attempts":4,"playable":91.97704236624698,"score":91.97704236624698},"GB2-08":{"attempts":3,"playable":91.0756418958665,"score":91.0756418958665}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":93.15989233649182,"score":93.15989233649182},"GB2-02":{"attempts":1,"playable":95.09196858035578,"score":95.09196858035578},"GB2-03":{"attempts":2,"playable":95.39910279160684,"score":95.39910279160684},"GB2-04":{"attempts":2,"playable":87.98030366893738,"score":87.98030366893738},"GB2-05":{"attempts":1,"playable":93.41214839874009,"score":93.41214839874009},"GB2-06":{"attempts":1,"playable":98.24081452142869,"score":98.24081452142869},"GB2-07":{"attempts":2,"playable":93.85788217399038,"score":93.85788217399038},"GB2-08":{"attempts":1,"playable":97.7924635549142,"score":97.7924635549142}},"medium":{"GB2-01":{"attempts":1,"playable":73.85519804895645,"score":73.85519804895645},"GB2-02":{"attempts":1,"playable":91.36643949382484,"score":91.36643949382484},"GB2-03":{"attempts":1,"playable":92.31429760149187,"score":92.31429760149187},"GB2-04":{"attempts":1,"playable":64.6256422345308,"score":64.6256422345308},"GB2-05":{"attempts":1,"playable":88.56478659126304,"score":88.56478659126304},"GB2-06":{"attempts":1,"playable":88.43679175363576,"score":88.43679175363576},"GB2-07":{"attempts":1,"playable":93.85761207733375,"score":93.85761207733375},"GB2-08":{"attempts":1,"playable":85.62759131113107,"score":85.62759131113107}},"none":{"GB2-01":{"attempts":1,"playable":88.26538965593794,"score":88.26538965593794},"GB2-02":{"attempts":1,"playable":83.43951956350753,"score":83.43951956350753},"GB2-03":{"attempts":1,"playable":93.2563755212143,"score":93.2563755212143},"GB2-04":{"attempts":1,"playable":74.19118166112764,"score":74.19118166112764},"GB2-05":{"attempts":1,"playable":91.73309054449655,"score":91.73309054449655},"GB2-06":{"attempts":1,"playable":83.91017408920956,"score":83.91017408920956},"GB2-07":{"attempts":1,"playable":88.2156328474168,"score":88.2156328474168},"GB2-08":{"attempts":1,"playable":89.80687082155418,"score":89.80687082155418}}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:27Z","match_totals_all":{"draws":749,"losses":1215,"wins":11820},"match_totals_tracks":{"highest":{"draws":125,"losses":288,"wins":5197},"medium":{"draws":299,"losses":509,"wins":3279},"none":{"draws":325,"losses":418,"wins":3344}},"model_slug":"claude-fable-5-1","official_rank_by_reasoning":{"highest":3,"medium":4,"none":3},"overall":{"max":98.24081452142869,"mean":88.60004874346238,"min":64.6256422345308},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":93.15989233649182,"GB2-02":95.09196858035578,"GB2-03":95.39910279160684,"GB2-04":87.98030366893738,"GB2-05":93.41214839874009,"GB2-06":98.24081452142869,"GB2-07":93.85788217399038,"GB2-08":97.7924635549142},"per_game_all":{"GB2-01":85.09349334712874,"GB2-02":89.96597587922939,"GB2-03":93.65659197143766,"GB2-04":75.59904252153194,"GB2-05":91.23667517816655,"GB2-06":90.19592678809134,"GB2-07":91.97704236624698,"GB2-08":91.0756418958665},"per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":250,"wins":1290},"GB2-02":{"draws":171,"losses":65,"wins":1204},"GB2-03":{"draws":19,"losses":117,"wins":1840},"GB2-04":{"draws":509,"losses":193,"wins":1289},"GB2-05":{"draws":0,"losses":144,"wins":1446},"GB2-06":{"draws":42,"losses":141,"wins":1323},"GB2-07":{"draws":0,"losses":148,"wins":1972},"GB2-08":{"draws":1,"losses":157,"wins":1456}},"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":6,"losses":45,"wins":937},"GB2-04":{"draws":90,"losses":82,"wins":824},"GB2-05":{"draws":0,"losses":35,"wins":495},"GB2-06":{"draws":4,"losses":6,"wins":492},"GB2-07":{"draws":0,"losses":58,"wins":1002},"GB2-08":{"draws":0,"losses":11,"wins":527}},"medium":{"GB2-01":{"draws":1,"losses":145,"wins":370},"GB2-02":{"draws":36,"losses":25,"wins":419},"GB2-03":{"draws":10,"losses":37,"wins":447},"GB2-04":{"draws":237,"losses":66,"wins":194},"GB2-05":{"draws":0,"losses":64,"wins":466},"GB2-06":{"draws":15,"losses":57,"wins":430},"GB2-07":{"draws":0,"losses":29,"wins":501},"GB2-08":{"draws":0,"losses":86,"wins":452}},"none":{"GB2-01":{"draws":4,"losses":66,"wins":445},"GB2-02":{"draws":112,"losses":28,"wins":340},"GB2-03":{"draws":3,"losses":35,"wins":456},"GB2-04":{"draws":182,"losses":45,"wins":271},"GB2-05":{"draws":0,"losses":45,"wins":485},"GB2-06":{"draws":23,"losses":78,"wins":401},"GB2-07":{"draws":0,"losses":61,"wins":469},"GB2-08":{"draws":1,"losses":60,"wins":477}}},"per_game_raw_elo_all":{"GB2-01":1912.262508994819,"GB2-02":1954.858015694654,"GB2-03":2144.100850421101,"GB2-04":1721.1429952508754,"GB2-05":2309.8490006364677,"GB2-06":2252.6587899761103,"GB2-07":2282.233133435308,"GB2-08":2250.172260062522},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2076.104428787874,"GB2-02":2095.60495264058,"GB2-03":2231.479119675335,"GB2-04":1883.4477509716717,"GB2-05":2413.2929559070535,"GB2-06":2599.836365295248,"GB2-07":2367.4599450798287,"GB2-08":2567.006352280212},"medium":{"GB2-01":1716.897175467125,"GB2-02":1965.3740081316919,"GB2-03":2080.321641258075,"GB2-04":1593.8975643889628,"GB2-05":2188.9115842559268,"GB2-06":2132.28193072238,"GB2-07":2367.3623135282437,"GB2-08":2031.0269512284044},"none":{"GB2-01":1943.785922729458,"GB2-02":1803.59508631169,"GB2-03":2120.501790329892,"GB2-04":1686.0836703919924,"GB2-05":2327.3424617464225,"GB2-06":2025.8580739107028,"GB2-07":2111.877141697852,"GB2-08":2152.4834766789495}},"per_game_tracks":{"highest":{"GB2-01":93.15989233649182,"GB2-02":95.09196858035578,"GB2-03":95.39910279160684,"GB2-04":87.98030366893738,"GB2-05":93.41214839874009,"GB2-06":98.24081452142869,"GB2-07":93.85788217399038,"GB2-08":97.7924635549142},"medium":{"GB2-01":73.85519804895645,"GB2-02":91.36643949382484,"GB2-03":92.31429760149187,"GB2-04":64.6256422345308,"GB2-05":88.56478659126304,"GB2-06":88.43679175363576,"GB2-07":93.85761207733375,"GB2-08":85.62759131113107},"none":{"GB2-01":88.26538965593794,"GB2-02":83.43951956350753,"GB2-03":93.2563755212143,"GB2-04":74.19118166112764,"GB2-05":91.73309054449655,"GB2-06":83.91017408920956,"GB2-07":88.2156328474168,"GB2-08":89.80687082155418}},"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":"2026-10-24T19:21:00Z","reasoning":{"highest":94.36682200330814,"medium":84.83104488902094,"none":86.60227933805807},"reasoning_agg":{"highest":{"max":98.24081452142869,"mean":94.36682200330814,"min":87.98030366893738},"medium":{"max":93.85761207733375,"mean":84.83104488902094,"min":64.6256422345308},"none":{"max":93.2563755212143,"mean":86.60227933805807,"min":74.19118166112764}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.5357771142872},"working_program_strength":{"all":88.60004874346238,"highest":94.36682200330814,"medium":84.83104488902094,"none":86.60227933805807}},{"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":0.6746989999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.388508}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.674699},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.3885080000000001},"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":3.1954350000000007},"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":85.9716434243253,"highest":92.68939233394522,"medium":87.46655549866425,"none":77.7589824403664},"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":67.64844394678822,"score":67.64844394678822},"GB2-02":{"attempts":3,"playable":79.80683956559766,"score":79.80683956559766},"GB2-03":{"attempts":3,"playable":93.61112444837455,"score":93.61112444837455},"GB2-04":{"attempts":3,"playable":85.34411766436392,"score":85.34411766436392},"GB2-05":{"attempts":3,"playable":94.69036448273654,"score":94.69036448273654},"GB2-06":{"attempts":3,"playable":87.26876988775354,"score":87.26876988775354},"GB2-07":{"attempts":3,"playable":95.4000297519724,"score":95.4000297519724},"GB2-08":{"attempts":3,"playable":84.00345764701542,"score":84.00345764701542}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.04019891391917,"score":76.04019891391917},"GB2-02":{"attempts":1,"playable":94.71067501688863,"score":94.71067501688863},"GB2-03":{"attempts":1,"playable":98.23172588248056,"score":98.23172588248056},"GB2-04":{"attempts":1,"playable":95.07823560912824,"score":95.07823560912824},"GB2-05":{"attempts":1,"playable":97.89828459794494,"score":97.89828459794494},"GB2-06":{"attempts":1,"playable":89.8754449934844,"score":89.8754449934844},"GB2-07":{"attempts":1,"playable":95.8986580939694,"score":95.8986580939694},"GB2-08":{"attempts":1,"playable":93.78191556374637,"score":93.78191556374637}},"medium":{"GB2-01":{"attempts":1,"playable":75.37631164228648,"score":75.37631164228648},"GB2-02":{"attempts":1,"playable":79.70569279156288,"score":79.70569279156288},"GB2-03":{"attempts":1,"playable":96.60103548840144,"score":96.60103548840144},"GB2-04":{"attempts":1,"playable":87.15128537218678,"score":87.15128537218678},"GB2-05":{"attempts":1,"playable":94.7735320011636,"score":94.7735320011636},"GB2-06":{"attempts":1,"playable":91.92773394831342,"score":91.92773394831342},"GB2-07":{"attempts":1,"playable":95.71002403331707,"score":95.71002403331707},"GB2-08":{"attempts":1,"playable":78.48682871208231,"score":78.48682871208231}},"none":{"GB2-01":{"attempts":1,"playable":51.52882128415899,"score":51.52882128415899},"GB2-02":{"attempts":1,"playable":65.00415088834143,"score":65.00415088834143},"GB2-03":{"attempts":1,"playable":86.00061197424166,"score":86.00061197424166},"GB2-04":{"attempts":1,"playable":73.80283201177676,"score":73.80283201177676},"GB2-05":{"attempts":1,"playable":91.3992768491011,"score":91.3992768491011},"GB2-06":{"attempts":1,"playable":80.00313072146281,"score":80.00313072146281},"GB2-07":{"attempts":1,"playable":94.5914071286307,"score":94.5914071286307},"GB2-08":{"attempts":1,"playable":79.74162866521762,"score":79.74162866521762}}},"id":"gpt-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:23Z","match_totals_all":{"draws":890,"losses":1370,"wins":10004},"match_totals_tracks":{"highest":{"draws":105,"losses":259,"wins":3724},"medium":{"draws":211,"losses":440,"wins":3437},"none":{"draws":574,"losses":671,"wins":2843}},"model_slug":"gpt-6-1-sol","official_rank_by_reasoning":{"highest":4,"medium":3,"none":8},"overall":{"max":98.23172588248056,"mean":85.9716434243253,"min":51.52882128415899},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.04019891391917,"GB2-02":94.71067501688863,"GB2-03":98.23172588248056,"GB2-04":95.07823560912824,"GB2-05":97.89828459794494,"GB2-06":89.8754449934844,"GB2-07":95.8986580939694,"GB2-08":93.78191556374637},"per_game_all":{"GB2-01":67.64844394678822,"GB2-02":79.80683956559766,"GB2-03":93.61112444837455,"GB2-04":85.34411766436392,"GB2-05":94.69036448273654,"GB2-06":87.26876988775354,"GB2-07":95.4000297519724,"GB2-08":84.00345764701542},"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":86,"wins":1362},"GB2-04":{"draws":240,"losses":111,"wins":1143},"GB2-05":{"draws":0,"losses":83,"wins":1507},"GB2-06":{"draws":93,"losses":166,"wins":1247},"GB2-07":{"draws":0,"losses":62,"wins":1528},"GB2-08":{"draws":1,"losses":286,"wins":1327}},"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":36,"losses":7,"wins":455},"GB2-05":{"draws":0,"losses":9,"wins":521},"GB2-06":{"draws":37,"losses":38,"wins":427},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":36,"wins":502}},"medium":{"GB2-01":{"draws":11,"losses":132,"wins":373},"GB2-02":{"draws":134,"losses":36,"wins":310},"GB2-03":{"draws":4,"losses":15,"wins":475},"GB2-04":{"draws":38,"losses":49,"wins":411},"GB2-05":{"draws":0,"losses":27,"wins":503},"GB2-06":{"draws":24,"losses":33,"wins":445},"GB2-07":{"draws":0,"losses":19,"wins":511},"GB2-08":{"draws":0,"losses":129,"wins":409}},"none":{"GB2-01":{"draws":64,"losses":229,"wins":223},"GB2-02":{"draws":282,"losses":35,"wins":163},"GB2-03":{"draws":29,"losses":64,"wins":401},"GB2-04":{"draws":166,"losses":55,"wins":277},"GB2-05":{"draws":0,"losses":47,"wins":483},"GB2-06":{"draws":32,"losses":95,"wins":375},"GB2-07":{"draws":0,"losses":25,"wins":505},"GB2-08":{"draws":1,"losses":121,"wins":416}}},"per_game_raw_elo_all":{"GB2-01":1654.6231662019081,"GB2-02":1807.7678297477826,"GB2-03":2221.9202669820183,"GB2-04":1873.0818630845813,"GB2-05":2524.204702152341,"GB2-06":2115.974920073158,"GB2-07":2462.9682777388966,"GB2-08":2016.1048784677048},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.372985551633,"GB2-02":2078.8936560674356,"GB2-03":2467.625310786872,"GB2-04":2073.8308232527907,"GB2-05":2767.4838491880637,"GB2-06":2170.878986633923,"GB2-07":2495.8104039775276,"GB2-08":2302.274525312386},"medium":{"GB2-01":1735.8666026145631,"GB2-02":1750.1119049923257,"GB2-03":2312.1020067206755,"GB2-04":1863.4748548130044,"GB2-05":2493.643309605238,"GB2-06":2232.8180021339726,"GB2-07":2482.646067763699,"GB2-08":1858.9336969499197},"none":{"GB2-01":1483.6299104395284,"GB2-02":1594.2979281835865,"GB2-03":1886.0334834385073,"GB2-04":1681.9399111879488,"GB2-05":2311.4869476637214,"GB2-06":1944.2277714515794,"GB2-07":2410.448361475462,"GB2-08":1887.106413140808}},"per_game_tracks":{"highest":{"GB2-01":76.04019891391917,"GB2-02":94.71067501688863,"GB2-03":98.23172588248056,"GB2-04":95.07823560912824,"GB2-05":97.89828459794494,"GB2-06":89.8754449934844,"GB2-07":95.8986580939694,"GB2-08":93.78191556374637},"medium":{"GB2-01":75.37631164228648,"GB2-02":79.70569279156288,"GB2-03":96.60103548840144,"GB2-04":87.15128537218678,"GB2-05":94.7735320011636,"GB2-06":91.92773394831342,"GB2-07":95.71002403331707,"GB2-08":78.48682871208231},"none":{"GB2-01":51.52882128415899,"GB2-02":65.00415088834143,"GB2-03":86.00061197424166,"GB2-04":73.80283201177676,"GB2-05":91.3992768491011,"GB2-06":80.00313072146281,"GB2-07":94.5914071286307,"GB2-08":79.74162866521762}},"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":"2026-10-24T19:17:41Z","reasoning":{"highest":92.68939233394522,"medium":87.46655549866425,"none":77.7589824403664},"reasoning_agg":{"highest":{"max":98.23172588248056,"mean":92.68939233394522,"min":76.04019891391917},"medium":{"max":96.60103548840144,"mean":87.46655549866425,"min":75.37631164228648},"none":{"max":94.5914071286307,"mean":77.7589824403664,"min":51.52882128415899}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.930409893578826},"working_program_strength":{"all":85.9716434243253,"highest":92.68939233394522,"medium":87.46655549866425,"none":77.7589824403664}},{"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":3.5240959999999997},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7743340000000001},"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":83.29135088464709,"highest":90.10521246266784,"medium":78.74051338079505,"none":81.02832681047835},"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":92.96786719250883,"score":92.96786719250883},"GB2-02":{"attempts":3,"playable":79.11339082681899,"score":79.11339082681899},"GB2-03":{"attempts":3,"playable":86.026447093223,"score":86.026447093223},"GB2-04":{"attempts":3,"playable":72.13765196143093,"score":72.13765196143093},"GB2-05":{"attempts":3,"playable":91.70839638119408,"score":91.70839638119408},"GB2-06":{"attempts":3,"playable":93.57765180649874,"score":93.57765180649874},"GB2-07":{"attempts":3,"playable":73.86654091603708,"score":73.86654091603708},"GB2-08":{"attempts":3,"playable":76.93286089946498,"score":76.93286089946498}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.3283412053958,"score":95.3283412053958},"GB2-02":{"attempts":1,"playable":94.90134536902329,"score":94.90134536902329},"GB2-03":{"attempts":1,"playable":92.31429760149187,"score":92.31429760149187},"GB2-04":{"attempts":1,"playable":71.36738900330297,"score":71.36738900330297},"GB2-05":{"attempts":1,"playable":96.32822867229156,"score":96.32822867229156},"GB2-06":{"attempts":1,"playable":97.59621949905328,"score":97.59621949905328},"GB2-07":{"attempts":1,"playable":84.26031114528222,"score":84.26031114528222},"GB2-08":{"attempts":1,"playable":88.74556720550174,"score":88.74556720550174}},"medium":{"GB2-01":{"attempts":1,"playable":91.09689584420343,"score":91.09689584420343},"GB2-02":{"attempts":1,"playable":65.3112643213262,"score":65.3112643213262},"GB2-03":{"attempts":1,"playable":80.0135112307614,"score":80.0135112307614},"GB2-04":{"attempts":1,"playable":68.91831714733743,"score":68.91831714733743},"GB2-05":{"attempts":1,"playable":90.39961322834613,"score":90.39961322834613},"GB2-06":{"attempts":1,"playable":92.72384329500343,"score":92.72384329500343},"GB2-07":{"attempts":1,"playable":77.8944751985715,"score":77.8944751985715},"GB2-08":{"attempts":1,"playable":63.566186780810916,"score":63.566186780810916}},"none":{"GB2-01":{"attempts":1,"playable":92.47836452792725,"score":92.47836452792725},"GB2-02":{"attempts":1,"playable":77.12756279010748,"score":77.12756279010748},"GB2-03":{"attempts":1,"playable":85.75153244741574,"score":85.75153244741574},"GB2-04":{"attempts":1,"playable":76.12724973365236,"score":76.12724973365236},"GB2-05":{"attempts":1,"playable":88.39734724294453,"score":88.39734724294453},"GB2-06":{"attempts":1,"playable":90.41289262543951,"score":90.41289262543951},"GB2-07":{"attempts":1,"playable":59.444836404257536,"score":59.444836404257536},"GB2-08":{"attempts":1,"playable":78.48682871208231,"score":78.48682871208231}}},"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":97.59621949905328,"mean":83.29135088464709,"min":59.444836404257536},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.3283412053958,"GB2-02":94.90134536902329,"GB2-03":92.31429760149187,"GB2-04":71.36738900330297,"GB2-05":96.32822867229156,"GB2-06":97.59621949905328,"GB2-07":84.26031114528222,"GB2-08":88.74556720550174},"per_game_all":{"GB2-01":92.96786719250883,"GB2-02":79.11339082681899,"GB2-03":86.026447093223,"GB2-04":72.13765196143093,"GB2-05":91.70839638119408,"GB2-06":93.57765180649874,"GB2-07":73.86654091603708,"GB2-08":76.93286089946498},"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":2076.6581343922003,"GB2-02":1800.6315672086969,"GB2-03":1908.9677064775842,"GB2-04":1665.7779455742536,"GB2-05":2351.474224757169,"GB2-06":2324.2268211273945,"GB2-07":1803.7735815997887,"GB2-08":1851.2751610413704},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2163.432412376966,"GB2-02":2087.114888483457,"GB2-03":2080.321641258075,"GB2-04":1656.8686365638298,"GB2-05":2606.2084915529167,"GB2-06":2526.5508185952312,"GB2-07":1991.7706523482495,"GB2-08":2119.290618805424},"medium":{"GB2-01":2012.918723403062,"GB2-02":1597.039337102794,"GB2-03":1766.4198831055983,"GB2-04":1633.0392406409867,"GB2-05":2265.955669865375,"GB2-06":2259.9343719507233,"GB2-07":1851.0318162291715,"GB2-08":1575.6011673687674},"none":{"GB2-01":2053.6232673965724,"GB2-02":1717.74047603984,"GB2-03":1880.1615950690796,"GB2-04":1707.425959517944,"GB2-05":2182.2585128532146,"GB2-06":2186.1952728362294,"GB2-07":1568.5182762219456,"GB2-08":1858.9336969499197}},"per_game_tracks":{"highest":{"GB2-01":95.3283412053958,"GB2-02":94.90134536902329,"GB2-03":92.31429760149187,"GB2-04":71.36738900330297,"GB2-05":96.32822867229156,"GB2-06":97.59621949905328,"GB2-07":84.26031114528222,"GB2-08":88.74556720550174},"medium":{"GB2-01":91.09689584420343,"GB2-02":65.3112643213262,"GB2-03":80.0135112307614,"GB2-04":68.91831714733743,"GB2-05":90.39961322834613,"GB2-06":92.72384329500343,"GB2-07":77.8944751985715,"GB2-08":63.566186780810916},"none":{"GB2-01":92.47836452792725,"GB2-02":77.12756279010748,"GB2-03":85.75153244741574,"GB2-04":76.12724973365236,"GB2-05":88.39734724294453,"GB2-06":90.41289262543951,"GB2-07":59.444836404257536,"GB2-08":78.48682871208231}},"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":"2026-10-24T18:07:57Z","reasoning":{"highest":90.10521246266784,"medium":78.74051338079505,"none":81.02832681047835},"reasoning_agg":{"highest":{"max":97.59621949905328,"mean":90.10521246266784,"min":71.36738900330297},"medium":{"max":92.72384329500343,"mean":78.74051338079505,"min":63.566186780810916},"none":{"max":92.47836452792725,"mean":81.02832681047835,"min":59.444836404257536}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.364699081872786},"working_program_strength":{"all":83.29135088464709,"highest":90.10521246266784,"medium":78.74051338079505,"none":81.02832681047835}},{"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":1.40954},"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":1.4095399999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.31477,"mean":0.2003284,"median":0.218258,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.6026272000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.520818,"mean":0.45841275000000004,"median":0.456374,"min":0.383384,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":3.6673019999999994}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.520818,"mean":0.2783112166666667,"median":0.227979,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":24,"run_count":24,"total":6.679469199999999},"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":82.91015210616541,"highest":85.71901534767252,"medium":82.25744477813679,"none":80.75399619268694},"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":65.99690136083493,"score":65.99690136083493},"GB2-02":{"attempts":3,"playable":79.43193483784925,"score":79.43193483784925},"GB2-03":{"attempts":3,"playable":88.27733468525632,"score":88.27733468525632},"GB2-04":{"attempts":3,"playable":81.615561366007,"score":81.615561366007},"GB2-05":{"attempts":3,"playable":85.3448453006314,"score":85.3448453006314},"GB2-06":{"attempts":3,"playable":89.85734070960962,"score":89.85734070960962},"GB2-07":{"attempts":3,"playable":79.89582656411649,"score":79.89582656411649},"GB2-08":{"attempts":3,"playable":92.86147202501836,"score":92.86147202501836}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":93.24462885290633,"score":93.24462885290633},"GB2-02":{"attempts":1,"playable":79.70569279156288,"score":79.70569279156288},"GB2-03":{"attempts":1,"playable":87.31263492362999,"score":87.31263492362999},"GB2-04":{"attempts":1,"playable":83.76963489563613,"score":83.76963489563613},"GB2-05":{"attempts":1,"playable":90.39961322834613,"score":90.39961322834613},"GB2-06":{"attempts":1,"playable":85.3619372693454,"score":85.3619372693454},"GB2-07":{"attempts":1,"playable":74.60507048095543,"score":74.60507048095543},"GB2-08":{"attempts":1,"playable":91.35291033899789,"score":91.35291033899789}},"medium":{"GB2-01":{"attempts":1,"playable":61.260978179454206,"score":61.260978179454206},"GB2-02":{"attempts":1,"playable":76.03122628576318,"score":76.03122628576318},"GB2-03":{"attempts":1,"playable":88.7307271728901,"score":88.7307271728901},"GB2-04":{"attempts":1,"playable":82.15998971270707,"score":82.15998971270707},"GB2-05":{"attempts":1,"playable":80.97524285754415,"score":80.97524285754415},"GB2-06":{"attempts":1,"playable":92.1050424297417,"score":92.1050424297417},"GB2-07":{"attempts":1,"playable":85.11872824703423,"score":85.11872824703423},"GB2-08":{"attempts":1,"playable":91.67762333995961,"score":91.67762333995961}},"none":{"GB2-01":{"attempts":1,"playable":43.485097050144255,"score":43.485097050144255},"GB2-02":{"attempts":1,"playable":82.55888543622167,"score":82.55888543622167},"GB2-03":{"attempts":1,"playable":88.78864195924888,"score":88.78864195924888},"GB2-04":{"attempts":1,"playable":78.91705948967778,"score":78.91705948967778},"GB2-05":{"attempts":1,"playable":84.65967981600397,"score":84.65967981600397},"GB2-06":{"attempts":1,"playable":92.1050424297417,"score":92.1050424297417},"GB2-07":{"attempts":1,"playable":79.9636809643598,"score":79.9636809643598},"GB2-08":{"attempts":1,"playable":95.55388239609753,"score":95.55388239609753}}},"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":95.55388239609753,"mean":82.91015210616541,"min":43.485097050144255},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":6,"overall_ranking_status":"partial","per_game":{"GB2-01":93.24462885290633,"GB2-02":79.70569279156288,"GB2-03":87.31263492362999,"GB2-04":83.76963489563613,"GB2-05":90.39961322834613,"GB2-06":85.3619372693454,"GB2-07":74.60507048095543,"GB2-08":91.35291033899789},"per_game_all":{"GB2-01":65.99690136083493,"GB2-02":79.43193483784925,"GB2-03":88.27733468525632,"GB2-04":81.615561366007,"GB2-05":85.3448453006314,"GB2-06":89.85734070960962,"GB2-07":79.89582656411649,"GB2-08":92.86147202501836},"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":1688.217454475807,"GB2-02":1748.3631574655883,"GB2-03":1945.2686261887181,"GB2-04":1776.9907193496676,"GB2-05":2085.0079725688065,"GB2-06":2178.5024952458225,"GB2-07":1899.6243961800162,"GB2-08":2271.6797282713305},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2079.0321928963276,"GB2-02":1750.1119049923257,"GB2-03":1918.6853679187197,"GB2-04":1807.0306896972174,"GB2-05":2265.955669865375,"GB2-06":2058.1538704894015,"GB2-07":1791.8421164892864,"GB2-08":2204.9659507031483},"medium":{"GB2-01":1578.6091824657888,"GB2-02":1704.8472701708965,"GB2-03":1957.7162043194905,"GB2-04":1783.4280715702848,"GB2-05":1940.6679328305208,"GB2-06":2238.6768076240332,"GB2-07":2014.9440785629004,"GB2-08":2216.758933206887},"none":{"GB2-01":1407.0109880653047,"GB2-02":1790.130297233542,"GB2-03":1959.4043063279437,"GB2-04":1740.5133967815011,"GB2-05":2048.400315010524,"GB2-06":2238.6768076240332,"GB2-07":1892.0869934878622,"GB2-08":2393.3143009039554}},"per_game_tracks":{"highest":{"GB2-01":93.24462885290633,"GB2-02":79.70569279156288,"GB2-03":87.31263492362999,"GB2-04":83.76963489563613,"GB2-05":90.39961322834613,"GB2-06":85.3619372693454,"GB2-07":74.60507048095543,"GB2-08":91.35291033899789},"medium":{"GB2-01":61.260978179454206,"GB2-02":76.03122628576318,"GB2-03":88.7307271728901,"GB2-04":82.15998971270707,"GB2-05":80.97524285754415,"GB2-06":92.1050424297417,"GB2-07":85.11872824703423,"GB2-08":91.67762333995961},"none":{"GB2-01":43.485097050144255,"GB2-02":82.55888543622167,"GB2-03":88.78864195924888,"GB2-04":78.91705948967778,"GB2-05":84.65967981600397,"GB2-06":92.1050424297417,"GB2-07":79.9636809643598,"GB2-08":95.55388239609753}},"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":85.71901534767252,"medium":82.25744477813679,"none":80.75399619268694},"reasoning_agg":{"highest":{"max":93.24462885290633,"mean":85.71901534767252,"min":74.60507048095543},"medium":{"max":92.1050424297417,"mean":82.25744477813679,"min":61.260978179454206},"none":{"max":95.55388239609753,"mean":80.75399619268694,"min":43.485097050144255}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":4.965019154985583},"working_program_strength":{"all":82.91015210616541,"highest":85.71901534767252,"medium":82.25744477813679,"none":80.75399619268694}},{"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":22.074450000000002},"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":4.570124999999999},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.07445}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.783449999999995},"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":78.1353671853794,"highest":86.13426288072226,"medium":76.4778641336363,"none":71.79397454177959},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"too_slow"},"medium":{"GB2-06":"too_slow"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["end_turn"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":48,"requested_max_output_token_observations":48,"requested_max_output_tokens":[128000],"total_output_tokens":1230744,"total_reasoning_output_tokens":878158,"total_visible_output_tokens":352586,"visible_token_observations":48},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":72.79797622160557,"score":72.79797622160557},"GB2-02":{"attempts":6,"playable":74.85751737915977,"score":74.85751737915977},"GB2-03":{"attempts":6,"playable":77.71484544433575,"score":77.71484544433575},"GB2-04":{"attempts":6,"playable":58.10556718072454,"score":58.10556718072454},"GB2-05":{"attempts":6,"playable":90.47948806016366,"score":90.47948806016366},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":4,"playable":85.39201401487168,"score":85.39201401487168},"GB2-08":{"attempts":6,"playable":81.99248710158273,"score":81.99248710158273}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":70.03278917166492,"score":70.03278917166492},"GB2-02":{"attempts":2,"playable":83.41388903712786,"score":83.41388903712786},"GB2-03":{"attempts":2,"playable":94.75591830600256,"score":94.75591830600256},"GB2-04":{"attempts":2,"playable":80.43217375160833,"score":80.43217375160833},"GB2-05":{"attempts":2,"playable":93.32967242190527,"score":93.32967242190527},"GB2-07":{"attempts":1,"playable":95.89865809396942,"score":95.89865809396942},"GB2-08":{"attempts":2,"playable":85.07673938277742,"score":85.07673938277742}},"medium":{"GB2-01":{"attempts":2,"playable":71.66073214835362,"score":71.66073214835362},"GB2-02":{"attempts":2,"playable":69.61904934172595,"score":69.61904934172595},"GB2-03":{"attempts":2,"playable":86.70136256363813,"score":86.70136256363813},"GB2-04":{"attempts":2,"playable":44.74996282207886,"score":44.74996282207886},"GB2-05":{"attempts":2,"playable":88.95917231625977,"score":88.95917231625977},"GB2-07":{"attempts":2,"playable":84.28516202622764,"score":84.28516202622764},"GB2-08":{"attempts":2,"playable":89.36960771717011,"score":89.36960771717011}},"none":{"GB2-01":{"attempts":2,"playable":76.70040734479815,"score":76.70040734479815},"GB2-02":{"attempts":2,"playable":71.53961375862548,"score":71.53961375862548},"GB2-03":{"attempts":2,"playable":51.687255463366554,"score":51.687255463366554},"GB2-04":{"attempts":2,"playable":49.134564968486444,"score":49.134564968486444},"GB2-05":{"attempts":2,"playable":89.14961944232594,"score":89.14961944232594},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":1,"playable":75.99222192441798,"score":75.99222192441798},"GB2-08":{"attempts":2,"playable":71.53111420480064,"score":71.53111420480064}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:21Z","match_totals_all":{"draws":2690,"losses":3672,"wins":14595},"match_totals_tracks":{"highest":{"draws":377,"losses":835,"wins":5430},"medium":{"draws":994,"losses":1255,"wins":4922},"none":{"draws":1319,"losses":1582,"wins":4243}},"model_slug":"claude-opus-5","official_rank_by_reasoning":{"highest":7,"medium":6,"none":9},"overall":{"max":95.89865809396942,"mean":78.1353671853794,"min":44.74996282207886},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":70.03278917166492,"GB2-02":83.41388903712786,"GB2-03":94.75591830600256,"GB2-04":80.43217375160833,"GB2-05":93.32967242190527,"GB2-07":95.89865809396942,"GB2-08":85.07673938277742},"per_game_all":{"GB2-01":72.79797622160557,"GB2-02":74.85751737915977,"GB2-03":77.71484544433575,"GB2-04":58.10556718072454,"GB2-05":90.47948806016366,"GB2-07":85.39201401487168,"GB2-08":81.99248710158273},"per_game_match_totals_all":{"GB2-01":{"draws":469,"losses":662,"wins":1965},"GB2-02":{"draws":1001,"losses":261,"wins":1617},"GB2-03":{"draws":156,"losses":643,"wins":2165},"GB2-04":{"draws":1016,"losses":789,"wins":1183},"GB2-05":{"draws":0,"losses":316,"wins":2864},"GB2-06":{"draws":23,"losses":52,"wins":427},"GB2-07":{"draws":0,"losses":318,"wins":1802},"GB2-08":{"draws":25,"losses":631,"wins":2572}},"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":51,"wins":928},"GB2-04":{"draws":165,"losses":124,"wins":707},"GB2-05":{"draws":0,"losses":72,"wins":988},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":178,"wins":898}},"medium":{"GB2-01":{"draws":98,"losses":264,"wins":670},"GB2-02":{"draws":422,"losses":95,"wins":442},"GB2-03":{"draws":16,"losses":141,"wins":831},"GB2-04":{"draws":456,"losses":339,"wins":201},"GB2-05":{"draws":0,"losses":123,"wins":937},"GB2-07":{"draws":0,"losses":168,"wins":892},"GB2-08":{"draws":2,"losses":125,"wins":949}},"none":{"GB2-01":{"draws":354,"losses":81,"wins":597},"GB2-02":{"draws":393,"losses":91,"wins":476},"GB2-03":{"draws":131,"losses":451,"wins":406},"GB2-04":{"draws":395,"losses":326,"wins":275},"GB2-05":{"draws":0,"losses":121,"wins":939},"GB2-06":{"draws":23,"losses":52,"wins":427},"GB2-07":{"draws":0,"losses":132,"wins":398},"GB2-08":{"draws":23,"losses":328,"wins":725}}},"per_game_raw_elo_all":{"GB2-01":1747.7917124158903,"GB2-02":1702.1735142986474,"GB2-03":1847.1281522193333,"GB2-04":1558.1985599025386,"GB2-05":2332.5966950690918,"GB2-07":2120.2597153940956,"GB2-08":1973.6089423322464},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.3846270191943,"GB2-02":1810.5184274829405,"GB2-03":2195.4994855511886,"GB2-04":1771.5149579701506,"GB2-05":2565.1814349193282,"GB2-07":2495.810403977528,"GB2-08":2040.1918099553495},"medium":{"GB2-01":1703.6636209749533,"GB2-02":1637.168389042536,"GB2-03":1903.1577602345221,"GB2-04":1434.2644060019313,"GB2-05":2219.910221470681,"GB2-07":2048.9361567422693,"GB2-08":2162.9108719079436},"none":{"GB2-01":1795.3268892535239,"GB2-02":1658.8337263704664,"GB2-03":1442.727210872289,"GB2-04":1468.8163157355334,"GB2-05":2212.698428817266,"GB2-06":2136.948866428713,"GB2-07":1816.0325854624894,"GB2-08":1717.7241451334462}},"per_game_tracks":{"highest":{"GB2-01":70.03278917166492,"GB2-02":83.41388903712786,"GB2-03":94.75591830600256,"GB2-04":80.43217375160833,"GB2-05":93.32967242190527,"GB2-07":95.89865809396942,"GB2-08":85.07673938277742},"medium":{"GB2-01":71.66073214835362,"GB2-02":69.61904934172595,"GB2-03":86.70136256363813,"GB2-04":44.74996282207886,"GB2-05":88.95917231625977,"GB2-07":84.28516202622764,"GB2-08":89.36960771717011},"none":{"GB2-01":76.70040734479815,"GB2-02":71.53961375862548,"GB2-03":51.687255463366554,"GB2-04":49.134564968486444,"GB2-05":89.14961944232594,"GB2-06":88.61699922741556,"GB2-07":75.99222192441798,"GB2-08":71.53111420480064}},"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":"2026-10-24T19:14:15Z","reasoning":{"highest":86.13426288072226,"medium":76.4778641336363,"none":71.79397454177959},"reasoning_agg":{"highest":{"max":95.89865809396942,"mean":86.13426288072226,"min":70.03278917166492},"medium":{"max":89.36960771717011,"mean":76.4778641336363,"min":44.74996282207886},"none":{"max":89.14961944232594,"mean":71.79397454177959,"min":49.134564968486444}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.34028833894267},"working_program_strength":{"all":78.1353671853794,"highest":86.13426288072226,"medium":76.4778641336363,"none":71.79397454177959}},{"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":0.6265164999999999},"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":2.6264425000000005},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":74.6543777201625,"highest":80.57319747530642,"medium":76.36599413720651,"none":67.02394154797457},"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":37.34508605251494,"score":37.34508605251494},"GB2-02":{"attempts":3,"playable":68.67341510548484,"score":68.67341510548484},"GB2-03":{"attempts":3,"playable":83.9238618625356,"score":83.9238618625356},"GB2-04":{"attempts":3,"playable":68.60793756021666,"score":68.60793756021666},"GB2-05":{"attempts":3,"playable":87.74504261374699,"score":87.74504261374699},"GB2-06":{"attempts":3,"playable":81.77693599914004,"score":81.77693599914004},"GB2-07":{"attempts":3,"playable":82.03156085480362,"score":82.03156085480362},"GB2-08":{"attempts":3,"playable":87.13118171285733,"score":87.13118171285733}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":10.356509846524498,"score":10.356509846524498},"GB2-02":{"attempts":1,"playable":83.63490681890951,"score":83.63490681890951},"GB2-03":{"attempts":1,"playable":94.37003524976566,"score":94.37003524976566},"GB2-04":{"attempts":1,"playable":88.27020369252344,"score":88.27020369252344},"GB2-05":{"attempts":1,"playable":93.750733178957,"score":93.750733178957},"GB2-06":{"attempts":1,"playable":90.23388548276091,"score":90.23388548276091},"GB2-07":{"attempts":1,"playable":94.40710040325735,"score":94.40710040325735},"GB2-08":{"attempts":1,"playable":89.56220512975295,"score":89.56220512975295}},"medium":{"GB2-01":{"attempts":1,"playable":39.836679794128194,"score":39.836679794128194},"GB2-02":{"attempts":1,"playable":69.48910933445279,"score":69.48910933445279},"GB2-03":{"attempts":1,"playable":75.12913585488103,"score":75.12913585488103},"GB2-04":{"attempts":1,"playable":73.60851800637032,"score":73.60851800637032},"GB2-05":{"attempts":1,"playable":91.5661282050239,"score":91.5661282050239},"GB2-06":{"attempts":1,"playable":81.54823367582276,"score":81.54823367582276},"GB2-07":{"attempts":1,"playable":94.04021600292965,"score":94.04021600292965},"GB2-08":{"attempts":1,"playable":85.70993222404344,"score":85.70993222404344}},"none":{"GB2-01":{"attempts":1,"playable":61.84206851689213,"score":61.84206851689213},"GB2-02":{"attempts":1,"playable":52.89622916309222,"score":52.89622916309222},"GB2-03":{"attempts":1,"playable":82.27241448296013,"score":82.27241448296013},"GB2-04":{"attempts":1,"playable":43.945090981756195,"score":43.945090981756195},"GB2-05":{"attempts":1,"playable":77.91826645726006,"score":77.91826645726006},"GB2-06":{"attempts":1,"playable":73.54868883883643,"score":73.54868883883643},"GB2-07":{"attempts":1,"playable":57.64736615822385,"score":57.64736615822385},"GB2-08":{"attempts":1,"playable":86.1214077847756,"score":86.1214077847756}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-10-26T01:50:40Z","match_totals_all":{"draws":1572,"losses":2466,"wins":8226},"match_totals_tracks":{"highest":{"draws":240,"losses":698,"wins":3150},"medium":{"draws":626,"losses":701,"wins":2761},"none":{"draws":706,"losses":1067,"wins":2315}},"model_slug":"gpt-6-sol","official_rank_by_reasoning":{"highest":10,"medium":7,"none":10},"overall":{"max":94.40710040325735,"mean":74.6543777201625,"min":10.356509846524498},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":10.356509846524498,"GB2-02":83.63490681890951,"GB2-03":94.37003524976566,"GB2-04":88.27020369252344,"GB2-05":93.750733178957,"GB2-06":90.23388548276091,"GB2-07":94.40710040325735,"GB2-08":89.56220512975295},"per_game_all":{"GB2-01":37.34508605251494,"GB2-02":68.67341510548484,"GB2-03":83.9238618625356,"GB2-04":68.60793756021666,"GB2-05":87.74504261374699,"GB2-06":81.77693599914004,"GB2-07":82.03156085480362,"GB2-08":87.13118171285733},"per_game_match_totals_all":{"GB2-01":{"draws":208,"losses":892,"wins":448},"GB2-02":{"draws":643,"losses":150,"wins":647},"GB2-03":{"draws":76,"losses":230,"wins":1176},"GB2-04":{"draws":523,"losses":227,"wins":744},"GB2-05":{"draws":0,"losses":204,"wins":1386},"GB2-06":{"draws":105,"losses":251,"wins":1150},"GB2-07":{"draws":0,"losses":290,"wins":1300},"GB2-08":{"draws":17,"losses":222,"wins":1375}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":453,"wins":34},"GB2-02":{"draws":128,"losses":19,"wins":333},"GB2-03":{"draws":4,"losses":28,"wins":462},"GB2-04":{"draws":54,"losses":35,"wins":409},"GB2-05":{"draws":0,"losses":33,"wins":497},"GB2-06":{"draws":25,"losses":42,"wins":435},"GB2-07":{"draws":0,"losses":26,"wins":504},"GB2-08":{"draws":0,"losses":62,"wins":476}},"medium":{"GB2-01":{"draws":163,"losses":239,"wins":114},"GB2-02":{"draws":218,"losses":45,"wins":217},"GB2-03":{"draws":39,"losses":119,"wins":336},"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":297,"losses":86,"wins":97},"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":43,"losses":125,"wins":334},"GB2-07":{"draws":0,"losses":236,"wins":294},"GB2-08":{"draws":8,"losses":79,"wins":451}}},"per_game_raw_elo_all":{"GB2-01":1315.439987865404,"GB2-02":1645.6092160905962,"GB2-03":1890.894213738509,"GB2-04":1664.2977404343856,"GB2-05":2205.7918846923444,"GB2-06":1991.936905231083,"GB2-07":2107.3551979844983,"GB2-08":2074.0468541290666},"per_game_raw_elo_tracks":{"highest":{"GB2-01":990.0346525947057,"GB2-02":1806.6650309680745,"GB2-03":2174.1415376681953,"GB2-04":1884.8324442678904,"GB2-05":2432.180309228762,"GB2-06":2181.0320870366377,"GB2-07":2399.3496329208683,"GB2-08":2144.6518970332586},"medium":{"GB2-01":1371.7959985331972,"GB2-02":1635.9057115768715,"GB2-03":1691.5737740691018,"GB2-04":1679.8825590052788,"GB2-05":2319.3682279720074,"GB2-06":1975.7691192211446,"GB2-07":2377.8173145492083,"GB2-08":2033.2189154404587},"none":{"GB2-01":1584.489312468309,"GB2-02":1494.2569057268424,"GB2-03":1806.9673294782294,"GB2-04":1428.1782180299879,"GB2-05":1865.8271168762633,"GB2-06":1819.0095094354679,"GB2-07":1544.898646483419,"GB2-08":2044.2697499134833}},"per_game_tracks":{"highest":{"GB2-01":10.356509846524498,"GB2-02":83.63490681890951,"GB2-03":94.37003524976566,"GB2-04":88.27020369252344,"GB2-05":93.750733178957,"GB2-06":90.23388548276091,"GB2-07":94.40710040325735,"GB2-08":89.56220512975295},"medium":{"GB2-01":39.836679794128194,"GB2-02":69.48910933445279,"GB2-03":75.12913585488103,"GB2-04":73.60851800637032,"GB2-05":91.5661282050239,"GB2-06":81.54823367582276,"GB2-07":94.04021600292965,"GB2-08":85.70993222404344},"none":{"GB2-01":61.84206851689213,"GB2-02":52.89622916309222,"GB2-03":82.27241448296013,"GB2-04":43.945090981756195,"GB2-05":77.91826645726006,"GB2-06":73.54868883883643,"GB2-07":57.64736615822385,"GB2-08":86.1214077847756}},"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":"2026-10-24T19:20:38Z","reasoning":{"highest":80.57319747530642,"medium":76.36599413720651,"none":67.02394154797457},"reasoning_agg":{"highest":{"max":94.40710040325735,"mean":80.57319747530642,"min":10.356509846524498},"medium":{"max":94.04021600292965,"mean":76.36599413720651,"min":39.836679794128194},"none":{"max":86.1214077847756,"mean":67.02394154797457,"min":43.945090981756195}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.549255927331842},"working_program_strength":{"all":74.6543777201625,"highest":80.57319747530642,"medium":76.36599413720651,"none":67.02394154797457}},{"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":1.832505},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.8325049999999998},"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":68.71889732947413,"highest":81.09567801680645,"medium":67.9956324960286,"none":57.06538147558733},"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":74.4383451676892,"score":74.4383451676892},"GB2-02":{"attempts":3,"playable":63.1856358272517,"score":63.1856358272517},"GB2-03":{"attempts":3,"playable":65.49737405025711,"score":65.49737405025711},"GB2-04":{"attempts":3,"playable":67.86626132998586,"score":67.86626132998586},"GB2-05":{"attempts":3,"playable":68.76280511643667,"score":68.76280511643667},"GB2-06":{"attempts":3,"playable":62.7995232098101,"score":62.7995232098101},"GB2-07":{"attempts":3,"playable":69.21418690191489,"score":69.21418690191489},"GB2-08":{"attempts":3,"playable":77.98704703244748,"score":77.98704703244748}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":75.18644442389503,"score":75.18644442389503},"GB2-02":{"attempts":1,"playable":75.83154243743509,"score":75.83154243743509},"GB2-03":{"attempts":1,"playable":80.64898951980767,"score":80.64898951980767},"GB2-04":{"attempts":1,"playable":83.86406826181346,"score":83.86406826181346},"GB2-05":{"attempts":1,"playable":75.91303436651312,"score":75.91303436651312},"GB2-06":{"attempts":1,"playable":85.27126349579316,"score":85.27126349579316},"GB2-07":{"attempts":1,"playable":88.7341773057466,"score":88.7341773057466},"GB2-08":{"attempts":1,"playable":83.31590432344747,"score":83.31590432344747}},"medium":{"GB2-01":{"attempts":1,"playable":68.78596380719114,"score":68.78596380719114},"GB2-02":{"attempts":1,"playable":67.96492649750486,"score":67.96492649750486},"GB2-03":{"attempts":1,"playable":62.16771778328458,"score":62.16771778328458},"GB2-04":{"attempts":1,"playable":78.34160803379433,"score":78.34160803379433},"GB2-05":{"attempts":1,"playable":76.8267887285266,"score":76.8267887285266},"GB2-06":{"attempts":1,"playable":41.85962447765607,"score":41.85962447765607},"GB2-07":{"attempts":1,"playable":71.2967744860653,"score":71.2967744860653},"GB2-08":{"attempts":1,"playable":76.7216561542059,"score":76.7216561542059}},"none":{"GB2-01":{"attempts":1,"playable":79.34262727198148,"score":79.34262727198148},"GB2-02":{"attempts":1,"playable":45.76043854681514,"score":45.76043854681514},"GB2-03":{"attempts":1,"playable":53.67541484767906,"score":53.67541484767906},"GB2-04":{"attempts":1,"playable":41.39310769434979,"score":41.39310769434979},"GB2-05":{"attempts":1,"playable":53.54859225427029,"score":53.54859225427029},"GB2-06":{"attempts":1,"playable":61.26768165598104,"score":61.26768165598104},"GB2-07":{"attempts":1,"playable":47.61160891393276,"score":47.61160891393276},"GB2-08":{"attempts":1,"playable":73.92358061968909,"score":73.92358061968909}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-10-26T01:03:22Z","match_totals_all":{"draws":1678,"losses":3239,"wins":7347},"match_totals_tracks":{"highest":{"draws":300,"losses":681,"wins":3107},"medium":{"draws":544,"losses":1126,"wins":2418},"none":{"draws":834,"losses":1432,"wins":1822}},"model_slug":"gpt-5-6-sol","official_rank_by_reasoning":{"highest":9,"medium":12,"none":12},"overall":{"max":88.7341773057466,"mean":68.71889732947413,"min":41.39310769434979},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":75.18644442389503,"GB2-02":75.83154243743509,"GB2-03":80.64898951980767,"GB2-04":83.86406826181346,"GB2-05":75.91303436651312,"GB2-06":85.27126349579316,"GB2-07":88.7341773057466,"GB2-08":83.31590432344747},"per_game_all":{"GB2-01":74.4383451676892,"GB2-02":63.1856358272517,"GB2-03":65.49737405025711,"GB2-04":67.86626132998586,"GB2-05":68.76280511643667,"GB2-06":62.7995232098101,"GB2-07":69.21418690191489,"GB2-08":77.98704703244748},"per_game_match_totals_all":{"GB2-01":{"draws":124,"losses":365,"wins":1059},"GB2-02":{"draws":751,"losses":177,"wins":512},"GB2-03":{"draws":198,"losses":464,"wins":820},"GB2-04":{"draws":536,"losses":232,"wins":726},"GB2-05":{"draws":0,"losses":522,"wins":1068},"GB2-06":{"draws":24,"losses":598,"wins":884},"GB2-07":{"draws":0,"losses":508,"wins":1082},"GB2-08":{"draws":45,"losses":373,"wins":1196}},"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":14,"losses":75,"wins":413},"GB2-07":{"draws":0,"losses":58,"wins":472},"GB2-08":{"draws":0,"losses":100,"wins":438}},"medium":{"GB2-01":{"draws":110,"losses":117,"wins":289},"GB2-02":{"draws":215,"losses":54,"wins":211},"GB2-03":{"draws":52,"losses":180,"wins":262},"GB2-04":{"draws":129,"losses":50,"wins":319},"GB2-05":{"draws":0,"losses":131,"wins":399},"GB2-06":{"draws":7,"losses":311,"wins":184},"GB2-07":{"draws":0,"losses":159,"wins":371},"GB2-08":{"draws":31,"losses":124,"wins":383}},"none":{"GB2-01":{"draws":1,"losses":116,"wins":399},"GB2-02":{"draws":357,"losses":90,"wins":33},"GB2-03":{"draws":141,"losses":178,"wins":175},"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":291,"wins":239},"GB2-08":{"draws":14,"losses":149,"wins":375}}},"per_game_raw_elo_all":{"GB2-01":1726.8407023480293,"GB2-02":1587.6357101943674,"GB2-03":1592.8513183295163,"GB2-04":1650.0803694014892,"GB2-05":1715.247132375341,"GB2-06":1650.6456256598442,"GB2-07":1762.0016234367213,"GB2-08":1851.5280839432407},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1733.4602585338487,"GB2-02":1702.5484000698048,"GB2-03":1777.372615499862,"GB2-04":1808.472048227705,"GB2-05":1822.350537410597,"GB2-06":2056.095424597048,"GB2-07":2130.6046636518868,"GB2-08":1971.799213921062},"medium":{"GB2-01":1657.9311853391996,"GB2-02":1621.3585354868248,"GB2-03":1540.786143196647,"GB2-04":1733.4334284108695,"GB2-05":1841.6765223784937,"GB2-06":1295.422775566106,"GB2-07":1737.6956879524764,"GB2-08":1820.4969430956755},"none":{"GB2-01":1789.1306631710397,"GB2-02":1439.000195026472,"GB2-03":1460.3951962920405,"GB2-04":1408.3356315658925,"GB2-05":1481.7143373369327,"GB2-06":1600.4186768163788,"GB2-07":1417.7045187058002,"GB2-08":1762.2880948129853}},"per_game_tracks":{"highest":{"GB2-01":75.18644442389503,"GB2-02":75.83154243743509,"GB2-03":80.64898951980767,"GB2-04":83.86406826181346,"GB2-05":75.91303436651312,"GB2-06":85.27126349579316,"GB2-07":88.7341773057466,"GB2-08":83.31590432344747},"medium":{"GB2-01":68.78596380719114,"GB2-02":67.96492649750486,"GB2-03":62.16771778328458,"GB2-04":78.34160803379433,"GB2-05":76.8267887285266,"GB2-06":41.85962447765607,"GB2-07":71.2967744860653,"GB2-08":76.7216561542059},"none":{"GB2-01":79.34262727198148,"GB2-02":45.76043854681514,"GB2-03":53.67541484767906,"GB2-04":41.39310769434979,"GB2-05":53.54859225427029,"GB2-06":61.26768165598104,"GB2-07":47.61160891393276,"GB2-08":73.92358061968909}},"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":"2026-10-24T18:22:52Z","reasoning":{"highest":81.09567801680645,"medium":67.9956324960286,"none":57.06538147558733},"reasoning_agg":{"highest":{"max":88.7341773057466,"mean":81.09567801680645,"min":75.18644442389503},"medium":{"max":78.34160803379433,"mean":67.9956324960286,"min":41.85962447765607},"none":{"max":79.34262727198148,"mean":57.06538147558733,"min":41.39310769434979}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.030296541219116},"working_program_strength":{"all":68.71889732947413,"highest":81.09567801680645,"medium":67.9956324960286,"none":57.06538147558733}},{"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":11.76455},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885},"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":11.764550000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":0.7608541666666667,"median":0.47084000000000004,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":18.2605},"codegen_output_tokens":{"attempt_count":24,"output_max":40578,"output_mean":12704.708333333334,"output_min":2179,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":40578,"output_mean":26899.0,"output_min":17366,"run_count":8},"medium":{"attempt_count":8,"output_max":12403,"output_mean":7955.375,"output_min":4188,"run_count":8},"none":{"attempt_count":8,"output_max":4224,"output_mean":3259.75,"output_min":2179,"run_count":8}},"display_name":"Claude Fable 5","economics":{"all":67.64435819062936,"highest":76.91860004426469,"medium":65.81695308116886,"none":60.19752144645451},"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":78.02734128003563,"score":78.02734128003563},"GB2-02":{"attempts":3,"playable":60.51420484516879,"score":60.51420484516879},"GB2-03":{"attempts":3,"playable":47.596672170908796,"score":47.596672170908796},"GB2-04":{"attempts":3,"playable":58.850930683219,"score":58.850930683219},"GB2-05":{"attempts":3,"playable":64.90913079811553,"score":64.90913079811553},"GB2-06":{"attempts":3,"playable":82.11945177061433,"score":82.11945177061433},"GB2-07":{"attempts":3,"playable":67.17881235615329,"score":67.17881235615329},"GB2-08":{"attempts":3,"playable":81.95832162081943,"score":81.95832162081943}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":86.19355407039457,"score":86.19355407039457},"GB2-02":{"attempts":1,"playable":80.0019542790766,"score":80.0019542790766},"GB2-03":{"attempts":1,"playable":86.8763585040966,"score":86.8763585040966},"GB2-04":{"attempts":1,"playable":84.24151960692818,"score":84.24151960692818},"GB2-05":{"attempts":1,"playable":56.79079270779831,"score":56.79079270779831},"GB2-06":{"attempts":1,"playable":87.62475669772357,"score":87.62475669772357},"GB2-07":{"attempts":1,"playable":65.85198272520387,"score":65.85198272520387},"GB2-08":{"attempts":1,"playable":67.76788176289583,"score":67.76788176289583}},"medium":{"GB2-01":{"attempts":1,"playable":76.4190951971478,"score":76.4190951971478},"GB2-02":{"attempts":1,"playable":57.996058159075126,"score":57.996058159075126},"GB2-03":{"attempts":1,"playable":20.85286434586851,"score":20.85286434586851},"GB2-04":{"attempts":1,"playable":53.57872837341826,"score":53.57872837341826},"GB2-05":{"attempts":1,"playable":69.24862460139967,"score":69.24862460139967},"GB2-06":{"attempts":1,"playable":81.72998896896267,"score":81.72998896896267},"GB2-07":{"attempts":1,"playable":73.7364089726703,"score":73.7364089726703},"GB2-08":{"attempts":1,"playable":92.97385603080852,"score":92.97385603080852}},"none":{"GB2-01":{"attempts":1,"playable":71.46937457256453,"score":71.46937457256453},"GB2-02":{"attempts":1,"playable":43.54460209735465,"score":43.54460209735465},"GB2-03":{"attempts":1,"playable":35.06079366276128,"score":35.06079366276128},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":68.68797508514861,"score":68.68797508514861},"GB2-06":{"attempts":1,"playable":77.00360964515674,"score":77.00360964515674},"GB2-07":{"attempts":1,"playable":61.94804537058572,"score":61.94804537058572},"GB2-08":{"attempts":1,"playable":85.13322706875395,"score":85.13322706875395}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-10-26T01:48:13Z","match_totals_all":{"draws":1958,"losses":3184,"wins":7122},"match_totals_tracks":{"highest":{"draws":307,"losses":873,"wins":2908},"medium":{"draws":734,"losses":1078,"wins":2276},"none":{"draws":917,"losses":1233,"wins":1938}},"model_slug":"claude-fable-5","official_rank_by_reasoning":{"highest":12,"medium":16,"none":11},"overall":{"max":92.97385603080852,"mean":67.64435819062936,"min":20.85286434586851},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":86.19355407039457,"GB2-02":80.0019542790766,"GB2-03":86.8763585040966,"GB2-04":84.24151960692818,"GB2-05":56.79079270779831,"GB2-06":87.62475669772357,"GB2-07":65.85198272520387,"GB2-08":67.76788176289583},"per_game_all":{"GB2-01":78.02734128003563,"GB2-02":60.51420484516879,"GB2-03":47.596672170908796,"GB2-04":58.850930683219,"GB2-05":64.90913079811553,"GB2-06":82.11945177061433,"GB2-07":67.17881235615329,"GB2-08":81.95832162081943},"per_game_match_totals_all":{"GB2-01":{"draws":103,"losses":318,"wins":1127},"GB2-02":{"draws":759,"losses":211,"wins":470},"GB2-03":{"draws":336,"losses":647,"wins":499},"GB2-04":{"draws":663,"losses":305,"wins":526},"GB2-05":{"draws":0,"losses":585,"wins":1005},"GB2-06":{"draws":62,"losses":267,"wins":1177},"GB2-07":{"draws":0,"losses":547,"wins":1043},"GB2-08":{"draws":35,"losses":304,"wins":1275}},"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":58,"wins":422},"GB2-07":{"draws":0,"losses":190,"wins":340},"GB2-08":{"draws":35,"losses":174,"wins":329}},"medium":{"GB2-01":{"draws":38,"losses":113,"wins":365},"GB2-02":{"draws":282,"losses":69,"wins":129},"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":27,"losses":88,"wins":387},"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":188,"losses":244,"wins":62},"GB2-04":{"draws":300,"losses":163,"wins":35},"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":0,"losses":89,"wins":449}}},"per_game_raw_elo_all":{"GB2-01":1779.702284255998,"GB2-02":1570.2713807448906,"GB2-03":1452.8354095445065,"GB2-04":1568.1808746120012,"GB2-05":1638.2410445410285,"GB2-06":1992.083454352891,"GB2-07":1678.5389878490976,"GB2-08":1977.049746054322},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1901.3922953285614,"GB2-02":1754.0417056590265,"GB2-03":1907.4901793030406,"GB2-04":1814.3011955954241,"GB2-05":1522.955755354125,"GB2-06":2111.7611316098973,"GB2-07":1656.3614423284157,"GB2-08":1645.869336392291},"medium":{"GB2-01":1749.294697825931,"GB2-02":1534.8835723213037,"GB2-03":1154.2090918509548,"GB2-04":1502.8494403264513,"GB2-05":1700.4202257172562,"GB2-06":1979.5357740090376,"GB2-07":1777.1802573955938,"GB2-08":2267.2836666461235},"none":{"GB2-01":1688.419859613501,"GB2-02":1421.8888642543418,"GB2-03":1296.806957479525,"GB2-04":1387.3919879141274,"GB2-05":1691.3471525517039,"GB2-06":1884.9534574397385,"GB2-07":1602.0752638232827,"GB2-08":2017.9962351245513}},"per_game_tracks":{"highest":{"GB2-01":86.19355407039457,"GB2-02":80.0019542790766,"GB2-03":86.8763585040966,"GB2-04":84.24151960692818,"GB2-05":56.79079270779831,"GB2-06":87.62475669772357,"GB2-07":65.85198272520387,"GB2-08":67.76788176289583},"medium":{"GB2-01":76.4190951971478,"GB2-02":57.996058159075126,"GB2-03":20.85286434586851,"GB2-04":53.57872837341826,"GB2-05":69.24862460139967,"GB2-06":81.72998896896267,"GB2-07":73.7364089726703,"GB2-08":92.97385603080852},"none":{"GB2-01":71.46937457256453,"GB2-02":43.54460209735465,"GB2-03":35.06079366276128,"GB2-04":38.73254406931057,"GB2-05":68.68797508514861,"GB2-06":77.00360964515674,"GB2-07":61.94804537058572,"GB2-08":85.13322706875395}},"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":"2026-10-24T18:32:54Z","reasoning":{"highest":76.91860004426469,"medium":65.81695308116886,"none":60.19752144645451},"reasoning_agg":{"highest":{"max":87.62475669772357,"mean":76.91860004426469,"min":56.79079270779831},"medium":{"max":92.97385603080852,"mean":65.81695308116886,"min":20.85286434586851},"none":{"max":85.13322706875395,"mean":60.19752144645451,"min":35.06079366276128}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.721078597810184},"working_program_strength":{"all":67.64435819062936,"highest":76.91860004426469,"medium":65.81695308116886,"none":60.19752144645451}},{"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":0.9656475999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007552}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.2861911833333333,"median":0.206604,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":30},"recorded_attempt_count":30,"run_count":24,"total":6.868588399999999},"codegen_latency_ms":{"attempt_count":30,"max_ms":235793,"mean_ms":83718.41666666667,"min_ms":17910,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":235793,"mean_ms":170391.375,"min_ms":123596,"run_count":8},"medium":{"attempt_count":11,"max_ms":84789,"mean_ms":58477.125,"min_ms":40383,"run_count":8},"none":{"attempt_count":10,"max_ms":29743,"mean_ms":22286.75,"min_ms":17910,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":29674,"output_mean":12261.208333333334,"output_min":3304,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":29674,"output_mean":22547.25,"output_min":16651,"run_count":8},"medium":{"attempt_count":11,"output_max":17493,"output_mean":10166.125,"output_min":6634,"run_count":8},"none":{"attempt_count":10,"output_max":5361,"output_mean":4070.25,"output_min":3304,"run_count":8}},"display_name":"Muse Wonder","economics":{"all":66.360366811438,"highest":78.79080297221228,"medium":63.482439435561815,"none":56.80785802653988},"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":69.12115266528907,"score":69.12115266528907},"GB2-02":{"attempts":3,"playable":55.29575213336481,"score":55.29575213336481},"GB2-03":{"attempts":3,"playable":45.64873763691519,"score":45.64873763691519},"GB2-04":{"attempts":3,"playable":58.436023354009336,"score":58.436023354009336},"GB2-05":{"attempts":3,"playable":87.86645242679431,"score":87.86645242679431},"GB2-06":{"attempts":3,"playable":76.88027256656011,"score":76.88027256656011},"GB2-07":{"attempts":3,"playable":71.87919552199297,"score":71.87919552199297},"GB2-08":{"attempts":3,"playable":65.7553481865781,"score":65.7553481865781}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":85.09852264593735,"score":85.09852264593735},"GB2-02":{"attempts":1,"playable":66.63991156296852,"score":66.63991156296852},"GB2-03":{"attempts":1,"playable":82.98897640682239,"score":82.98897640682239},"GB2-04":{"attempts":1,"playable":81.87510366079515,"score":81.87510366079515},"GB2-05":{"attempts":1,"playable":93.07462175455832,"score":93.07462175455832},"GB2-06":{"attempts":1,"playable":84.54555662982366,"score":84.54555662982366},"GB2-07":{"attempts":1,"playable":74.0840341297721,"score":74.0840341297721},"GB2-08":{"attempts":1,"playable":62.019696987020644,"score":62.019696987020644}},"medium":{"GB2-01":{"attempts":1,"playable":53.286943540124355,"score":53.286943540124355},"GB2-02":{"attempts":1,"playable":56.23109924276132,"score":56.23109924276132},"GB2-03":{"attempts":1,"playable":36.86911022917292,"score":36.86911022917292},"GB2-04":{"attempts":1,"playable":39.55185774658149,"score":39.55185774658149},"GB2-05":{"attempts":1,"playable":85.34823456158135,"score":85.34823456158135},"GB2-06":{"attempts":1,"playable":77.0945052028131,"score":77.0945052028131},"GB2-07":{"attempts":1,"playable":87.52572113245827,"score":87.52572113245827},"GB2-08":{"attempts":1,"playable":71.95204382900168,"score":71.95204382900168}},"none":{"GB2-01":{"attempts":1,"playable":68.97799180980552,"score":68.97799180980552},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"GB2-03":{"attempts":1,"playable":17.08812627475027,"score":17.08812627475027},"GB2-04":{"attempts":1,"playable":53.881108654651364,"score":53.881108654651364},"GB2-05":{"attempts":1,"playable":85.1765009642433,"score":85.1765009642433},"GB2-06":{"attempts":1,"playable":69.00075586704354,"score":69.00075586704354},"GB2-07":{"attempts":1,"playable":54.02783130374852,"score":54.02783130374852},"GB2-08":{"attempts":1,"playable":63.294303743711986,"score":63.294303743711986}}},"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":17,"none":13},"overall":{"max":93.07462175455832,"mean":66.360366811438,"min":17.08812627475027},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":85.09852264593735,"GB2-02":66.63991156296852,"GB2-03":82.98897640682239,"GB2-04":81.87510366079515,"GB2-05":93.07462175455832,"GB2-06":84.54555662982366,"GB2-07":74.0840341297721,"GB2-08":62.019696987020644},"per_game_all":{"GB2-01":69.12115266528907,"GB2-02":55.29575213336481,"GB2-03":45.64873763691519,"GB2-04":58.436023354009336,"GB2-05":87.86645242679431,"GB2-06":76.88027256656011,"GB2-07":71.87919552199297,"GB2-08":65.7553481865781},"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":1680.4999289616217,"GB2-02":1515.836395648733,"GB2-03":1413.678597623958,"GB2-04":1559.5105395193796,"GB2-05":2177.1451457459607,"GB2-06":1887.2506294254244,"GB2-07":1789.8271454467786,"GB2-08":1615.3568592551785},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1880.9852121041804,"GB2-02":1609.0676706845873,"GB2-03":1820.8537210749887,"GB2-04":1779.4268430315033,"GB2-05":2395.054730741312,"GB2-06":2039.8263305802402,"GB2-07":1783.005848020484,"GB2-08":1551.5209233850107},"medium":{"GB2-01":1500.448657626208,"GB2-02":1520.645109281515,"GB2-03":1312.9886283267042,"GB2-04":1393.8774951379276,"GB2-05":2071.055882575526,"GB2-06":1886.718674914524,"GB2-07":2088.186191803314,"GB2-08":1723.2487452513005},"none":{"GB2-01":1660.0659171544767,"GB2-02":1417.796406980097,"GB2-03":1107.1934434701814,"GB2-04":1505.2272803887083,"GB2-05":2065.3248239210448,"GB2-06":1735.206882781509,"GB2-07":1498.2893965165374,"GB2-08":1571.3009091292242}},"per_game_tracks":{"highest":{"GB2-01":85.09852264593735,"GB2-02":66.63991156296852,"GB2-03":82.98897640682239,"GB2-04":81.87510366079515,"GB2-05":93.07462175455832,"GB2-06":84.54555662982366,"GB2-07":74.0840341297721,"GB2-08":62.019696987020644},"medium":{"GB2-01":53.286943540124355,"GB2-02":56.23109924276132,"GB2-03":36.86911022917292,"GB2-04":39.55185774658149,"GB2-05":85.34823456158135,"GB2-06":77.0945052028131,"GB2-07":87.52572113245827,"GB2-08":71.95204382900168},"none":{"GB2-01":68.97799180980552,"GB2-02":43.016245594364584,"GB2-03":17.08812627475027,"GB2-04":53.881108654651364,"GB2-05":85.1765009642433,"GB2-06":69.00075586704354,"GB2-07":54.02783130374852,"GB2-08":63.294303743711986}},"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":"2026-10-24T16:50:59Z","reasoning":{"highest":78.79080297221228,"medium":63.482439435561815,"none":56.80785802653988},"reasoning_agg":{"highest":{"max":93.07462175455832,"mean":78.79080297221228,"min":62.019696987020644},"medium":{"max":87.52572113245827,"mean":63.482439435561815,"min":36.86911022917292},"none":{"max":85.1765009642433,"mean":56.80785802653988,"min":17.08812627475027}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":21.982944945672394},"working_program_strength":{"all":66.360366811438,"highest":78.79080297221228,"medium":63.482439435561815,"none":56.80785802653988}},{"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":1.2555551600000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181688}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.25555516},"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":4.3974162}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.2535328433333333,"median":0.1720692,"min":0.0217974,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":28,"run_count":24,"total":6.084788240000001},"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":65.67017991657261,"highest":73.5396849506316,"medium":72.04274607752602,"none":51.42810872156023},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":29,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":84,"requested_max_output_token_observations":10,"requested_max_output_tokens":[131072],"total_output_tokens":1317942,"total_reasoning_output_tokens":1189870,"total_visible_output_tokens":128072,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":60.01415966011352,"score":40.009439773409014},"GB2-02":{"attempts":3,"playable":57.38827055721098,"score":57.38827055721098},"GB2-03":{"attempts":3,"playable":68.50875129105536,"score":68.50875129105536},"GB2-04":{"attempts":3,"playable":69.75879863429311,"score":69.75879863429311},"GB2-05":{"attempts":3,"playable":72.35485792778526,"score":72.35485792778526},"GB2-06":{"attempts":3,"playable":77.77405117187433,"score":77.77405117187433},"GB2-07":{"attempts":3,"playable":75.75480727616724,"score":75.75480727616724},"GB2-08":{"attempts":3,"playable":63.812462700785574,"score":63.812462700785574}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":73.62806649246055,"score":73.62806649246055},"GB2-03":{"attempts":1,"playable":84.67860328128754,"score":84.67860328128754},"GB2-04":{"attempts":1,"playable":77.09164191029542,"score":77.09164191029542},"GB2-05":{"attempts":1,"playable":90.23309662476808,"score":90.23309662476808},"GB2-06":{"attempts":1,"playable":91.12735803677934,"score":91.12735803677934},"GB2-07":{"attempts":1,"playable":78.58485722865328,"score":78.58485722865328},"GB2-08":{"attempts":1,"playable":92.97385603080852,"score":92.97385603080852}},"medium":{"GB2-01":{"attempts":1,"playable":51.62656602805672,"score":51.62656602805672},"GB2-02":{"attempts":1,"playable":54.25293952450121,"score":54.25293952450121},"GB2-03":{"attempts":1,"playable":78.18527157184437,"score":78.18527157184437},"GB2-04":{"attempts":1,"playable":83.56150075093387,"score":83.56150075093387},"GB2-05":{"attempts":1,"playable":67.18977853745805,"score":67.18977853745805},"GB2-06":{"attempts":1,"playable":92.45899504353238,"score":92.45899504353238},"GB2-07":{"attempts":1,"playable":76.68460518642742,"score":76.68460518642742},"GB2-08":{"attempts":1,"playable":72.38231197745408,"score":72.38231197745408}},"none":{"GB2-01":{"attempts":1,"playable":68.40175329217033,"score":68.40175329217033},"GB2-02":{"attempts":1,"playable":44.2838056546712,"score":44.2838056546712},"GB2-03":{"attempts":1,"playable":42.6623790200342,"score":42.6623790200342},"GB2-04":{"attempts":1,"playable":48.62325324165005,"score":48.62325324165005},"GB2-05":{"attempts":1,"playable":59.641698621129635,"score":59.641698621129635},"GB2-06":{"attempts":1,"playable":49.7358004353113,"score":49.7358004353113},"GB2-07":{"attempts":1,"playable":71.99495941342104,"score":71.99495941342104},"GB2-08":{"attempts":1,"playable":26.081220094094103,"score":26.081220094094103}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:10Z","match_totals_all":{"draws":2102,"losses":2844,"wins":6801},"match_totals_tracks":{"highest":{"draws":380,"losses":412,"wins":2780},"medium":{"draws":591,"losses":920,"wins":2576},"none":{"draws":1131,"losses":1512,"wins":1445}},"model_slug":"z-ai-glm-5-3","official_rank_by_reasoning":{"highest":13,"medium":10,"none":19},"overall":{"max":92.97385603080852,"mean":65.67017991657261,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-02":73.62806649246055,"GB2-03":84.67860328128754,"GB2-04":77.09164191029542,"GB2-05":90.23309662476808,"GB2-06":91.12735803677934,"GB2-07":78.58485722865328,"GB2-08":92.97385603080852},"per_game_all":{"GB2-02":57.38827055721098,"GB2-03":68.50875129105536,"GB2-04":69.75879863429311,"GB2-05":72.35485792778526,"GB2-06":77.77405117187433,"GB2-07":75.75480727616724,"GB2-08":63.812462700785574},"per_game_match_totals_all":{"GB2-01":{"draws":171,"losses":349,"wins":512},"GB2-02":{"draws":918,"losses":178,"wins":344},"GB2-03":{"draws":158,"losses":431,"wins":893},"GB2-04":{"draws":563,"losses":191,"wins":739},"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":234,"losses":498,"wins":882}},"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":109,"wins":359},"GB2-04":{"draws":96,"losses":39,"wins":362},"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":30,"losses":150,"wins":358}},"none":{"GB2-01":{"draws":82,"losses":133,"wins":301},"GB2-02":{"draws":379,"losses":86,"wins":15},"GB2-03":{"draws":128,"losses":238,"wins":128},"GB2-04":{"draws":329,"losses":100,"wins":69},"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":204,"losses":307,"wins":27}}},"per_game_raw_elo_all":{"GB2-02":1536.8732955616397,"GB2-03":1652.101216900089,"GB2-04":1662.2359970587656,"GB2-05":1828.9011492505012,"GB2-06":1957.8822117652628,"GB2-07":1813.8719269413748,"GB2-08":1708.5261638504069},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1678.0917212486065,"GB2-03":1855.9296265353014,"GB2-04":1718.5247261173417,"GB2-05":2258.6323713136853,"GB2-06":2207.482489624122,"GB2-07":1864.3458172857052,"GB2-08":2267.2836666461235},"medium":{"GB2-01":1484.5628456821335,"GB2-02":1504.9232170819803,"GB2-03":1736.6263209410274,"GB2-04":1803.8772885975188,"GB2-05":1667.7809781301496,"GB2-06":2250.6738685445744,"GB2-07":1828.5068971348796,"GB2-08":1731.628825773015},"none":{"GB2-01":1653.6799692997133,"GB2-02":1427.6049483543318,"GB2-03":1363.747703223939,"GB2-04":1464.3059764614363,"GB2-05":1560.2900983076688,"GB2-06":1415.4902771270913,"GB2-07":1748.7630664035394,"GB2-08":1126.665999132082}},"per_game_tracks":{"highest":{"GB2-02":73.62806649246055,"GB2-03":84.67860328128754,"GB2-04":77.09164191029542,"GB2-05":90.23309662476808,"GB2-06":91.12735803677934,"GB2-07":78.58485722865328,"GB2-08":92.97385603080852},"medium":{"GB2-01":51.62656602805672,"GB2-02":54.25293952450121,"GB2-03":78.18527157184437,"GB2-04":83.56150075093387,"GB2-05":67.18977853745805,"GB2-06":92.45899504353238,"GB2-07":76.68460518642742,"GB2-08":72.38231197745408},"none":{"GB2-01":68.40175329217033,"GB2-02":44.2838056546712,"GB2-03":42.6623790200342,"GB2-04":48.62325324165005,"GB2-05":59.641698621129635,"GB2-06":49.7358004353113,"GB2-07":71.99495941342104,"GB2-08":26.081220094094103}},"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":"2026-10-24T19:06:22Z","reasoning":{"highest":73.5396849506316,"medium":72.04274607752602,"none":51.42810872156023},"reasoning_agg":{"highest":{"max":92.97385603080852,"mean":73.5396849506316,"min":0.0},"medium":{"max":92.45899504353238,"mean":72.04274607752602,"min":51.62656602805672},"none":{"max":71.99495941342104,"mean":51.42810872156023,"min":26.081220094094103}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":22.111576229071368},"working_program_strength":{"all":69.1720696761265,"highest":84.04535422929325,"medium":72.04274607752602,"none":51.42810872156023}},{"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":3.1897539999999998},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.6637360000000001},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.2355599999999995}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":1.2177,"mean":0.4203770833333333,"median":0.380795,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":10.089049999999999},"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":64.99344158851608,"highest":73.1864075659005,"medium":73.35158403731948,"none":48.44233316232824},"first_seen_at":null,"game_gaps":{"highest":{"GB2-04":"failed"},"medium":{"GB2-06":"failed"},"none":{"GB2-03":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[450000],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[450000],"total_output_tokens":1623223,"total_reasoning_output_tokens":1401661,"total_visible_output_tokens":221562,"visible_token_observations":29},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":450000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":55.64478851395012,"score":55.64478851395012},"GB2-02":{"attempts":3,"playable":74.38105609074306,"score":74.38105609074306},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":80.34837814926223,"score":53.56558543284149},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.78420162519383,"score":45.18946775012922},"GB2-05":{"attempts":3,"playable":76.3656192059414,"score":76.3656192059414},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":86.52710957920813,"score":57.684739719472084},"GB2-07":{"attempts":3,"playable":70.07682688622897,"score":70.07682688622897},"GB2-08":{"attempts":3,"playable":87.03944910882228,"score":87.03944910882228}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":59.41863663239461,"score":59.41863663239461},"GB2-02":{"attempts":1,"playable":89.06248216137189,"score":89.06248216137189},"GB2-03":{"attempts":1,"playable":88.00858030972678,"score":88.00858030972678},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":93.41214839874009,"score":93.41214839874009},"GB2-06":{"attempts":1,"playable":90.23388548276091,"score":90.23388548276091},"GB2-07":{"attempts":1,"playable":78.41232521796309,"score":78.41232521796309},"GB2-08":{"attempts":1,"playable":86.94320232424666,"score":86.94320232424666}},"medium":{"GB2-01":{"attempts":1,"playable":79.99922856456925,"score":79.99922856456925},"GB2-02":{"attempts":1,"playable":81.18445694776506,"score":81.18445694776506},"GB2-03":{"attempts":1,"playable":72.68817598879767,"score":72.68817598879767},"GB2-04":{"attempts":1,"playable":92.33722489519916,"score":92.33722489519916},"GB2-05":{"attempts":1,"playable":93.07462175455832,"score":93.07462175455832},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":76.33850998213276,"score":76.33850998213276},"GB2-08":{"attempts":1,"playable":91.19045416553367,"score":91.19045416553367}},"none":{"GB2-01":{"attempts":1,"playable":27.516500344886474,"score":27.516500344886474},"GB2-02":{"attempts":1,"playable":52.89622916309222,"score":52.89622916309222},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.2311783551885,"score":43.2311783551885},"GB2-05":{"attempts":1,"playable":42.610087464525805,"score":42.610087464525805},"GB2-06":{"attempts":1,"playable":82.82033367565535,"score":82.82033367565535},"GB2-07":{"attempts":1,"playable":55.47964545859105,"score":55.47964545859105},"GB2-08":{"attempts":1,"playable":82.98469083668653,"score":82.98469083668653}}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:26Z","match_totals_all":{"draws":1031,"losses":2397,"wins":7342},"match_totals_tracks":{"highest":{"draws":160,"losses":548,"wins":2882},"medium":{"draws":214,"losses":512,"wins":2860},"none":{"draws":657,"losses":1337,"wins":1600}},"model_slug":"x-ai-grok-4-7","official_rank_by_reasoning":{"highest":14,"medium":8,"none":25},"overall":{"max":93.41214839874009,"mean":64.99344158851608,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.41863663239461,"GB2-02":89.06248216137189,"GB2-03":88.00858030972678,"GB2-05":93.41214839874009,"GB2-06":90.23388548276091,"GB2-07":78.41232521796309,"GB2-08":86.94320232424666},"per_game_all":{"GB2-01":55.64478851395012,"GB2-02":74.38105609074306,"GB2-05":76.3656192059414,"GB2-07":70.07682688622897,"GB2-08":87.03944910882228},"per_game_match_totals_all":{"GB2-01":{"draws":202,"losses":615,"wins":731},"GB2-02":{"draws":490,"losses":140,"wins":810},"GB2-03":{"draws":113,"losses":162,"wins":713},"GB2-04":{"draws":176,"losses":243,"wins":577},"GB2-05":{"draws":0,"losses":384,"wins":1206},"GB2-06":{"draws":50,"losses":125,"wins":829},"GB2-07":{"draws":0,"losses":496,"wins":1094},"GB2-08":{"draws":0,"losses":232,"wins":1382}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":214,"wins":289},"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":13,"losses":48,"wins":441},"GB2-07":{"draws":0,"losses":118,"wins":412},"GB2-08":{"draws":0,"losses":78,"wins":460}},"medium":{"GB2-01":{"draws":34,"losses":96,"wins":386},"GB2-02":{"draws":107,"losses":42,"wins":331},"GB2-03":{"draws":29,"losses":137,"wins":328},"GB2-04":{"draws":44,"losses":18,"wins":436},"GB2-05":{"draws":0,"losses":37,"wins":493},"GB2-07":{"draws":0,"losses":130,"wins":400},"GB2-08":{"draws":0,"losses":52,"wins":486}},"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":102,"wins":436}}},"per_game_raw_elo_all":{"GB2-01":1534.3428418060573,"GB2-02":1724.190823701492,"GB2-05":2051.1301616717556,"GB2-07":1733.3571057534127,"GB2-08":2076.557647264151},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1560.168604817883,"GB2-02":1908.0939301775334,"GB2-03":1937.307831999818,"GB2-05":2413.2929559070535,"GB2-06":2181.0320870366377,"GB2-07":1860.9848648173966,"GB2-08":2066.860001818117},"medium":{"GB2-01":1798.5941161967007,"GB2-02":1770.2216352001,"GB2-03":1658.9845732753292,"GB2-04":1980.4687635144578,"GB2-05":2395.054730741312,"GB2-07":1822.235918662621,"GB2-08":2199.1771192303845},"none":{"GB2-01":1244.2658044035877,"GB2-02":1494.2569057268424,"GB2-04":1422.6446576786338,"GB2-05":1345.042798366901,"GB2-06":2002.4204727883566,"GB2-07":1516.8505337802205,"GB2-08":1963.6358207439523}},"per_game_tracks":{"highest":{"GB2-01":59.41863663239461,"GB2-02":89.06248216137189,"GB2-03":88.00858030972678,"GB2-05":93.41214839874009,"GB2-06":90.23388548276091,"GB2-07":78.41232521796309,"GB2-08":86.94320232424666},"medium":{"GB2-01":79.99922856456925,"GB2-02":81.18445694776506,"GB2-03":72.68817598879767,"GB2-04":92.33722489519916,"GB2-05":93.07462175455832,"GB2-07":76.33850998213276,"GB2-08":91.19045416553367},"none":{"GB2-01":27.516500344886474,"GB2-02":52.89622916309222,"GB2-04":43.2311783551885,"GB2-05":42.610087464525805,"GB2-06":82.82033367565535,"GB2-07":55.47964545859105,"GB2-08":82.98469083668653}},"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":"2026-10-24T19:17:40Z","reasoning":{"highest":73.1864075659005,"medium":73.35158403731948,"none":48.44233316232824},"reasoning_agg":{"highest":{"max":93.41214839874009,"mean":73.1864075659005,"min":0.0},"medium":{"max":93.07462175455832,"mean":73.35158403731948,"min":0.0},"none":{"max":82.98469083668653,"mean":48.44233316232824,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.909250874991244},"working_program_strength":{"all":74.27821895830408,"highest":83.64160864674342,"medium":83.83038175693655,"none":55.362666471232274}},{"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":0.6043883939999999},"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":0.33613289399999996},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.046843572},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.11170938600000001,"mean":0.0411402025,"median":0.037120068,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":27,"run_count":24,"total":0.9873648600000001},"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":63.43270120656255,"highest":71.86740093318276,"medium":66.72194055046423,"none":51.708762136040676},"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":75.47936527617212,"score":75.47936527617212},"GB2-02":{"attempts":3,"playable":56.27206891131873,"score":56.27206891131873},"GB2-03":{"attempts":3,"playable":45.96271504595918,"score":45.96271504595918},"GB2-04":{"attempts":3,"playable":60.67637985206303,"score":60.67637985206303},"GB2-05":{"attempts":3,"playable":62.736626792975215,"score":62.736626792975215},"GB2-06":{"attempts":3,"playable":69.2890949169914,"score":69.2890949169914},"GB2-07":{"attempts":3,"playable":59.91203425761618,"score":59.91203425761618},"GB2-08":{"attempts":3,"playable":77.1333245994046,"score":77.1333245994046}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.88198430461675,"score":68.88198430461675},"GB2-02":{"attempts":1,"playable":80.9876563481334,"score":80.9876563481334},"GB2-03":{"attempts":1,"playable":46.81990753998457,"score":46.81990753998457},"GB2-04":{"attempts":1,"playable":70.19348371023403,"score":70.19348371023403},"GB2-05":{"attempts":1,"playable":73.8910899940238,"score":73.8910899940238},"GB2-06":{"attempts":1,"playable":77.9827938772014,"score":77.9827938772014},"GB2-07":{"attempts":1,"playable":72.86638736782065,"score":72.86638736782065},"GB2-08":{"attempts":1,"playable":83.31590432344747,"score":83.31590432344747}},"medium":{"GB2-01":{"attempts":1,"playable":84.27255262799545,"score":84.27255262799545},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":51.133542812877764,"score":51.133542812877764},"GB2-04":{"attempts":1,"playable":69.11472471991067,"score":69.11472471991067},"GB2-05":{"attempts":1,"playable":61.72584535971883,"score":61.72584535971883},"GB2-06":{"attempts":1,"playable":83.84426380372147,"score":83.84426380372147},"GB2-07":{"attempts":1,"playable":73.56251496756252,"score":73.56251496756252},"GB2-08":{"attempts":1,"playable":66.2606052041496,"score":66.2606052041496}},"none":{"GB2-01":{"attempts":1,"playable":73.28355889590416,"score":73.28355889590416},"GB2-02":{"attempts":1,"playable":43.967075478045246,"score":43.967075478045246},"GB2-03":{"attempts":1,"playable":39.9346947850152,"score":39.9346947850152},"GB2-04":{"attempts":1,"playable":42.72093112604436,"score":42.72093112604436},"GB2-05":{"attempts":1,"playable":52.59294502518301,"score":52.59294502518301},"GB2-06":{"attempts":1,"playable":46.0402270700513,"score":46.0402270700513},"GB2-07":{"attempts":1,"playable":33.30720043746538,"score":33.30720043746538},"GB2-08":{"attempts":1,"playable":81.82346427061673,"score":81.82346427061673}}},"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":84.27255262799545,"mean":63.43270120656255,"min":33.30720043746538},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.88198430461675,"GB2-02":80.9876563481334,"GB2-03":46.81990753998457,"GB2-04":70.19348371023403,"GB2-05":73.8910899940238,"GB2-06":77.9827938772014,"GB2-07":72.86638736782065,"GB2-08":83.31590432344747},"per_game_all":{"GB2-01":75.47936527617212,"GB2-02":56.27206891131873,"GB2-03":45.96271504595918,"GB2-04":60.67637985206303,"GB2-05":62.736626792975215,"GB2-06":69.2890949169914,"GB2-07":59.91203425761618,"GB2-08":77.1333245994046},"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":1745.0945097823433,"GB2-02":1538.989607519582,"GB2-03":1392.5011997563754,"GB2-04":1566.292554845929,"GB2-05":1613.4519526623887,"GB2-06":1762.4304619899813,"GB2-07":1591.4389394085592,"GB2-08":1842.393332613114},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1658.9977809510447,"GB2-02":1767.471459423531,"GB2-03":1399.8398614381695,"GB2-04":1645.2899773963784,"GB2-05":1782.1421076935292,"GB2-06":1904.0631076100094,"GB2-07":1762.8302046036797,"GB2-08":1971.799213921062},"medium":{"GB2-01":1866.3449279495826,"GB2-02":1424.340397604501,"GB2-03":1437.669861669138,"GB2-04":1634.905295386943,"GB2-05":1588.4904382390546,"GB2-06":2024.4226689857041,"GB2-07":1774.2862766731314,"GB2-08":1619.8211959911964},"none":{"GB2-01":1709.9408204464023,"GB2-02":1425.1569655307137,"GB2-03":1339.9938761618187,"GB2-04":1418.6823917544662,"GB2-05":1469.7233120545827,"GB2-06":1358.8056093742307,"GB2-07":1237.2003369488662,"GB2-08":1935.5595879270838}},"per_game_tracks":{"highest":{"GB2-01":68.88198430461675,"GB2-02":80.9876563481334,"GB2-03":46.81990753998457,"GB2-04":70.19348371023403,"GB2-05":73.8910899940238,"GB2-06":77.9827938772014,"GB2-07":72.86638736782065,"GB2-08":83.31590432344747},"medium":{"GB2-01":84.27255262799545,"GB2-02":43.861474907777556,"GB2-03":51.133542812877764,"GB2-04":69.11472471991067,"GB2-05":61.72584535971883,"GB2-06":83.84426380372147,"GB2-07":73.56251496756252,"GB2-08":66.2606052041496},"none":{"GB2-01":73.28355889590416,"GB2-02":43.967075478045246,"GB2-03":39.9346947850152,"GB2-04":42.72093112604436,"GB2-05":52.59294502518301,"GB2-06":46.0402270700513,"GB2-07":33.30720043746538,"GB2-08":81.82346427061673}},"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":"2026-10-24T17:50:09Z","reasoning":{"highest":71.86740093318276,"medium":66.72194055046423,"none":51.708762136040676},"reasoning_agg":{"highest":{"max":83.31590432344747,"mean":71.86740093318276,"min":46.81990753998457},"medium":{"max":84.27255262799545,"mean":66.72194055046423,"min":43.861474907777556},"none":{"max":81.82346427061673,"mean":51.708762136040676,"min":33.30720043746538}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":20.15863879714209},"working_program_strength":{"all":63.43270120656255,"highest":71.86740093318276,"medium":66.72194055046423,"none":51.708762136040676}},{"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":4.385362000000001},"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":0.48637800000000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.327498}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.486378},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.327498},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385361999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199238},"codegen_output_tokens":{"attempt_count":28,"output_max":70064,"output_mean":18803.166666666668,"output_min":1228,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":70064,"output_mean":51989.0,"output_min":25995,"run_count":8},"medium":{"attempt_count":11,"output_max":4348,"output_mean":2842.75,"output_min":1552,"run_count":8},"none":{"attempt_count":8,"output_max":2376,"output_mean":1577.75,"output_min":1228,"run_count":8}},"display_name":"Claude Sonnet 5.5","economics":{"all":61.672627451419544,"highest":91.82247923237178,"medium":51.92727517846182,"none":41.268127943425036},"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":59.545403869126524,"score":59.545403869126524},"GB2-02":{"attempts":3,"playable":61.75072730977678,"score":61.75072730977678},"GB2-03":{"attempts":3,"playable":58.63277592898211,"score":58.63277592898211},"GB2-04":{"attempts":3,"playable":56.478012701276356,"score":56.478012701276356},"GB2-05":{"attempts":3,"playable":43.73283861049588,"score":43.73283861049588},"GB2-06":{"attempts":3,"playable":61.60341237032839,"score":61.60341237032839},"GB2-07":{"attempts":3,"playable":70.60018416029764,"score":70.60018416029764},"GB2-08":{"attempts":3,"playable":81.03766466107267,"score":81.03766466107267}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.28018091451669,"score":80.28018091451669},"GB2-02":{"attempts":1,"playable":95.94910286467913,"score":95.94910286467913},"GB2-03":{"attempts":1,"playable":95.05594147453033,"score":95.05594147453033},"GB2-04":{"attempts":1,"playable":83.48616604723223,"score":83.48616604723223},"GB2-05":{"attempts":1,"playable":97.3747731499052,"score":97.3747731499052},"GB2-06":{"attempts":1,"playable":89.78575025805709,"score":89.78575025805709},"GB2-07":{"attempts":1,"playable":93.6755483450511,"score":93.6755483450511},"GB2-08":{"attempts":1,"playable":98.97237080500244,"score":98.97237080500244}},"medium":{"GB2-01":{"attempts":1,"playable":46.827209408703894,"score":46.827209408703894},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":32.06442448205719,"score":32.06442448205719},"GB2-04":{"attempts":1,"playable":40.881961647250705,"score":40.881961647250705},"GB2-05":{"attempts":1,"playable":19.50173450694367,"score":19.50173450694367},"GB2-06":{"attempts":1,"playable":77.0945052028131,"score":77.0945052028131},"GB2-07":{"attempts":1,"playable":71.99495941342104,"score":71.99495941342104},"GB2-08":{"attempts":1,"playable":84.14286747057714,"score":84.14286747057714}},"none":{"GB2-01":{"attempts":1,"playable":51.52882128415899,"score":51.52882128415899},"GB2-02":{"attempts":1,"playable":46.39253976872338,"score":46.39253976872338},"GB2-03":{"attempts":1,"playable":48.77796183035881,"score":48.77796183035881},"GB2-04":{"attempts":1,"playable":45.06591040934613,"score":45.06591040934613},"GB2-05":{"attempts":1,"playable":14.322008174638762,"score":14.322008174638762},"GB2-06":{"attempts":1,"playable":17.929981650115,"score":17.929981650115},"GB2-07":{"attempts":1,"playable":46.13004472242078,"score":46.13004472242078},"GB2-08":{"attempts":1,"playable":59.997755707638426,"score":59.997755707638426}}},"id":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:58Z","match_totals_all":{"draws":2109,"losses":3822,"wins":6333},"match_totals_tracks":{"highest":{"draws":313,"losses":190,"wins":3585},"medium":{"draws":931,"losses":1565,"wins":1592},"none":{"draws":865,"losses":2067,"wins":1156}},"model_slug":"claude-sonnet-5-5","official_rank_by_reasoning":{"highest":5,"medium":34,"none":40},"overall":{"max":98.97237080500244,"mean":61.672627451419544,"min":14.322008174638762},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.28018091451669,"GB2-02":95.94910286467913,"GB2-03":95.05594147453033,"GB2-04":83.48616604723223,"GB2-05":97.3747731499052,"GB2-06":89.78575025805709,"GB2-07":93.6755483450511,"GB2-08":98.97237080500244},"per_game_all":{"GB2-01":59.545403869126524,"GB2-02":61.75072730977678,"GB2-03":58.63277592898211,"GB2-04":56.478012701276356,"GB2-05":43.73283861049588,"GB2-06":61.60341237032839,"GB2-07":70.60018416029764,"GB2-08":81.03766466107267},"per_game_match_totals_all":{"GB2-01":{"draws":217,"losses":549,"wins":782},"GB2-02":{"draws":767,"losses":183,"wins":490},"GB2-03":{"draws":329,"losses":486,"wins":667},"GB2-04":{"draws":690,"losses":327,"wins":477},"GB2-05":{"draws":0,"losses":903,"wins":687},"GB2-06":{"draws":44,"losses":588,"wins":874},"GB2-07":{"draws":0,"losses":484,"wins":1106},"GB2-08":{"draws":62,"losses":302,"wins":1250}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":157,"losses":33,"wins":326},"GB2-02":{"draws":22,"losses":8,"wins":450},"GB2-03":{"draws":0,"losses":26,"wins":468},"GB2-04":{"draws":91,"losses":42,"wins":365},"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":214,"losses":245,"wins":35},"GB2-04":{"draws":317,"losses":144,"wins":37},"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":6,"losses":92,"wins":440}},"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":4,"losses":424,"wins":74},"GB2-07":{"draws":0,"losses":299,"wins":231},"GB2-08":{"draws":49,"losses":210,"wins":279}}},"per_game_raw_elo_all":{"GB2-01":1575.0767008889986,"GB2-02":1666.1892767030477,"GB2-03":1632.5580306908385,"GB2-04":1547.9756755683975,"GB2-05":1534.5219943885115,"GB2-06":1660.3617966763413,"GB2-07":1835.049945238612,"GB2-08":2084.365874662652},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1802.7093298817929,"GB2-02":2137.7180912756417,"GB2-03":2211.3523858115955,"GB2-04":1802.743722940353,"GB2-05":2705.3040715640163,"GB2-06":2168.3752034718004,"GB2-07":2357.1025756104495,"GB2-08":2739.211573657699},"medium":{"GB2-01":1438.8908623456746,"GB2-02":1416.9768592403107,"GB2-03":1269.3945715157106,"GB2-04":1404.3363235972802,"GB2-05":1000.7576969567793,"GB2-06":1886.718674914524,"GB2-07":1748.7630664035394,"GB2-08":1992.5110635047229},"none":{"GB2-01":1483.6299104395284,"GB2-02":1443.8728795931909,"GB2-03":1416.9271347452086,"GB2-04":1436.8469801675587,"GB2-05":897.5042146447391,"GB2-06":925.9915116426993,"GB2-07":1399.2841937018475,"GB2-08":1521.374986825534}},"per_game_tracks":{"highest":{"GB2-01":80.28018091451669,"GB2-02":95.94910286467913,"GB2-03":95.05594147453033,"GB2-04":83.48616604723223,"GB2-05":97.3747731499052,"GB2-06":89.78575025805709,"GB2-07":93.6755483450511,"GB2-08":98.97237080500244},"medium":{"GB2-01":46.827209408703894,"GB2-02":42.910539295927805,"GB2-03":32.06442448205719,"GB2-04":40.881961647250705,"GB2-05":19.50173450694367,"GB2-06":77.0945052028131,"GB2-07":71.99495941342104,"GB2-08":84.14286747057714},"none":{"GB2-01":51.52882128415899,"GB2-02":46.39253976872338,"GB2-03":48.77796183035881,"GB2-04":45.06591040934613,"GB2-05":14.322008174638762,"GB2-06":17.929981650115,"GB2-07":46.13004472242078,"GB2-08":59.997755707638426}},"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":"2026-10-24T19:04:54Z","reasoning":{"highest":91.82247923237178,"medium":51.92727517846182,"none":41.268127943425036},"reasoning_agg":{"highest":{"max":98.97237080500244,"mean":91.82247923237178,"min":80.28018091451669},"medium":{"max":84.14286747057714,"mean":51.92727517846182,"min":19.50173450694367},"none":{"max":59.997755707638426,"mean":41.268127943425036,"min":14.322008174638762}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":50.55435128894674},"working_program_strength":{"all":61.672627451419544,"highest":91.82247923237178,"medium":51.92727517846182,"none":41.268127943425036}},{"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":61.05082837287173,"highest":66.35912688101574,"medium":71.44109447735818,"none":45.352263760241286},"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":59.945710831495376,"score":59.945710831495376},"GB2-02":{"attempts":3,"playable":60.64171007306382,"score":60.64171007306382},"GB2-03":{"attempts":3,"playable":54.642487794993606,"score":54.642487794993606},"GB2-04":{"attempts":3,"playable":56.1651601782638,"score":56.1651601782638},"GB2-05":{"attempts":3,"playable":73.00065410228923,"score":73.00065410228923},"GB2-06":{"attempts":3,"playable":53.25793054650156,"score":53.25793054650156},"GB2-07":{"attempts":3,"playable":70.1081126356943,"score":70.1081126356943},"GB2-08":{"attempts":3,"playable":60.64486082067217,"score":60.64486082067217}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":50.55091318051426,"score":50.55091318051426},"GB2-02":{"attempts":1,"playable":83.28680710805719,"score":83.28680710805719},"GB2-03":{"attempts":1,"playable":51.74536624339686,"score":51.74536624339686},"GB2-04":{"attempts":1,"playable":60.20104195579413,"score":60.20104195579413},"GB2-05":{"attempts":1,"playable":85.00449802467791,"score":85.00449802467791},"GB2-06":{"attempts":1,"playable":66.33931517535959,"score":66.33931517535959},"GB2-07":{"attempts":1,"playable":76.16539028897841,"score":76.16539028897841},"GB2-08":{"attempts":1,"playable":57.579683071347496,"score":57.579683071347496}},"medium":{"GB2-01":{"attempts":1,"playable":62.519569499522106,"score":62.519569499522106},"GB2-02":{"attempts":1,"playable":54.56565896441634,"score":54.56565896441634},"GB2-03":{"attempts":1,"playable":67.43501293246544,"score":67.43501293246544},"GB2-04":{"attempts":1,"playable":65.36937787646515,"score":65.36937787646515},"GB2-05":{"attempts":1,"playable":82.74387796459857,"score":82.74387796459857},"GB2-06":{"attempts":1,"playable":79.7304481203572,"score":79.7304481203572},"GB2-07":{"attempts":1,"playable":76.51158145988063,"score":76.51158145988063},"GB2-08":{"attempts":1,"playable":82.65322900116001,"score":82.65322900116001}},"none":{"GB2-01":{"attempts":1,"playable":66.76664981444975,"score":66.76664981444975},"GB2-02":{"attempts":1,"playable":44.07266414671792,"score":44.07266414671792},"GB2-03":{"attempts":1,"playable":44.74708420911853,"score":44.74708420911853},"GB2-04":{"attempts":1,"playable":42.9250607025321,"score":42.9250607025321},"GB2-05":{"attempts":1,"playable":51.25358631759123,"score":51.25358631759123},"GB2-06":{"attempts":1,"playable":13.704028343787897,"score":13.704028343787897},"GB2-07":{"attempts":1,"playable":57.64736615822385,"score":57.64736615822385},"GB2-08":{"attempts":1,"playable":41.70167038950902,"score":41.70167038950902}}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-10-26T01:51:38Z","match_totals_all":{"draws":2989,"losses":3526,"wins":5748},"match_totals_tracks":{"highest":{"draws":832,"losses":1049,"wins":2206},"medium":{"draws":787,"losses":841,"wins":2460},"none":{"draws":1370,"losses":1636,"wins":1082}},"model_slug":"x-ai-grok-4-6","official_rank_by_reasoning":{"highest":22,"medium":11,"none":29},"overall":{"max":85.00449802467791,"mean":61.05082837287173,"min":13.704028343787897},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.55091318051426,"GB2-02":83.28680710805719,"GB2-03":51.74536624339686,"GB2-04":60.20104195579413,"GB2-05":85.00449802467791,"GB2-06":66.33931517535959,"GB2-07":76.16539028897841,"GB2-08":57.579683071347496},"per_game_all":{"GB2-01":59.945710831495376,"GB2-02":60.64171007306382,"GB2-03":54.642487794993606,"GB2-04":56.1651601782638,"GB2-05":73.00065410228923,"GB2-06":53.25793054650156,"GB2-07":70.1081126356943,"GB2-08":60.64486082067217},"per_game_match_totals_all":{"GB2-01":{"draws":444,"losses":431,"wins":673},"GB2-02":{"draws":747,"losses":214,"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":50,"losses":718,"wins":738},"GB2-07":{"draws":0,"losses":496,"wins":1094},"GB2-08":{"draws":323,"losses":520,"wins":771}},"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":30,"losses":171,"wins":301},"GB2-07":{"draws":0,"losses":131,"wins":399},"GB2-08":{"draws":109,"losses":193,"wins":236}},"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":104,"wins":434}},"none":{"GB2-01":{"draws":61,"losses":152,"wins":303},"GB2-02":{"draws":379,"losses":87,"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":214,"losses":223,"wins":101}}},"per_game_raw_elo_all":{"GB2-01":1567.1874478304874,"GB2-02":1578.194852585254,"GB2-03":1473.7620181886714,"GB2-04":1525.6340244835685,"GB2-05":1834.1110130751756,"GB2-06":1491.6131579182522,"GB2-07":1729.7957975980246,"GB2-08":1579.6927993047282},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1474.3067566041636,"GB2-02":1801.2171220536632,"GB2-03":1443.1025465734922,"GB2-04":1556.1582138984336,"GB2-05":2059.6387087218595,"GB2-06":1687.70246150215,"GB2-07":1819.1259736797747,"GB2-08":1487.1546796485402},"medium":{"GB2-01":1591.387623972785,"GB2-02":1507.3941942241584,"GB2-03":1596.3480403182261,"GB2-04":1600.4755187945482,"GB2-05":1989.6957052169648,"GB2-06":1938.741680823816,"GB2-07":1825.3627726308805,"GB2-08":1955.5374663752286},"none":{"GB2-01":1635.8679629145136,"GB2-02":1425.9732414779407,"GB2-03":1381.8354676742956,"GB2-04":1420.268340757724,"GB2-05":1452.998625286702,"GB2-06":848.3953314287912,"GB2-07":1544.898646483419,"GB2-08":1296.3862518904152}},"per_game_tracks":{"highest":{"GB2-01":50.55091318051426,"GB2-02":83.28680710805719,"GB2-03":51.74536624339686,"GB2-04":60.20104195579413,"GB2-05":85.00449802467791,"GB2-06":66.33931517535959,"GB2-07":76.16539028897841,"GB2-08":57.579683071347496},"medium":{"GB2-01":62.519569499522106,"GB2-02":54.56565896441634,"GB2-03":67.43501293246544,"GB2-04":65.36937787646515,"GB2-05":82.74387796459857,"GB2-06":79.7304481203572,"GB2-07":76.51158145988063,"GB2-08":82.65322900116001},"none":{"GB2-01":66.76664981444975,"GB2-02":44.07266414671792,"GB2-03":44.74708420911853,"GB2-04":42.9250607025321,"GB2-05":51.25358631759123,"GB2-06":13.704028343787897,"GB2-07":57.64736615822385,"GB2-08":41.70167038950902}},"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":"2026-10-24T19:17:18Z","reasoning":{"highest":66.35912688101574,"medium":71.44109447735818,"none":45.352263760241286},"reasoning_agg":{"highest":{"max":85.00449802467791,"mean":66.35912688101574,"min":50.55091318051426},"medium":{"max":82.74387796459857,"mean":71.44109447735818,"min":54.56565896441634},"none":{"max":66.76664981444975,"mean":45.352263760241286,"min":13.704028343787897}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":26.088830717116892},"working_program_strength":{"all":61.05082837287173,"highest":66.35912688101574,"medium":71.44109447735818,"none":45.352263760241286}},{"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":0.5746151281850015},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.25553343903391196},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.9756462499999998},"codegen_output_tokens":{"attempt_count":25,"output_max":73160,"output_mean":20095.833333333332,"output_min":1712,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":73160,"output_mean":40784.875,"output_min":28671,"run_count":8},"medium":{"attempt_count":8,"output_max":31721,"output_mean":16792.0,"output_min":5265,"run_count":8},"none":{"attempt_count":8,"output_max":3473,"output_mean":2710.625,"output_min":1712,"run_count":8}},"display_name":"Gemini 3.8 Flash","economics":{"all":60.976867033102714,"highest":66.20021724635149,"medium":61.2087923226988,"none":55.521591530257865},"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":61.071609658113346,"score":61.071609658113346},"GB2-02":{"attempts":3,"playable":50.10874937058625,"score":50.10874937058625},"GB2-03":{"attempts":3,"playable":69.25956906229072,"score":69.25956906229072},"GB2-04":{"attempts":3,"playable":51.32723164139757,"score":51.32723164139757},"GB2-05":{"attempts":3,"playable":59.30442629553894,"score":59.30442629553894},"GB2-06":{"attempts":3,"playable":80.48059755963308,"score":80.48059755963308},"GB2-07":{"attempts":3,"playable":56.65909001065621,"score":56.65909001065621},"GB2-08":{"attempts":3,"playable":59.6036626666056,"score":59.6036626666056}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.432052071829915,"score":55.432052071829915},"GB2-02":{"attempts":1,"playable":69.69194480968862,"score":69.69194480968862},"GB2-03":{"attempts":1,"playable":71.64705790034347,"score":71.64705790034347},"GB2-04":{"attempts":1,"playable":47.20198870902211,"score":47.20198870902211},"GB2-05":{"attempts":1,"playable":67.18977853745804,"score":67.18977853745804},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":1,"playable":69.5471049404985,"score":69.5471049404985},"GB2-08":{"attempts":1,"playable":60.274811774555594,"score":60.274811774555594}},"medium":{"GB2-01":{"attempts":1,"playable":71.18240320394425,"score":71.18240320394425},"GB2-02":{"attempts":1,"playable":40.05218343975386,"score":40.05218343975386},"GB2-03":{"attempts":1,"playable":84.5901003533996,"score":84.5901003533996},"GB2-04":{"attempts":1,"playable":60.89947429906761,"score":60.89947429906761},"GB2-05":{"attempts":1,"playable":55.07572688871119,"score":55.07572688871119},"GB2-06":{"attempts":1,"playable":79.09418456303702,"score":79.09418456303702},"GB2-07":{"attempts":1,"playable":57.467174986402846,"score":57.467174986402846},"GB2-08":{"attempts":1,"playable":41.30909084727405,"score":41.30909084727405}},"none":{"GB2-01":{"attempts":1,"playable":56.60037369856589,"score":56.60037369856589},"GB2-02":{"attempts":1,"playable":40.58211986231627,"score":40.58211986231627},"GB2-03":{"attempts":1,"playable":51.541548933129086,"score":51.541548933129086},"GB2-04":{"attempts":1,"playable":45.880231916103,"score":45.880231916103},"GB2-05":{"attempts":1,"playable":55.64777346044759,"score":55.64777346044759},"GB2-06":{"attempts":1,"playable":73.73060888844665,"score":73.73060888844665},"GB2-07":{"attempts":1,"playable":42.96299010506729,"score":42.96299010506729},"GB2-08":{"attempts":1,"playable":77.22708537798715,"score":77.22708537798715}}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T01:47:54Z","match_totals_all":{"draws":2408,"losses":3851,"wins":6005},"match_totals_tracks":{"highest":{"draws":460,"losses":1241,"wins":2387},"medium":{"draws":968,"losses":1193,"wins":1927},"none":{"draws":980,"losses":1417,"wins":1691}},"model_slug":"google-gemini-3-8-flash","official_rank_by_reasoning":{"highest":24,"medium":21,"none":15},"overall":{"max":88.61699922741556,"mean":60.976867033102714,"min":40.05218343975386},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.432052071829915,"GB2-02":69.69194480968862,"GB2-03":71.64705790034347,"GB2-04":47.20198870902211,"GB2-05":67.18977853745804,"GB2-06":88.61699922741556,"GB2-07":69.5471049404985,"GB2-08":60.274811774555594},"per_game_all":{"GB2-01":61.071609658113346,"GB2-02":50.10874937058625,"GB2-03":69.25956906229072,"GB2-04":51.32723164139757,"GB2-05":59.30442629553894,"GB2-06":80.48059755963308,"GB2-07":56.65909001065621,"GB2-08":59.6036626666056},"per_game_match_totals_all":{"GB2-01":{"draws":317,"losses":477,"wins":754},"GB2-02":{"draws":935,"losses":274,"wins":231},"GB2-03":{"draws":189,"losses":408,"wins":885},"GB2-04":{"draws":700,"losses":403,"wins":391},"GB2-05":{"draws":0,"losses":674,"wins":916},"GB2-06":{"draws":44,"losses":303,"wins":1159},"GB2-07":{"draws":0,"losses":722,"wins":868},"GB2-08":{"draws":223,"losses":590,"wins":801}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":46,"losses":218,"wins":252},"GB2-02":{"draws":198,"losses":54,"wins":228},"GB2-03":{"draws":6,"losses":154,"wins":334},"GB2-04":{"draws":91,"losses":226,"wins":181},"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":120,"losses":272,"wins":146}},"none":{"GB2-01":{"draws":194,"losses":138,"wins":184},"GB2-02":{"draws":372,"losses":107,"wins":1},"GB2-03":{"draws":86,"losses":216,"wins":192},"GB2-04":{"draws":308,"losses":124,"wins":66},"GB2-05":{"draws":0,"losses":244,"wins":286},"GB2-06":{"draws":7,"losses":142,"wins":353},"GB2-07":{"draws":0,"losses":316,"wins":214},"GB2-08":{"draws":13,"losses":130,"wins":395}}},"per_game_raw_elo_all":{"GB2-01":1579.553697219356,"GB2-02":1477.132698878471,"GB2-03":1647.0435018975677,"GB2-04":1486.148622475673,"GB2-05":1559.030782921781,"GB2-06":1961.8009258483607,"GB2-07":1537.7139859328881,"GB2-08":1549.6348242797258},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1521.1144109640904,"GB2-02":1637.8774351163736,"GB2-03":1645.836900221734,"GB2-04":1453.3346944861967,"GB2-05":1667.7809781301494,"GB2-06":2136.948866428713,"GB2-07":1710.6717704030666,"GB2-08":1525.4198892421878},"medium":{"GB2-01":1685.0873258496945,"GB2-02":1394.6820857363336,"GB2-03":1854.0032305981367,"GB2-04":1561.9757795171104,"GB2-05":1501.0140959543232,"GB2-06":1926.0237516463853,"GB2-07":1542.550069757832,"GB2-08":1292.1202084907613},"none":{"GB2-01":1532.4593548442836,"GB2-02":1398.8385757827054,"GB2-03":1441.2903748728327,"GB2-04":1443.1353934237127,"GB2-05":1508.297274680871,"GB2-06":1822.4301594699841,"GB2-07":1359.9201176377655,"GB2-08":1831.3643751062284}},"per_game_tracks":{"highest":{"GB2-01":55.432052071829915,"GB2-02":69.69194480968862,"GB2-03":71.64705790034347,"GB2-04":47.20198870902211,"GB2-05":67.18977853745804,"GB2-06":88.61699922741556,"GB2-07":69.5471049404985,"GB2-08":60.274811774555594},"medium":{"GB2-01":71.18240320394425,"GB2-02":40.05218343975386,"GB2-03":84.5901003533996,"GB2-04":60.89947429906761,"GB2-05":55.07572688871119,"GB2-06":79.09418456303702,"GB2-07":57.467174986402846,"GB2-08":41.30909084727405},"none":{"GB2-01":56.60037369856589,"GB2-02":40.58211986231627,"GB2-03":51.541548933129086,"GB2-04":45.880231916103,"GB2-05":55.64777346044759,"GB2-06":73.73060888844665,"GB2-07":42.96299010506729,"GB2-08":77.22708537798715}},"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":"2026-10-24T19:13:27Z","reasoning":{"highest":66.20021724635149,"medium":61.2087923226988,"none":55.521591530257865},"reasoning_agg":{"highest":{"max":88.61699922741556,"mean":66.20021724635149,"min":47.20198870902211},"medium":{"max":84.5901003533996,"mean":61.2087923226988,"min":40.05218343975386},"none":{"max":77.22708537798715,"mean":55.521591530257865,"min":40.58211986231627}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.67862571609362},"working_program_strength":{"all":60.976867033102714,"highest":66.20021724635149,"medium":61.2087923226988,"none":55.521591530257865}},{"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":0.41740125000000006},"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":1.9894712500000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.10824926041666667,"median":0.050446875,"min":0.017614,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":27,"run_count":24,"total":2.5979822500000007},"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":59.72279120765243,"highest":70.94238807829937,"medium":66.77284273884489,"none":41.453142805813016},"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":59.56850786159851,"score":59.56850786159851},"GB2-02":{"attempts":3,"playable":55.99258597942677,"score":55.99258597942677},"GB2-03":{"attempts":3,"playable":67.23438275469339,"score":67.23438275469339},"GB2-04":{"attempts":3,"playable":52.92226867121973,"score":52.92226867121973},"GB2-05":{"attempts":3,"playable":59.961613575740635,"score":59.961613575740635},"GB2-06":{"attempts":3,"playable":69.33502790114143,"score":69.33502790114143},"GB2-07":{"attempts":3,"playable":50.27667758984105,"score":50.27667758984105},"GB2-08":{"attempts":3,"playable":62.49126532755784,"score":62.49126532755784}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.79763775927,"score":76.79763775927},"GB2-02":{"attempts":1,"playable":62.84925449361422,"score":62.84925449361422},"GB2-03":{"attempts":1,"playable":83.16763929406432,"score":83.16763929406432},"GB2-04":{"attempts":1,"playable":51.35760364448936,"score":51.35760364448936},"GB2-05":{"attempts":1,"playable":79.36395137706818,"score":79.36395137706818},"GB2-06":{"attempts":1,"playable":84.72703232529484,"score":84.72703232529484},"GB2-07":{"attempts":1,"playable":58.18745218546933,"score":58.18745218546933},"GB2-08":{"attempts":1,"playable":71.08853354712474,"score":71.08853354712474}},"medium":{"GB2-01":{"attempts":1,"playable":75.09148073051385,"score":75.09148073051385},"GB2-02":{"attempts":1,"playable":57.78866741068549,"score":57.78866741068549},"GB2-03":{"attempts":1,"playable":63.44521844397948,"score":63.44521844397948},"GB2-04":{"attempts":1,"playable":64.2800529662376,"score":64.2800529662376},"GB2-05":{"attempts":1,"playable":59.45194791054944,"score":59.45194791054944},"GB2-06":{"attempts":1,"playable":81.8208639592235,"score":81.8208639592235},"GB2-07":{"attempts":1,"playable":54.57289357501711,"score":54.57289357501711},"GB2-08":{"attempts":1,"playable":77.7316169145525,"score":77.7316169145525}},"none":{"GB2-01":{"attempts":1,"playable":26.816405095011675,"score":26.816405095011675},"GB2-02":{"attempts":1,"playable":47.33983603398062,"score":47.33983603398062},"GB2-03":{"attempts":1,"playable":55.09029052603637,"score":55.09029052603637},"GB2-04":{"attempts":1,"playable":43.12914940293223,"score":43.12914940293223},"GB2-05":{"attempts":1,"playable":41.0689414396043,"score":41.0689414396043},"GB2-06":{"attempts":1,"playable":41.45718741890594,"score":41.45718741890594},"GB2-07":{"attempts":1,"playable":38.069687009036706,"score":38.069687009036706},"GB2-08":{"attempts":1,"playable":38.653645520996264,"score":38.653645520996264}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:38Z","match_totals_all":{"draws":2242,"losses":4100,"wins":5922},"match_totals_tracks":{"highest":{"draws":529,"losses":1005,"wins":2554},"medium":{"draws":625,"losses":1135,"wins":2328},"none":{"draws":1088,"losses":1960,"wins":1040}},"model_slug":"meta-muse-spark-1-3","official_rank_by_reasoning":{"highest":16,"medium":13,"none":38},"overall":{"max":84.72703232529484,"mean":59.72279120765243,"min":26.816405095011675},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.79763775927,"GB2-02":62.84925449361422,"GB2-03":83.16763929406432,"GB2-04":51.35760364448936,"GB2-05":79.36395137706818,"GB2-06":84.72703232529484,"GB2-07":58.18745218546933,"GB2-08":71.08853354712474},"per_game_all":{"GB2-01":59.56850786159851,"GB2-02":55.99258597942677,"GB2-03":67.23438275469339,"GB2-04":52.92226867121973,"GB2-05":59.961613575740635,"GB2-06":69.33502790114143,"GB2-07":50.27667758984105,"GB2-08":62.49126532755784},"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":446,"wins":857},"GB2-04":{"draws":660,"losses":399,"wins":435},"GB2-05":{"draws":0,"losses":661,"wins":929},"GB2-06":{"draws":61,"losses":472,"wins":973},"GB2-07":{"draws":0,"losses":828,"wins":762},"GB2-08":{"draws":303,"losses":500,"wins":811}},"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":170,"wins":265},"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":200,"wins":211},"GB2-04":{"draws":281,"losses":151,"wins":66},"GB2-05":{"draws":0,"losses":320,"wins":210},"GB2-06":{"draws":13,"losses":310,"wins":179},"GB2-07":{"draws":0,"losses":342,"wins":188},"GB2-08":{"draws":247,"losses":222,"wins":69}}},"per_game_raw_elo_all":{"GB2-01":1574.2841953521104,"GB2-02":1519.935317703915,"GB2-03":1617.1328460793209,"GB2-04":1499.4035206350136,"GB2-05":1594.310995552607,"GB2-06":1771.5451313194892,"GB2-07":1451.9207828037909,"GB2-08":1604.160917877557},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1754.2625824995005,"GB2-02":1575.4328648433377,"GB2-03":1824.4023836683273,"GB2-04":1485.4910833932902,"GB2-05":1899.798073762115,"GB2-06":2043.8616814678119,"GB2-07":1551.958211993245,"GB2-08":1706.6676382787518},"medium":{"GB2-01":1732.2609870523827,"GB2-02":1533.1987190471755,"GB2-03":1553.7479247544882,"GB2-04":1590.8665883714207,"GB2-05":1557.764699267156,"GB2-06":1981.4239281222963,"GB2-07":1505.2390445780861,"GB2-08":1842.322381019295},"none":{"GB2-01":1236.3290165044486,"GB2-02":1451.1743692212322,"GB2-03":1473.2482298151472,"GB2-04":1421.8528901403297,"GB2-05":1325.3702136285501,"GB2-06":1289.3497843683604,"GB2-07":1298.5650918400415,"GB2-08":1263.4927343346244}},"per_game_tracks":{"highest":{"GB2-01":76.79763775927,"GB2-02":62.84925449361422,"GB2-03":83.16763929406432,"GB2-04":51.35760364448936,"GB2-05":79.36395137706818,"GB2-06":84.72703232529484,"GB2-07":58.18745218546933,"GB2-08":71.08853354712474},"medium":{"GB2-01":75.09148073051385,"GB2-02":57.78866741068549,"GB2-03":63.44521844397948,"GB2-04":64.2800529662376,"GB2-05":59.45194791054944,"GB2-06":81.8208639592235,"GB2-07":54.57289357501711,"GB2-08":77.7316169145525},"none":{"GB2-01":26.816405095011675,"GB2-02":47.33983603398062,"GB2-03":55.09029052603637,"GB2-04":43.12914940293223,"GB2-05":41.0689414396043,"GB2-06":41.45718741890594,"GB2-07":38.069687009036706,"GB2-08":38.653645520996264}},"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":"2026-10-24T19:02:08Z","reasoning":{"highest":70.94238807829937,"medium":66.77284273884489,"none":41.453142805813016},"reasoning_agg":{"highest":{"max":84.72703232529484,"mean":70.94238807829937,"min":51.35760364448936},"medium":{"max":81.8208639592235,"mean":66.77284273884489,"min":54.57289357501711},"none":{"max":55.09029052603637,"mean":41.453142805813016,"min":26.816405095011675}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.489245272486357},"working_program_strength":{"all":59.72279120765243,"highest":70.94238807829937,"medium":66.77284273884489,"none":41.453142805813016}},{"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":0.2214736}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876985},"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":0.8333794999999999}},"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":1.3936229500000001},"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":58.29964782102038,"highest":63.6342594029209,"medium":54.98399866703712,"none":56.28068539310311},"economics_best_value":{"per_model":{"none":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"infra_excluded"}},"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":69.59116526057646,"score":69.59116526057646},"GB2-02":{"attempts":2,"playable":44.97685382422647,"score":44.97685382422647},"GB2-03":{"attempts":3,"playable":52.832539963614614,"score":52.832539963614614},"GB2-04":{"attempts":3,"playable":44.48230166257378,"score":44.48230166257378},"GB2-05":{"attempts":3,"playable":52.1826652760445,"score":52.1826652760445},"GB2-06":{"attempts":3,"playable":63.03599264094472,"score":63.03599264094472},"GB2-07":{"attempts":3,"playable":54.818925847519154,"score":54.818925847519154},"GB2-08":{"attempts":3,"playable":78.25760289976516,"score":78.25760289976516}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":92.30699442734611,"score":92.30699442734611},"GB2-03":{"attempts":1,"playable":67.72454367206943,"score":67.72454367206943},"GB2-04":{"attempts":1,"playable":39.44947595905667,"score":39.44947595905667},"GB2-05":{"attempts":1,"playable":40.68351463237852,"score":40.68351463237852},"GB2-06":{"attempts":1,"playable":50.025467562234596,"score":50.025467562234596},"GB2-07":{"attempts":1,"playable":74.25776604435315,"score":74.25776604435315},"GB2-08":{"attempts":1,"playable":80.99205352300777,"score":80.99205352300777}},"medium":{"GB2-01":{"attempts":1,"playable":51.72430239386958,"score":51.72430239386958},"GB2-02":{"attempts":1,"playable":44.38935843142217,"score":44.38935843142217},"GB2-03":{"attempts":1,"playable":33.672393099704045,"score":33.672393099704045},"GB2-04":{"attempts":1,"playable":47.30358303033733,"score":47.30358303033733},"GB2-05":{"attempts":1,"playable":57.55198442693155,"score":57.55198442693155},"GB2-06":{"attempts":1,"playable":77.6293099265343,"score":77.6293099265343},"GB2-07":{"attempts":1,"playable":57.467174986402846,"score":57.467174986402846},"GB2-08":{"attempts":1,"playable":70.13388304109516,"score":70.13388304109516}},"none":{"GB2-01":{"attempts":1,"playable":64.74219896051368,"score":64.74219896051368},"GB2-02":{"attempts":1,"playable":45.56434921703077,"score":45.56434921703077},"GB2-03":{"attempts":1,"playable":57.100683119070354,"score":57.100683119070354},"GB2-04":{"attempts":1,"playable":46.69384599832737,"score":46.69384599832737},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":61.45320043406526,"score":61.45320043406526},"GB2-07":{"attempts":1,"playable":32.73183651180149,"score":32.73183651180149},"GB2-08":{"attempts":1,"playable":83.64687213519258,"score":83.64687213519258}}},"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":92.30699442734611,"mean":58.29964782102038,"min":32.73183651180149},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":19,"overall_ranking_status":"partial","per_game":{"GB2-01":92.30699442734611,"GB2-03":67.72454367206943,"GB2-04":39.44947595905667,"GB2-05":40.68351463237852,"GB2-06":50.025467562234596,"GB2-07":74.25776604435315,"GB2-08":80.99205352300777},"per_game_all":{"GB2-01":69.59116526057646,"GB2-03":52.832539963614614,"GB2-04":44.48230166257378,"GB2-05":52.1826652760445,"GB2-06":63.03599264094472,"GB2-07":54.818925847519154,"GB2-08":78.25760289976516},"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":1716.039177714624,"GB2-03":1458.539489814747,"GB2-04":1432.2005399219067,"GB2-05":1465.3159293164808,"GB2-06":1640.2156207791606,"GB2-07":1519.3666608903688,"GB2-08":1861.5578344486082},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2048.245060608446,"GB2-03":1599.5842524068637,"GB2-04":1393.0689936762606,"GB2-05":1320.4124541529663,"GB2-06":1419.9690796058724,"GB2-07":1785.9379596442523,"GB2-08":1915.936940196441},"medium":{"GB2-01":1485.4959178849647,"GB2-02":1428.4203946875823,"GB2-03":1284.210955983745,"GB2-04":1454.1185960640555,"GB2-05":1532.8064519950885,"GB2-06":1897.1402691463989,"GB2-07":1542.550069757832,"GB2-08":1688.7061292018748},"none":{"GB2-01":1614.3765546504605,"GB2-02":1437.4881845654618,"GB2-03":1491.8232610536325,"GB2-04":1449.4140300254037,"GB2-05":1542.7288818013874,"GB2-06":1603.5375135852112,"GB2-07":1229.6119532690227,"GB2-08":1980.0304339475088}},"per_game_tracks":{"highest":{"GB2-01":92.30699442734611,"GB2-03":67.72454367206943,"GB2-04":39.44947595905667,"GB2-05":40.68351463237852,"GB2-06":50.025467562234596,"GB2-07":74.25776604435315,"GB2-08":80.99205352300777},"medium":{"GB2-01":51.72430239386958,"GB2-02":44.38935843142217,"GB2-03":33.672393099704045,"GB2-04":47.30358303033733,"GB2-05":57.55198442693155,"GB2-06":77.6293099265343,"GB2-07":57.467174986402846,"GB2-08":70.13388304109516},"none":{"GB2-01":64.74219896051368,"GB2-02":45.56434921703077,"GB2-03":57.100683119070354,"GB2-04":46.69384599832737,"GB2-05":58.31249676882345,"GB2-06":61.45320043406526,"GB2-07":32.73183651180149,"GB2-08":83.64687213519258}},"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":63.6342594029209,"medium":54.98399866703712,"none":56.28068539310311},"reasoning_agg":{"highest":{"max":92.30699442734611,"mean":63.6342594029209,"min":39.44947595905667},"medium":{"max":77.6293099265343,"mean":54.98399866703712,"min":33.672393099704045},"none":{"max":83.64687213519258,"mean":56.28068539310311,"min":32.73183651180149}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.650260735883776},"working_program_strength":{"all":58.29964782102038,"highest":63.6342594029209,"medium":54.98399866703712,"none":56.28068539310311}},{"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":0.5087455999999999},"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":0.5964052000000001}},"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":1.6998543999999998},"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":58.254135909935,"highest":63.4772921247202,"medium":61.882626639667734,"none":49.40248896541706},"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":73.32550975897233,"score":73.32550975897233},"GB2-02":{"attempts":3,"playable":51.85956656434964,"score":51.85956656434964},"GB2-03":{"attempts":3,"playable":39.1401135347381,"score":39.1401135347381},"GB2-04":{"attempts":3,"playable":43.332986106347384,"score":43.332986106347384},"GB2-05":{"attempts":3,"playable":61.2955042190537,"score":61.2955042190537},"GB2-06":{"attempts":3,"playable":47.60965884887411,"score":47.60965884887411},"GB2-07":{"attempts":3,"playable":61.494631657523314,"score":61.494631657523314},"GB2-08":{"attempts":3,"playable":87.97511658962145,"score":87.97511658962145}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":83.6275738997741,"score":83.6275738997741},"GB2-02":{"attempts":1,"playable":59.238956333712366,"score":59.238956333712366},"GB2-03":{"attempts":1,"playable":45.37018462718579,"score":45.37018462718579},"GB2-04":{"attempts":1,"playable":44.25089660655846,"score":44.25089660655846},"GB2-05":{"attempts":1,"playable":73.70656014798726,"score":73.70656014798726},"GB2-06":{"attempts":1,"playable":54.51921324294854,"score":54.51921324294854},"GB2-07":{"attempts":1,"playable":56.56499142897715,"score":56.56499142897715},"GB2-08":{"attempts":1,"playable":90.53996071061802,"score":90.53996071061802}},"medium":{"GB2-01":{"attempts":1,"playable":83.90425679819714,"score":83.90425679819714},"GB2-02":{"attempts":1,"playable":52.478268451558996,"score":52.478268451558996},"GB2-03":{"attempts":1,"playable":56.29807121307564,"score":56.29807121307564},"GB2-04":{"attempts":1,"playable":42.9250607025321,"score":42.9250607025321},"GB2-05":{"attempts":1,"playable":67.37729200558647,"score":67.37729200558647},"GB2-06":{"attempts":1,"playable":44.94891798146081,"score":44.94891798146081},"GB2-07":{"attempts":1,"playable":58.54710537662376,"score":58.54710537662376},"GB2-08":{"attempts":1,"playable":88.58204058830702,"score":88.58204058830702}},"none":{"GB2-01":{"attempts":1,"playable":52.44469857894575,"score":52.44469857894575},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":15.752084763952883,"score":15.752084763952883},"GB2-04":{"attempts":1,"playable":42.82300100995158,"score":42.82300100995158},"GB2-05":{"attempts":1,"playable":42.80266050358737,"score":42.80266050358737},"GB2-06":{"attempts":1,"playable":43.36084532221298,"score":43.36084532221298},"GB2-07":{"attempts":1,"playable":69.37179816696903,"score":69.37179816696903},"GB2-08":{"attempts":1,"playable":84.80334846993928,"score":84.80334846993928}}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-10-26T01:18:06Z","match_totals_all":{"draws":2561,"losses":4056,"wins":5646},"match_totals_tracks":{"highest":{"draws":672,"losses":1232,"wins":2184},"medium":{"draws":845,"losses":1214,"wins":2029},"none":{"draws":1044,"losses":1610,"wins":1433}},"model_slug":"x-ai-grok-4-5","official_rank_by_reasoning":{"highest":31,"medium":20,"none":23},"overall":{"max":90.53996071061802,"mean":58.254135909935,"min":15.752084763952883},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":83.6275738997741,"GB2-02":59.238956333712366,"GB2-03":45.37018462718579,"GB2-04":44.25089660655846,"GB2-05":73.70656014798726,"GB2-06":54.51921324294854,"GB2-07":56.56499142897715,"GB2-08":90.53996071061802},"per_game_all":{"GB2-01":73.32550975897233,"GB2-02":51.85956656434964,"GB2-03":39.1401135347381,"GB2-04":43.332986106347384,"GB2-05":61.2955042190537,"GB2-06":47.60965884887411,"GB2-07":61.494631657523314,"GB2-08":87.97511658962145},"per_game_match_totals_all":{"GB2-01":{"draws":395,"losses":244,"wins":908},"GB2-02":{"draws":908,"losses":264,"wins":268},"GB2-03":{"draws":316,"losses":793,"wins":373},"GB2-04":{"draws":909,"losses":417,"wins":168},"GB2-05":{"draws":0,"losses":641,"wins":949},"GB2-06":{"draws":33,"losses":839,"wins":634},"GB2-07":{"draws":0,"losses":643,"wins":947},"GB2-08":{"draws":0,"losses":215,"wins":1399}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":105,"losses":41,"wins":370},"GB2-02":{"draws":236,"losses":86,"wins":158},"GB2-03":{"draws":112,"losses":233,"wins":149},"GB2-04":{"draws":210,"losses":181,"wins":107},"GB2-05":{"draws":0,"losses":148,"wins":382},"GB2-06":{"draws":9,"losses":245,"wins":248},"GB2-07":{"draws":0,"losses":242,"wins":288},"GB2-08":{"draws":0,"losses":56,"wins":482}},"medium":{"GB2-01":{"draws":44,"losses":70,"wins":402},"GB2-02":{"draws":307,"losses":83,"wins":90},"GB2-03":{"draws":133,"losses":169,"wins":192},"GB2-04":{"draws":345,"losses":120,"wins":33},"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":0,"losses":68,"wins":470}},"none":{"GB2-01":{"draws":246,"losses":133,"wins":136},"GB2-02":{"draws":365,"losses":95,"wins":20},"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":91,"wins":447}}},"per_game_raw_elo_all":{"GB2-01":1735.8997507929598,"GB2-02":1486.7936815185376,"GB2-03":1320.118397398535,"GB2-04":1423.4297633888464,"GB2-05":1598.932218394005,"GB2-06":1383.554398437792,"GB2-07":1598.510537306229,"GB2-08":2100.147366630846},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1855.313598133685,"GB2-02":1545.0538546978576,"GB2-03":1387.2424753401822,"GB2-04":1430.545404647071,"GB2-05":1778.6316153882026,"GB2-06":1490.3486807465188,"GB2-07":1530.83938107489,"GB2-08":2176.6778970782098},"medium":{"GB2-01":1860.004954533737,"GB2-02":1490.986792253254,"GB2-03":1484.3595446906118,"GB2-04":1420.268340757724,"GB2-05":1670.6794824430442,"GB2-06":1342.1991170874016,"GB2-07":1556.6766612607728,"GB2-08":2114.344958837818},"none":{"GB2-01":1492.380699711458,"GB2-02":1424.340397604501,"GB2-03":1088.753172164811,"GB2-04":1419.475544761744,"GB2-05":1347.4855573507684,"GB2-06":1318.115397479456,"GB2-07":1708.0155695830242,"GB2-08":2009.41924397651}},"per_game_tracks":{"highest":{"GB2-01":83.6275738997741,"GB2-02":59.238956333712366,"GB2-03":45.37018462718579,"GB2-04":44.25089660655846,"GB2-05":73.70656014798726,"GB2-06":54.51921324294854,"GB2-07":56.56499142897715,"GB2-08":90.53996071061802},"medium":{"GB2-01":83.90425679819714,"GB2-02":52.478268451558996,"GB2-03":56.29807121307564,"GB2-04":42.9250607025321,"GB2-05":67.37729200558647,"GB2-06":44.94891798146081,"GB2-07":58.54710537662376,"GB2-08":88.58204058830702},"none":{"GB2-01":52.44469857894575,"GB2-02":43.861474907777556,"GB2-03":15.752084763952883,"GB2-04":42.82300100995158,"GB2-05":42.80266050358737,"GB2-06":43.36084532221298,"GB2-07":69.37179816696903,"GB2-08":84.80334846993928}},"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":"2026-10-24T19:06:41Z","reasoning":{"highest":63.4772921247202,"medium":61.882626639667734,"none":49.40248896541706},"reasoning_agg":{"highest":{"max":90.53996071061802,"mean":63.4772921247202,"min":44.25089660655846},"medium":{"max":88.58204058830702,"mean":61.882626639667734,"min":42.9250607025321},"none":{"max":84.80334846993928,"mean":49.40248896541706,"min":15.752084763952883}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":14.074803159303144},"working_program_strength":{"all":58.254135909935,"highest":63.4772921247202,"medium":61.882626639667734,"none":49.40248896541706}},{"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":0.06816269999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296144}},"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":0.7626897200000001},"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":57.60504035134287,"highest":68.6039314720645,"medium":52.348000012946464,"none":51.86318956901767},"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":61.82023570125329,"score":61.82023570125329},"GB2-02":{"attempts":3,"playable":54.47284991410866,"score":54.47284991410866},"GB2-03":{"attempts":3,"playable":63.33512100666218,"score":63.33512100666218},"GB2-04":{"attempts":3,"playable":62.00393183817469,"score":62.00393183817469},"GB2-05":{"attempts":3,"playable":56.34900698086208,"score":56.34900698086208},"GB2-06":{"attempts":3,"playable":67.20437084313345,"score":67.20437084313345},"GB2-07":{"attempts":3,"playable":66.05609167262041,"score":66.05609167262041},"GB2-08":{"attempts":3,"playable":29.5987148539283,"score":29.5987148539283}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":42.00746268161959,"score":42.00746268161959},"GB2-02":{"attempts":1,"playable":68.98161685961959,"score":68.98161685961959},"GB2-03":{"attempts":1,"playable":84.85546915992354,"score":84.85546915992354},"GB2-04":{"attempts":1,"playable":78.0535351595473,"score":78.0535351595473},"GB2-05":{"attempts":1,"playable":78.64256950562759,"score":78.64256950562759},"GB2-06":{"attempts":1,"playable":81.8208639592235,"score":81.8208639592235},"GB2-07":{"attempts":1,"playable":72.86638736782065,"score":72.86638736782065},"GB2-08":{"attempts":1,"playable":41.60354708313428,"score":41.60354708313428}},"medium":{"GB2-01":{"attempts":1,"playable":77.55361591884589,"score":77.55361591884589},"GB2-02":{"attempts":1,"playable":52.478268451558996,"score":52.478268451558996},"GB2-03":{"attempts":1,"playable":57.401127531830454,"score":57.401127531830454},"GB2-04":{"attempts":1,"playable":55.99426584982658,"score":55.99426584982658},"GB2-05":{"attempts":1,"playable":40.68351463237852,"score":40.68351463237852},"GB2-06":{"attempts":1,"playable":55.84310189813421,"score":55.84310189813421},"GB2-07":{"attempts":1,"playable":59.80337275739795,"score":59.80337275739795},"GB2-08":{"attempts":1,"playable":19.026733063599135,"score":19.026733063599135}},"none":{"GB2-01":{"attempts":1,"playable":65.89962850329437,"score":65.89962850329437},"GB2-02":{"attempts":1,"playable":41.95866443114737,"score":41.95866443114737},"GB2-03":{"attempts":1,"playable":47.74876632823254,"score":47.74876632823254},"GB2-04":{"attempts":1,"playable":51.96399450515018,"score":51.96399450515018},"GB2-05":{"attempts":1,"playable":49.72093680458015,"score":49.72093680458015},"GB2-06":{"attempts":1,"playable":63.94914667204261,"score":63.94914667204261},"GB2-07":{"attempts":1,"playable":65.49851489264262,"score":65.49851489264262},"GB2-08":{"attempts":1,"playable":28.165864415051487,"score":28.165864415051487}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:25Z","match_totals_all":{"draws":2603,"losses":4185,"wins":5476},"match_totals_tracks":{"highest":{"draws":619,"losses":1060,"wins":2409},"medium":{"draws":851,"losses":1628,"wins":1609},"none":{"draws":1133,"losses":1497,"wins":1458}},"model_slug":"z-ai-glm-5-3-flashx","official_rank_by_reasoning":{"highest":20,"medium":33,"none":16},"overall":{"max":84.85546915992354,"mean":57.60504035134287,"min":19.026733063599135},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.00746268161959,"GB2-02":68.98161685961959,"GB2-03":84.85546915992354,"GB2-04":78.0535351595473,"GB2-05":78.64256950562759,"GB2-06":81.8208639592235,"GB2-07":72.86638736782065,"GB2-08":41.60354708313428},"per_game_all":{"GB2-01":61.82023570125329,"GB2-02":54.47284991410866,"GB2-03":63.33512100666218,"GB2-04":62.00393183817469,"GB2-05":56.34900698086208,"GB2-06":67.20437084313345,"GB2-07":66.05609167262041,"GB2-08":29.5987148539283},"per_game_match_totals_all":{"GB2-01":{"draws":115,"losses":565,"wins":868},"GB2-02":{"draws":939,"losses":210,"wins":291},"GB2-03":{"draws":163,"losses":511,"wins":808},"GB2-04":{"draws":792,"losses":196,"wins":506},"GB2-05":{"draws":0,"losses":718,"wins":872},"GB2-06":{"draws":55,"losses":515,"wins":936},"GB2-07":{"draws":0,"losses":566,"wins":1024},"GB2-08":{"draws":539,"losses":904,"wins":171}},"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":82,"wins":406},"GB2-04":{"draws":158,"losses":37,"wins":303},"GB2-05":{"draws":0,"losses":121,"wins":409},"GB2-06":{"draws":26,"losses":88,"wins":388},"GB2-07":{"draws":0,"losses":150,"wins":380},"GB2-08":{"draws":205,"losses":228,"wins":105}},"medium":{"GB2-01":{"draws":6,"losses":123,"wins":387},"GB2-02":{"draws":351,"losses":61,"wins":68},"GB2-03":{"draws":52,"losses":204,"wins":238},"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":127,"losses":381,"wins":30}},"none":{"GB2-01":{"draws":106,"losses":134,"wins":276},"GB2-02":{"draws":367,"losses":103,"wins":10},"GB2-03":{"draws":105,"losses":225,"wins":164},"GB2-04":{"draws":342,"losses":77,"wins":79},"GB2-05":{"draws":0,"losses":275,"wins":255},"GB2-06":{"draws":6,"losses":196,"wins":300},"GB2-07":{"draws":0,"losses":192,"wins":338},"GB2-08":{"draws":207,"losses":295,"wins":36}}},"per_game_raw_elo_all":{"GB2-01":1594.585109649505,"GB2-02":1510.5268086039944,"GB2-03":1587.459471114933,"GB2-04":1580.7082071619664,"GB2-05":1545.6317186963158,"GB2-06":1712.97747862463,"GB2-07":1662.478379200311,"GB2-08":1161.8384121941306},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1392.8192463823204,"GB2-02":1631.0103512706908,"GB2-03":1859.81120047012,"GB2-04":1729.9419564484056,"GB2-05":1882.5489676203924,"GB2-06":1981.4239281222963,"GB2-07":1762.8302046036797,"GB2-08":1295.3189797004013},"medium":{"GB2-01":1764.3431992141468,"GB2-02":1490.986792253254,"GB2-03":1494.6348488431468,"GB2-04":1521.969378124514,"GB2-05":1320.4124541529663,"GB2-06":1511.4702719944983,"GB2-07":1573.2743162589618,"GB2-08":1039.9826834953928},"none":{"GB2-01":1626.5928833520472,"GB2-02":1409.5832822880382,"GB2-03":1407.9323640315326,"GB2-04":1490.2132869129803,"GB2-05":1433.933734315588,"GB2-06":1646.038235757096,"GB2-07":1651.3306167382923,"GB2-08":1150.2135733865975}},"per_game_tracks":{"highest":{"GB2-01":42.00746268161959,"GB2-02":68.98161685961959,"GB2-03":84.85546915992354,"GB2-04":78.0535351595473,"GB2-05":78.64256950562759,"GB2-06":81.8208639592235,"GB2-07":72.86638736782065,"GB2-08":41.60354708313428},"medium":{"GB2-01":77.55361591884589,"GB2-02":52.478268451558996,"GB2-03":57.401127531830454,"GB2-04":55.99426584982658,"GB2-05":40.68351463237852,"GB2-06":55.84310189813421,"GB2-07":59.80337275739795,"GB2-08":19.026733063599135},"none":{"GB2-01":65.89962850329437,"GB2-02":41.95866443114737,"GB2-03":47.74876632823254,"GB2-04":51.96399450515018,"GB2-05":49.72093680458015,"GB2-06":63.94914667204261,"GB2-07":65.49851489264262,"GB2-08":28.165864415051487}},"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":"2026-10-24T19:12:16Z","reasoning":{"highest":68.6039314720645,"medium":52.348000012946464,"none":51.86318956901767},"reasoning_agg":{"highest":{"max":84.85546915992354,"mean":68.6039314720645,"min":41.60354708313428},"medium":{"max":77.55361591884589,"mean":52.348000012946464,"min":19.026733063599135},"none":{"max":65.89962850329437,"mean":51.86318956901767,"min":28.165864415051487}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":16.740741903046832},"working_program_strength":{"all":57.60504035134287,"highest":68.6039314720645,"medium":52.348000012946464,"none":51.86318956901767}},{"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":0.0955808},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.024963200000000005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.0955808},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.0249632},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3826036}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.020964483333333336,"median":0.012623549999999999,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":0.5031476},"codegen_output_tokens":{"attempt_count":28,"output_max":128000,"output_mean":38910.541666666664,"output_min":1643,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":128000,"output_mean":92691.0,"output_min":56566,"run_count":8},"medium":{"attempt_count":9,"output_max":32619,"output_mean":20970.375,"output_min":8448,"run_count":8},"none":{"attempt_count":10,"output_max":6434,"output_mean":3070.25,"output_min":1643,"run_count":8}},"display_name":"Claude Haiku 5.5","economics":{"all":57.26920075540992,"highest":74.85461771544894,"medium":57.64469547081516,"none":39.308289079965675},"economics_best_value":{"per_model":{"all":true,"highest":true},"per_setting":{"highest":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"infra_excluded"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":933853,"total_reasoning_output_tokens":827092,"total_visible_output_tokens":106761,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":40.81592221955691,"score":40.81592221955691},"GB2-02":{"attempts":3,"playable":58.61208442610843,"score":58.61208442610843},"GB2-03":{"attempts":2,"playable":55.45062198753941,"score":55.45062198753941},"GB2-04":{"attempts":3,"playable":63.135820902353565,"score":63.135820902353565},"GB2-05":{"attempts":3,"playable":53.38848570569018,"score":53.38848570569018},"GB2-06":{"attempts":3,"playable":70.02989645121926,"score":70.02989645121926},"GB2-07":{"attempts":3,"playable":58.678591756396,"score":58.678591756396},"GB2-08":{"attempts":3,"playable":51.57418401844583,"score":51.57418401844583}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.51447974442542,"score":41.51447974442542},"GB2-02":{"attempts":1,"playable":70.50235193557407,"score":70.50235193557407},"GB2-04":{"attempts":1,"playable":79.96961832899599,"score":79.96961832899599},"GB2-05":{"attempts":1,"playable":86.37309679864593,"score":86.37309679864593},"GB2-06":{"attempts":1,"playable":91.83900036619863,"score":91.83900036619863},"GB2-07":{"attempts":1,"playable":67.08694959374789,"score":67.08694959374789},"GB2-08":{"attempts":1,"playable":86.69682724055463,"score":86.69682724055463}},"medium":{"GB2-01":{"attempts":1,"playable":45.55051096100455,"score":45.55051096100455},"GB2-02":{"attempts":1,"playable":62.952066864120745,"score":62.952066864120745},"GB2-03":{"attempts":1,"playable":67.82097932487197,"score":67.82097932487197},"GB2-04":{"attempts":1,"playable":67.73816657363633,"score":67.73816657363633},"GB2-05":{"attempts":1,"playable":57.55198442693155,"score":57.55198442693155},"GB2-06":{"attempts":1,"playable":68.90168340024606,"score":68.90168340024606},"GB2-07":{"attempts":1,"playable":56.92611116770436,"score":56.92611116770436},"GB2-08":{"attempts":1,"playable":33.71606104800567,"score":33.71606104800567}},"none":{"GB2-01":{"attempts":1,"playable":35.382775953240746,"score":35.382775953240746},"GB2-02":{"attempts":1,"playable":42.38183447863047,"score":42.38183447863047},"GB2-03":{"attempts":1,"playable":43.08026465020685,"score":43.08026465020685},"GB2-04":{"attempts":1,"playable":41.69967780442835,"score":41.69967780442835},"GB2-05":{"attempts":1,"playable":16.24037589149305,"score":16.24037589149305},"GB2-06":{"attempts":1,"playable":49.34900558721307,"score":49.34900558721307},"GB2-07":{"attempts":1,"playable":52.022714507735756,"score":52.022714507735756},"GB2-08":{"attempts":1,"playable":34.30966376677716,"score":34.30966376677716}}},"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":91.83900036619863,"mean":57.26920075540992,"min":16.24037589149305},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":22,"overall_ranking_status":"partial","per_game":{"GB2-01":41.51447974442542,"GB2-02":70.50235193557407,"GB2-04":79.96961832899599,"GB2-05":86.37309679864593,"GB2-06":91.83900036619863,"GB2-07":67.08694959374789,"GB2-08":86.69682724055463},"per_game_all":{"GB2-01":40.81592221955691,"GB2-02":58.61208442610843,"GB2-04":63.135820902353565,"GB2-05":53.38848570569018,"GB2-06":70.02989645121926,"GB2-07":58.678591756396,"GB2-08":51.57418401844583},"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":1380.8317562240302,"GB2-02":1545.0125804529725,"GB2-04":1595.5188081702665,"GB2-05":1525.6545481958453,"GB2-06":1790.95278840503,"GB2-07":1560.8530301318297,"GB2-08":1495.9107592232983},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1388.065126574323,"GB2-02":1645.8451909105013,"GB2-04":1753.850143746638,"GB2-05":2106.400811429203,"GB2-06":2229.9216714799804,"GB2-07":1674.1473627045448,"GB2-08":2060.0107848673315},"medium":{"GB2-01":1426.7376997328356,"GB2-02":1576.3191505136463,"GB2-03":1600.6670328503253,"GB2-04":1621.976637675898,"GB2-05":1532.8064519950885,"GB2-06":1733.4178689933622,"GB2-07":1535.5174277179951,"GB2-08":1210.6808429606326},"none":{"GB2-01":1327.6924423649327,"GB2-02":1412.8733999347703,"GB2-03":1367.3752054116387,"GB2-04":1410.7296430882634,"GB2-05":937.7563811632441,"GB2-06":1409.518824741747,"GB2-07":1472.8942999729484,"GB2-08":1217.0406498419302}},"per_game_tracks":{"highest":{"GB2-01":41.51447974442542,"GB2-02":70.50235193557407,"GB2-04":79.96961832899599,"GB2-05":86.37309679864593,"GB2-06":91.83900036619863,"GB2-07":67.08694959374789,"GB2-08":86.69682724055463},"medium":{"GB2-01":45.55051096100455,"GB2-02":62.952066864120745,"GB2-03":67.82097932487197,"GB2-04":67.73816657363633,"GB2-05":57.55198442693155,"GB2-06":68.90168340024606,"GB2-07":56.92611116770436,"GB2-08":33.71606104800567},"none":{"GB2-01":35.382775953240746,"GB2-02":42.38183447863047,"GB2-03":43.08026465020685,"GB2-04":41.69967780442835,"GB2-05":16.24037589149305,"GB2-06":49.34900558721307,"GB2-07":52.022714507735756,"GB2-08":34.30966376677716}},"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":74.85461771544894,"medium":57.64469547081516,"none":39.308289079965675},"reasoning_agg":{"highest":{"max":91.83900036619863,"mean":74.85461771544894,"min":41.51447974442542},"medium":{"max":68.90168340024606,"mean":57.64469547081516,"min":33.71606104800567},"none":{"max":52.022714507735756,"mean":39.308289079965675,"min":16.24037589149305}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":35.54632863548326},"working_program_strength":{"all":57.26920075540992,"highest":74.85461771544894,"medium":57.64469547081516,"none":39.308289079965675}},{"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":0.04628865},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.0298479}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847899999999997},"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":0.195345875},"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":56.87187236559882,"highest":59.095129153799014,"medium":63.334509179752644,"none":48.185978763244805},"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":58.116106176436375,"score":58.116106176436375},"GB2-02":{"attempts":3,"playable":52.581739533246896,"score":52.581739533246896},"GB2-03":{"attempts":3,"playable":71.74503189743697,"score":71.74503189743697},"GB2-04":{"attempts":3,"playable":72.46521015506944,"score":72.46521015506944},"GB2-05":{"attempts":3,"playable":53.47620686150221,"score":53.47620686150221},"GB2-06":{"attempts":3,"playable":47.51896278648835,"score":47.51896278648835},"GB2-07":{"attempts":3,"playable":72.39619581433568,"score":72.39619581433568},"GB2-08":{"attempts":3,"playable":26.675525700274658,"score":26.675525700274658}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":65.99600951760388,"score":65.99600951760388},"GB2-02":{"attempts":1,"playable":66.43573754691377,"score":66.43573754691377},"GB2-03":{"attempts":1,"playable":78.36892503795902,"score":78.36892503795902},"GB2-04":{"attempts":1,"playable":78.82121553724855,"score":78.82121553724855},"GB2-05":{"attempts":1,"playable":74.2598107921713,"score":74.2598107921713},"GB2-06":{"attempts":1,"playable":17.24808744063479,"score":17.24808744063479},"GB2-07":{"attempts":1,"playable":69.72234893364258,"score":69.72234893364258},"GB2-08":{"attempts":1,"playable":21.90889842421831,"score":21.90889842421831}},"medium":{"GB2-01":{"attempts":1,"playable":71.08671603660993,"score":71.08671603660993},"GB2-02":{"attempts":1,"playable":46.39253976872338,"score":46.39253976872338},"GB2-03":{"attempts":1,"playable":80.46765982501938,"score":80.46765982501938},"GB2-04":{"attempts":1,"playable":73.99705337511335,"score":73.99705337511335},"GB2-05":{"attempts":1,"playable":48.570174105681495,"score":48.570174105681495},"GB2-06":{"attempts":1,"playable":81.45735359322124,"score":81.45735359322124},"GB2-07":{"attempts":1,"playable":75.64573739534956,"score":75.64573739534956},"GB2-08":{"attempts":1,"playable":29.05883933830283,"score":29.05883933830283}},"none":{"GB2-01":{"attempts":1,"playable":37.2655929750953,"score":37.2655929750953},"GB2-02":{"attempts":1,"playable":44.91694128410355,"score":44.91694128410355},"GB2-03":{"attempts":1,"playable":56.39851082933254,"score":56.39851082933254},"GB2-04":{"attempts":1,"playable":64.57736155284643,"score":64.57736155284643},"GB2-05":{"attempts":1,"playable":37.59863568665383,"score":37.59863568665383},"GB2-06":{"attempts":1,"playable":43.85144732560902,"score":43.85144732560902},"GB2-07":{"attempts":1,"playable":71.8205011140149,"score":71.8205011140149},"GB2-08":{"attempts":1,"playable":29.05883933830283,"score":29.05883933830283}}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T01:37:36Z","match_totals_all":{"draws":2169,"losses":4478,"wins":5616},"match_totals_tracks":{"highest":{"draws":455,"losses":1533,"wins":2100},"medium":{"draws":706,"losses":1231,"wins":2151},"none":{"draws":1008,"losses":1714,"wins":1365}},"model_slug":"z-ai-glm-5-3-flash","official_rank_by_reasoning":{"highest":34,"medium":18,"none":26},"overall":{"max":81.45735359322124,"mean":56.87187236559882,"min":17.24808744063479},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":65.99600951760388,"GB2-02":66.43573754691377,"GB2-03":78.36892503795902,"GB2-04":78.82121553724855,"GB2-05":74.2598107921713,"GB2-06":17.24808744063479,"GB2-07":69.72234893364258,"GB2-08":21.90889842421831},"per_game_all":{"GB2-01":58.116106176436375,"GB2-02":52.581739533246896,"GB2-03":71.74503189743697,"GB2-04":72.46521015506944,"GB2-05":53.47620686150221,"GB2-06":47.51896278648835,"GB2-07":72.39619581433568,"GB2-08":26.675525700274658},"per_game_match_totals_all":{"GB2-01":{"draws":242,"losses":559,"wins":747},"GB2-02":{"draws":958,"losses":228,"wins":254},"GB2-03":{"draws":147,"losses":392,"wins":943},"GB2-04":{"draws":500,"losses":184,"wins":810},"GB2-05":{"draws":0,"losses":764,"wins":826},"GB2-06":{"draws":64,"losses":804,"wins":637},"GB2-07":{"draws":0,"losses":458,"wins":1132},"GB2-08":{"draws":258,"losses":1089,"wins":267}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":184,"wins":327},"GB2-02":{"draws":246,"losses":46,"wins":188},"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":349,"losses":91,"wins":40},"GB2-03":{"draws":25,"losses":97,"wins":372},"GB2-04":{"draws":160,"losses":57,"wins":281},"GB2-05":{"draws":0,"losses":281,"wins":249},"GB2-06":{"draws":32,"losses":87,"wins":383},"GB2-07":{"draws":0,"losses":134,"wins":396},"GB2-08":{"draws":120,"losses":334,"wins":84}},"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":18,"losses":295,"wins":188},"GB2-07":{"draws":0,"losses":156,"wins":374},"GB2-08":{"draws":94,"losses":347,"wins":97}}},"per_game_raw_elo_all":{"GB2-01":1552.709059766253,"GB2-02":1494.5225069730889,"GB2-03":1666.3386838837278,"GB2-04":1672.2680889376363,"GB2-05":1496.3128689665639,"GB2-06":1404.5216243109833,"GB2-07":1756.403769453447,"GB2-08":1132.4412166046993},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1627.618501970005,"GB2-02":1607.2007798515776,"GB2-03":1739.5127408459666,"GB2-04":1739.324203810943,"GB2-05":1789.2322732761932,"GB2-06":914.1281794407054,"GB2-07":1713.3359171638647,"GB2-08":1077.0776141852089},"medium":{"GB2-01":1683.9802176030062,"GB2-02":1443.8728795931909,"GB2-03":1774.2133910637026,"GB2-04":1684.006896825348,"GB2-05":1419.6403280906447,"GB2-06":1973.8905303534104,"GB2-07":1809.8941153778012,"GB2-08":1160.1230178144444},"none":{"GB2-01":1346.5284597257478,"GB2-02":1432.4938614744979,"GB2-03":1485.2899197415138,"GB2-04":1593.4731661766184,"GB2-05":1280.0660055328544,"GB2-06":1325.5461631388343,"GB2-07":1745.9812758186752,"GB2-08":1160.1230178144444}},"per_game_tracks":{"highest":{"GB2-01":65.99600951760388,"GB2-02":66.43573754691377,"GB2-03":78.36892503795902,"GB2-04":78.82121553724855,"GB2-05":74.2598107921713,"GB2-06":17.24808744063479,"GB2-07":69.72234893364258,"GB2-08":21.90889842421831},"medium":{"GB2-01":71.08671603660993,"GB2-02":46.39253976872338,"GB2-03":80.46765982501938,"GB2-04":73.99705337511335,"GB2-05":48.570174105681495,"GB2-06":81.45735359322124,"GB2-07":75.64573739534956,"GB2-08":29.05883933830283},"none":{"GB2-01":37.2655929750953,"GB2-02":44.91694128410355,"GB2-03":56.39851082933254,"GB2-04":64.57736155284643,"GB2-05":37.59863568665383,"GB2-06":43.85144732560902,"GB2-07":71.8205011140149,"GB2-08":29.05883933830283}},"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":"2026-10-24T19:18:28Z","reasoning":{"highest":59.095129153799014,"medium":63.334509179752644,"none":48.185978763244805},"reasoning_agg":{"highest":{"max":78.82121553724855,"mean":59.095129153799014,"min":17.24808744063479},"medium":{"max":81.45735359322124,"mean":63.334509179752644,"min":29.05883933830283},"none":{"max":71.8205011140149,"mean":48.185978763244805,"min":29.05883933830283}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":15.148530416507839},"working_program_strength":{"all":56.87187236559882,"highest":59.095129153799014,"medium":63.334509179752644,"none":48.185978763244805}},{"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":3.1890240000000003}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.20968833333333334,"median":0.124697,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":19,"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":30,"run_count":24,"total":5.03252},"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":55.32207094530897,"highest":70.20934940685238,"medium":45.01534092627758,"none":50.741522502796954},"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":48.37634039151422,"score":48.37634039151422},"GB2-02":{"attempts":3,"playable":46.84228892261627,"score":46.84228892261627},"GB2-03":{"attempts":3,"playable":61.38604365750964,"score":61.38604365750964},"GB2-04":{"attempts":3,"playable":56.13434881666783,"score":56.13434881666783},"GB2-05":{"attempts":3,"playable":65.33300897941776,"score":65.33300897941776},"GB2-06":{"attempts":3,"playable":68.39526626644407,"score":68.39526626644407},"GB2-07":{"attempts":3,"playable":50.76114605467618,"score":50.76114605467618},"GB2-08":{"attempts":3,"playable":45.34812447362585,"score":45.34812447362585}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.60841138976626,"score":76.60841138976626},"GB2-02":{"attempts":1,"playable":49.546072293601604,"score":49.546072293601604},"GB2-03":{"attempts":1,"playable":71.3622706955068,"score":71.3622706955068},"GB2-04":{"attempts":1,"playable":84.71269669876197,"score":84.71269669876197},"GB2-05":{"attempts":1,"playable":92.40236120027856,"score":92.40236120027856},"GB2-06":{"attempts":1,"playable":64.40973208370043,"score":64.40973208370043},"GB2-07":{"attempts":1,"playable":76.33850998213276,"score":76.33850998213276},"GB2-08":{"attempts":1,"playable":46.294740911070704,"score":46.294740911070704}},"medium":{"GB2-01":{"attempts":1,"playable":26.31601551085625,"score":26.31601551085625},"GB2-02":{"attempts":1,"playable":48.916320467449594,"score":48.916320467449594},"GB2-03":{"attempts":1,"playable":57.000469978231585,"score":57.000469978231585},"GB2-04":{"attempts":1,"playable":45.88023191610302,"score":45.88023191610302},"GB2-05":{"attempts":1,"playable":43.76526237793952,"score":43.76526237793952},"GB2-06":{"attempts":1,"playable":59.500477636639005,"score":59.500477636639005},"GB2-07":{"attempts":1,"playable":36.55188391526639,"score":36.55188391526639},"GB2-08":{"attempts":1,"playable":42.192065607735294,"score":42.192065607735294}},"none":{"GB2-01":{"attempts":1,"playable":42.20459427392016,"score":42.20459427392016},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":55.795390298790515,"score":55.795390298790515},"GB2-04":{"attempts":1,"playable":37.810117835138485,"score":37.810117835138485},"GB2-05":{"attempts":1,"playable":59.83140336003518,"score":59.83140336003518},"GB2-06":{"attempts":1,"playable":81.27558907899275,"score":81.27558907899275},"GB2-07":{"attempts":1,"playable":39.3930442666294,"score":39.3930442666294},"GB2-08":{"attempts":1,"playable":47.55756690207156,"score":47.55756690207156}}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:49Z","match_totals_all":{"draws":3001,"losses":4264,"wins":4999},"match_totals_tracks":{"highest":{"draws":816,"losses":887,"wins":2385},"medium":{"draws":1039,"losses":1839,"wins":1210},"none":{"draws":1146,"losses":1538,"wins":1404}},"model_slug":"qwen-qwen3-8-max-0902","official_rank_by_reasoning":{"highest":17,"medium":46,"none":22},"overall":{"max":92.40236120027856,"mean":55.32207094530897,"min":26.31601551085625},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.60841138976626,"GB2-02":49.546072293601604,"GB2-03":71.3622706955068,"GB2-04":84.71269669876197,"GB2-05":92.40236120027856,"GB2-06":64.40973208370043,"GB2-07":76.33850998213276,"GB2-08":46.294740911070704},"per_game_all":{"GB2-01":48.37634039151422,"GB2-02":46.84228892261627,"GB2-03":61.38604365750964,"GB2-04":56.13434881666783,"GB2-05":65.33300897941776,"GB2-06":68.39526626644407,"GB2-07":50.76114605467618,"GB2-08":45.34812447362585},"per_game_match_totals_all":{"GB2-01":{"draws":306,"losses":675,"wins":567},"GB2-02":{"draws":1040,"losses":270,"wins":130},"GB2-03":{"draws":275,"losses":491,"wins":716},"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":582,"losses":643,"wins":389}},"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":78,"wins":51},"GB2-03":{"draws":90,"losses":187,"wins":217},"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":173,"losses":241,"wins":124}},"none":{"GB2-01":{"draws":209,"losses":204,"wins":103},"GB2-02":{"draws":358,"losses":107,"wins":15},"GB2-03":{"draws":92,"losses":192,"wins":210},"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":160,"losses":220,"wins":158}}},"per_game_raw_elo_all":{"GB2-01":1459.0265649485393,"GB2-02":1447.3154558698077,"GB2-03":1537.6388431182565,"GB2-04":1548.3054886908367,"GB2-05":1760.909807889994,"GB2-06":1731.7042653812161,"GB2-07":1472.2519702867178,"GB2-08":1336.9329500877723},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.7727722455481,"GB2-02":1468.2034154735177,"GB2-03":1642.3106849482892,"GB2-04":1821.7365200101046,"GB2-05":2360.256617051119,"GB2-06":1653.9929603164394,"GB2-07":1822.235918662621,"GB2-08":1347.317353549424},"medium":{"GB2-01":1230.5895430371938,"GB2-02":1463.336495286813,"GB2-03":1490.88764528281,"GB2-04":1443.135393423713,"GB2-05":1359.6513997399575,"GB2-06":1570.9772211576603,"GB2-07":1279.2462788719884,"GB2-08":1301.7306936943392},"none":{"GB2-01":1394.717379562876,"GB2-02":1410.4064568490924,"GB2-03":1479.7181991236705,"GB2-04":1380.0445526386927,"GB2-05":1562.8214068789055,"GB2-06":1970.1426146695485,"GB2-07":1315.273713325544,"GB2-08":1361.7508030195536}},"per_game_tracks":{"highest":{"GB2-01":76.60841138976626,"GB2-02":49.546072293601604,"GB2-03":71.3622706955068,"GB2-04":84.71269669876197,"GB2-05":92.40236120027856,"GB2-06":64.40973208370043,"GB2-07":76.33850998213276,"GB2-08":46.294740911070704},"medium":{"GB2-01":26.31601551085625,"GB2-02":48.916320467449594,"GB2-03":57.000469978231585,"GB2-04":45.88023191610302,"GB2-05":43.76526237793952,"GB2-06":59.500477636639005,"GB2-07":36.55188391526639,"GB2-08":42.192065607735294},"none":{"GB2-01":42.20459427392016,"GB2-02":42.06447400679762,"GB2-03":55.795390298790515,"GB2-04":37.810117835138485,"GB2-05":59.83140336003518,"GB2-06":81.27558907899275,"GB2-07":39.3930442666294,"GB2-08":47.55756690207156}},"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":1,"rank_movement_baseline_at":"2026-10-24T19:04:31Z","reasoning":{"highest":70.20934940685238,"medium":45.01534092627758,"none":50.741522502796954},"reasoning_agg":{"highest":{"max":92.40236120027856,"mean":70.20934940685238,"min":46.294740911070704},"medium":{"max":59.500477636639005,"mean":45.01534092627758,"min":26.31601551085625},"none":{"max":81.27558907899275,"mean":50.741522502796954,"min":37.810117835138485}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.1940084805748},"working_program_strength":{"all":55.32207094530897,"highest":70.20934940685238,"medium":45.01534092627758,"none":50.741522502796954}},{"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":2.266995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":0.6328307291666667,"median":0.26543625,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":15.1879375},"codegen_output_tokens":{"attempt_count":27,"output_max":146534,"output_mean":40675.041666666664,"output_min":3180,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":146534,"output_mean":99672.5,"output_min":71368,"run_count":8},"medium":{"attempt_count":8,"output_max":26272,"output_mean":17600.375,"output_min":12941,"run_count":8},"none":{"attempt_count":10,"output_max":8643,"output_mean":4752.25,"output_min":3180,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":55.2337248875208,"highest":63.534530244821404,"medium":55.33043041538656,"none":46.83621400235444},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":976201,"total_reasoning_output_tokens":819733,"total_visible_output_tokens":156468,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":91.13368962862563,"score":91.13368962862563},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.11479577593353,"score":28.743197183955687},"GB2-03":{"attempts":3,"playable":40.3506487529719,"score":40.3506487529719},"GB2-04":{"attempts":3,"playable":43.11141213977535,"score":43.11141213977535},"GB2-05":{"attempts":3,"playable":73.08699157140634,"score":73.08699157140634},"GB2-06":{"attempts":3,"playable":73.95034038677376,"score":73.95034038677376},"GB2-07":{"attempts":3,"playable":46.82589519449482,"score":46.82589519449482},"GB2-08":{"attempts":3,"playable":44.66762424216294,"score":44.66762424216294}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.24631432919804,"score":95.24631432919804},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.22701691364703,"score":44.22701691364703},"GB2-04":{"attempts":1,"playable":56.69724994545443,"score":56.69724994545443},"GB2-05":{"attempts":1,"playable":85.86183696737152,"score":85.86183696737152},"GB2-06":{"attempts":1,"playable":81.63911217049767,"score":81.63911217049767},"GB2-07":{"attempts":1,"playable":77.7217719313222,"score":77.7217719313222},"GB2-08":{"attempts":1,"playable":66.88293970108037,"score":66.88293970108037}},"medium":{"GB2-01":{"attempts":1,"playable":97.50040588860446,"score":97.50040588860446},"GB2-02":{"attempts":1,"playable":46.81368819709062,"score":46.81368819709062},"GB2-03":{"attempts":1,"playable":44.33108968183731,"score":44.33108968183731},"GB2-04":{"attempts":1,"playable":33.187510514814925,"score":33.187510514814925},"GB2-05":{"attempts":1,"playable":71.4841167856698,"score":71.4841167856698},"GB2-06":{"attempts":1,"playable":77.18540045807114,"score":77.18540045807114},"GB2-07":{"attempts":1,"playable":33.881725359608645,"score":33.881725359608645},"GB2-08":{"attempts":1,"playable":38.25950643739559,"score":38.25950643739559}},"none":{"GB2-01":{"attempts":1,"playable":80.65434866807438,"score":80.65434866807438},"GB2-02":{"attempts":1,"playable":39.41590335477645,"score":39.41590335477645},"GB2-03":{"attempts":1,"playable":32.49383966343138,"score":32.49383966343138},"GB2-04":{"attempts":1,"playable":39.44947595905667,"score":39.44947595905667},"GB2-05":{"attempts":1,"playable":61.9150209611777,"score":61.9150209611777},"GB2-06":{"attempts":1,"playable":63.02650853175248,"score":63.02650853175248},"GB2-07":{"attempts":1,"playable":28.874188292553626,"score":28.874188292553626},"GB2-08":{"attempts":1,"playable":28.86042658801284,"score":28.86042658801284}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:17Z","match_totals_all":{"draws":2491,"losses":3978,"wins":5315},"match_totals_tracks":{"highest":{"draws":504,"losses":795,"wins":2309},"medium":{"draws":988,"losses":1415,"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":97.50040588860446,"mean":55.2337248875208,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.24631432919804,"GB2-03":44.22701691364703,"GB2-04":56.69724994545443,"GB2-05":85.86183696737152,"GB2-06":81.63911217049767,"GB2-07":77.7217719313222,"GB2-08":66.88293970108037},"per_game_all":{"GB2-01":91.13368962862563,"GB2-03":40.3506487529719,"GB2-04":43.11141213977535,"GB2-05":73.08699157140634,"GB2-06":73.95034038677376,"GB2-07":46.82589519449482,"GB2-08":44.66762424216294},"per_game_match_totals_all":{"GB2-01":{"draws":71,"losses":115,"wins":1362},"GB2-02":{"draws":718,"losses":203,"wins":39},"GB2-03":{"draws":541,"losses":668,"wins":273},"GB2-04":{"draws":824,"losses":462,"wins":208},"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":270,"losses":804,"wins":540}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":21,"wins":482},"GB2-03":{"draws":145,"losses":222,"wins":127},"GB2-04":{"draws":265,"losses":92,"wins":141},"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":43,"losses":175,"wins":320}},"medium":{"GB2-01":{"draws":7,"losses":10,"wins":499},"GB2-02":{"draws":369,"losses":79,"wins":32},"GB2-03":{"draws":224,"losses":182,"wins":88},"GB2-04":{"draws":258,"losses":211,"wins":29},"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":349,"losses":124,"wins":7},"GB2-03":{"draws":172,"losses":264,"wins":58},"GB2-04":{"draws":301,"losses":159,"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":2088.542336522211,"GB2-03":1342.9761974732482,"GB2-04":1420.9751902189812,"GB2-05":1805.930193663513,"GB2-06":1832.1151874902162,"GB2-07":1423.2829266700264,"GB2-08":1349.2193333193593},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2159.541449758341,"GB2-03":1377.3239915238432,"GB2-04":1527.5945001538819,"GB2-05":2088.5212892087325,"GB2-06":1977.6508525308602,"GB2-07":1847.755825364758,"GB2-08":1630.460039476635},"medium":{"GB2-01":2297.83138957205,"GB2-02":1447.118858812865,"GB2-03":1378.2267530540141,"GB2-04":1342.2620768268016,"GB2-05":1738.1731566383469,"GB2-06":1888.4856130160579,"GB2-07":1244.733585803933,"GB2-08":1259.268822144077},"none":{"GB2-01":1808.2541702362414,"GB2-02":1389.6744481272335,"GB2-03":1273.3778478418872,"GB2-04":1393.0689936762606,"GB2-05":1591.0961351434594,"GB2-06":1630.2090969237306,"GB2-07":1177.359368841388,"GB2-08":1157.929138337366}},"per_game_tracks":{"highest":{"GB2-01":95.24631432919804,"GB2-03":44.22701691364703,"GB2-04":56.69724994545443,"GB2-05":85.86183696737152,"GB2-06":81.63911217049767,"GB2-07":77.7217719313222,"GB2-08":66.88293970108037},"medium":{"GB2-01":97.50040588860446,"GB2-02":46.81368819709062,"GB2-03":44.33108968183731,"GB2-04":33.187510514814925,"GB2-05":71.4841167856698,"GB2-06":77.18540045807114,"GB2-07":33.881725359608645,"GB2-08":38.25950643739559},"none":{"GB2-01":80.65434866807438,"GB2-02":39.41590335477645,"GB2-03":32.49383966343138,"GB2-04":39.44947595905667,"GB2-05":61.9150209611777,"GB2-06":63.02650853175248,"GB2-07":28.874188292553626,"GB2-08":28.86042658801284}},"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":-1,"rank_movement_baseline_at":"2026-10-24T19:04:27Z","reasoning":{"highest":63.534530244821404,"medium":55.33043041538656,"none":46.83621400235444},"reasoning_agg":{"highest":{"max":95.24631432919804,"mean":63.534530244821404,"min":0.0},"medium":{"max":97.50040588860446,"mean":55.33043041538656,"min":33.187510514814925},"none":{"max":80.65434866807438,"mean":46.83621400235444,"min":28.86042658801284}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.698316242466966},"working_program_strength":{"all":58.25917870870277,"highest":72.61089170836732,"medium":55.33043041538656,"none":46.83621400235444}},{"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":3.4542268568195333},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.4542268568195333}},"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":54.573052824399376,"highest":68.68946946146029,"medium":43.827347139161155,"none":51.202341872576675},"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":49.43483652738795,"score":49.43483652738795},"GB2-02":{"attempts":3,"playable":48.87117735906679,"score":48.87117735906679},"GB2-03":{"attempts":3,"playable":58.56663015581648,"score":58.56663015581648},"GB2-04":{"attempts":3,"playable":43.802824876162724,"score":43.802824876162724},"GB2-05":{"attempts":3,"playable":51.67542135380611,"score":51.67542135380611},"GB2-06":{"attempts":3,"playable":63.21345403070339,"score":63.21345403070339},"GB2-07":{"attempts":3,"playable":48.595474022350686,"score":48.595474022350686},"GB2-08":{"attempts":3,"playable":72.42460426990085,"score":72.42460426990085}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":58.641928528358974,"score":58.641928528358974},"GB2-02":{"attempts":1,"playable":53.62708451092556,"score":53.62708451092556},"GB2-03":{"attempts":1,"playable":82.09279624646348,"score":82.09279624646348},"GB2-04":{"attempts":1,"playable":46.490509638186836,"score":46.490509638186836},"GB2-05":{"attempts":1,"playable":69.0618156800023,"score":69.0618156800023},"GB2-06":{"attempts":1,"playable":80.00313072146281,"score":80.00313072146281},"GB2-07":{"attempts":1,"playable":69.5471049404985,"score":69.5471049404985},"GB2-08":{"attempts":1,"playable":90.05138542578382,"score":90.05138542578382}},"medium":{"GB2-01":{"attempts":1,"playable":53.189341463485576,"score":53.189341463485576},"GB2-02":{"attempts":1,"playable":43.65023818652617,"score":43.65023818652617},"GB2-03":{"attempts":1,"playable":43.39336960174158,"score":43.39336960174158},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":50.48751301185782,"score":50.48751301185782},"GB2-06":{"attempts":1,"playable":46.426033908503975,"score":46.426033908503975},"GB2-07":{"attempts":1,"playable":32.155628167045116,"score":32.155628167045116},"GB2-08":{"attempts":1,"playable":42.58410870481845,"score":42.58410870481845}},"none":{"GB2-01":{"attempts":1,"playable":36.473239590319295,"score":36.473239590319295},"GB2-02":{"attempts":1,"playable":49.33620937974867,"score":49.33620937974867},"GB2-03":{"attempts":1,"playable":50.213724619244374,"score":50.213724619244374},"GB2-04":{"attempts":1,"playable":46.18542092099077,"score":46.18542092099077},"GB2-05":{"attempts":1,"playable":35.476935369558205,"score":35.476935369558205},"GB2-06":{"attempts":1,"playable":63.21119746214339,"score":63.21119746214339},"GB2-07":{"attempts":1,"playable":44.08368895950843,"score":44.08368895950843},"GB2-08":{"attempts":1,"playable":84.6383186791003,"score":84.6383186791003}}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:09Z","match_totals_all":{"draws":3053,"losses":4305,"wins":4906},"match_totals_tracks":{"highest":{"draws":840,"losses":923,"wins":2325},"medium":{"draws":1225,"losses":1791,"wins":1072},"none":{"draws":988,"losses":1591,"wins":1509}},"model_slug":"qwen-qwen3-8-2-4t-a95b","official_rank_by_reasoning":{"highest":19,"medium":49,"none":20},"overall":{"max":90.05138542578382,"mean":54.573052824399376,"min":32.155628167045116},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.641928528358974,"GB2-02":53.62708451092556,"GB2-03":82.09279624646348,"GB2-04":46.490509638186836,"GB2-05":69.0618156800023,"GB2-06":80.00313072146281,"GB2-07":69.5471049404985,"GB2-08":90.05138542578382},"per_game_all":{"GB2-01":49.43483652738795,"GB2-02":48.87117735906679,"GB2-03":58.56663015581648,"GB2-04":43.802824876162724,"GB2-05":51.67542135380611,"GB2-06":63.21345403070339,"GB2-07":48.595474022350686,"GB2-08":72.42460426990085},"per_game_match_totals_all":{"GB2-01":{"draws":599,"losses":515,"wins":434},"GB2-02":{"draws":1054,"losses":234,"wins":152},"GB2-03":{"draws":227,"losses":551,"wins":704},"GB2-04":{"draws":943,"losses":393,"wins":158},"GB2-05":{"draws":0,"losses":793,"wins":797},"GB2-06":{"draws":105,"losses":553,"wins":848},"GB2-07":{"draws":0,"losses":852,"wins":738},"GB2-08":{"draws":125,"losses":414,"wins":1075}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":151,"losses":149,"wins":216},"GB2-02":{"draws":334,"losses":64,"wins":82},"GB2-03":{"draws":13,"losses":94,"wins":387},"GB2-04":{"draws":300,"losses":125,"wins":73},"GB2-05":{"draws":0,"losses":173,"wins":357},"GB2-06":{"draws":42,"losses":90,"wins":370},"GB2-07":{"draws":0,"losses":169,"wins":361},"GB2-08":{"draws":0,"losses":59,"wins":479}},"medium":{"GB2-01":{"draws":261,"losses":122,"wins":133},"GB2-02":{"draws":359,"losses":99,"wins":22},"GB2-03":{"draws":159,"losses":219,"wins":116},"GB2-04":{"draws":290,"losses":168,"wins":40},"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":125,"losses":263,"wins":150}},"none":{"GB2-01":{"draws":187,"losses":244,"wins":85},"GB2-02":{"draws":361,"losses":71,"wins":48},"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":32,"losses":187,"wins":283},"GB2-07":{"draws":0,"losses":310,"wins":220},"GB2-08":{"draws":0,"losses":92,"wins":446}}},"per_game_raw_elo_all":{"GB2-01":1463.5433808716741,"GB2-02":1463.093195963801,"GB2-03":1534.4006844612175,"GB2-04":1426.9093134477746,"GB2-05":1464.1117147183402,"GB2-06":1647.427736984674,"GB2-07":1435.498764505897,"GB2-08":1823.8687909830776},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1552.4772204097799,"GB2-02":1499.9924368060479,"GB2-03":1803.5698349406316,"GB2-04":1447.845104509816,"GB2-05":1697.3807723643008,"GB2-06":1944.2277714515794,"GB2-07":1710.6717704030666,"GB2-08":2160.427602686852},"medium":{"GB2-01":1499.5125672257302,"GB2-02":1422.7063547595108,"GB2-03":1370.0921697841738,"GB2-04":1387.3919879141274,"GB2-05":1443.4625680267284,"GB2-06":1364.6889831740202,"GB2-07":1221.9652252478904,"GB2-08":1306.0165647195483},"none":{"GB2-01":1338.6403549795118,"GB2-02":1466.5807963258444,"GB2-03":1429.5400486588471,"GB2-04":1445.4908479193803,"GB2-05":1251.4918037639904,"GB2-06":1633.3664563284226,"GB2-07":1373.8592978667336,"GB2-08":2005.162205542832}},"per_game_tracks":{"highest":{"GB2-01":58.641928528358974,"GB2-02":53.62708451092556,"GB2-03":82.09279624646348,"GB2-04":46.490509638186836,"GB2-05":69.0618156800023,"GB2-06":80.00313072146281,"GB2-07":69.5471049404985,"GB2-08":90.05138542578382},"medium":{"GB2-01":53.189341463485576,"GB2-02":43.65023818652617,"GB2-03":43.39336960174158,"GB2-04":38.73254406931057,"GB2-05":50.48751301185782,"GB2-06":46.426033908503975,"GB2-07":32.155628167045116,"GB2-08":42.58410870481845},"none":{"GB2-01":36.473239590319295,"GB2-02":49.33620937974867,"GB2-03":50.213724619244374,"GB2-04":46.18542092099077,"GB2-05":35.476935369558205,"GB2-06":63.21119746214339,"GB2-07":44.08368895950843,"GB2-08":84.6383186791003}},"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":"2026-10-24T19:05:18Z","reasoning":{"highest":68.68946946146029,"medium":43.827347139161155,"none":51.202341872576675},"reasoning_agg":{"highest":{"max":90.05138542578382,"mean":68.68946946146029,"min":46.490509638186836},"medium":{"max":53.189341463485576,"mean":43.827347139161155,"min":32.155628167045116},"none":{"max":84.6383186791003,"mean":51.202341872576675,"min":35.476935369558205}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.862122322299136},"working_program_strength":{"all":54.573052824399376,"highest":68.68946946146029,"medium":43.827347139161155,"none":51.202341872576675}},{"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":0.028788054}},"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":0.21121389}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.3927312839999999},"codegen_latency_ms":{"attempt_count":26,"max_ms":176041,"mean_ms":89449.0,"min_ms":6041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":176041,"mean_ms":153558.625,"min_ms":128316,"run_count":8},"medium":{"attempt_count":9,"max_ms":152315,"mean_ms":102702.875,"min_ms":61501,"run_count":8},"none":{"attempt_count":9,"max_ms":25470,"mean_ms":12085.5,"min_ms":6041,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":50785,"output_mean":25087.541666666668,"output_min":1796,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50785,"output_mean":42017.75,"output_min":28632,"run_count":8},"medium":{"attempt_count":9,"output_max":44567,"output_mean":29519.625,"output_min":16614,"run_count":8},"none":{"attempt_count":9,"output_max":8282,"output_mean":3725.25,"output_min":1796,"run_count":8}},"display_name":"DeepSeek V4.1 Flash","economics":{"all":53.71272226575852,"highest":69.02452864844383,"medium":55.58022173760598,"none":36.533416411225765},"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":59.148438368069236,"score":59.148438368069236},"GB2-02":{"attempts":3,"playable":52.51122611991057,"score":52.51122611991057},"GB2-03":{"attempts":3,"playable":54.54687443341282,"score":54.54687443341282},"GB2-04":{"attempts":3,"playable":50.87516661732659,"score":50.87516661732659},"GB2-05":{"attempts":3,"playable":55.58974300772159,"score":55.58974300772159},"GB2-06":{"attempts":3,"playable":62.60778903581805,"score":62.60778903581805},"GB2-07":{"attempts":3,"playable":56.976717857389524,"score":56.976717857389524},"GB2-08":{"attempts":3,"playable":37.44582268641985,"score":37.44582268641985}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.486591391141424,"score":63.486591391141424},"GB2-02":{"attempts":1,"playable":57.4774541619302,"score":57.4774541619302},"GB2-03":{"attempts":1,"playable":59.99259918658731,"score":59.99259918658731},"GB2-04":{"attempts":1,"playable":75.16041171335864,"score":75.16041171335864},"GB2-05":{"attempts":1,"playable":82.56812866647837,"score":82.56812866647837},"GB2-06":{"attempts":1,"playable":82.27520760420894,"score":82.27520760420894},"GB2-07":{"attempts":1,"playable":75.81900444019345,"score":75.81900444019345},"GB2-08":{"attempts":1,"playable":55.41683202365234,"score":55.41683202365234}},"medium":{"GB2-01":{"attempts":1,"playable":68.11346235814054,"score":68.11346235814054},"GB2-02":{"attempts":1,"playable":58.20338066890267,"score":58.20338066890267},"GB2-03":{"attempts":1,"playable":55.09029052603635,"score":55.09029052603635},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":53.930599354883036,"score":53.930599354883036},"GB2-06":{"attempts":1,"playable":76.73092068582082,"score":76.73092068582082},"GB2-07":{"attempts":1,"playable":69.5471049404985,"score":69.5471049404985},"GB2-08":{"attempts":1,"playable":24.29347129725537,"score":24.29347129725537}},"none":{"GB2-01":{"attempts":1,"playable":45.84526135492576,"score":45.84526135492576},"GB2-02":{"attempts":1,"playable":41.852843528898845,"score":41.852843528898845},"GB2-03":{"attempts":1,"playable":48.557733587614784,"score":48.557733587614784},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":30.270501001803357,"score":30.270501001803357},"GB2-06":{"attempts":1,"playable":28.81723881742438,"score":28.81723881742438},"GB2-07":{"attempts":1,"playable":25.564044191476587,"score":25.564044191476587},"GB2-08":{"attempts":1,"playable":32.62716473835184,"score":32.62716473835184}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:43Z","match_totals_all":{"draws":3175,"losses":4369,"wins":4719},"match_totals_tracks":{"highest":{"draws":757,"losses":971,"wins":2360},"medium":{"draws":1194,"losses":1311,"wins":1583},"none":{"draws":1224,"losses":2087,"wins":776}},"model_slug":"deepseek-deepseek-v4-1-flash","official_rank_by_reasoning":{"highest":18,"medium":26,"none":50},"overall":{"max":82.56812866647837,"mean":53.71272226575852,"min":24.29347129725537},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.486591391141424,"GB2-02":57.4774541619302,"GB2-03":59.99259918658731,"GB2-04":75.16041171335864,"GB2-05":82.56812866647837,"GB2-06":82.27520760420894,"GB2-07":75.81900444019345,"GB2-08":55.41683202365234},"per_game_all":{"GB2-01":59.148438368069236,"GB2-02":52.51122611991057,"GB2-03":54.54687443341282,"GB2-04":50.87516661732659,"GB2-05":55.58974300772159,"GB2-06":62.60778903581805,"GB2-07":56.976717857389524,"GB2-08":37.44582268641985},"per_game_match_totals_all":{"GB2-01":{"draws":472,"losses":429,"wins":647},"GB2-02":{"draws":987,"losses":215,"wins":238},"GB2-03":{"draws":317,"losses":573,"wins":591},"GB2-04":{"draws":730,"losses":392,"wins":372},"GB2-05":{"draws":0,"losses":728,"wins":862},"GB2-06":{"draws":79,"losses":565,"wins":862},"GB2-07":{"draws":0,"losses":709,"wins":881},"GB2-08":{"draws":590,"losses":758,"wins":266}},"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":189,"wins":249},"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":198,"losses":160,"wins":180}},"medium":{"GB2-01":{"draws":289,"losses":31,"wins":196},"GB2-02":{"draws":312,"losses":53,"wins":115},"GB2-03":{"draws":147,"losses":168,"wins":179},"GB2-04":{"draws":260,"losses":183,"wins":55},"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":160,"losses":338,"wins":40}},"none":{"GB2-01":{"draws":162,"losses":209,"wins":145},"GB2-02":{"draws":382,"losses":96,"wins":2},"GB2-03":{"draws":114,"losses":216,"wins":163},"GB2-04":{"draws":316,"losses":155,"wins":27},"GB2-05":{"draws":0,"losses":376,"wins":154},"GB2-06":{"draws":18,"losses":368,"wins":116},"GB2-07":{"draws":0,"losses":407,"wins":123},"GB2-08":{"draws":232,"losses":260,"wins":46}}},"per_game_raw_elo_all":{"GB2-01":1560.457161195135,"GB2-02":1492.0024804872446,"GB2-03":1469.1940500975923,"GB2-04":1490.4679839108874,"GB2-05":1549.5924795030512,"GB2-06":1656.5711923973201,"GB2-07":1551.2172370992528,"GB2-08":1254.3114097491168},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1601.318861867325,"GB2-02":1530.6765499992507,"GB2-03":1519.3343786965465,"GB2-04":1696.6199759044068,"GB2-05":1984.6122670610062,"GB2-06":1990.9147978757085,"GB2-07":1812.9554108331154,"GB2-08":1458.0620274002204},"medium":{"GB2-01":1650.5071520267834,"GB2-02":1536.571227560628,"GB2-03":1473.248229815147,"GB2-04":1387.3919879141274,"GB2-05":1486.5246097693077,"GB2-06":1879.667956933521,"GB2-07":1710.6717704030666,"GB2-08":1105.8906974521633},"none":{"GB2-01":1429.5454696912966,"GB2-02":1408.7596639018554,"GB2-03":1414.9995417810833,"GB2-04":1387.3919879141274,"GB2-05":1177.6405616788397,"GB2-06":1099.1308223827314,"GB2-07":1130.0245300615766,"GB2-08":1198.9815043949666}},"per_game_tracks":{"highest":{"GB2-01":63.486591391141424,"GB2-02":57.4774541619302,"GB2-03":59.99259918658731,"GB2-04":75.16041171335864,"GB2-05":82.56812866647837,"GB2-06":82.27520760420894,"GB2-07":75.81900444019345,"GB2-08":55.41683202365234},"medium":{"GB2-01":68.11346235814054,"GB2-02":58.20338066890267,"GB2-03":55.09029052603635,"GB2-04":38.73254406931057,"GB2-05":53.930599354883036,"GB2-06":76.73092068582082,"GB2-07":69.5471049404985,"GB2-08":24.29347129725537},"none":{"GB2-01":45.84526135492576,"GB2-02":41.852843528898845,"GB2-03":48.557733587614784,"GB2-04":38.73254406931057,"GB2-05":30.270501001803357,"GB2-06":28.81723881742438,"GB2-07":25.564044191476587,"GB2-08":32.62716473835184}},"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":0,"rank_movement_baseline_at":"2026-10-24T19:20:59Z","reasoning":{"highest":69.02452864844383,"medium":55.58022173760598,"none":36.533416411225765},"reasoning_agg":{"highest":{"max":82.56812866647837,"mean":69.02452864844383,"min":55.41683202365234},"medium":{"max":76.73092068582082,"mean":55.58022173760598,"min":24.29347129725537},"none":{"max":48.557733587614784,"mean":36.533416411225765,"min":25.564044191476587}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":32.49111223721807},"working_program_strength":{"all":53.71272226575852,"highest":69.02452864844383,"medium":55.58022173760598,"none":36.533416411225765}},{"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":0.37616799999999995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.7147189999999999},"codegen_latency_ms":{"attempt_count":27,"max_ms":194716,"mean_ms":65710.04166666667,"min_ms":14709,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":194716,"mean_ms":132597.5,"min_ms":94687,"run_count":8},"medium":{"attempt_count":9,"max_ms":66794,"mean_ms":45688.625,"min_ms":28293,"run_count":8},"none":{"attempt_count":9,"max_ms":26924,"mean_ms":18844.0,"min_ms":14709,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":46299,"output_mean":14240.0,"output_min":2554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":46299,"output_mean":31097.375,"output_min":22420,"run_count":8},"medium":{"attempt_count":9,"output_max":11293,"output_mean":8521.75,"output_min":5500,"run_count":8},"none":{"attempt_count":9,"output_max":3991,"output_mean":3100.875,"output_min":2554,"run_count":8}},"display_name":"Muse Spark 1.2","economics":{"all":53.66606728971573,"highest":59.674538064803045,"medium":59.33488623832671,"none":41.98877756601745},"first_seen_at":null,"game_gaps":{"medium":{"GB2-06":"too_slow"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":87,"requested_max_output_token_observations":9,"requested_max_output_tokens":[943718],"total_output_tokens":341760,"total_reasoning_output_tokens":238816,"total_visible_output_tokens":102944,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":67.88527572944297,"score":67.88527572944297},"GB2-02":{"attempts":3,"playable":45.72116971349883,"score":45.72116971349883},"GB2-03":{"attempts":3,"playable":53.21313346646502,"score":53.21313346646502},"GB2-04":{"attempts":3,"playable":47.74243731992615,"score":47.74243731992615},"GB2-05":{"attempts":3,"playable":54.361891615453,"score":54.361891615453},"GB2-06":{"attempts":2,"playable":23.408619728961654,"score":23.408619728961654},"GB2-07":{"attempts":3,"playable":57.89475401346008,"score":57.89475401346008},"GB2-08":{"attempts":3,"playable":67.12583456072983,"score":67.12583456072983}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.5608541872989,"score":80.5608541872989},"GB2-02":{"attempts":1,"playable":48.39115651225852,"score":48.39115651225852},"GB2-03":{"attempts":1,"playable":61.08221142804463,"score":61.08221142804463},"GB2-04":{"attempts":1,"playable":49.535698213129706,"score":49.535698213129706},"GB2-05":{"attempts":1,"playable":61.53661978064131,"score":61.53661978064131},"GB2-06":{"attempts":1,"playable":27.07629811042509,"score":27.07629811042509},"GB2-07":{"attempts":1,"playable":74.77864378963382,"score":74.77864378963382},"GB2-08":{"attempts":1,"playable":74.43482249699235,"score":74.43482249699235}},"medium":{"GB2-01":{"attempts":1,"playable":85.82938002593471,"score":85.82938002593471},"GB2-02":{"attempts":1,"playable":46.81368819709062,"score":46.81368819709062},"GB2-03":{"attempts":1,"playable":52.25436624935729,"score":52.25436624935729},"GB2-04":{"attempts":1,"playable":45.880231916103,"score":45.880231916103},"GB2-05":{"attempts":1,"playable":49.912626901458104,"score":49.912626901458104},"GB2-07":{"attempts":1,"playable":64.25915621579892,"score":64.25915621579892},"GB2-08":{"attempts":1,"playable":70.3947541625443,"score":70.3947541625443}},"none":{"GB2-01":{"attempts":1,"playable":37.2655929750953,"score":37.2655929750953},"GB2-02":{"attempts":1,"playable":41.95866443114737,"score":41.95866443114737},"GB2-03":{"attempts":1,"playable":46.30282272199312,"score":46.30282272199312},"GB2-04":{"attempts":1,"playable":47.81138183054571,"score":47.81138183054571},"GB2-05":{"attempts":1,"playable":51.63642816425957,"score":51.63642816425957},"GB2-06":{"attempts":1,"playable":19.740941347498214,"score":19.740941347498214},"GB2-07":{"attempts":1,"playable":34.646462034947504,"score":34.646462034947504},"GB2-08":{"attempts":1,"playable":56.54792702265282,"score":56.54792702265282}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:49Z","match_totals_all":{"draws":2409,"losses":4520,"wins":4833},"match_totals_tracks":{"highest":{"draws":689,"losses":1383,"wins":2016},"medium":{"draws":780,"losses":1138,"wins":1668},"none":{"draws":940,"losses":1999,"wins":1149}},"model_slug":"meta-muse-spark-1-2","official_rank_by_reasoning":{"highest":33,"medium":23,"none":36},"overall":{"max":85.82938002593471,"mean":53.66606728971573,"min":19.740941347498214},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.5608541872989,"GB2-02":48.39115651225852,"GB2-03":61.08221142804463,"GB2-04":49.535698213129706,"GB2-05":61.53661978064131,"GB2-06":27.07629811042509,"GB2-07":74.77864378963382,"GB2-08":74.43482249699235},"per_game_all":{"GB2-01":67.88527572944297,"GB2-02":45.72116971349883,"GB2-03":53.21313346646502,"GB2-04":47.74243731992615,"GB2-05":54.361891615453,"GB2-07":57.89475401346008,"GB2-08":67.12583456072983},"per_game_match_totals_all":{"GB2-01":{"draws":192,"losses":429,"wins":927},"GB2-02":{"draws":1076,"losses":268,"wins":96},"GB2-03":{"draws":193,"losses":655,"wins":634},"GB2-04":{"draws":893,"losses":360,"wins":241},"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":566,"wins":1015}},"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":361,"losses":83,"wins":36},"GB2-03":{"draws":105,"losses":203,"wins":186},"GB2-04":{"draws":270,"losses":143,"wins":85},"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":69,"losses":250,"wins":175},"GB2-04":{"draws":353,"losses":92,"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":252,"wins":284}}},"per_game_raw_elo_all":{"GB2-01":1682.62003498139,"GB2-02":1438.6614763134892,"GB2-03":1457.657160363516,"GB2-04":1457.510879460482,"GB2-05":1493.3264002310814,"GB2-07":1561.1323506102588,"GB2-08":1646.4542876875457},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1806.8616430198902,"GB2-02":1459.282287839564,"GB2-03":1529.9894917582742,"GB2-04":1471.3599457831835,"GB2-05":1585.892242767181,"GB2-06":1072.6176491805222,"GB2-07":1794.8147015710883,"GB2-08":1772.6782075798524},"medium":{"GB2-01":1894.4700021985323,"GB2-02":1447.118858812865,"GB2-03":1447.6390746055445,"GB2-04":1443.1353934237127,"GB2-05":1436.3156100355102,"GB2-07":1633.8849204486182,"GB2-08":1693.5757179418601},"none":{"GB2-01":1346.5284597257478,"GB2-02":1409.5832822880382,"GB2-03":1395.3429147267298,"GB2-04":1458.0372991745503,"GB2-05":1457.771347890552,"GB2-06":956.6172901516067,"GB2-07":1254.6974298110697,"GB2-08":1473.1089375409242}},"per_game_tracks":{"highest":{"GB2-01":80.5608541872989,"GB2-02":48.39115651225852,"GB2-03":61.08221142804463,"GB2-04":49.535698213129706,"GB2-05":61.53661978064131,"GB2-06":27.07629811042509,"GB2-07":74.77864378963382,"GB2-08":74.43482249699235},"medium":{"GB2-01":85.82938002593471,"GB2-02":46.81368819709062,"GB2-03":52.25436624935729,"GB2-04":45.880231916103,"GB2-05":49.912626901458104,"GB2-07":64.25915621579892,"GB2-08":70.3947541625443},"none":{"GB2-01":37.2655929750953,"GB2-02":41.95866443114737,"GB2-03":46.30282272199312,"GB2-04":47.81138183054571,"GB2-05":51.63642816425957,"GB2-06":19.740941347498214,"GB2-07":34.646462034947504,"GB2-08":56.54792702265282}},"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":"2026-10-24T18:36:08Z","reasoning":{"highest":59.674538064803045,"medium":59.33488623832671,"none":41.98877756601745},"reasoning_agg":{"highest":{"max":80.5608541872989,"mean":59.674538064803045,"min":27.07629811042509},"medium":{"max":85.82938002593471,"mean":59.33488623832671,"min":45.880231916103},"none":{"max":56.54792702265282,"mean":41.98877756601745,"min":19.740941347498214}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.685760498785598},"working_program_strength":{"all":53.66606728971573,"highest":59.674538064803045,"medium":59.33488623832671,"none":41.98877756601745}},{"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":0.9693815250000001},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"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":1.086615744},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.1835153939999996},"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":53.26183710226135,"highest":64.4909676291399,"medium":51.06366821708653,"none":44.23087546055762},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":131,"total_output_tokens":812278,"total_reasoning_output_tokens":673611,"total_visible_output_tokens":138667,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":51.45796696411949,"score":51.45796696411949},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":60.97197592066588,"score":40.64798394711058},"GB2-03":{"attempts":3,"playable":59.04453884432379,"score":59.04453884432379},"GB2-04":{"attempts":3,"playable":44.446796643258416,"score":44.446796643258416},"GB2-05":{"attempts":3,"playable":57.75235880154906,"score":57.75235880154906},"GB2-06":{"attempts":3,"playable":60.254600854956,"score":60.254600854956},"GB2-07":{"attempts":3,"playable":60.895110102345484,"score":60.895110102345484},"GB2-08":{"attempts":3,"playable":51.595340660427986,"score":51.595340660427986}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.042337638007275,"score":55.042337638007275},"GB2-02":{"attempts":1,"playable":78.71632855665378,"score":78.71632855665378},"GB2-03":{"attempts":1,"playable":72.4992470077333,"score":72.4992470077333},"GB2-04":{"attempts":1,"playable":56.39605880742696,"score":56.39605880742696},"GB2-05":{"attempts":1,"playable":70.36785336156095,"score":70.36785336156095},"GB2-06":{"attempts":1,"playable":81.00293289509779,"score":81.00293289509779},"GB2-07":{"attempts":1,"playable":67.79115840389798,"score":67.79115840389798},"GB2-08":{"attempts":1,"playable":34.11182436274114,"score":34.11182436274114}},"medium":{"GB2-01":{"attempts":1,"playable":52.79884906579119,"score":52.79884906579119},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":41.09112538431462,"score":41.09112538431462},"GB2-04":{"attempts":1,"playable":35.34683349909481,"score":35.34683349909481},"GB2-05":{"attempts":1,"playable":52.40171003122839,"score":52.40171003122839},"GB2-06":{"attempts":1,"playable":60.43168330617621,"score":60.43168330617621},"GB2-07":{"attempts":1,"playable":77.20339463461717,"score":77.20339463461717},"GB2-08":{"attempts":1,"playable":89.23574981546986,"score":89.23574981546986}},"none":{"GB2-01":{"attempts":1,"playable":46.53271418856003,"score":46.53271418856003},"GB2-02":{"attempts":1,"playable":43.227623284677975,"score":43.227623284677975},"GB2-03":{"attempts":1,"playable":63.54324414092344,"score":63.54324414092344},"GB2-04":{"attempts":1,"playable":41.597497623253474,"score":41.597497623253474},"GB2-05":{"attempts":1,"playable":50.48751301185782,"score":50.48751301185782},"GB2-06":{"attempts":1,"playable":39.329186363594,"score":39.329186363594},"GB2-07":{"attempts":1,"playable":37.69077726852129,"score":37.69077726852129},"GB2-08":{"attempts":1,"playable":31.43844780307297,"score":31.43844780307297}}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:44Z","match_totals_all":{"draws":2640,"losses":4179,"wins":4965},"match_totals_tracks":{"highest":{"draws":973,"losses":1062,"wins":2053},"medium":{"draws":573,"losses":1275,"wins":1760},"none":{"draws":1094,"losses":1842,"wins":1152}},"model_slug":"tencent-hy4-preview","official_rank_by_reasoning":{"highest":27,"medium":35,"none":31},"overall":{"max":89.23574981546986,"mean":53.26183710226135,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.042337638007275,"GB2-02":78.71632855665378,"GB2-03":72.4992470077333,"GB2-04":56.39605880742696,"GB2-05":70.36785336156095,"GB2-06":81.00293289509779,"GB2-07":67.79115840389798,"GB2-08":34.11182436274114},"per_game_all":{"GB2-01":51.45796696411949,"GB2-03":59.04453884432379,"GB2-04":44.446796643258416,"GB2-05":57.75235880154906,"GB2-06":60.254600854956,"GB2-07":60.895110102345484,"GB2-08":51.595340660427986},"per_game_match_totals_all":{"GB2-01":{"draws":360,"losses":604,"wins":584},"GB2-02":{"draws":513,"losses":132,"wins":315},"GB2-03":{"draws":434,"losses":444,"wins":604},"GB2-04":{"draws":847,"losses":431,"wins":216},"GB2-05":{"draws":0,"losses":698,"wins":892},"GB2-06":{"draws":43,"losses":629,"wins":834},"GB2-07":{"draws":0,"losses":648,"wins":942},"GB2-08":{"draws":443,"losses":593,"wins":578}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":244,"losses":121,"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":271,"losses":233,"wins":34}},"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":12,"losses":212,"wins":278},"GB2-07":{"draws":0,"losses":125,"wins":405},"GB2-08":{"draws":0,"losses":64,"wins":474}},"none":{"GB2-01":{"draws":83,"losses":245,"wins":188},"GB2-02":{"draws":385,"losses":88,"wins":7},"GB2-03":{"draws":118,"losses":140,"wins":236},"GB2-04":{"draws":326,"losses":136,"wins":36},"GB2-05":{"draws":0,"losses":271,"wins":259},"GB2-06":{"draws":10,"losses":322,"wins":170},"GB2-07":{"draws":0,"losses":344,"wins":186},"GB2-08":{"draws":172,"losses":296,"wins":70}}},"per_game_raw_elo_all":{"GB2-01":1483.0683734208335,"GB2-03":1520.469321118769,"GB2-04":1431.7502214510375,"GB2-05":1543.260959824254,"GB2-06":1602.756638024173,"GB2-07":1605.416918630244,"GB2-08":1511.8130913931836},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1517.3453761866508,"GB2-02":1737.3184218103338,"GB2-03":1656.5677909318867,"GB2-04":1525.1806823678367,"GB2-05":1718.990103558363,"GB2-06":1964.5432725933783,"GB2-07":1684.4448970304045,"GB2-08":1214.9221491261173},"medium":{"GB2-01":1495.7704881783357,"GB2-03":1350.0854607728024,"GB2-04":1360.1378958335974,"GB2-05":1467.3302078876711,"GB2-06":1586.4312996293643,"GB2-07":1838.0466556649042,"GB2-08":2134.3752800362945},"none":{"GB2-01":1436.0892558975147,"GB2-02":1419.4344223818925,"GB2-03":1554.7547116516178,"GB2-04":1409.9320861516785,"GB2-05":1443.4625680267284,"GB2-06":1257.2953418497764,"GB2-07":1293.7592031954234,"GB2-08":1186.1418450171386}},"per_game_tracks":{"highest":{"GB2-01":55.042337638007275,"GB2-02":78.71632855665378,"GB2-03":72.4992470077333,"GB2-04":56.39605880742696,"GB2-05":70.36785336156095,"GB2-06":81.00293289509779,"GB2-07":67.79115840389798,"GB2-08":34.11182436274114},"medium":{"GB2-01":52.79884906579119,"GB2-03":41.09112538431462,"GB2-04":35.34683349909481,"GB2-05":52.40171003122839,"GB2-06":60.43168330617621,"GB2-07":77.20339463461717,"GB2-08":89.23574981546986},"none":{"GB2-01":46.53271418856003,"GB2-02":43.227623284677975,"GB2-03":63.54324414092344,"GB2-04":41.597497623253474,"GB2-05":50.48751301185782,"GB2-06":39.329186363594,"GB2-07":37.69077726852129,"GB2-08":31.43844780307297}},"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":"2026-10-24T19:06:54Z","reasoning":{"highest":64.4909676291399,"medium":51.06366821708654,"none":44.23087546055762},"reasoning_agg":{"highest":{"max":81.00293289509779,"mean":64.4909676291399,"min":34.11182436274114},"medium":{"max":89.23574981546986,"mean":51.06366821708654,"min":0.0},"none":{"max":63.54324414092344,"mean":44.23087546055762,"min":31.43844780307297}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":20.260092168582283},"working_program_strength":{"all":55.69344035069404,"highest":64.4909676291399,"medium":58.358477962384605,"none":44.23087546055762}},{"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":8.014536974999999},"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":8.014536974999999}},"codegen_cost_usd":{"admitted_cell_count":46,"cell_count":24,"cost_basis_counts":{"provider_reported":130},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.531673125,"mean":0.24710551171874998,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":130,"run_count":52,"total":13.077675974999998},"codegen_latency_ms":{"attempt_count":126,"max_ms":348942,"mean_ms":134334.75,"min_ms":17298,"run_count":52},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":348942,"mean_ms":213753.4,"min_ms":85578,"run_count":20},"medium":{"attempt_count":44,"max_ms":261708,"mean_ms":136549.0,"min_ms":44747,"run_count":16},"none":{"attempt_count":29,"max_ms":50160,"mean_ms":32847.1875,"min_ms":17298,"run_count":16}},"codegen_output_tokens":{"attempt_count":130,"output_max":100087,"output_mean":31640.134615384617,"output_min":2060,"run_count":52},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":57,"output_max":100087,"output_mean":54101.95,"output_min":17027,"run_count":20},"medium":{"attempt_count":44,"output_max":63652,"output_mean":30566.4375,"output_min":8874,"run_count":16},"none":{"attempt_count":29,"output_max":7962,"output_mean":4636.5625,"output_min":2060,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":52.48838164855539,"highest":64.58218353568154,"medium":52.45865827510061,"none":40.424303134884006},"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":53.22947120280666,"score":53.22947120280666},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":44.2674916189132,"score":38.01669357287391},"GB2-03":{"attempts":6,"playable":58.30222758111196,"score":58.30222758111196},"GB2-04":{"attempts":6,"playable":48.922383298974495,"score":48.922383298974495},"GB2-05":{"attempts":6,"playable":67.13980293728622,"score":67.13980293728622},"GB2-06":{"attempts":6,"playable":63.41658403111146,"score":63.41658403111146},"GB2-07":{"attempts":6,"playable":49.13477581545826,"score":49.13477581545826},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":53.62204145996665,"score":41.74511474882007}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":55.81610926740474,"score":55.81610926740474},"GB2-02":{"attempts":2,"playable":54.980534929468845,"score":54.980534929468845},"GB2-03":{"attempts":2,"playable":69.05690088333495,"score":69.05690088333495},"GB2-04":{"attempts":2,"playable":63.06826791424943,"score":63.06826791424943},"GB2-05":{"attempts":2,"playable":83.85508646801725,"score":83.85508646801725},"GB2-06":{"attempts":2,"playable":82.60903300478043,"score":82.60903300478043},"GB2-07":{"attempts":2,"playable":51.38166979730925,"score":51.38166979730925},"GB2-08":{"attempts":2,"playable":55.88986602088737,"score":55.88986602088737}},"medium":{"GB2-01":{"attempts":2,"playable":72.36687780212262,"score":72.36687780212262},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":37.504788276235715,"score":18.752394138117857},"GB2-03":{"attempts":2,"playable":49.340297921174475,"score":49.340297921174475},"GB2-04":{"attempts":2,"playable":41.33829786076156,"score":41.33829786076156},"GB2-05":{"attempts":2,"playable":69.95613195624621,"score":69.95613195624621},"GB2-06":{"attempts":2,"playable":83.77303910526301,"score":83.77303910526301},"GB2-07":{"attempts":2,"playable":48.51144728367936,"score":48.51144728367936},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":71.26156026687946,"score":35.63078013343973}},"none":{"GB2-01":{"attempts":2,"playable":31.505426538892607,"score":31.505426538892607},"GB2-02":{"attempts":2,"playable":40.31715165103505,"score":40.31715165103505},"GB2-03":{"attempts":2,"playable":56.50948393882645,"score":56.50948393882645},"GB2-04":{"attempts":2,"playable":42.36058412191249,"score":42.36058412191249},"GB2-05":{"attempts":2,"playable":47.6081903875952,"score":47.6081903875952},"GB2-06":{"attempts":2,"playable":23.867679983290934,"score":23.867679983290934},"GB2-07":{"attempts":2,"playable":47.51121036538618,"score":47.51121036538618},"GB2-08":{"attempts":2,"playable":33.714698092133126,"score":33.714698092133126}}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:27Z","match_totals_all":{"draws":5149,"losses":8559,"wins":9803},"match_totals_tracks":{"highest":{"draws":1492,"losses":2326,"wins":4359},"medium":{"draws":1392,"losses":2301,"wins":3465},"none":{"draws":2265,"losses":3932,"wins":1979}},"model_slug":"google-gemini-3-6-flash","official_rank_by_reasoning":{"highest":26,"medium":32,"none":44},"overall":{"max":83.85508646801725,"mean":52.48838164855539,"min":18.752394138117857},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.81610926740474,"GB2-02":54.980534929468845,"GB2-03":69.05690088333495,"GB2-04":63.06826791424943,"GB2-05":83.85508646801725,"GB2-06":82.60903300478043,"GB2-07":51.38166979730925,"GB2-08":55.88986602088737},"per_game_all":{"GB2-01":53.22947120280666,"GB2-02":44.2674916189132,"GB2-03":58.30222758111196,"GB2-04":48.922383298974495,"GB2-05":67.13980293728622,"GB2-06":63.41658403111146,"GB2-07":49.13477581545826,"GB2-08":53.62204145996665},"per_game_match_totals_all":{"GB2-01":{"draws":701,"losses":1152,"wins":1243},"GB2-02":{"draws":1641,"losses":524,"wins":235},"GB2-03":{"draws":306,"losses":1193,"wins":1466},"GB2-04":{"draws":1773,"losses":689,"wins":526},"GB2-05":{"draws":0,"losses":1083,"wins":2097},"GB2-06":{"draws":137,"losses":1103,"wins":1772},"GB2-07":{"draws":0,"losses":1693,"wins":1487},"GB2-08":{"draws":591,"losses":1122,"wins":977}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":248,"losses":353,"wins":431},"GB2-02":{"draws":575,"losses":161,"wins":224},"GB2-03":{"draws":52,"losses":316,"wins":621},"GB2-04":{"draws":469,"losses":150,"wins":377},"GB2-05":{"draws":0,"losses":181,"wins":879},"GB2-06":{"draws":14,"losses":186,"wins":804},"GB2-07":{"draws":0,"losses":541,"wins":519},"GB2-08":{"draws":134,"losses":438,"wins":504}},"medium":{"GB2-01":{"draws":269,"losses":166,"wins":597},"GB2-02":{"draws":335,"losses":140,"wins":5},"GB2-03":{"draws":79,"losses":496,"wins":413},"GB2-04":{"draws":615,"losses":293,"wins":88},"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":47,"losses":148,"wins":343}},"none":{"GB2-01":{"draws":184,"losses":633,"wins":215},"GB2-02":{"draws":731,"losses":223,"wins":6},"GB2-03":{"draws":175,"losses":381,"wins":432},"GB2-04":{"draws":689,"losses":246,"wins":61},"GB2-05":{"draws":0,"losses":572,"wins":488},"GB2-06":{"draws":76,"losses":760,"wins":168},"GB2-07":{"draws":0,"losses":581,"wins":479},"GB2-08":{"draws":410,"losses":536,"wins":130}}},"per_game_raw_elo_all":{"GB2-01":1534.2236303564905,"GB2-02":1428.0098900410478,"GB2-03":1510.1167023541793,"GB2-04":1469.5774434938064,"GB2-05":1768.488553379512,"GB2-06":1687.03847919864,"GB2-07":1437.5316405313017,"GB2-08":1477.4921980903728},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1530.8140487751652,"GB2-02":1512.7670033843572,"GB2-03":1614.8330048468683,"GB2-04":1585.185776321929,"GB2-05":2066.871627391639,"GB2-06":2019.4162510848982,"GB2-07":1464.8412380000818,"GB2-08":1511.9118998087147},"medium":{"GB2-01":1784.4091724954735,"GB2-02":1374.5023359792667,"GB2-03":1427.9226976800198,"GB2-04":1407.760361607136,"GB2-05":1830.9621717712819,"GB2-06":2023.6631785977252,"GB2-07":1430.0596669591555,"GB2-08":1709.964696009407},"none":{"GB2-01":1287.447669798833,"GB2-02":1396.7603307595195,"GB2-03":1487.59440453565,"GB2-04":1415.786192552354,"GB2-05":1407.6318609756156,"GB2-06":1018.0360079132971,"GB2-07":1417.6940166346683,"GB2-08":1210.5999984529972}},"per_game_tracks":{"highest":{"GB2-01":55.81610926740474,"GB2-02":54.980534929468845,"GB2-03":69.05690088333495,"GB2-04":63.06826791424943,"GB2-05":83.85508646801725,"GB2-06":82.60903300478043,"GB2-07":51.38166979730925,"GB2-08":55.88986602088737},"medium":{"GB2-01":72.36687780212262,"GB2-02":37.504788276235715,"GB2-03":49.340297921174475,"GB2-04":41.33829786076156,"GB2-05":69.95613195624621,"GB2-06":83.77303910526301,"GB2-07":48.51144728367936,"GB2-08":71.26156026687946},"none":{"GB2-01":31.505426538892607,"GB2-02":40.31715165103505,"GB2-03":56.50948393882645,"GB2-04":42.36058412191249,"GB2-05":47.6081903875952,"GB2-06":23.867679983290934,"GB2-07":47.51121036538618,"GB2-08":33.714698092133126}},"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":0,"rank_movement_baseline_at":"2026-10-24T19:15:38Z","reasoning":{"highest":64.58218353568154,"medium":52.45865827510061,"none":40.424303134884006},"reasoning_agg":{"highest":{"max":83.85508646801725,"mean":64.58218353568154,"min":51.38166979730925},"medium":{"max":83.77303910526301,"mean":52.45865827510061,"min":18.752394138117857},"none":{"max":56.50948393882645,"mean":40.424303134884006,"min":23.867679983290934}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":24.15788040079753},"working_program_strength":{"all":54.75434724320362,"highest":64.58218353568154,"medium":59.2565550590453,"none":40.424303134884006}},{"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":0.582672}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399970000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.582672},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816},"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":52.388726378033454,"highest":65.0853117856486,"medium":54.68341219816406,"none":37.39745515028769},"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":59.68780144994155,"score":59.68780144994155},"GB2-02":{"attempts":3,"playable":44.388756334693575,"score":44.388756334693575},"GB2-03":{"attempts":3,"playable":60.03308572453606,"score":60.03308572453606},"GB2-04":{"attempts":3,"playable":45.11562851619331,"score":45.11562851619331},"GB2-05":{"attempts":3,"playable":44.21785279783825,"score":44.21785279783825},"GB2-06":{"attempts":3,"playable":52.35744341819355,"score":52.35744341819355},"GB2-07":{"attempts":3,"playable":59.00334571957314,"score":59.00334571957314},"GB2-08":{"attempts":3,"playable":54.30589706329817,"score":54.30589706329817}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.08130575673387,"score":77.08130575673387},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":81.1918431229029,"score":81.1918431229029},"GB2-04":{"attempts":1,"playable":41.08644928581932,"score":41.08644928581932},"GB2-05":{"attempts":1,"playable":63.237816289157955,"score":63.237816289157955},"GB2-06":{"attempts":1,"playable":51.75602740212671,"score":51.75602740212671},"GB2-07":{"attempts":1,"playable":75.81900444019345,"score":75.81900444019345},"GB2-08":{"attempts":1,"playable":87.59950869232675,"score":87.59950869232675}},"medium":{"GB2-01":{"attempts":1,"playable":51.235536792230654,"score":51.235536792230654},"GB2-02":{"attempts":1,"playable":44.91694128410355,"score":44.91694128410355},"GB2-03":{"attempts":1,"playable":62.46304509166916,"score":62.46304509166916},"GB2-04":{"attempts":1,"playable":53.276225943954394,"score":53.276225943954394},"GB2-05":{"attempts":1,"playable":47.61042676894488,"score":47.61042676894488},"GB2-06":{"attempts":1,"playable":57.91147700886635,"score":57.91147700886635},"GB2-07":{"attempts":1,"playable":64.25915621579892,"score":64.25915621579892},"GB2-08":{"attempts":1,"playable":55.7944884797446,"score":55.7944884797446}},"none":{"GB2-01":{"attempts":1,"playable":50.746561800860114,"score":50.746561800860114},"GB2-02":{"attempts":1,"playable":45.338788424049355,"score":45.338788424049355},"GB2-03":{"attempts":1,"playable":36.44436895903613,"score":36.44436895903613},"GB2-04":{"attempts":1,"playable":40.98421031880623,"score":40.98421031880623},"GB2-05":{"attempts":1,"playable":21.805315335411894,"score":21.805315335411894},"GB2-06":{"attempts":1,"playable":47.40482584358757,"score":47.40482584358757},"GB2-07":{"attempts":1,"playable":36.93187650272706,"score":36.93187650272706},"GB2-08":{"attempts":1,"playable":19.523694017823157,"score":19.523694017823157}}},"id":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:27Z","match_totals_all":{"draws":2989,"losses":4618,"wins":4657},"match_totals_tracks":{"highest":{"draws":717,"losses":1134,"wins":2237},"medium":{"draws":1061,"losses":1424,"wins":1603},"none":{"draws":1211,"losses":2060,"wins":817}},"model_slug":"fireworks-ember-1","official_rank_by_reasoning":{"highest":25,"medium":29,"none":49},"overall":{"max":87.59950869232675,"mean":52.388726378033454,"min":19.523694017823157},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.08130575673387,"GB2-02":42.910539295927805,"GB2-03":81.1918431229029,"GB2-04":41.08644928581932,"GB2-05":63.237816289157955,"GB2-06":51.75602740212671,"GB2-07":75.81900444019345,"GB2-08":87.59950869232675},"per_game_all":{"GB2-01":59.68780144994155,"GB2-02":44.388756334693575,"GB2-03":60.03308572453606,"GB2-04":45.11562851619331,"GB2-05":44.21785279783825,"GB2-06":52.35744341819355,"GB2-07":59.00334571957314,"GB2-08":54.30589706329817},"per_game_match_totals_all":{"GB2-01":{"draws":466,"losses":423,"wins":659},"GB2-02":{"draws":1068,"losses":291,"wins":81},"GB2-03":{"draws":295,"losses":494,"wins":693},"GB2-04":{"draws":898,"losses":396,"wins":200},"GB2-05":{"draws":0,"losses":910,"wins":680},"GB2-06":{"draws":60,"losses":752,"wins":694},"GB2-07":{"draws":0,"losses":680,"wins":910},"GB2-08":{"draws":202,"losses":672,"wins":740}},"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":15,"losses":98,"wins":381},"GB2-04":{"draws":313,"losses":145,"wins":40},"GB2-05":{"draws":0,"losses":204,"wins":326},"GB2-06":{"draws":14,"losses":257,"wins":231},"GB2-07":{"draws":0,"losses":133,"wins":397},"GB2-08":{"draws":2,"losses":73,"wins":463}},"medium":{"GB2-01":{"draws":257,"losses":134,"wins":125},"GB2-02":{"draws":357,"losses":94,"wins":29},"GB2-03":{"draws":41,"losses":184,"wins":269},"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":84,"losses":215,"wins":239}},"none":{"GB2-01":{"draws":200,"losses":165,"wins":151},"GB2-02":{"draws":347,"losses":97,"wins":36},"GB2-03":{"draws":239,"losses":212,"wins":43},"GB2-04":{"draws":282,"losses":161,"wins":55},"GB2-05":{"draws":0,"losses":420,"wins":110},"GB2-06":{"draws":27,"losses":273,"wins":202},"GB2-07":{"draws":0,"losses":348,"wins":182},"GB2-08":{"draws":116,"losses":384,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1571.6740777813056,"GB2-02":1428.406431134507,"GB2-03":1546.654799922096,"GB2-04":1437.1830619978593,"GB2-05":1353.1173001728923,"GB2-06":1457.1358672034848,"GB2-07":1576.9802726608539,"GB2-08":1531.697798765769},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1758.0197362298013,"GB2-02":1416.9768592403107,"GB2-03":1786.9994355841945,"GB2-04":1405.9374854214225,"GB2-05":1609.5592400340436,"GB2-06":1446.8596724577853,"GB2-07":1812.9554108331154,"GB2-08":2085.4531269597574},"medium":{"GB2-01":1480.831865818067,"GB2-02":1432.4938614744979,"GB2-03":1543.75711224058,"GB2-04":1500.4745512171003,"GB2-05":1407.7157535228107,"GB2-06":1544.9002573264027,"GB2-07":1633.8849204486182,"GB2-08":1463.046527045305},"none":{"GB2-01":1476.1706312960487,"GB2-02":1435.7485726887123,"GB2-03":1309.207851941514,"GB2-04":1405.1371493550557,"GB2-05":1042.0769069618225,"GB2-06":1379.6476718262668,"GB2-07":1284.1004867008278,"GB2-08":1046.5937422922445}},"per_game_tracks":{"highest":{"GB2-01":77.08130575673387,"GB2-02":42.910539295927805,"GB2-03":81.1918431229029,"GB2-04":41.08644928581932,"GB2-05":63.237816289157955,"GB2-06":51.75602740212671,"GB2-07":75.81900444019345,"GB2-08":87.59950869232675},"medium":{"GB2-01":51.235536792230654,"GB2-02":44.91694128410355,"GB2-03":62.46304509166916,"GB2-04":53.276225943954394,"GB2-05":47.61042676894488,"GB2-06":57.91147700886635,"GB2-07":64.25915621579892,"GB2-08":55.7944884797446},"none":{"GB2-01":50.746561800860114,"GB2-02":45.338788424049355,"GB2-03":36.44436895903613,"GB2-04":40.98421031880623,"GB2-05":21.805315335411894,"GB2-06":47.40482584358757,"GB2-07":36.93187650272706,"GB2-08":19.523694017823157}},"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":0,"rank_movement_baseline_at":"2026-10-24T19:21:04Z","reasoning":{"highest":65.0853117856486,"medium":54.68341219816406,"none":37.39745515028769},"reasoning_agg":{"highest":{"max":87.59950869232675,"mean":65.0853117856486,"min":41.08644928581932},"medium":{"max":64.25915621579892,"mean":54.68341219816406,"min":44.91694128410355},"none":{"max":50.746561800860114,"mean":37.39745515028769,"min":19.523694017823157}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.68785663536091},"working_program_strength":{"all":52.388726378033454,"highest":65.0853117856486,"medium":54.68341219816406,"none":37.39745515028769}},{"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":52.290550795837326,"highest":68.34010983325358,"medium":47.30904896839931,"none":41.22249358585908},"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":54.48051454195302,"score":47.55602714764904},"GB2-02":{"attempts":8,"playable":55.7605382835805,"score":55.7605382835805},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":58.05639394722551,"score":52.10729996334184},"GB2-04":{"attempts":9,"playable":59.45397589319106,"score":59.45397589319106},"GB2-05":{"attempts":9,"playable":54.55134879725673,"score":54.55134879725673},"GB2-06":{"attempts":8,"playable":46.51228991006703,"score":46.51228991006703},"GB2-07":{"attempts":9,"playable":50.68573409502079,"score":50.68573409502079},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":55.05801707098516,"score":51.69719227659158}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":3,"playable":58.588730554692084,"score":58.588730554692084},"GB2-02":{"attempts":2,"playable":74.06155524082445,"score":74.06155524082445},"GB2-03":{"attempts":5,"playable":71.23432297404122,"score":71.23432297404122},"GB2-04":{"attempts":3,"playable":71.51274169554084,"score":71.51274169554084},"GB2-05":{"attempts":3,"playable":62.63991432545314,"score":62.63991432545314},"GB2-06":{"attempts":3,"playable":68.62895630210221,"score":68.62895630210221},"GB2-07":{"attempts":3,"playable":66.69265511451336,"score":66.69265511451336},"GB2-08":{"attempts":3,"playable":73.36200245886134,"score":73.36200245886134}},"medium":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":62.32038654873581,"score":41.54692436582388},"GB2-02":{"attempts":3,"playable":50.16934662495466,"score":50.16934662495466},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":57.69067869722377,"score":44.870527875618485},"GB2-04":{"attempts":3,"playable":57.29271491847438,"score":57.29271491847438},"GB2-05":{"attempts":3,"playable":49.32461277255595,"score":49.32461277255595},"GB2-06":{"attempts":2,"playable":28.098379301525302,"score":28.098379301525302},"GB2-07":{"attempts":3,"playable":45.60526028368986,"score":45.60526028368986},"GB2-08":{"attempts":3,"playable":61.56462560455196,"score":61.56462560455196}},"none":{"GB2-01":{"attempts":3,"playable":42.53242652243116,"score":42.53242652243116},"GB2-02":{"attempts":3,"playable":43.05071298496239,"score":43.05071298496239},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":45.24418017041154,"score":40.217049040365815},"GB2-04":{"attempts":3,"playable":49.55647106555795,"score":49.55647106555795},"GB2-05":{"attempts":3,"playable":51.6895192937611,"score":51.6895192937611},"GB2-06":{"attempts":3,"playable":42.80953412657357,"score":42.80953412657357},"GB2-07":{"attempts":3,"playable":39.759286886859144,"score":39.759286886859144},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":30.247423149542144,"score":20.16494876636143}}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:13Z","match_totals_all":{"draws":8251,"losses":15097,"wins":16839},"match_totals_tracks":{"highest":{"draws":1292,"losses":3684,"wins":7795},"medium":{"draws":2819,"losses":5143,"wins":5258},"none":{"draws":4140,"losses":6270,"wins":3786}},"model_slug":"stealth-ox-alpha","official_rank_by_reasoning":{"highest":21,"medium":44,"none":41},"overall":{"max":74.06155524082445,"mean":52.290550795837326,"min":20.16494876636143},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.588730554692084,"GB2-02":74.06155524082445,"GB2-03":71.23432297404122,"GB2-04":71.51274169554084,"GB2-05":62.63991432545314,"GB2-06":68.62895630210221,"GB2-07":66.69265511451337,"GB2-08":73.36200245886134},"per_game_all":{"GB2-01":54.48051454195302,"GB2-02":55.7605382835805,"GB2-03":58.05639394722551,"GB2-04":59.45397589319106,"GB2-05":54.55134879725673,"GB2-06":46.51228991006703,"GB2-07":50.68573409502079,"GB2-08":55.05801707098516},"per_game_match_totals_all":{"GB2-01":{"draws":659,"losses":1675,"wins":1794},"GB2-02":{"draws":2495,"losses":601,"wins":744},"GB2-03":{"draws":1873,"losses":3749,"wins":4257},"GB2-04":{"draws":2373,"losses":704,"wins":1405},"GB2-05":{"draws":0,"losses":2246,"wins":2524},"GB2-06":{"draws":127,"losses":2119,"wins":1768},"GB2-07":{"draws":0,"losses":2441,"wins":2329},"GB2-08":{"draws":724,"losses":1562,"wins":2018}},"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":714,"wins":1612},"GB2-04":{"draws":565,"losses":164,"wins":765},"GB2-05":{"draws":0,"losses":621,"wins":969},"GB2-06":{"draws":80,"losses":473,"wins":953},"GB2-07":{"draws":0,"losses":555,"wins":1035},"GB2-08":{"draws":79,"losses":434,"wins":1101}},"medium":{"GB2-01":{"draws":218,"losses":302,"wins":512},"GB2-02":{"draws":1037,"losses":224,"wins":179},"GB2-03":{"draws":385,"losses":1395,"wins":1678},"GB2-04":{"draws":873,"losses":228,"wins":393},"GB2-05":{"draws":0,"losses":831,"wins":759},"GB2-06":{"draws":21,"losses":738,"wins":243},"GB2-07":{"draws":0,"losses":893,"wins":697},"GB2-08":{"draws":285,"losses":532,"wins":797}},"none":{"GB2-01":{"draws":368,"losses":736,"wins":444},"GB2-02":{"draws":1106,"losses":291,"wins":43},"GB2-03":{"draws":1345,"losses":1640,"wins":967},"GB2-04":{"draws":935,"losses":312,"wins":247},"GB2-05":{"draws":0,"losses":794,"wins":796},"GB2-06":{"draws":26,"losses":908,"wins":572},"GB2-07":{"draws":0,"losses":993,"wins":597},"GB2-08":{"draws":360,"losses":596,"wins":120}}},"per_game_raw_elo_all":{"GB2-01":1513.653581091814,"GB2-02":1527.5663123428906,"GB2-03":1525.316786893589,"GB2-04":1562.369196529322,"GB2-05":1498.2737557830715,"GB2-06":1371.245031677188,"GB2-07":1453.1308302647778,"GB2-08":1502.3974422146748},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1555.1107220517213,"GB2-02":1691.4988614925528,"GB2-03":1674.3092227955283,"GB2-04":1682.653738806185,"GB2-05":1606.930988180319,"GB2-06":1761.1297954862755,"GB2-07":1673.3920833498075,"GB2-08":1775.8089822598547},"medium":{"GB2-01":1589.9205725373454,"GB2-02":1473.1531351654096,"GB2-03":1515.9477622196587,"GB2-04":1532.6882869025164,"GB2-05":1429.0594385050135,"GB2-06":1041.4504431817795,"GB2-07":1381.6485463732076,"GB2-08":1558.4944720858186},"none":{"GB2-01":1395.9294486863757,"GB2-02":1418.0469403707095,"GB2-03":1385.693375665581,"GB2-04":1471.765563879264,"GB2-05":1458.8308406638819,"GB2-06":1311.1548563635088,"GB2-07":1304.3518610713188,"GB2-08":1172.8888722983506}},"per_game_tracks":{"highest":{"GB2-01":58.588730554692084,"GB2-02":74.06155524082445,"GB2-03":71.23432297404122,"GB2-04":71.51274169554084,"GB2-05":62.63991432545314,"GB2-06":68.62895630210221,"GB2-07":66.69265511451337,"GB2-08":73.36200245886134},"medium":{"GB2-01":62.32038654873581,"GB2-02":50.16934662495466,"GB2-03":57.69067869722377,"GB2-04":57.29271491847438,"GB2-05":49.32461277255595,"GB2-06":28.098379301525302,"GB2-07":45.60526028368986,"GB2-08":61.56462560455196},"none":{"GB2-01":42.53242652243116,"GB2-02":43.05071298496239,"GB2-03":45.24418017041154,"GB2-04":49.55647106555796,"GB2-05":51.6895192937611,"GB2-06":42.80953412657357,"GB2-07":39.759286886859144,"GB2-08":30.247423149542144}},"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":"2026-10-24T19:18:13Z","reasoning":{"highest":68.34010983325358,"medium":47.30904896839931,"none":41.22249358585908},"reasoning_agg":{"highest":{"max":74.06155524082445,"mean":68.34010983325358,"min":58.588730554692084},"medium":{"max":61.56462560455196,"mean":47.30904896839931,"min":28.098379301525302},"none":{"max":51.6895192937611,"mean":41.22249358585908,"min":20.16494876636143}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.1176162473945},"working_program_strength":{"all":54.31985156740998,"highest":68.34010983325358,"medium":51.508250593963965,"none":43.11119427501237}},{"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":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628249999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825},"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":51.617997916413266,"highest":63.77550845017813,"medium":48.29706343241805,"none":42.78142186664362},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed"},"none":{"GB2-03":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":31,"output_token_observations":25,"total_output_tokens":356249},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":55.53585330792611,"score":55.53585330792611},"GB2-02":{"attempts":3,"playable":53.59917885207099,"score":53.59917885207099},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":31.204237061055146,"score":10.401412353685048},"GB2-04":{"attempts":3,"playable":51.738146668414174,"score":51.738146668414174},"GB2-05":{"attempts":3,"playable":40.0324741750251,"score":40.0324741750251},"GB2-06":{"attempts":3,"playable":70.34614857644128,"score":70.34614857644128},"GB2-07":{"attempts":3,"playable":65.73529110751599,"score":65.73529110751599},"GB2-08":{"attempts":3,"playable":65.55547829022743,"score":65.55547829022743}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.78596380719114,"score":68.78596380719114},"GB2-02":{"attempts":1,"playable":79.21136097509942,"score":79.21136097509942},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":70.48724931008368,"score":70.48724931008368},"GB2-05":{"attempts":1,"playable":49.337466438153236,"score":49.337466438153236},"GB2-06":{"attempts":1,"playable":82.4569280608738,"score":82.4569280608738},"GB2-07":{"attempts":1,"playable":76.85758163467997,"score":76.85758163467997},"GB2-08":{"attempts":1,"playable":83.06751737534383,"score":83.06751737534383}},"medium":{"GB2-01":{"attempts":1,"playable":41.41585669789332,"score":41.41585669789332},"GB2-02":{"attempts":1,"playable":42.1702722263371,"score":42.1702722263371},"GB2-03":{"attempts":1,"playable":31.204237061055146,"score":31.204237061055146},"GB2-04":{"attempts":1,"playable":42.516760894618045,"score":42.516760894618045},"GB2-05":{"attempts":1,"playable":48.18635741237079,"score":48.18635741237079},"GB2-06":{"attempts":1,"playable":79.71694138066104,"score":79.71694138066104},"GB2-07":{"attempts":1,"playable":68.14286552155062,"score":68.14286552155062},"GB2-08":{"attempts":1,"playable":33.02321626485831,"score":33.02321626485831}},"none":{"GB2-01":{"attempts":1,"playable":56.40573941869387,"score":56.40573941869387},"GB2-02":{"attempts":1,"playable":39.41590335477645,"score":39.41590335477645},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.2104298005408,"score":42.2104298005408},"GB2-05":{"attempts":1,"playable":22.573598674551278,"score":22.573598674551278},"GB2-06":{"attempts":1,"playable":48.864576287789,"score":48.864576287789},"GB2-07":{"attempts":1,"playable":52.205426166317395,"score":52.205426166317395},"GB2-08":{"attempts":1,"playable":80.57570123048013,"score":80.57570123048013}}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:18Z","match_totals_all":{"draws":2495,"losses":3891,"wins":4889},"match_totals_tracks":{"highest":{"draws":485,"losses":793,"wins":2316},"medium":{"draws":1206,"losses":1592,"wins":1289},"none":{"draws":804,"losses":1506,"wins":1284}},"model_slug":"claude-opus-4-8","official_rank_by_reasoning":{"highest":29,"medium":41,"none":33},"overall":{"max":83.06751737534383,"mean":51.617997916413266,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.78596380719114,"GB2-02":79.21136097509942,"GB2-04":70.48724931008368,"GB2-05":49.337466438153236,"GB2-06":82.4569280608738,"GB2-07":76.85758163467997,"GB2-08":83.06751737534383},"per_game_all":{"GB2-01":55.53585330792611,"GB2-02":53.59917885207099,"GB2-04":51.738146668414174,"GB2-05":40.0324741750251,"GB2-06":70.34614857644128,"GB2-07":65.73529110751599,"GB2-08":65.55547829022743},"per_game_match_totals_all":{"GB2-01":{"draws":257,"losses":592,"wins":699},"GB2-02":{"draws":899,"losses":240,"wins":301},"GB2-03":{"draws":152,"losses":280,"wins":62},"GB2-04":{"draws":861,"losses":315,"wins":318},"GB2-05":{"draws":0,"losses":976,"wins":614},"GB2-06":{"draws":66,"losses":456,"wins":983},"GB2-07":{"draws":0,"losses":570,"wins":1020},"GB2-08":{"draws":260,"losses":462,"wins":892}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":68,"losses":138,"wins":310},"GB2-02":{"draws":179,"losses":16,"wins":285},"GB2-04":{"draws":208,"losses":51,"wins":239},"GB2-05":{"draws":0,"losses":277,"wins":253},"GB2-06":{"draws":29,"losses":83,"wins":390},"GB2-07":{"draws":0,"losses":127,"wins":403},"GB2-08":{"draws":1,"losses":101,"wins":436}},"medium":{"GB2-01":{"draws":75,"losses":275,"wins":166},"GB2-02":{"draws":385,"losses":93,"wins":2},"GB2-03":{"draws":152,"losses":280,"wins":62},"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":258,"losses":245,"wins":35}},"none":{"GB2-01":{"draws":114,"losses":179,"wins":223},"GB2-02":{"draws":335,"losses":131,"wins":14},"GB2-04":{"draws":326,"losses":133,"wins":39},"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":116,"wins":421}}},"per_game_raw_elo_all":{"GB2-01":1525.2027380351901,"GB2-02":1514.8538446051025,"GB2-04":1493.3217723806745,"GB2-05":1299.8038135839631,"GB2-06":1778.4200352358732,"GB2-07":1665.5000414009664,"GB2-08":1691.720825051565},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1657.9311853391996,"GB2-02":1743.6578898519156,"GB2-04":1648.1593101491233,"GB2-05":1429.1700627766422,"GB2-06":1994.7354169422476,"GB2-07":1831.6686633539225,"GB2-08":1965.670466234945},"medium":{"GB2-01":1387.1127372718006,"GB2-02":1411.229195836158,"GB2-03":1261.3517250612656,"GB2-04":1417.09498613261,"GB2-05":1414.872725579725,"GB2-06":1938.4705107471407,"GB2-07":1689.6331172820478,"GB2-08":1203.242561572809},"none":{"GB2-01":1530.56429149457,"GB2-02":1389.6744481272335,"GB2-04":1414.7110208602899,"GB2-05":1055.3686523955218,"GB2-06":1402.0541780182316,"GB2-07":1475.1983435669285,"GB2-08":1906.2494473469412}},"per_game_tracks":{"highest":{"GB2-01":68.78596380719114,"GB2-02":79.21136097509942,"GB2-04":70.48724931008368,"GB2-05":49.337466438153236,"GB2-06":82.4569280608738,"GB2-07":76.85758163467997,"GB2-08":83.06751737534383},"medium":{"GB2-01":41.41585669789332,"GB2-02":42.1702722263371,"GB2-03":31.204237061055146,"GB2-04":42.516760894618045,"GB2-05":48.18635741237079,"GB2-06":79.71694138066104,"GB2-07":68.14286552155062,"GB2-08":33.02321626485831},"none":{"GB2-01":56.40573941869387,"GB2-02":39.41590335477645,"GB2-04":42.2104298005408,"GB2-05":22.573598674551278,"GB2-06":48.864576287789,"GB2-07":52.205426166317395,"GB2-08":80.57570123048013}},"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":"2026-10-24T19:04:49Z","reasoning":{"highest":63.77550845017813,"medium":48.29706343241805,"none":42.78142186664362},"reasoning_agg":{"highest":{"max":83.06751737534383,"mean":63.77550845017813,"min":0.0},"medium":{"max":79.71694138066104,"mean":48.29706343241805,"min":31.204237061055146},"none":{"max":80.57570123048013,"mean":42.78142186664362,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":20.99408658353451},"working_program_strength":{"all":56.692137455309535,"highest":72.88629537163214,"medium":48.29706343241805,"none":48.893053561878425}},{"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":2.1645493884651272},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478316},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870414}},"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":1.5865090123478311},"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":4.9824165},"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":51.10849993862242,"highest":64.0865576806636,"medium":57.363642946497215,"none":31.87529918870642},"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":71.11213512710803,"score":71.11213512710803},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":49.02590731481388,"score":42.42123405192025},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":54.73535610166027,"score":50.89321777915992},"GB2-04":{"attempts":4,"playable":45.38246694915117,"score":45.38246694915117},"GB2-05":{"attempts":4,"playable":45.117778352907806,"score":45.117778352907806},"GB2-06":{"attempts":4,"playable":63.145123774759575,"score":63.145123774759575},"GB2-07":{"attempts":4,"playable":50.50312401702641,"score":50.50312401702641},"GB2-08":{"attempts":4,"playable":40.292919456946116,"score":40.292919456946116}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.48531473976723,"score":90.48531473976723},"GB2-02":{"attempts":1,"playable":62.84925449361422,"score":62.84925449361422},"GB2-03":{"attempts":1,"playable":70.98199665336188,"score":70.98199665336188},"GB2-04":{"attempts":1,"playable":39.96129123978842,"score":39.96129123978842},"GB2-05":{"attempts":1,"playable":52.01913687544882,"score":52.01913687544882},"GB2-06":{"attempts":1,"playable":75.5491946702753,"score":75.5491946702753},"GB2-07":{"attempts":1,"playable":52.022714507735756,"score":52.022714507735756},"GB2-08":{"attempts":1,"playable":68.82355826531712,"score":68.82355826531712}},"medium":{"GB2-01":{"attempts":1,"playable":73.3788760709071,"score":73.3788760709071},"GB2-02":{"attempts":1,"playable":44.600427873465655,"score":44.600427873465655},"GB2-03":{"attempts":1,"playable":70.17124171661679,"score":70.17124171661679},"GB2-04":{"attempts":1,"playable":54.28409063356446,"score":54.28409063356446},"GB2-05":{"attempts":1,"playable":67.18977853745804,"score":67.18977853745804},"GB2-06":{"attempts":1,"playable":74.45815982704819,"score":74.45815982704819},"GB2-07":{"attempts":1,"playable":54.209603332930065,"score":54.209603332930065},"GB2-08":{"attempts":1,"playable":20.616965579987426,"score":20.616965579987426}},"none":{"GB2-01":{"attempts":2,"playable":49.47221457064977,"score":49.47221457064977},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.62803957736176,"score":19.81401978868088},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":23.052829935002148,"score":11.526414967501074},"GB2-04":{"attempts":2,"playable":41.90201897410065,"score":41.90201897410065},"GB2-05":{"attempts":2,"playable":16.144419645816544,"score":16.144419645816544},"GB2-06":{"attempts":2,"playable":39.42801682695523,"score":39.42801682695523},"GB2-07":{"attempts":2,"playable":45.27705421041341,"score":45.27705421041341},"GB2-08":{"attempts":2,"playable":31.438234525533804,"score":31.438234525533804}}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:21Z","match_totals_all":{"draws":3138,"losses":6570,"wins":5669},"match_totals_tracks":{"highest":{"draws":675,"losses":1223,"wins":2190},"medium":{"draws":828,"losses":1425,"wins":1834},"none":{"draws":1635,"losses":3922,"wins":1645}},"model_slug":"google-gemini-3-5-flash","official_rank_by_reasoning":{"highest":28,"medium":25,"none":56},"overall":{"max":90.48531473976723,"mean":51.10849993862242,"min":11.526414967501074},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.48531473976723,"GB2-02":62.84925449361422,"GB2-03":70.98199665336188,"GB2-04":39.96129123978842,"GB2-05":52.01913687544882,"GB2-06":75.5491946702753,"GB2-07":52.022714507735756,"GB2-08":68.82355826531712},"per_game_all":{"GB2-01":71.11213512710803,"GB2-02":49.02590731481388,"GB2-03":54.73535610166027,"GB2-04":45.38246694915117,"GB2-05":45.117778352907806,"GB2-06":63.145123774759575,"GB2-07":50.50312401702641,"GB2-08":40.292919456946116},"per_game_match_totals_all":{"GB2-01":{"draws":220,"losses":636,"wins":1208},"GB2-02":{"draws":1032,"losses":242,"wins":166},"GB2-03":{"draws":161,"losses":638,"wins":682},"GB2-04":{"draws":1183,"losses":547,"wins":262},"GB2-05":{"draws":0,"losses":1345,"wins":775},"GB2-06":{"draws":20,"losses":909,"wins":1079},"GB2-07":{"draws":0,"losses":1128,"wins":992},"GB2-08":{"draws":522,"losses":1125,"wins":505}},"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":43,"losses":139,"wins":312},"GB2-04":{"draws":264,"losses":175,"wins":59},"GB2-05":{"draws":0,"losses":263,"wins":267},"GB2-06":{"draws":7,"losses":132,"wins":363},"GB2-07":{"draws":0,"losses":267,"wins":263},"GB2-08":{"draws":75,"losses":148,"wins":315}},"medium":{"GB2-01":{"draws":14,"losses":141,"wins":361},"GB2-02":{"draws":406,"losses":71,"wins":3},"GB2-03":{"draws":49,"losses":140,"wins":304},"GB2-04":{"draws":283,"losses":95,"wins":120},"GB2-05":{"draws":0,"losses":183,"wins":347},"GB2-06":{"draws":7,"losses":138,"wins":357},"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":359,"wins":66},"GB2-04":{"draws":636,"losses":277,"wins":83},"GB2-05":{"draws":0,"losses":899,"wins":161},"GB2-06":{"draws":6,"losses":639,"wins":359},"GB2-07":{"draws":0,"losses":606,"wins":454},"GB2-08":{"draws":378,"losses":575,"wins":123}}},"per_game_raw_elo_all":{"GB2-01":1724.0707910455956,"GB2-02":1465.6098503220537,"GB2-03":1481.549242841915,"GB2-04":1439.24900924406,"GB2-05":1355.0771323495694,"GB2-06":1651.1937508571839,"GB2-07":1454.028130632057,"GB2-08":1303.8683381873925},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1996.5824241757837,"GB2-02":1575.4328648433377,"GB2-03":1637.6469557889357,"GB2-04":1397.1055807696607,"GB2-05":1462.5482712980647,"GB2-06":1856.9309063407354,"GB2-07":1472.8942999729484,"GB2-08":1664.6869802359463},"medium":{"GB2-01":1711.0945864932187,"GB2-02":1430.050511493092,"GB2-03":1627.8679213199543,"GB2-04":1508.402622343839,"GB2-05":1667.7809781301494,"GB2-06":1836.1649457030608,"GB2-07":1500.6046230470124,"GB2-08":1060.80549548712},"none":{"GB2-01":1464.5353624677841,"GB2-02":1391.3461746297314,"GB2-03":1179.1328514168551,"GB2-04":1412.2388246186802,"GB2-05":934.9021476204941,"GB2-06":1260.4854005277562,"GB2-07":1388.5854688762106,"GB2-08":1186.112538839111}},"per_game_tracks":{"highest":{"GB2-01":90.48531473976723,"GB2-02":62.84925449361422,"GB2-03":70.98199665336188,"GB2-04":39.96129123978842,"GB2-05":52.01913687544882,"GB2-06":75.5491946702753,"GB2-07":52.022714507735756,"GB2-08":68.82355826531712},"medium":{"GB2-01":73.3788760709071,"GB2-02":44.600427873465655,"GB2-03":70.17124171661679,"GB2-04":54.28409063356446,"GB2-05":67.18977853745804,"GB2-06":74.45815982704819,"GB2-07":54.209603332930065,"GB2-08":20.616965579987426},"none":{"GB2-01":49.47221457064977,"GB2-02":39.62803957736176,"GB2-03":23.052829935002148,"GB2-04":41.90201897410065,"GB2-05":16.144419645816544,"GB2-06":39.42801682695523,"GB2-07":45.27705421041341,"GB2-08":31.438234525533804}},"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":"2026-10-24T19:15:48Z","reasoning":{"highest":64.0865576806636,"medium":57.363642946497215,"none":31.875299188706418},"reasoning_agg":{"highest":{"max":90.48531473976723,"mean":64.0865576806636,"min":39.96129123978842},"medium":{"max":74.45815982704819,"mean":57.363642946497215,"min":20.616965579987426},"none":{"max":49.47221457064977,"mean":31.875299188706418,"min":11.526414967501074}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":32.21125849195718},"working_program_strength":{"all":52.41435138679666,"highest":64.0865576806636,"medium":57.363642946497215,"none":35.79285353322917}},{"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":21.885475000000003},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"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":1.13802}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"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":50.73999029500178,"highest":61.55442465713748,"medium":53.14804758528771,"none":37.517498642580165},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed"},"none":{"GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"total_output_tokens":851788},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":65.70179578073153,"score":65.70179578073153},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":48.88778117281322,"score":32.59185411520881},"GB2-03":{"attempts":3,"playable":43.17566151443841,"score":43.17566151443841},"GB2-04":{"attempts":3,"playable":39.31131441995884,"score":39.31131441995884},"GB2-05":{"attempts":3,"playable":68.8035962844332,"score":68.8035962844332},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":55.45313616439678,"score":36.968757442931185},"GB2-07":{"attempts":3,"playable":62.04487131523927,"score":62.04487131523927},"GB2-08":{"attempts":3,"playable":57.32207148707306,"score":57.32207148707306}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.9346384024902,"score":80.9346384024902},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":51.133542812877764,"score":51.133542812877764},"GB2-04":{"attempts":1,"playable":36.88696967756637,"score":36.88696967756637},"GB2-05":{"attempts":1,"playable":77.19125124108702,"score":77.19125124108702},"GB2-06":{"attempts":1,"playable":81.54823367582276,"score":81.54823367582276},"GB2-07":{"attempts":1,"playable":87.00914453270325,"score":87.00914453270325},"GB2-08":{"attempts":1,"playable":77.7316169145525,"score":77.7316169145525}},"medium":{"GB2-01":{"attempts":1,"playable":64.93521214747375,"score":64.93521214747375},"GB2-02":{"attempts":1,"playable":55.711088338828816,"score":55.711088338828816},"GB2-03":{"attempts":1,"playable":39.61869369407654,"score":39.61869369407654},"GB2-04":{"attempts":1,"playable":39.44947595905667,"score":39.44947595905667},"GB2-05":{"attempts":1,"playable":77.0090970640164,"score":77.0090970640164},"GB2-06":{"attempts":1,"playable":29.358038652970798,"score":29.358038652970798},"GB2-07":{"attempts":1,"playable":61.05578240397785,"score":61.05578240397785},"GB2-08":{"attempts":1,"playable":58.04699242190091,"score":58.04699242190091}},"none":{"GB2-01":{"attempts":1,"playable":51.235536792230675,"score":51.235536792230675},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":38.774748036360926,"score":38.774748036360926},"GB2-04":{"attempts":1,"playable":41.597497623253474,"score":41.597497623253474},"GB2-05":{"attempts":1,"playable":52.210440548196146,"score":52.210440548196146},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":38.069687009036706,"score":38.069687009036706},"GB2-08":{"attempts":1,"playable":36.18760512476575,"score":36.18760512476575}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-10-26T01:51:19Z","match_totals_all":{"draws":3155,"losses":3682,"wins":4445},"match_totals_tracks":{"highest":{"draws":626,"losses":811,"wins":2171},"medium":{"draws":1171,"losses":1420,"wins":1497},"none":{"draws":1358,"losses":1451,"wins":777}},"model_slug":"gpt-5-5","official_rank_by_reasoning":{"highest":32,"medium":31,"none":48},"overall":{"max":87.00914453270325,"mean":50.73999029500178,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.9346384024902,"GB2-03":51.133542812877764,"GB2-04":36.88696967756637,"GB2-05":77.19125124108702,"GB2-06":81.54823367582276,"GB2-07":87.00914453270325,"GB2-08":77.7316169145525},"per_game_all":{"GB2-01":65.70179578073153,"GB2-03":43.17566151443841,"GB2-04":39.31131441995884,"GB2-05":68.8035962844332,"GB2-07":62.04487131523927,"GB2-08":57.32207148707306},"per_game_match_totals_all":{"GB2-01":{"draws":717,"losses":204,"wins":627},"GB2-02":{"draws":690,"losses":162,"wins":108},"GB2-03":{"draws":438,"losses":679,"wins":365},"GB2-04":{"draws":869,"losses":496,"wins":129},"GB2-05":{"draws":0,"losses":521,"wins":1069},"GB2-06":{"draws":32,"losses":461,"wins":511},"GB2-07":{"draws":0,"losses":627,"wins":963},"GB2-08":{"draws":409,"losses":532,"wins":673}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":126,"losses":45,"wins":345},"GB2-03":{"draws":146,"losses":188,"wins":160},"GB2-04":{"draws":282,"losses":181,"wins":35},"GB2-05":{"draws":0,"losses":129,"wins":401},"GB2-06":{"draws":21,"losses":92,"wins":389},"GB2-07":{"draws":0,"losses":68,"wins":462},"GB2-08":{"draws":51,"losses":108,"wins":379}},"medium":{"GB2-01":{"draws":280,"losses":52,"wins":184},"GB2-02":{"draws":304,"losses":69,"wins":107},"GB2-03":{"draws":163,"losses":235,"wins":96},"GB2-04":{"draws":283,"losses":168,"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":130,"losses":180,"wins":228}},"none":{"GB2-01":{"draws":311,"losses":107,"wins":98},"GB2-02":{"draws":386,"losses":93,"wins":1},"GB2-03":{"draws":129,"losses":256,"wins":109},"GB2-04":{"draws":304,"losses":147,"wins":47},"GB2-05":{"draws":0,"losses":262,"wins":268},"GB2-07":{"draws":0,"losses":342,"wins":188},"GB2-08":{"draws":228,"losses":244,"wins":66}}},"per_game_raw_elo_all":{"GB2-01":1636.5635726462358,"GB2-03":1368.2417429561665,"GB2-04":1391.879273737697,"GB2-05":1720.0574117886197,"GB2-07":1653.2941481906325,"GB2-08":1524.353405873516},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1812.4575725561367,"GB2-03":1437.669861669138,"GB2-04":1372.6367413851515,"GB2-05":1849.6067194464542,"GB2-06":1975.7691192211446,"GB2-07":2071.300907203259,"GB2-08":1842.322381019295},"medium":{"GB2-01":1616.4012795645033,"GB2-02":1516.4901351937958,"GB2-03":1337.2290097072948,"GB2-04":1393.0689936762606,"GB2-05":1845.6269540384772,"GB2-06":1107.3275202572759,"GB2-07":1590.016445528597,"GB2-08":1493.6219877705162},"none":{"GB2-01":1480.8318658180672,"GB2-02":1410.4064568490924,"GB2-03":1329.826357492067,"GB2-04":1409.9320861516785,"GB2-05":1464.9385618809279,"GB2-07":1298.5650918400415,"GB2-08":1237.115848830737}},"per_game_tracks":{"highest":{"GB2-01":80.9346384024902,"GB2-03":51.133542812877764,"GB2-04":36.88696967756637,"GB2-05":77.19125124108702,"GB2-06":81.54823367582276,"GB2-07":87.00914453270325,"GB2-08":77.7316169145525},"medium":{"GB2-01":64.93521214747375,"GB2-02":55.711088338828816,"GB2-03":39.61869369407654,"GB2-04":39.44947595905667,"GB2-05":77.0090970640164,"GB2-06":29.358038652970798,"GB2-07":61.05578240397785,"GB2-08":58.04699242190091},"none":{"GB2-01":51.235536792230675,"GB2-02":42.06447400679762,"GB2-03":38.774748036360926,"GB2-04":41.597497623253474,"GB2-05":52.210440548196146,"GB2-07":38.069687009036706,"GB2-08":36.18760512476575}},"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":"2026-10-24T18:49:01Z","reasoning":{"highest":61.55442465713748,"medium":53.14804758528771,"none":37.517498642580165},"reasoning_agg":{"highest":{"max":87.00914453270325,"mean":61.55442465713748,"min":0.0},"medium":{"max":77.0090970640164,"mean":53.14804758528771,"min":29.358038652970798},"none":{"max":52.210440548196146,"mean":37.517498642580165,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":24.036926014557316},"working_program_strength":{"all":55.45770092832168,"highest":70.34791389387141,"medium":53.14804758528771,"none":42.8771413058059}},{"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":4.659586},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.8354800000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586}},"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":6.452750000000001},"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":50.39499061460254,"highest":51.92913059864392,"medium":50.66565082784072,"none":48.59019041732298},"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":33.939977751428835,"score":33.939977751428835},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":45.079193043121215,"score":36.43737879826312},"GB2-03":{"attempts":3,"playable":51.030697618296664,"score":51.030697618296664},"GB2-04":{"attempts":3,"playable":48.72015787073858,"score":48.72015787073858},"GB2-05":{"attempts":3,"playable":68.70373295088216,"score":68.70373295088216},"GB2-06":{"attempts":3,"playable":41.54818149107941,"score":41.54818149107941},"GB2-07":{"attempts":3,"playable":63.27747842396685,"score":63.27747842396685},"GB2-08":{"attempts":3,"playable":59.502320012164716,"score":59.502320012164716}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":32.60183738521237,"score":32.60183738521237},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":51.85088546914854,"score":25.92544273457427},"GB2-03":{"attempts":1,"playable":57.30101192815999,"score":57.30101192815999},"GB2-04":{"attempts":1,"playable":66.75252041544007,"score":66.75252041544007},"GB2-05":{"attempts":1,"playable":47.41839642713655,"score":47.41839642713655},"GB2-06":{"attempts":1,"playable":52.13892655650203,"score":52.13892655650203},"GB2-07":{"attempts":1,"playable":78.06713479000248,"score":78.06713479000248},"GB2-08":{"attempts":1,"playable":55.22777455212362,"score":55.22777455212362}},"medium":{"GB2-01":{"attempts":1,"playable":42.401690774062445,"score":42.401690774062445},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":56.69963599400225,"score":56.69963599400225},"GB2-04":{"attempts":1,"playable":37.912645619152194,"score":37.912645619152194},"GB2-05":{"attempts":1,"playable":68.12667167289695,"score":68.12667167289695},"GB2-06":{"attempts":1,"playable":49.7358004353113,"score":49.7358004353113},"GB2-07":{"attempts":1,"playable":39.77034106847703,"score":39.77034106847703},"GB2-08":{"attempts":1,"playable":67.76788176289583,"score":67.76788176289583}},"none":{"GB2-01":{"attempts":1,"playable":26.816405095011675,"score":26.816405095011675},"GB2-02":{"attempts":1,"playable":40.47615436428729,"score":40.47615436428729},"GB2-03":{"attempts":1,"playable":39.091444932727754,"score":39.091444932727754},"GB2-04":{"attempts":1,"playable":41.49530757762349,"score":41.49530757762349},"GB2-05":{"attempts":1,"playable":90.56613075261299,"score":90.56613075261299},"GB2-06":{"attempts":1,"playable":22.7698174814249,"score":22.7698174814249},"GB2-07":{"attempts":1,"playable":71.99495941342104,"score":71.99495941342104},"GB2-08":{"attempts":1,"playable":55.51130372147471,"score":55.51130372147471}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:00Z","match_totals_all":{"draws":3042,"losses":4694,"wins":4528},"match_totals_tracks":{"highest":{"draws":824,"losses":1518,"wins":1746},"medium":{"draws":1066,"losses":1584,"wins":1438},"none":{"draws":1152,"losses":1592,"wins":1344}},"model_slug":"qwen-qwen3-8-max","official_rank_by_reasoning":{"highest":42,"medium":37,"none":24},"overall":{"max":90.56613075261299,"mean":50.39499061460254,"min":22.7698174814249},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.60183738521237,"GB2-02":51.85088546914854,"GB2-03":57.30101192815999,"GB2-04":66.75252041544007,"GB2-05":47.41839642713655,"GB2-06":52.13892655650203,"GB2-07":78.06713479000248,"GB2-08":55.22777455212362},"per_game_all":{"GB2-01":33.939977751428835,"GB2-02":45.079193043121215,"GB2-03":51.030697618296664,"GB2-04":48.72015787073858,"GB2-05":68.70373295088216,"GB2-06":41.54818149107941,"GB2-07":63.27747842396685,"GB2-08":59.502320012164716},"per_game_match_totals_all":{"GB2-01":{"draws":381,"losses":860,"wins":307},"GB2-02":{"draws":1074,"losses":278,"wins":88},"GB2-03":{"draws":302,"losses":632,"wins":548},"GB2-04":{"draws":837,"losses":372,"wins":285},"GB2-05":{"draws":0,"losses":517,"wins":1073},"GB2-06":{"draws":80,"losses":901,"wins":525},"GB2-07":{"draws":0,"losses":608,"wins":982},"GB2-08":{"draws":368,"losses":526,"wins":720}},"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":212,"wins":245},"GB2-04":{"draws":200,"losses":74,"wins":224},"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":108,"losses":206,"wins":224}},"medium":{"GB2-01":{"draws":167,"losses":224,"wins":125},"GB2-02":{"draws":380,"losses":92,"wins":8},"GB2-03":{"draws":99,"losses":184,"wins":211},"GB2-04":{"draws":326,"losses":154,"wins":18},"GB2-05":{"draws":0,"losses":178,"wins":352},"GB2-06":{"draws":23,"losses":263,"wins":216},"GB2-07":{"draws":0,"losses":333,"wins":197},"GB2-08":{"draws":71,"losses":156,"wins":311}},"none":{"GB2-01":{"draws":118,"losses":327,"wins":71},"GB2-02":{"draws":351,"losses":118,"wins":11},"GB2-03":{"draws":166,"losses":236,"wins":92},"GB2-04":{"draws":311,"losses":144,"wins":43},"GB2-05":{"draws":0,"losses":52,"wins":478},"GB2-06":{"draws":17,"losses":396,"wins":89},"GB2-07":{"draws":0,"losses":155,"wins":375},"GB2-08":{"draws":189,"losses":164,"wins":185}}},"per_game_raw_elo_all":{"GB2-01":1310.7155618522231,"GB2-02":1433.6918907629831,"GB2-03":1438.129961179285,"GB2-04":1467.6401078881354,"GB2-05":1787.0282905949516,"GB2-06":1291.3409277328883,"GB2-07":1641.036536769665,"GB2-08":1520.2519445395167},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1299.2040770825197,"GB2-02":1486.0903916748318,"GB2-03":1493.6968538760366,"GB2-04":1612.9224418696983,"GB2-05":1405.3282314315234,"GB2-06":1452.8427649003856,"GB2-07":1854.3283440765927,"GB2-08":1455.5812177639675},"medium":{"GB2-01":1396.6135919697008,"GB2-02":1416.9768592403107,"GB2-03":1488.0854136386583,"GB2-04":1380.8637969944034,"GB2-05":1682.4062467977706,"GB2-06":1415.4902771270913,"GB2-07":1320.018199828863,"GB2-08":1645.869336392291},"none":{"GB2-01":1236.3290165044486,"GB2-02":1398.0084213738069,"GB2-03":1332.6076160231596,"GB2-04":1409.1340848003047,"GB2-05":2273.3503935555614,"GB2-06":1005.6897411711877,"GB2-07":1748.7630664035394,"GB2-08":1459.3052794622922}},"per_game_tracks":{"highest":{"GB2-01":32.60183738521237,"GB2-02":51.85088546914854,"GB2-03":57.30101192815999,"GB2-04":66.75252041544007,"GB2-05":47.41839642713655,"GB2-06":52.13892655650203,"GB2-07":78.06713479000248,"GB2-08":55.22777455212362},"medium":{"GB2-01":42.401690774062445,"GB2-02":42.910539295927805,"GB2-03":56.69963599400225,"GB2-04":37.912645619152194,"GB2-05":68.12667167289695,"GB2-06":49.7358004353113,"GB2-07":39.77034106847703,"GB2-08":67.76788176289583},"none":{"GB2-01":26.816405095011675,"GB2-02":40.47615436428729,"GB2-03":39.091444932727754,"GB2-04":41.49530757762349,"GB2-05":90.56613075261299,"GB2-06":22.7698174814249,"GB2-07":71.99495941342104,"GB2-08":55.51130372147471}},"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":"2026-10-24T18:50:39Z","reasoning":{"highest":51.92913059864392,"medium":50.66565082784072,"none":48.59019041732298},"reasoning_agg":{"highest":{"max":78.06713479000248,"mean":51.92913059864392,"min":25.92544273457427},"medium":{"max":68.12667167289695,"mean":50.66565082784072,"min":37.912645619152194},"none":{"max":90.56613075261299,"mean":48.59019041732298,"min":22.7698174814249}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":3.338940181320943},"working_program_strength":{"all":51.4752173952098,"highest":55.16981094046571,"medium":50.66565082784072,"none":48.59019041732298}},{"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":0.030688899999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.025451050000000003}},"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":48.99673040150003,"highest":57.91646553492024,"medium":43.94225192948782,"none":45.13147374009205},"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":39.05265189796705,"score":39.05265189796705},"GB2-02":{"attempts":3,"playable":50.7509384246112,"score":50.7509384246112},"GB2-03":{"attempts":3,"playable":49.283684192055375,"score":49.283684192055375},"GB2-04":{"attempts":3,"playable":53.3247935991944,"score":53.3247935991944},"GB2-05":{"attempts":3,"playable":46.95227241794306,"score":46.95227241794306},"GB2-06":{"attempts":3,"playable":64.26530201669188,"score":64.26530201669188},"GB2-07":{"attempts":3,"playable":42.18301268298145,"score":42.18301268298145},"GB2-08":{"attempts":3,"playable":46.16118798055593,"score":46.16118798055593}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":29.81318081377865,"score":29.81318081377865},"GB2-02":{"attempts":1,"playable":63.15763310706362,"score":63.15763310706362},"GB2-03":{"attempts":1,"playable":50.213724619244374,"score":50.213724619244374},"GB2-04":{"attempts":1,"playable":65.07251021291862,"score":65.07251021291862},"GB2-05":{"attempts":1,"playable":53.930599354883036,"score":53.930599354883036},"GB2-06":{"attempts":1,"playable":85.72453199600761,"score":85.72453199600761},"GB2-07":{"attempts":1,"playable":39.204261853711586,"score":39.204261853711586},"GB2-08":{"attempts":1,"playable":76.2152823217545,"score":76.2152823217545}},"medium":{"GB2-01":{"attempts":1,"playable":39.04623118521132,"score":39.04623118521132},"GB2-02":{"attempts":1,"playable":44.91694128410355,"score":44.91694128410355},"GB2-03":{"attempts":1,"playable":51.541548933129086,"score":51.541548933129086},"GB2-04":{"attempts":1,"playable":50.44715644017009,"score":50.44715644017009},"GB2-05":{"attempts":1,"playable":50.870613777803655,"score":50.870613777803655},"GB2-06":{"attempts":1,"playable":34.887629105231156,"score":34.887629105231156},"GB2-07":{"attempts":1,"playable":53.84597448275231,"score":53.84597448275231},"GB2-08":{"attempts":1,"playable":25.981920227501416,"score":25.981920227501416}},"none":{"GB2-01":{"attempts":1,"playable":48.29854369491118,"score":48.29854369491118},"GB2-02":{"attempts":1,"playable":44.17824088266641,"score":44.17824088266641},"GB2-03":{"attempts":1,"playable":46.09577902379266,"score":46.09577902379266},"GB2-04":{"attempts":1,"playable":44.454714144494474,"score":44.454714144494474},"GB2-05":{"attempts":1,"playable":36.0556041211425,"score":36.0556041211425},"GB2-06":{"attempts":1,"playable":72.18374494883687,"score":72.18374494883687},"GB2-07":{"attempts":1,"playable":33.49880171248045,"score":33.49880171248045},"GB2-08":{"attempts":1,"playable":36.28636139241186,"score":36.28636139241186}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-10-26T01:39:32Z","match_totals_all":{"draws":3088,"losses":5014,"wins":4162},"match_totals_tracks":{"highest":{"draws":574,"losses":1528,"wins":1986},"medium":{"draws":1201,"losses":1795,"wins":1092},"none":{"draws":1313,"losses":1691,"wins":1084}},"model_slug":"gpt-6-luna","official_rank_by_reasoning":{"highest":35,"medium":48,"none":30},"overall":{"max":85.72453199600761,"mean":48.99673040150003,"min":25.981920227501416},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.81318081377865,"GB2-02":63.15763310706362,"GB2-03":50.213724619244374,"GB2-04":65.07251021291862,"GB2-05":53.930599354883036,"GB2-06":85.72453199600761,"GB2-07":39.204261853711586,"GB2-08":76.2152823217545},"per_game_all":{"GB2-01":39.05265189796705,"GB2-02":50.7509384246112,"GB2-03":49.283684192055375,"GB2-04":53.3247935991944,"GB2-05":46.95227241794306,"GB2-06":64.26530201669188,"GB2-07":42.18301268298145,"GB2-08":46.16118798055593},"per_game_match_totals_all":{"GB2-01":{"draws":470,"losses":738,"wins":340},"GB2-02":{"draws":1055,"losses":206,"wins":179},"GB2-03":{"draws":208,"losses":706,"wins":568},"GB2-04":{"draws":836,"losses":305,"wins":353},"GB2-05":{"draws":0,"losses":868,"wins":722},"GB2-06":{"draws":68,"losses":548,"wins":890},"GB2-07":{"draws":0,"losses":959,"wins":631},"GB2-08":{"draws":451,"losses":684,"wins":479}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":370,"wins":144},"GB2-02":{"draws":274,"losses":48,"wins":158},"GB2-03":{"draws":25,"losses":253,"wins":216},"GB2-04":{"draws":231,"losses":67,"wins":200},"GB2-05":{"draws":0,"losses":253,"wins":277},"GB2-06":{"draws":23,"losses":68,"wins":411},"GB2-07":{"draws":0,"losses":336,"wins":194},"GB2-08":{"draws":19,"losses":133,"wins":386}},"medium":{"GB2-01":{"draws":191,"losses":229,"wins":96},"GB2-02":{"draws":395,"losses":75,"wins":10},"GB2-03":{"draws":98,"losses":210,"wins":186},"GB2-04":{"draws":285,"losses":113,"wins":100},"GB2-05":{"draws":0,"losses":269,"wins":261},"GB2-06":{"draws":23,"losses":337,"wins":142},"GB2-07":{"draws":0,"losses":257,"wins":273},"GB2-08":{"draws":209,"losses":305,"wins":24}},"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":1362.1903857388995,"GB2-02":1479.12608037611,"GB2-03":1421.4580113348995,"GB2-04":1502.794339604694,"GB2-05":1398.038298673125,"GB2-06":1683.513372304132,"GB2-07":1349.5298729394106,"GB2-08":1391.1389341383365},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1269.6150612586878,"GB2-02":1578.0951464723453,"GB2-03":1429.5400486588471,"GB2-04":1597.8406699360814,"GB2-05":1486.5246097693077,"GB2-06":2066.4465470781247,"GB2-07":1312.896799124468,"GB2-08":1809.718456815865},"medium":{"GB2-01":1364.0759484250154,"GB2-02":1432.4938614744979,"GB2-03":1441.2903748728327,"GB2-04":1478.4201288045658,"GB2-05":1448.2292982110532,"GB2-06":1190.5791244340528,"GB2-07":1495.9754279304793,"GB2-08":1125.5275394174269},"none":{"GB2-01":1452.8801475329951,"GB2-02":1426.7892331814874,"GB2-03":1393.543610473019,"GB2-04":1432.122220073435,"GB2-05":1259.3609880390136,"GB2-06":1793.514445400218,"GB2-07":1239.717391763284,"GB2-08":1238.1708061817171}},"per_game_tracks":{"highest":{"GB2-01":29.81318081377865,"GB2-02":63.15763310706362,"GB2-03":50.213724619244374,"GB2-04":65.07251021291862,"GB2-05":53.930599354883036,"GB2-06":85.72453199600761,"GB2-07":39.204261853711586,"GB2-08":76.2152823217545},"medium":{"GB2-01":39.04623118521132,"GB2-02":44.91694128410355,"GB2-03":51.541548933129086,"GB2-04":50.44715644017009,"GB2-05":50.870613777803655,"GB2-06":34.887629105231156,"GB2-07":53.84597448275231,"GB2-08":25.981920227501416},"none":{"GB2-01":48.29854369491118,"GB2-02":44.17824088266641,"GB2-03":46.09577902379266,"GB2-04":44.454714144494474,"GB2-05":36.0556041211425,"GB2-06":72.18374494883687,"GB2-07":33.49880171248045,"GB2-08":36.28636139241186}},"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":"2026-10-24T18:53:50Z","reasoning":{"highest":57.91646553492024,"medium":43.94225192948782,"none":45.13147374009205},"reasoning_agg":{"highest":{"max":85.72453199600761,"mean":57.91646553492024,"min":29.81318081377865},"medium":{"max":53.84597448275231,"mean":43.94225192948782,"min":25.981920227501416},"none":{"max":72.18374494883687,"mean":45.13147374009205,"min":33.49880171248045}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.974213605432425},"working_program_strength":{"all":48.99673040150003,"highest":57.91646553492024,"medium":43.94225192948782,"none":45.13147374009205}},{"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":6.887695000000001},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.266665,"mean":0.20888499999999996,"median":0.20905875000000002,"min":0.14104,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-10-09":8},"run_count":16,"token_priced_attempt_count":16,"total":3.3421600000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.19681749999999998,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.42452},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.5886581249999999,"median":0.58241,"min":0.410635,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":4.709265},"historical-thinking-budget-setting":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":17},"run_count":16,"token_priced_attempt_count":17,"total":4.096070000000001}},"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":11.203785000000002},"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":48.88199851451484,"highest":49.96341810697696,"medium":48.79485459282151,"none":47.88772284374605},"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":47.28716580795276,"score":47.28716580795276},"GB2-02":{"attempts":5,"playable":44.01978269800272,"score":44.01978269800272},"GB2-03":{"attempts":4,"playable":47.350346721040445,"score":47.350346721040445},"GB2-04":{"attempts":5,"playable":43.68286333176297,"score":43.68286333176297},"GB2-05":{"attempts":5,"playable":46.55163473624464,"score":46.55163473624464},"GB2-06":{"attempts":5,"playable":48.758492343157336,"score":48.758492343157336},"GB2-07":{"attempts":5,"playable":45.71519328759636,"score":45.71519328759636},"GB2-08":{"attempts":5,"playable":67.69050919036148,"score":67.69050919036148}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":49.877453769583994,"score":49.877453769583994},"GB2-02":{"attempts":2,"playable":43.54454909622777,"score":43.54454909622777},"GB2-03":{"attempts":1,"playable":50.4183440046138,"score":50.4183440046138},"GB2-04":{"attempts":2,"playable":41.08627412387009,"score":41.08627412387009},"GB2-05":{"attempts":2,"playable":47.413182397033594,"score":47.413182397033594},"GB2-06":{"attempts":2,"playable":52.83041078869151,"score":52.83041078869151},"GB2-07":{"attempts":2,"playable":55.44459326150065,"score":55.44459326150065},"GB2-08":{"attempts":2,"playable":59.0925374142943,"score":59.0925374142943}},"medium":{"GB2-01":{"attempts":2,"playable":47.41658998607956,"score":47.41658998607956},"GB2-02":{"attempts":2,"playable":44.12544056635822,"score":44.12544056635822},"GB2-03":{"attempts":2,"playable":49.284040130739754,"score":49.284040130739754},"GB2-04":{"attempts":2,"playable":41.33906262976875,"score":41.33906262976875},"GB2-05":{"attempts":2,"playable":45.20746417918481,"score":45.20746417918481},"GB2-06":{"attempts":2,"playable":47.80546089179842,"score":47.80546089179842},"GB2-07":{"attempts":2,"playable":49.35319480930599,"score":49.35319480930599},"GB2-08":{"attempts":2,"playable":65.82758354933654,"score":65.82758354933654}},"none":{"GB2-01":{"attempts":1,"playable":44.56745366819474,"score":44.56745366819474},"GB2-02":{"attempts":1,"playable":44.38935843142217,"score":44.38935843142217},"GB2-03":{"attempts":1,"playable":42.34865602776778,"score":42.34865602776778},"GB2-04":{"attempts":1,"playable":48.62325324165005,"score":48.62325324165005},"GB2-05":{"attempts":1,"playable":47.03425763251552,"score":47.03425763251552},"GB2-06":{"attempts":1,"playable":45.63960534898207,"score":45.63960534898207},"GB2-07":{"attempts":1,"playable":32.34779179198245,"score":32.34779179198245},"GB2-08":{"attempts":1,"playable":78.1514066074536,"score":78.1514066074536}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:04Z","match_totals_all":{"draws":5275,"losses":7994,"wins":6677},"match_totals_tracks":{"highest":{"draws":1879,"losses":3079,"wins":2724},"medium":{"draws":2250,"losses":3261,"wins":2665},"none":{"draws":1146,"losses":1654,"wins":1288}},"model_slug":"claude-opus-4-5","official_rank_by_reasoning":{"highest":43,"medium":40,"none":27},"overall":{"max":78.1514066074536,"mean":48.88199851451484,"min":32.34779179198245},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.877453769583994,"GB2-02":43.54454909622777,"GB2-03":50.4183440046138,"GB2-04":41.08627412387009,"GB2-05":47.413182397033594,"GB2-06":52.83041078869151,"GB2-07":55.44459326150065,"GB2-08":59.0925374142943},"per_game_all":{"GB2-01":47.28716580795276,"GB2-02":44.01978269800272,"GB2-03":47.350346721040445,"GB2-04":43.68286333176297,"GB2-05":46.55163473624464,"GB2-06":48.758492343157336,"GB2-07":45.71519328759636,"GB2-08":67.69050919036148},"per_game_match_totals_all":{"GB2-01":{"draws":835,"losses":979,"wins":766},"GB2-02":{"draws":1881,"losses":445,"wins":74},"GB2-03":{"draws":482,"losses":867,"wins":627},"GB2-04":{"draws":1584,"losses":676,"wins":230},"GB2-05":{"draws":0,"losses":1460,"wins":1190},"GB2-06":{"draws":83,"losses":1339,"wins":1088},"GB2-07":{"draws":0,"losses":1431,"wins":1219},"GB2-08":{"draws":410,"losses":797,"wins":1483}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":229,"losses":422,"wins":381},"GB2-02":{"draws":758,"losses":179,"wins":23},"GB2-03":{"draws":75,"losses":227,"wins":192},"GB2-04":{"draws":586,"losses":310,"wins":100},"GB2-05":{"draws":0,"losses":574,"wins":486},"GB2-06":{"draws":35,"losses":499,"wins":470},"GB2-07":{"draws":0,"losses":496,"wins":564},"GB2-08":{"draws":196,"losses":372,"wins":508}},"medium":{"GB2-01":{"draws":371,"losses":378,"wins":283},"GB2-02":{"draws":753,"losses":176,"wins":31},"GB2-03":{"draws":236,"losses":422,"wins":330},"GB2-04":{"draws":673,"losses":264,"wins":59},"GB2-05":{"draws":0,"losses":597,"wins":463},"GB2-06":{"draws":37,"losses":550,"wins":417},"GB2-07":{"draws":0,"losses":563,"wins":497},"GB2-08":{"draws":180,"losses":311,"wins":585}},"none":{"GB2-01":{"draws":235,"losses":179,"wins":102},"GB2-02":{"draws":370,"losses":90,"wins":20},"GB2-03":{"draws":171,"losses":218,"wins":105},"GB2-04":{"draws":325,"losses":102,"wins":71},"GB2-05":{"draws":0,"losses":289,"wins":241},"GB2-06":{"draws":11,"losses":290,"wins":201},"GB2-07":{"draws":0,"losses":372,"wins":158},"GB2-08":{"draws":34,"losses":114,"wins":390}}},"per_game_raw_elo_all":{"GB2-01":1444.1296128667727,"GB2-02":1425.5629205411005,"GB2-03":1404.6107851234212,"GB2-04":1426.010515391854,"GB2-05":1394.4509425051522,"GB2-06":1401.081840077266,"GB2-07":1393.8727403748665,"GB2-08":1683.220967980028},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1470.8268423049703,"GB2-02":1421.8874099931968,"GB2-03":1431.3449224973967,"GB2-04":1405.928806533833,"GB2-05":1405.1114717748105,"GB2-06":1464.2909871166703,"GB2-07":1517.5515084068936,"GB2-08":1561.6661829942825},"medium":{"GB2-01":1444.2006033922216,"GB2-02":1426.3809569425227,"GB2-03":1421.464330205349,"GB2-04":1407.7967631802921,"GB2-05":1377.6915329808164,"GB2-06":1386.251083644552,"GB2-07":1439.545891039838,"GB2-08":1636.4720502284022},"none":{"GB2-01":1417.3613929031258,"GB2-02":1428.4203946875823,"GB2-03":1361.0231026675185,"GB2-04":1464.3059764614363,"GB2-05":1400.5498227598296,"GB2-06":1352.7034494705758,"GB2-07":1224.5208216778688,"GB2-08":1851.5246707173994}},"per_game_tracks":{"highest":{"GB2-01":49.877453769583994,"GB2-02":43.54454909622777,"GB2-03":50.4183440046138,"GB2-04":41.08627412387009,"GB2-05":47.413182397033594,"GB2-06":52.83041078869151,"GB2-07":55.44459326150065,"GB2-08":59.0925374142943},"medium":{"GB2-01":47.41658998607956,"GB2-02":44.12544056635822,"GB2-03":49.284040130739754,"GB2-04":41.33906262976875,"GB2-05":45.20746417918481,"GB2-06":47.80546089179842,"GB2-07":49.35319480930599,"GB2-08":65.82758354933654},"none":{"GB2-01":44.56745366819474,"GB2-02":44.38935843142217,"GB2-03":42.34865602776778,"GB2-04":48.62325324165005,"GB2-05":47.03425763251552,"GB2-06":45.63960534898207,"GB2-07":32.34779179198245,"GB2-08":78.1514066074536}},"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":1,"rank_movement_baseline_at":"2026-10-24T19:17:57Z","reasoning":{"highest":49.96341810697696,"medium":48.79485459282151,"none":47.88772284374605},"reasoning_agg":{"highest":{"max":59.0925374142943,"mean":49.96341810697696,"min":41.08627412387009},"medium":{"max":65.82758354933654,"mean":48.79485459282151,"min":41.33906262976875},"none":{"max":78.1514066074536,"mean":47.88772284374605,"min":32.34779179198245}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"reasoning_settings":{"balanced":"medium","intensive":"high"},"score_diagnostics":{"reasoning_variance":2.0756952632309122},"working_program_strength":{"all":48.88199851451484,"highest":49.96341810697696,"medium":48.79485459282151,"none":47.88772284374605}},{"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":0.6080262000000001}},"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":2.3233295999999997},"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":6.6471018000000015},"codegen_latency_ms":{"attempt_count":35,"max_ms":754602,"mean_ms":294629.0833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":415982,"mean_ms":310768.0,"min_ms":108461,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":41670,"output_mean":16512.916666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":41670,"output_mean":28939.0,"output_min":14510,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":48.768867551510986,"highest":45.117441870615195,"medium":49.57130649717783,"none":51.61785428673993},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[262144],"finish_reason_observations":35,"finish_reasons":["length","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":10,"provider_post_attempts":13,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[262144],"total_output_tokens":396310,"total_reasoning_output_tokens":285325,"total_visible_output_tokens":110985,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":42.45994842849361,"score":42.45994842849361},"GB2-02":{"attempts":3,"playable":42.134820181371204,"score":42.134820181371204},"GB2-03":{"attempts":3,"playable":64.49684846206823,"score":64.49684846206823},"GB2-04":{"attempts":3,"playable":48.75343845898933,"score":48.75343845898933},"GB2-05":{"attempts":3,"playable":56.39869895365223,"score":56.39869895365223},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":51.9133957045862,"score":34.608930469724136},"GB2-07":{"attempts":3,"playable":48.91728823039659,"score":48.91728823039659},"GB2-08":{"attempts":3,"playable":52.380967227392496,"score":52.380967227392496}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":6.581556640181834,"score":6.581556640181834},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":77.81741844741386,"score":77.81741844741386},"GB2-04":{"attempts":1,"playable":52.77178646458028,"score":52.77178646458028},"GB2-05":{"attempts":1,"playable":62.29322062554687,"score":62.29322062554687},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":93.6755483450511,"score":93.6755483450511},"GB2-08":{"attempts":1,"playable":24.889465146219823,"score":24.889465146219823}},"medium":{"GB2-01":{"attempts":1,"playable":69.07398625142943,"score":69.07398625142943},"GB2-02":{"attempts":1,"playable":41.4294472413882,"score":41.4294472413882},"GB2-03":{"attempts":1,"playable":66.17653557525448,"score":66.17653557525448},"GB2-04":{"attempts":1,"playable":47.60829699628472,"score":47.60829699628472},"GB2-05":{"attempts":1,"playable":51.63642816425957,"score":51.63642816425957},"GB2-06":{"attempts":1,"playable":56.0317286642899,"score":56.0317286642899},"GB2-07":{"attempts":1,"playable":25.17264569142056,"score":25.17264569142056},"GB2-08":{"attempts":1,"playable":39.44138339309575,"score":39.44138339309575}},"none":{"GB2-01":{"attempts":1,"playable":51.72430239386958,"score":51.72430239386958},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":49.49659136353635,"score":49.49659136353635},"GB2-04":{"attempts":1,"playable":45.880231916103,"score":45.880231916103},"GB2-05":{"attempts":1,"playable":55.266448071150265,"score":55.266448071150265},"GB2-06":{"attempts":1,"playable":47.7950627448825,"score":47.7950627448825},"GB2-07":{"attempts":1,"playable":27.903670654718134,"score":27.903670654718134},"GB2-08":{"attempts":1,"playable":92.81205314286193,"score":92.81205314286193}}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:49Z","match_totals_all":{"draws":2782,"losses":4631,"wins":4349},"match_totals_tracks":{"highest":{"draws":806,"losses":1387,"wins":1393},"medium":{"draws":1003,"losses":1670,"wins":1415},"none":{"draws":973,"losses":1574,"wins":1541}},"model_slug":"moonshotai-kimi-k3","official_rank_by_reasoning":{"highest":47,"medium":39,"none":18},"overall":{"max":93.6755483450511,"mean":48.768867551510986,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":6.581556640181834,"GB2-02":42.910539295927805,"GB2-03":77.81741844741386,"GB2-04":52.77178646458028,"GB2-05":62.29322062554687,"GB2-07":93.6755483450511,"GB2-08":24.889465146219823},"per_game_all":{"GB2-01":42.45994842849361,"GB2-02":42.134820181371204,"GB2-03":64.49684846206823,"GB2-04":48.75343845898933,"GB2-05":56.39869895365223,"GB2-07":48.91728823039659,"GB2-08":52.380967227392496},"per_game_match_totals_all":{"GB2-01":{"draws":359,"losses":737,"wins":452},"GB2-02":{"draws":1064,"losses":325,"wins":51},"GB2-03":{"draws":197,"losses":480,"wins":805},"GB2-04":{"draws":811,"losses":386,"wins":297},"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":305,"losses":646,"wins":663}},"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":352,"losses":113,"wins":15},"GB2-03":{"draws":73,"losses":149,"wins":272},"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":125,"losses":279,"wins":134}},"none":{"GB2-01":{"draws":262,"losses":129,"wins":125},"GB2-02":{"draws":374,"losses":99,"wins":7},"GB2-03":{"draws":92,"losses":223,"wins":179},"GB2-04":{"draws":226,"losses":165,"wins":107},"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":42,"wins":496}}},"per_game_raw_elo_all":{"GB2-01":1346.1143716768072,"GB2-02":1410.9479673438561,"GB2-03":1578.8888791789368,"GB2-04":1465.3759469880242,"GB2-05":1519.1802384305677,"GB2-07":1548.3650783957166,"GB2-08":1548.490257533985},"per_game_raw_elo_tracks":{"highest":{"GB2-01":891.7115910686188,"GB2-02":1416.9768592403107,"GB2-03":1730.9112995341034,"GB2-04":1496.5224941560548,"GB2-05":1596.3306522276794,"GB2-07":2357.1025756104495,"GB2-08":1112.8855837558451},"medium":{"GB2-01":1661.1356060768376,"GB2-02":1405.460585942165,"GB2-03":1582.5258010461962,"GB2-04":1456.4699533843047,"GB2-05":1457.771347890552,"GB2-06":1514.4964373543173,"GB2-07":1124.2332510074136,"GB2-08":1271.9505806055085},"none":{"GB2-01":1485.4959178849647,"GB2-02":1410.4064568490924,"GB2-03":1423.229536956511,"GB2-04":1443.1353934237127,"GB2-05":1503.4387151734718,"GB2-06":1385.625583413921,"GB2-07":1163.7594085692872,"GB2-08":2260.6346082406017}},"per_game_tracks":{"highest":{"GB2-01":6.581556640181834,"GB2-02":42.910539295927805,"GB2-03":77.81741844741386,"GB2-04":52.77178646458028,"GB2-05":62.29322062554687,"GB2-07":93.6755483450511,"GB2-08":24.889465146219823},"medium":{"GB2-01":69.07398625142943,"GB2-02":41.4294472413882,"GB2-03":66.17653557525448,"GB2-04":47.60829699628472,"GB2-05":51.63642816425957,"GB2-06":56.0317286642899,"GB2-07":25.17264569142056,"GB2-08":39.44138339309575},"none":{"GB2-01":51.72430239386958,"GB2-02":42.06447400679762,"GB2-03":49.49659136353635,"GB2-04":45.880231916103,"GB2-05":55.266448071150265,"GB2-06":47.7950627448825,"GB2-07":27.903670654718134,"GB2-08":92.81205314286193}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":2,"worked_first_time":21,"working":23},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:14:14Z","reasoning":{"highest":45.117441870615195,"medium":49.57130649717783,"none":51.61785428673993},"reasoning_agg":{"highest":{"max":93.6755483450511,"mean":45.117441870615195,"min":0.0},"medium":{"max":69.07398625142943,"mean":49.57130649717783,"min":25.17264569142056},"none":{"max":92.81205314286193,"mean":51.61785428673993,"min":27.903670654718134}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.500412416124732},"working_program_strength":{"all":50.917317164397424,"highest":51.56279070927451,"medium":49.57130649717783,"none":51.61785428673993}},{"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":0.49337000000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.826309999999999},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":48.113887037318364,"highest":56.542942439794004,"medium":44.0220882198153,"none":43.7766304523458},"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":53.097489202386434,"score":53.097489202386434},"GB2-02":{"attempts":3,"playable":42.91031926256279,"score":42.91031926256279},"GB2-03":{"attempts":3,"playable":52.944088155510975,"score":52.944088155510975},"GB2-04":{"attempts":3,"playable":47.36142387062464,"score":47.36142387062464},"GB2-05":{"attempts":3,"playable":40.34383703427311,"score":40.34383703427311},"GB2-06":{"attempts":3,"playable":38.90758686910235,"score":38.90758686910235},"GB2-07":{"attempts":3,"playable":51.43130291656032,"score":51.43130291656032},"GB2-08":{"attempts":3,"playable":57.91504898752631,"score":57.91504898752631}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.77650188114862,"score":63.77650188114862},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":60.29017029445606,"score":60.29017029445606},"GB2-04":{"attempts":1,"playable":53.17536482756301,"score":53.17536482756301},"GB2-05":{"attempts":1,"playable":54.69416900833654,"score":54.69416900833654},"GB2-06":{"attempts":1,"playable":28.7088915902937,"score":28.7088915902937},"GB2-07":{"attempts":1,"playable":68.14286552155062,"score":68.14286552155062},"GB2-08":{"attempts":1,"playable":81.4911023882058,"score":81.4911023882058}},"medium":{"GB2-01":{"attempts":1,"playable":46.04171899042915,"score":46.04171899042915},"GB2-02":{"attempts":1,"playable":43.65023818652617,"score":43.65023818652617},"GB2-03":{"attempts":1,"playable":42.24402295900123,"score":42.24402295900123},"GB2-04":{"attempts":1,"playable":45.16773876484072,"score":45.16773876484072},"GB2-05":{"attempts":1,"playable":42.99521653630814,"score":42.99521653630814},"GB2-06":{"attempts":1,"playable":39.63478336827751,"score":39.63478336827751},"GB2-07":{"attempts":1,"playable":50.74131656363051,"score":50.74131656363051},"GB2-08":{"attempts":1,"playable":41.70167038950902,"score":41.70167038950902}},"none":{"GB2-01":{"attempts":1,"playable":49.474246735581524,"score":49.474246735581524},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"GB2-03":{"attempts":1,"playable":56.29807121307564,"score":56.29807121307564},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":1,"playable":23.342125558174647,"score":23.342125558174647},"GB2-06":{"attempts":1,"playable":48.379085648735845,"score":48.379085648735845},"GB2-07":{"attempts":1,"playable":35.40972666449984,"score":35.40972666449984},"GB2-08":{"attempts":1,"playable":50.55237418486409,"score":50.55237418486409}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:41Z","match_totals_all":{"draws":3061,"losses":5129,"wins":4074},"match_totals_tracks":{"highest":{"draws":836,"losses":1438,"wins":1814},"medium":{"draws":1159,"losses":1813,"wins":1116},"none":{"draws":1066,"losses":1878,"wins":1144}},"model_slug":"claude-sonnet-5","official_rank_by_reasoning":{"highest":37,"medium":47,"none":32},"overall":{"max":81.4911023882058,"mean":48.113887037318364,"min":23.342125558174647},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.77650188114862,"GB2-02":42.06447400679762,"GB2-03":60.29017029445606,"GB2-04":53.17536482756301,"GB2-05":54.69416900833654,"GB2-06":28.7088915902937,"GB2-07":68.14286552155062,"GB2-08":81.4911023882058},"per_game_all":{"GB2-01":53.097489202386434,"GB2-02":42.91031926256279,"GB2-03":52.944088155510975,"GB2-04":47.36142387062464,"GB2-05":40.34383703427311,"GB2-06":38.90758686910235,"GB2-07":51.43130291656032,"GB2-08":57.91504898752631},"per_game_match_totals_all":{"GB2-01":{"draws":249,"losses":634,"wins":665},"GB2-02":{"draws":1134,"losses":279,"wins":27},"GB2-03":{"draws":328,"losses":591,"wins":563},"GB2-04":{"draws":924,"losses":350,"wins":220},"GB2-05":{"draws":0,"losses":971,"wins":619},"GB2-06":{"draws":29,"losses":970,"wins":507},"GB2-07":{"draws":0,"losses":807,"wins":783},"GB2-08":{"draws":397,"losses":527,"wins":690}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":54,"losses":171,"wins":291},"GB2-02":{"draws":376,"losses":98,"wins":6},"GB2-03":{"draws":105,"losses":163,"wins":226},"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":109,"wins":425}},"medium":{"GB2-01":{"draws":106,"losses":236,"wins":174},"GB2-02":{"draws":385,"losses":86,"wins":9},"GB2-03":{"draws":120,"losses":244,"wins":130},"GB2-04":{"draws":317,"losses":123,"wins":58},"GB2-05":{"draws":0,"losses":310,"wins":220},"GB2-06":{"draws":11,"losses":320,"wins":171},"GB2-07":{"draws":0,"losses":274,"wins":256},"GB2-08":{"draws":220,"losses":220,"wins":98}},"none":{"GB2-01":{"draws":89,"losses":227,"wins":200},"GB2-02":{"draws":373,"losses":95,"wins":12},"GB2-03":{"draws":103,"losses":184,"wins":207},"GB2-04":{"draws":317,"losses":130,"wins":51},"GB2-05":{"draws":0,"losses":412,"wins":118},"GB2-06":{"draws":11,"losses":276,"wins":215},"GB2-07":{"draws":0,"losses":356,"wins":174},"GB2-08":{"draws":173,"losses":198,"wins":167}}},"per_game_raw_elo_all":{"GB2-01":1499.9307303075439,"GB2-02":1416.9697395295668,"GB2-03":1455.5669041076596,"GB2-04":1454.6386446475726,"GB2-05":1304.8464956373725,"GB2-06":1251.3227269661413,"GB2-07":1470.3307991229647,"GB2-08":1540.345254637601},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1604.3168595739435,"GB2-02":1410.4064568490924,"GB2-03":1522.2270700346448,"GB2-04":1499.683547576248,"GB2-05":1496.173617861985,"GB2-06":1097.486682822946,"GB2-07":1689.6331172820478,"GB2-08":1927.6696732643722},"medium":{"GB2-01":1431.4161659394651,"GB2-02":1422.7063547595108,"GB2-03":1360.1140975977219,"GB2-04":1437.633681601274,"GB2-05":1349.9249968891866,"GB2-06":1261.893347840442,"GB2-07":1456.7836957679392,"GB2-08":1296.3862518904152},"none":{"GB2-01":1464.0591654092234,"GB2-02":1417.796406980097,"GB2-03":1484.3595446906118,"GB2-04":1426.598704765196,"GB2-05":1068.4408721609466,"GB2-06":1394.5881502350358,"GB2-07":1264.5755843189065,"GB2-08":1396.9798387580156}},"per_game_tracks":{"highest":{"GB2-01":63.77650188114862,"GB2-02":42.06447400679762,"GB2-03":60.29017029445606,"GB2-04":53.17536482756301,"GB2-05":54.69416900833654,"GB2-06":28.7088915902937,"GB2-07":68.14286552155062,"GB2-08":81.4911023882058},"medium":{"GB2-01":46.04171899042915,"GB2-02":43.65023818652617,"GB2-03":42.24402295900123,"GB2-04":45.16773876484072,"GB2-05":42.99521653630814,"GB2-06":39.63478336827751,"GB2-07":50.74131656363051,"GB2-08":41.70167038950902},"none":{"GB2-01":49.474246735581524,"GB2-02":43.016245594364584,"GB2-03":56.29807121307564,"GB2-04":43.74116801947021,"GB2-05":23.342125558174647,"GB2-06":48.379085648735845,"GB2-07":35.40972666449984,"GB2-08":50.55237418486409}},"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":"2026-10-24T19:18:32Z","reasoning":{"highest":56.542942439794004,"medium":44.0220882198153,"none":43.7766304523458},"reasoning_agg":{"highest":{"max":81.4911023882058,"mean":56.542942439794004,"min":28.7088915902937},"medium":{"max":50.74131656363051,"mean":44.0220882198153,"min":39.63478336827751},"none":{"max":56.29807121307564,"mean":43.7766304523458,"min":23.342125558174647}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.766311987448205},"working_program_strength":{"all":48.113887037318364,"highest":56.542942439794004,"medium":44.0220882198153,"none":43.7766304523458}},{"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":0.37461715},"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":47.818711234817805,"highest":59.55849753741169,"medium":44.97318802959071,"none":38.92444813745101},"first_seen_at":null,"game_gaps":{"highest":{"GB2-04":"infra_excluded","GB2-05":"infra_excluded","GB2-07":"infra_excluded"},"medium":{"GB2-01":"infra_excluded","GB2-03":"failed","GB2-04":"infra_excluded","GB2-05":"infra_excluded","GB2-06":"infra_excluded"}},"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":42.474188829410735,"score":42.474188829410735},"GB2-02":{"attempts":3,"playable":44.423290865053616,"score":44.423290865053616},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":47.92005544149431,"score":31.946703627662874},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":25.26458038695291,"score":25.26458038695291},"GB2-06":{"attempts":2,"playable":73.26054566875459,"score":73.26054566875459},"GB2-07":{"attempts":2,"playable":55.69663845552597,"score":55.69663845552597},"GB2-08":{"attempts":3,"playable":50.388693278788914,"score":50.388693278788914}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":50.06164504511567,"score":50.06164504511567},"GB2-02":{"attempts":1,"playable":44.17824088266641,"score":44.17824088266641},"GB2-03":{"attempts":1,"playable":62.16771778328458,"score":62.16771778328458},"GB2-06":{"attempts":1,"playable":79.63955354616625,"score":79.63955354616625},"GB2-08":{"attempts":1,"playable":61.74533042982549,"score":61.74533042982549}},"medium":{"GB2-02":{"attempts":1,"playable":46.39253976872338,"score":46.39253976872338},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":77.8944751985715,"score":77.8944751985715},"GB2-08":{"attempts":1,"playable":55.605737151067956,"score":55.605737151067956}},"none":{"GB2-01":{"attempts":1,"playable":34.886732613705796,"score":34.886732613705796},"GB2-02":{"attempts":1,"playable":42.69909194377107,"score":42.69909194377107},"GB2-03":{"attempts":1,"playable":33.672393099704045,"score":33.672393099704045},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":25.26458038695291,"score":25.26458038695291},"GB2-06":{"attempts":1,"playable":66.88153779134291,"score":66.88153779134291},"GB2-07":{"attempts":1,"playable":33.49880171248045,"score":33.49880171248045},"GB2-08":{"attempts":1,"playable":33.81501225547331,"score":33.81501225547331}}},"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":79.63955354616625,"mean":47.818711234817805,"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":50.06164504511567,"GB2-02":44.17824088266641,"GB2-03":62.16771778328458,"GB2-06":79.63955354616625,"GB2-08":61.74533042982549},"per_game_all":{"GB2-02":44.423290865053616,"GB2-08":50.388693278788914},"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":1428.6662521783328,"GB2-08":1406.5451992557666},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1469.648192944957,"GB2-02":1426.7892331814874,"GB2-03":1540.786143196647,"GB2-06":1936.917844233639,"GB2-08":1547.3434166557136},"medium":{"GB2-02":1443.8728795931909,"GB2-07":1851.0318162291715,"GB2-08":1460.5504410901856},"none":{"GB2-01":1322.6739551929347,"GB2-02":1415.3366437603197,"GB2-03":1284.210955983745,"GB2-04":1402.7331723403474,"GB2-05":1100.2265623820854,"GB2-06":1697.2863822581166,"GB2-07":1239.717391763284,"GB2-08":1211.7417400214008}},"per_game_tracks":{"highest":{"GB2-01":50.06164504511567,"GB2-02":44.17824088266641,"GB2-03":62.16771778328458,"GB2-06":79.63955354616625,"GB2-08":61.74533042982549},"medium":{"GB2-02":46.39253976872338,"GB2-07":77.8944751985715,"GB2-08":55.605737151067956},"none":{"GB2-01":34.886732613705796,"GB2-02":42.69909194377107,"GB2-03":33.672393099704045,"GB2-04":40.67743529617756,"GB2-05":25.26458038695291,"GB2-06":66.88153779134291,"GB2-07":33.49880171248045,"GB2-08":33.81501225547331}},"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":59.55849753741169,"medium":44.97318802959071,"none":38.92444813745101},"reasoning_agg":{"highest":{"max":79.63955354616625,"mean":59.55849753741169,"min":44.17824088266641},"medium":{"max":77.8944751985715,"mean":44.97318802959071,"min":0.0},"none":{"max":66.88153779134291,"mean":38.92444813745101,"min":25.26458038695291}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":20.63404939996068},"working_program_strength":{"all":52.815732126994554,"highest":59.55849753741169,"medium":59.96425070612094,"none":38.92444813745101}},{"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":0.7756987500000001},"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":0.6137425},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.0672337499999998}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.45800250000000003,"mean":0.18569479166666666,"median":0.091314375,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":28},"run_count":24,"token_priced_attempt_count":28,"total":4.456675000000001},"codegen_output_tokens":{"attempt_count":28,"output_max":28998,"output_mean":10500.666666666666,"output_min":2419,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":28998,"output_mean":23512.0,"output_min":18631,"run_count":8},"medium":{"attempt_count":9,"output_max":6917,"output_mean":4677.5,"output_min":3936,"run_count":8},"none":{"attempt_count":9,"output_max":6065,"output_mean":3312.5,"output_min":2419,"run_count":8}},"display_name":"GPT-5.6 Terra","economics":{"all":47.22570365069927,"highest":54.76266822043014,"medium":50.97355583210514,"none":35.940886899562535},"first_seen_at":null,"game_gaps":{"none":{"GB2-05":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"total_output_tokens":252016,"total_reasoning_output_tokens":152800,"total_visible_output_tokens":99216,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":67.9879135416809,"score":67.9879135416809},"GB2-02":{"attempts":3,"playable":50.03946358562255,"score":50.03946358562255},"GB2-03":{"attempts":3,"playable":34.807584793612236,"score":34.807584793612236},"GB2-04":{"attempts":3,"playable":43.53679970301437,"score":43.53679970301437},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.980135114635516,"score":37.986756743090346},"GB2-06":{"attempts":3,"playable":53.35798524194211,"score":53.35798524194211},"GB2-07":{"attempts":3,"playable":44.932025896483346,"score":44.932025896483346},"GB2-08":{"attempts":3,"playable":45.157099700148336,"score":45.157099700148336}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":72.1384361760712,"score":72.1384361760712},"GB2-02":{"attempts":1,"playable":59.65269552895921,"score":59.65269552895921},"GB2-03":{"attempts":1,"playable":36.76296797467189,"score":36.76296797467189},"GB2-04":{"attempts":1,"playable":42.31255022830733,"score":42.31255022830733},"GB2-05":{"attempts":1,"playable":55.64777346044759,"score":55.64777346044759},"GB2-06":{"attempts":1,"playable":80.7302675590266,"score":80.7302675590266},"GB2-07":{"attempts":1,"playable":44.27016262800866,"score":44.27016262800866},"GB2-08":{"attempts":1,"playable":46.586492207948666,"score":46.586492207948666}},"medium":{"GB2-01":{"attempts":1,"playable":77.27030124028664,"score":77.27030124028664},"GB2-02":{"attempts":1,"playable":46.181889573237264,"score":46.181889573237264},"GB2-03":{"attempts":1,"playable":34.41556090723444,"score":34.41556090723444},"GB2-04":{"attempts":1,"playable":43.843134736241275,"score":43.843134736241275},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":41.85962447765607,"score":41.85962447765607},"GB2-07":{"attempts":1,"playable":60.87709979353989,"score":60.87709979353989},"GB2-08":{"attempts":1,"playable":45.02833915982205,"score":45.02833915982205}},"none":{"GB2-01":{"attempts":1,"playable":54.55500320868485,"score":54.55500320868485},"GB2-02":{"attempts":1,"playable":44.2838056546712,"score":44.2838056546712},"GB2-03":{"attempts":1,"playable":33.244225498930376,"score":33.244225498930376},"GB2-04":{"attempts":1,"playable":44.454714144494474,"score":44.454714144494474},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":37.48406368914366,"score":37.48406368914366},"GB2-07":{"attempts":1,"playable":29.648815267901497,"score":29.648815267901497},"GB2-08":{"attempts":1,"playable":43.8564677326743,"score":43.8564677326743}}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:15Z","match_totals_all":{"draws":3246,"losses":4617,"wins":3872},"match_totals_tracks":{"highest":{"draws":986,"losses":1454,"wins":1648},"medium":{"draws":1035,"losses":1582,"wins":1472},"none":{"draws":1225,"losses":1581,"wins":752}},"model_slug":"gpt-5-6-terra","official_rank_by_reasoning":{"highest":41,"medium":36,"none":51},"overall":{"max":80.7302675590266,"mean":47.22570365069927,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":42,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.1384361760712,"GB2-02":59.65269552895921,"GB2-03":36.76296797467189,"GB2-04":42.31255022830733,"GB2-05":55.64777346044759,"GB2-06":80.7302675590266,"GB2-07":44.27016262800866,"GB2-08":46.586492207948666},"per_game_all":{"GB2-01":67.9879135416809,"GB2-02":50.03946358562255,"GB2-03":34.807584793612236,"GB2-04":43.53679970301437,"GB2-06":53.35798524194211,"GB2-07":44.932025896483346,"GB2-08":45.157099700148336},"per_game_match_totals_all":{"GB2-01":{"draws":243,"losses":406,"wins":899},"GB2-02":{"draws":1038,"losses":225,"wins":177},"GB2-03":{"draws":547,"losses":745,"wins":191},"GB2-04":{"draws":905,"losses":416,"wins":173},"GB2-05":{"draws":0,"losses":474,"wins":586},"GB2-06":{"draws":71,"losses":722,"wins":713},"GB2-07":{"draws":0,"losses":913,"wins":677},"GB2-08":{"draws":442,"losses":716,"wins":456}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":71,"losses":119,"wins":326},"GB2-02":{"draws":266,"losses":69,"wins":145},"GB2-03":{"draws":152,"losses":254,"wins":88},"GB2-04":{"draws":325,"losses":133,"wins":40},"GB2-05":{"draws":0,"losses":244,"wins":286},"GB2-06":{"draws":30,"losses":92,"wins":380},"GB2-07":{"draws":0,"losses":309,"wins":221},"GB2-08":{"draws":142,"losses":234,"wins":162}},"medium":{"GB2-01":{"draws":3,"losses":126,"wins":387},"GB2-02":{"draws":383,"losses":75,"wins":22},"GB2-03":{"draws":226,"losses":229,"wins":40},"GB2-04":{"draws":252,"losses":162,"wins":84},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":39,"losses":295,"wins":168},"GB2-07":{"draws":0,"losses":218,"wins":312},"GB2-08":{"draws":132,"losses":247,"wins":159}},"none":{"GB2-01":{"draws":169,"losses":161,"wins":186},"GB2-02":{"draws":389,"losses":81,"wins":10},"GB2-03":{"draws":169,"losses":262,"wins":63},"GB2-04":{"draws":328,"losses":121,"wins":49},"GB2-06":{"draws":2,"losses":335,"wins":165},"GB2-07":{"draws":0,"losses":386,"wins":144},"GB2-08":{"draws":168,"losses":235,"wins":135}}},"per_game_raw_elo_all":{"GB2-01":1656.4815946467836,"GB2-02":1472.774338889841,"GB2-03":1294.4366892281562,"GB2-04":1425.0056304769769,"GB2-06":1494.6514015459413,"GB2-07":1383.9538789638573,"GB2-08":1334.5675830407115},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1696.2630679006993,"GB2-02":1548.468862664743,"GB2-03":1312.0448754871325,"GB2-04":1415.5060664905627,"GB2-05":1508.297274680871,"GB2-06":1958.97000748353,"GB2-07":1376.1769439899874,"GB2-08":1350.632336171844},"medium":{"GB2-01":1760.5397602148364,"GB2-02":1442.2492056504484,"GB2-03":1290.9738286445238,"GB2-04":1427.3886048669326,"GB2-05":1542.7288818013874,"GB2-06":1295.422775566106,"GB2-07":1587.6150802649668,"GB2-08":1333.0531061045713},"none":{"GB2-01":1512.641955824815,"GB2-02":1427.6049483543318,"GB2-03":1280.2913635528125,"GB2-04":1432.122220073435,"GB2-06":1229.561421588188,"GB2-07":1188.069612636617,"GB2-08":1320.0173068457193}},"per_game_tracks":{"highest":{"GB2-01":72.1384361760712,"GB2-02":59.65269552895921,"GB2-03":36.76296797467189,"GB2-04":42.31255022830733,"GB2-05":55.64777346044759,"GB2-06":80.7302675590266,"GB2-07":44.27016262800866,"GB2-08":46.586492207948666},"medium":{"GB2-01":77.27030124028664,"GB2-02":46.181889573237264,"GB2-03":34.41556090723444,"GB2-04":43.843134736241275,"GB2-05":58.31249676882345,"GB2-06":41.85962447765607,"GB2-07":60.87709979353989,"GB2-08":45.02833915982205},"none":{"GB2-01":54.55500320868485,"GB2-02":44.2838056546712,"GB2-03":33.244225498930376,"GB2-04":44.454714144494474,"GB2-06":37.48406368914366,"GB2-07":29.648815267901497,"GB2-08":43.8564677326743}},"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":"2026-10-24T19:15:32Z","reasoning":{"highest":54.76266822043014,"medium":50.97355583210514,"none":35.940886899562535},"reasoning_agg":{"highest":{"max":80.7302675590266,"mean":54.76266822043014,"min":36.76296797467189},"medium":{"max":77.27030124028664,"mean":50.97355583210514,"min":34.41556090723444},"none":{"max":54.55500320868485,"mean":35.940886899562535,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":18.821781320867608},"working_program_strength":{"all":48.93717445544035,"highest":54.76266822043014,"medium":50.97355583210514,"none":41.075299313785756}},{"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":0.36704}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.642066},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704000000000003},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.592372}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.15006158333333333,"median":0.080065,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":3.6014779999999997},"codegen_latency_ms":{"attempt_count":28,"max_ms":255692,"mean_ms":76920.70833333333,"min_ms":12384,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":255692,"mean_ms":175619.75,"min_ms":52003,"run_count":8},"medium":{"attempt_count":8,"max_ms":58005,"mean_ms":37933.625,"min_ms":21700,"run_count":8},"none":{"attempt_count":9,"max_ms":20748,"mean_ms":17208.75,"min_ms":12384,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":36035,"output_mean":10826.541666666666,"output_min":1554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":36035,"output_mean":24993.125,"output_min":6631,"run_count":8},"medium":{"attempt_count":8,"output_max":7812,"output_mean":5238.375,"output_min":2903,"run_count":8},"none":{"attempt_count":9,"output_max":3115,"output_mean":2248.125,"output_min":1554,"run_count":8}},"display_name":"Gemini 3.1 Pro Preview","economics":{"all":46.238891376069596,"highest":66.23066407825534,"medium":42.25377008914947,"none":30.23223996080397},"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":50.14465808232043,"score":50.14465808232043},"GB2-02":{"attempts":3,"playable":43.57936484085988,"score":43.57936484085988},"GB2-03":{"attempts":3,"playable":53.934586152255015,"score":53.934586152255015},"GB2-04":{"attempts":3,"playable":56.417089976376325,"score":56.417089976376325},"GB2-05":{"attempts":3,"playable":39.60273081716763,"score":39.60273081716763},"GB2-06":{"attempts":3,"playable":21.315492922941452,"score":21.315492922941452},"GB2-07":{"attempts":3,"playable":56.82168142023283,"score":56.82168142023283},"GB2-08":{"attempts":3,"playable":48.095526796403156,"score":48.095526796403156}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.42618707235431,"score":74.42618707235431},"GB2-02":{"attempts":1,"playable":43.33329461578827,"score":43.33329461578827},"GB2-03":{"attempts":1,"playable":66.46750411509237,"score":66.46750411509237},"GB2-04":{"attempts":1,"playable":80.44699792971859,"score":80.44699792971859},"GB2-05":{"attempts":1,"playable":85.1765009642433,"score":85.1765009642433},"GB2-06":{"attempts":1,"playable":19.515189123449016,"score":19.515189123449016},"GB2-07":{"attempts":1,"playable":74.6050704809554,"score":74.6050704809554},"GB2-08":{"attempts":1,"playable":85.87456832444144,"score":85.87456832444144}},"medium":{"GB2-01":{"attempts":1,"playable":35.085178473954535,"score":35.085178473954535},"GB2-02":{"attempts":1,"playable":44.81144895648299,"score":44.81144895648299},"GB2-03":{"attempts":1,"playable":67.04845201670798,"score":67.04845201670798},"GB2-04":{"attempts":1,"playable":46.18542092099077,"score":46.18542092099077},"GB2-05":{"attempts":1,"playable":17.58313650452452,"score":17.58313650452452},"GB2-06":{"attempts":1,"playable":29.466010577145134,"score":29.466010577145134},"GB2-07":{"attempts":1,"playable":71.47140899698569,"score":71.47140899698569},"GB2-08":{"attempts":1,"playable":26.379104266404084,"score":26.379104266404084}},"none":{"GB2-01":{"attempts":1,"playable":40.92260870065246,"score":40.92260870065246},"GB2-02":{"attempts":1,"playable":42.59335095030837,"score":42.59335095030837},"GB2-03":{"attempts":1,"playable":28.2878023249647,"score":28.2878023249647},"GB2-04":{"attempts":1,"playable":42.61885107841961,"score":42.61885107841961},"GB2-05":{"attempts":1,"playable":16.048554982735062,"score":16.048554982735062},"GB2-06":{"attempts":1,"playable":14.965279068230211,"score":14.965279068230211},"GB2-07":{"attempts":1,"playable":24.38856478275738,"score":24.38856478275738},"GB2-08":{"attempts":1,"playable":32.032907798363944,"score":32.032907798363944}}},"id":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:15Z","match_totals_all":{"draws":2788,"losses":5443,"wins":4033},"match_totals_tracks":{"highest":{"draws":551,"losses":1162,"wins":2375},"medium":{"draws":1065,"losses":1924,"wins":1099},"none":{"draws":1172,"losses":2357,"wins":559}},"model_slug":"gemini-3-1-pro-preview","official_rank_by_reasoning":{"highest":23,"medium":52,"none":63},"overall":{"max":85.87456832444144,"mean":46.238891376069596,"min":14.965279068230211},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.42618707235431,"GB2-02":43.33329461578827,"GB2-03":66.46750411509237,"GB2-04":80.44699792971859,"GB2-05":85.1765009642433,"GB2-06":19.515189123449016,"GB2-07":74.6050704809554,"GB2-08":85.87456832444144},"per_game_all":{"GB2-01":50.14465808232043,"GB2-02":43.57936484085988,"GB2-03":53.934586152255015,"GB2-04":56.417089976376325,"GB2-05":39.60273081716763,"GB2-06":21.315492922941452,"GB2-07":56.82168142023283,"GB2-08":48.095526796403156},"per_game_match_totals_all":{"GB2-01":{"draws":280,"losses":662,"wins":606},"GB2-02":{"draws":1161,"losses":256,"wins":23},"GB2-03":{"draws":283,"losses":593,"wins":606},"GB2-04":{"draws":684,"losses":332,"wins":478},"GB2-05":{"draws":0,"losses":976,"wins":614},"GB2-06":{"draws":20,"losses":1222,"wins":264},"GB2-07":{"draws":0,"losses":711,"wins":879},"GB2-08":{"draws":360,"losses":691,"wins":563}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":132,"wins":363},"GB2-02":{"draws":390,"losses":85,"wins":5},"GB2-03":{"draws":30,"losses":169,"wins":295},"GB2-04":{"draws":107,"losses":50,"wins":341},"GB2-05":{"draws":0,"losses":84,"wins":446},"GB2-06":{"draws":2,"losses":418,"wins":82},"GB2-07":{"draws":0,"losses":140,"wins":390},"GB2-08":{"draws":1,"losses":84,"wins":453}},"medium":{"GB2-01":{"draws":173,"losses":258,"wins":85},"GB2-02":{"draws":382,"losses":82,"wins":16},"GB2-03":{"draws":98,"losses":132,"wins":264},"GB2-04":{"draws":273,"losses":140,"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":123,"losses":346,"wins":69}},"none":{"GB2-01":{"draws":86,"losses":272,"wins":158},"GB2-02":{"draws":389,"losses":89,"wins":2},"GB2-03":{"draws":155,"losses":292,"wins":47},"GB2-04":{"draws":304,"losses":142,"wins":52},"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":236,"losses":261,"wins":41}}},"per_game_raw_elo_all":{"GB2-01":1476.9880579243982,"GB2-02":1422.1495035355267,"GB2-03":1470.364350516563,"GB2-04":1541.1517503533387,"GB2-05":1321.20020257123,"GB2-06":978.1762886142736,"GB2-07":1548.2596685583148,"GB2-08":1453.4217281567962},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1723.9369632443327,"GB2-02":1420.252905931996,"GB2-03":1585.6874663493816,"GB2-04":1760.0755285417906,"GB2-05":2065.3248239210448,"GB2-06":952.8613192763182,"GB2-07":1791.8421164892861,"GB2-08":2037.6208102634512},"medium":{"GB2-01":1324.6846577455283,"GB2-02":1431.67964470658,"GB2-03":1592.0608204950722,"GB2-04":1445.4908479193803,"GB2-05":964.4230383328509,"GB2-06":1108.9621727235872,"GB2-07":1740.4477718400842,"GB2-08":1130.071258477523},"none":{"GB2-01":1382.342552783333,"GB2-02":1414.5159599680042,"GB2-03":1233.3447647052355,"GB2-04":1417.8888745988454,"GB2-05":933.8527454597945,"GB2-06":872.7053738429154,"GB2-07":1112.4891173455744,"GB2-08":1192.5731157294144}},"per_game_tracks":{"highest":{"GB2-01":74.42618707235431,"GB2-02":43.33329461578827,"GB2-03":66.46750411509237,"GB2-04":80.44699792971859,"GB2-05":85.1765009642433,"GB2-06":19.515189123449016,"GB2-07":74.6050704809554,"GB2-08":85.87456832444144},"medium":{"GB2-01":35.085178473954535,"GB2-02":44.81144895648299,"GB2-03":67.04845201670798,"GB2-04":46.18542092099077,"GB2-05":17.58313650452452,"GB2-06":29.466010577145134,"GB2-07":71.47140899698569,"GB2-08":26.379104266404084},"none":{"GB2-01":40.92260870065246,"GB2-02":42.59335095030837,"GB2-03":28.2878023249647,"GB2-04":42.61885107841961,"GB2-05":16.048554982735062,"GB2-06":14.965279068230211,"GB2-07":24.38856478275738,"GB2-08":32.032907798363944}},"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":"2026-10-24T18:46:30Z","reasoning":{"highest":66.23066407825534,"medium":42.25377008914947,"none":30.23223996080397},"reasoning_agg":{"highest":{"max":85.87456832444144,"mean":66.23066407825534,"min":19.515189123449016},"medium":{"max":71.47140899698569,"mean":42.25377008914947,"min":17.58313650452452},"none":{"max":42.61885107841961,"mean":30.23223996080397,"min":14.965279068230211}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":35.99842411745138},"working_program_strength":{"all":46.238891376069596,"highest":66.23066407825534,"medium":42.25377008914947,"none":30.23223996080397}},{"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":0.22766899999999998},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.0674595}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"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":0.38081825000000014},"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":44.722365610674636,"highest":55.60815060684604,"medium":37.70628363109249,"none":40.85266259408537},"first_seen_at":null,"game_gaps":{"medium":{"GB2-01":"failed"},"none":{"GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":36,"effective_max_output_tokens":[131072],"finish_reason_observations":36,"finish_reasons":["stop"],"indexed_attempts":36,"output_token_observations":36,"provider_post_attempt_observations":36,"provider_post_attempts":36,"reasoning_token_observations":36,"reconciliation_get_attempt_observations":36,"requested_max_output_token_observations":36,"requested_max_output_tokens":[131072],"total_output_tokens":310855,"total_reasoning_output_tokens":208237,"total_visible_output_tokens":102618,"visible_token_observations":36},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"reflection/beam-1.0-501b-a23b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":33.95312522498125,"score":22.635416816654168},"GB2-02":{"attempts":3,"playable":43.20367362278705,"score":43.20367362278705},"GB2-03":{"attempts":3,"playable":53.94951466976156,"score":53.94951466976156},"GB2-04":{"attempts":3,"playable":46.973032543533556,"score":46.973032543533556},"GB2-05":{"attempts":3,"playable":52.050134165299305,"score":52.050134165299305},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":65.19966332932201,"score":43.46644221954801},"GB2-07":{"attempts":3,"playable":26.91130255177551,"score":26.91130255177551},"GB2-08":{"attempts":3,"playable":68.58940829603792,"score":68.58940829603792}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":24.91348009565777,"score":24.91348009565777},"GB2-02":{"attempts":1,"playable":50.17533136484096,"score":50.17533136484096},"GB2-03":{"attempts":1,"playable":78.73568284375807,"score":78.73568284375807},"GB2-04":{"attempts":1,"playable":61.09887828448084,"score":61.09887828448084},"GB2-05":{"attempts":1,"playable":53.16644009511591,"score":53.16644009511591},"GB2-06":{"attempts":1,"playable":74.73094620480506,"score":74.73094620480506},"GB2-07":{"attempts":1,"playable":39.204261853711586,"score":39.204261853711586},"GB2-08":{"attempts":1,"playable":62.84018411239812,"score":62.84018411239812}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":33.88605126157579,"score":33.88605126157579},"GB2-03":{"attempts":1,"playable":39.302431406504105,"score":39.302431406504105},"GB2-04":{"attempts":1,"playable":40.06362607016069,"score":40.06362607016069},"GB2-05":{"attempts":1,"playable":41.0689414396043,"score":41.0689414396043},"GB2-06":{"attempts":1,"playable":55.66838045383894,"score":55.66838045383894},"GB2-07":{"attempts":1,"playable":31.386026642500507,"score":31.386026642500507},"GB2-08":{"attempts":1,"playable":60.274811774555594,"score":60.274811774555594}},"none":{"GB2-01":{"attempts":1,"playable":42.992770354304724,"score":42.992770354304724},"GB2-02":{"attempts":1,"playable":45.549638241944415,"score":45.549638241944415},"GB2-03":{"attempts":1,"playable":43.810429759022526,"score":43.810429759022526},"GB2-04":{"attempts":1,"playable":39.75659327595914,"score":39.75659327595914},"GB2-05":{"attempts":1,"playable":61.9150209611777,"score":61.9150209611777},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":10.143619159114431,"score":10.143619159114431},"GB2-08":{"attempts":1,"playable":82.65322900116001,"score":82.65322900116001}}},"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":82.65322900116001,"mean":44.722365610674636,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":24.91348009565777,"GB2-02":50.17533136484096,"GB2-03":78.73568284375807,"GB2-04":61.09887828448084,"GB2-05":53.16644009511591,"GB2-06":74.73094620480506,"GB2-07":39.204261853711586,"GB2-08":62.84018411239812},"per_game_all":{"GB2-02":43.20367362278705,"GB2-03":53.94951466976156,"GB2-04":46.973032543533556,"GB2-05":52.050134165299305,"GB2-07":26.91130255177551,"GB2-08":68.58940829603792},"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":1418.5030668996121,"GB2-03":1484.5045472571546,"GB2-04":1452.349738938766,"GB2-05":1464.4595857755078,"GB2-07":1120.6921738017847,"GB2-08":1681.7132525797035},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1214.1811856901504,"GB2-02":1473.0738311478888,"GB2-03":1745.3450568330168,"GB2-04":1563.6453485330758,"GB2-05":1476.9124085545136,"GB2-06":1841.3375646307277,"GB2-07":1312.896799124468,"GB2-08":1564.1824021216937},"medium":{"GB2-02":1345.0606295038485,"GB2-03":1334.4582272497532,"GB2-04":1397.9111624927277,"GB2-05":1325.3702136285501,"GB2-06":1508.6710268062009,"GB2-07":1211.6729906723265,"GB2-08":1525.4198892421878},"none":{"GB2-01":1402.291280446387,"GB2-02":1437.3747400470986,"GB2-03":1373.7103576886943,"GB2-04":1395.4927057904952,"GB2-05":1591.0961351434594,"GB2-07":837.5067316085596,"GB2-08":1955.5374663752286}},"per_game_tracks":{"highest":{"GB2-01":24.91348009565777,"GB2-02":50.17533136484096,"GB2-03":78.73568284375807,"GB2-04":61.09887828448084,"GB2-05":53.16644009511591,"GB2-06":74.73094620480506,"GB2-07":39.204261853711586,"GB2-08":62.84018411239812},"medium":{"GB2-02":33.88605126157579,"GB2-03":39.302431406504105,"GB2-04":40.06362607016069,"GB2-05":41.0689414396043,"GB2-06":55.66838045383894,"GB2-07":31.386026642500507,"GB2-08":60.274811774555594},"none":{"GB2-01":42.992770354304724,"GB2-02":45.549638241944415,"GB2-03":43.810429759022526,"GB2-04":39.75659327595914,"GB2-05":61.9150209611777,"GB2-07":10.143619159114431,"GB2-08":82.65322900116001}},"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":"2026-10-24T18:07:57Z","reasoning":{"highest":55.60815060684604,"medium":37.70628363109249,"none":40.85266259408537},"reasoning_agg":{"highest":{"max":78.73568284375807,"mean":55.60815060684604,"min":24.91348009565777},"medium":{"max":60.274811774555594,"mean":37.70628363109249,"min":0.0},"none":{"max":82.65322900116001,"mean":40.85266259408537,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.90186697575355},"working_program_strength":{"all":48.46326781187358,"highest":55.60815060684604,"medium":43.09289557839141,"none":46.68875725038328}},{"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":1.5025783626000002},"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":0.35917138039999996},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.2059380435},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303000003}},"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":44.513413179693636,"highest":44.45230475823284,"medium":47.79291287479861,"none":41.29502190604948},"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":40.56650772953453,"score":40.56650772953453},"GB2-02":{"attempts":6,"playable":50.65472668569851,"score":50.65472668569851},"GB2-03":{"attempts":6,"playable":35.99552912349877,"score":35.99552912349877},"GB2-04":{"attempts":6,"playable":50.00389491093432,"score":50.00389491093432},"GB2-05":{"attempts":6,"playable":49.4397351448528,"score":49.4397351448528},"GB2-06":{"attempts":6,"playable":55.887916627661006,"score":55.887916627661006},"GB2-07":{"attempts":6,"playable":38.958972619779836,"score":38.958972619779836},"GB2-08":{"attempts":6,"playable":34.60002259558937,"score":34.60002259558937}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":54.06745685878506,"score":54.06745685878506},"GB2-02":{"attempts":1,"playable":62.12902691074697,"score":62.12902691074697},"GB2-03":{"attempts":1,"playable":37.293391875996114,"score":37.293391875996114},"GB2-04":{"attempts":1,"playable":58.60166410752101,"score":58.60166410752101},"GB2-05":{"attempts":1,"playable":58.8824232837549,"score":58.8824232837549},"GB2-06":{"attempts":1,"playable":42.36140665519106,"score":42.36140665519106},"GB2-07":{"attempts":1,"playable":10.34922351327472,"score":10.34922351327472},"GB2-08":{"attempts":1,"playable":31.93384486059297,"score":31.93384486059297}},"medium":{"GB2-01":{"attempts":2,"playable":39.122828258443406,"score":39.122828258443406},"GB2-02":{"attempts":2,"playable":48.900777951833554,"score":48.900777951833554},"GB2-03":{"attempts":2,"playable":30.547648591738945,"score":30.547648591738945},"GB2-04":{"attempts":2,"playable":48.281005119550954,"score":48.281005119550954},"GB2-05":{"attempts":2,"playable":53.92969654816664,"score":53.92969654816664},"GB2-06":{"attempts":2,"playable":78.72629412605932,"score":78.72629412605932},"GB2-07":{"attempts":2,"playable":58.83961770106387,"score":58.83961770106387},"GB2-08":{"attempts":2,"playable":23.995434701532112,"score":23.995434701532112}},"none":{"GB2-01":{"attempts":3,"playable":28.509238071375133,"score":28.509238071375133},"GB2-02":{"attempts":3,"playable":40.934375194515006,"score":40.934375194515006},"GB2-03":{"attempts":3,"playable":40.145546902761254,"score":40.145546902761254},"GB2-04":{"attempts":3,"playable":43.129015505731,"score":43.129015505731},"GB2-05":{"attempts":3,"playable":35.50708560263685,"score":35.50708560263685},"GB2-06":{"attempts":3,"playable":46.57604910173263,"score":46.57604910173263},"GB2-07":{"attempts":3,"playable":47.68807664500091,"score":47.68807664500091},"GB2-08":{"attempts":3,"playable":47.870788224643036,"score":47.870788224643036}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:54Z","match_totals_all":{"draws":6599,"losses":11006,"wins":6923},"match_totals_tracks":{"highest":{"draws":1128,"losses":1818,"wins":1142},"medium":{"draws":2276,"losses":3306,"wins":2594},"none":{"draws":3195,"losses":5882,"wins":3187}},"model_slug":"z-ai-glm-5-2","official_rank_by_reasoning":{"highest":48,"medium":43,"none":39},"overall":{"max":78.72629412605932,"mean":44.513413179693636,"min":10.34922351327472},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.06745685878506,"GB2-02":62.12902691074697,"GB2-03":37.293391875996114,"GB2-04":58.60166410752101,"GB2-05":58.8824232837549,"GB2-06":42.36140665519106,"GB2-07":10.34922351327472,"GB2-08":31.93384486059297},"per_game_all":{"GB2-01":40.56650772953453,"GB2-02":50.65472668569851,"GB2-03":35.99552912349877,"GB2-04":50.00389491093432,"GB2-05":49.43973514485279,"GB2-06":55.887916627661006,"GB2-07":38.958972619779836,"GB2-08":34.60002259558937},"per_game_match_totals_all":{"GB2-01":{"draws":765,"losses":1646,"wins":685},"GB2-02":{"draws":2064,"losses":539,"wins":277},"GB2-03":{"draws":1092,"losses":1441,"wins":431},"GB2-04":{"draws":1691,"losses":776,"wins":521},"GB2-05":{"draws":0,"losses":1779,"wins":1401},"GB2-06":{"draws":114,"losses":1354,"wins":1544},"GB2-07":{"draws":0,"losses":1811,"wins":1369},"GB2-08":{"draws":873,"losses":1660,"wins":695}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":184,"losses":156,"wins":176},"GB2-02":{"draws":240,"losses":70,"wins":170},"GB2-03":{"draws":175,"losses":240,"wins":79},"GB2-04":{"draws":240,"losses":95,"wins":163},"GB2-05":{"draws":0,"losses":227,"wins":303},"GB2-06":{"draws":26,"losses":299,"wins":177},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":263,"losses":248,"wins":27}},"medium":{"GB2-01":{"draws":280,"losses":508,"wins":244},"GB2-02":{"draws":716,"losses":149,"wins":95},"GB2-03":{"draws":416,"losses":510,"wins":62},"GB2-04":{"draws":568,"losses":248,"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":256,"losses":711,"wins":109}},"none":{"GB2-01":{"draws":301,"losses":982,"wins":265},"GB2-02":{"draws":1108,"losses":320,"wins":12},"GB2-03":{"draws":501,"losses":691,"wins":290},"GB2-04":{"draws":883,"losses":433,"wins":178},"GB2-05":{"draws":0,"losses":1046,"wins":544},"GB2-06":{"draws":48,"losses":839,"wins":619},"GB2-07":{"draws":0,"losses":870,"wins":720},"GB2-08":{"draws":354,"losses":701,"wins":559}}},"per_game_raw_elo_all":{"GB2-01":1375.0847908517553,"GB2-02":1478.072034889541,"GB2-03":1304.2862586071806,"GB2-04":1475.5992335243618,"GB2-05":1422.816522965297,"GB2-06":1535.4952419198144,"GB2-07":1275.604938593791,"GB2-08":1242.6734478328542},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1507.9465543718034,"GB2-02":1569.259879609793,"GB2-03":1316.7543459411693,"GB2-04":1543.0006604710577,"GB2-05":1550.222606199291,"GB2-06":1303.0007246252244,"GB2-07":842.9845883524011,"GB2-08":1191.5029101745022},"medium":{"GB2-01":1363.2336213916392,"GB2-02":1463.3982143445023,"GB2-03":1254.5834233840415,"GB2-04":1461.9484333608598,"GB2-05":1486.5810136140271,"GB2-06":1925.964010384304,"GB2-07":1563.7002814651578,"GB2-08":1102.3468851467567},"none":{"GB2-01":1254.0741967918236,"GB2-02":1401.558010714328,"GB2-03":1341.5210064963314,"GB2-04":1421.8486067411675,"GB2-05":1231.6459490825735,"GB2-06":1377.520990749915,"GB2-07":1420.129945963814,"GB2-08":1434.170548177303}},"per_game_tracks":{"highest":{"GB2-01":54.06745685878506,"GB2-02":62.12902691074697,"GB2-03":37.293391875996114,"GB2-04":58.60166410752101,"GB2-05":58.8824232837549,"GB2-06":42.36140665519106,"GB2-07":10.34922351327472,"GB2-08":31.93384486059297},"medium":{"GB2-01":39.122828258443406,"GB2-02":48.900777951833554,"GB2-03":30.547648591738945,"GB2-04":48.281005119550954,"GB2-05":53.92969654816664,"GB2-06":78.72629412605932,"GB2-07":58.83961770106387,"GB2-08":23.995434701532112},"none":{"GB2-01":28.509238071375133,"GB2-02":40.934375194515006,"GB2-03":40.145546902761254,"GB2-04":43.129015505731,"GB2-05":35.50708560263684,"GB2-06":46.57604910173263,"GB2-07":47.68807664500091,"GB2-08":47.870788224643036}},"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":"2026-10-24T19:20:20Z","reasoning":{"highest":44.45230475823284,"medium":47.79291287479861,"none":41.29502190604948},"reasoning_agg":{"highest":{"max":62.12902691074697,"mean":44.45230475823284,"min":10.34922351327472},"medium":{"max":78.72629412605932,"mean":47.79291287479861,"min":23.995434701532112},"none":{"max":47.870788224643036,"mean":41.29502190604948,"min":28.509238071375133}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.497890968749132},"working_program_strength":{"all":44.513413179693636,"highest":44.45230475823284,"medium":47.79291287479861,"none":41.29502190604948}},{"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":1.1725616482799999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.9884523218400001},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784}},"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":43.77622037288331,"highest":55.91744014634476,"medium":46.91108795092154,"none":28.500133021383622},"first_seen_at":null,"game_gaps":{"none":{"GB2-02":"failed","GB2-05":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":31,"finish_reasons":["stop"],"indexed_attempts":31,"output_token_observations":31,"provider_post_attempt_observations":31,"provider_post_attempts":31,"reasoning_token_observations":31,"reconciliation_get_attempt_observations":31,"reconciliation_get_attempts":150,"total_output_tokens":797920,"total_reasoning_output_tokens":686933,"total_visible_output_tokens":110987,"visible_token_observations":31},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":43.564494832612546,"score":43.564494832612546},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.961185984424674,"score":28.640790656283116},"GB2-03":{"attempts":3,"playable":47.81425062042686,"score":47.81425062042686},"GB2-04":{"attempts":3,"playable":40.59883613538042,"score":40.59883613538042},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.67350852696781,"score":39.782339017978536},"GB2-06":{"attempts":3,"playable":55.636095484433945,"score":55.636095484433945},"GB2-07":{"attempts":3,"playable":58.9215429215626,"score":58.9215429215626},"GB2-08":{"attempts":3,"playable":35.25141331438848,"score":35.25141331438848}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":43.58353633785871,"score":43.58353633785871},"GB2-02":{"attempts":1,"playable":45.022421426676964,"score":45.022421426676964},"GB2-03":{"attempts":1,"playable":64.13066103380365,"score":64.13066103380365},"GB2-04":{"attempts":1,"playable":43.33319700499054,"score":43.33319700499054},"GB2-05":{"attempts":1,"playable":74.81201350070057,"score":74.81201350070057},"GB2-06":{"attempts":1,"playable":66.33931517535959,"score":66.33931517535959},"GB2-07":{"attempts":1,"playable":79.27457840265981,"score":79.27457840265981},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}},"medium":{"GB2-01":{"attempts":1,"playable":51.52882128415899,"score":51.52882128415899},"GB2-02":{"attempts":1,"playable":40.89995054217238,"score":40.89995054217238},"GB2-03":{"attempts":1,"playable":43.08026465020685,"score":43.08026465020685},"GB2-04":{"attempts":1,"playable":33.80482228941814,"score":33.80482228941814},"GB2-05":{"attempts":1,"playable":44.53500355323505,"score":44.53500355323505},"GB2-06":{"attempts":1,"playable":39.02304595041499,"score":39.02304595041499},"GB2-07":{"attempts":1,"playable":74.0840341297721,"score":74.0840341297721},"GB2-08":{"attempts":1,"playable":48.33276120799385,"score":48.33276120799385}},"none":{"GB2-01":{"attempts":1,"playable":35.58112687581995,"score":35.58112687581995},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.23182617727008,"score":36.23182617727008},"GB2-04":{"attempts":1,"playable":44.65848911173256,"score":44.65848911173256},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":61.54592532752725,"score":61.54592532752725},"GB2-07":{"attempts":1,"playable":23.406016232255876,"score":23.406016232255876},"GB2-08":{"attempts":1,"playable":26.57768044646329,"score":26.57768044646329}}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-10-26T00:22:44Z","match_totals_all":{"draws":2540,"losses":4870,"wins":3844},"match_totals_tracks":{"highest":{"draws":776,"losses":1498,"wins":1814},"medium":{"draws":970,"losses":1774,"wins":1344},"none":{"draws":794,"losses":1598,"wins":686}},"model_slug":"deepseek-deepseek-v4-pro-0813","official_rank_by_reasoning":{"highest":38,"medium":45,"none":68},"overall":{"max":79.27457840265981,"mean":43.77622037288331,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":46,"overall_ranking_status":"ranked","per_game":{"GB2-01":43.58353633785871,"GB2-02":45.022421426676964,"GB2-03":64.13066103380365,"GB2-04":43.33319700499054,"GB2-05":74.81201350070057,"GB2-06":66.33931517535959,"GB2-07":79.27457840265981,"GB2-08":30.843798288708303},"per_game_all":{"GB2-01":43.564494832612546,"GB2-03":47.81425062042686,"GB2-04":40.59883613538042,"GB2-06":55.636095484433945,"GB2-07":58.9215429215626,"GB2-08":35.25141331438848},"per_game_match_totals_all":{"GB2-01":{"draws":401,"losses":704,"wins":443},"GB2-02":{"draws":713,"losses":207,"wins":40},"GB2-03":{"draws":283,"losses":687,"wins":512},"GB2-04":{"draws":799,"losses":512,"wins":183},"GB2-05":{"draws":0,"losses":444,"wins":616},"GB2-06":{"draws":29,"losses":712,"wins":765},"GB2-07":{"draws":0,"losses":674,"wins":916},"GB2-08":{"draws":315,"losses":930,"wins":369}},"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":10,"losses":181,"wins":311},"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":188,"losses":243,"wins":67},"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":102,"losses":245,"wins":191}},"none":{"GB2-01":{"draws":102,"losses":291,"wins":123},"GB2-03":{"draws":217,"losses":224,"wins":53},"GB2-04":{"draws":366,"losses":101,"wins":31},"GB2-06":{"draws":4,"losses":210,"wins":288},"GB2-07":{"draws":0,"losses":418,"wins":112},"GB2-08":{"draws":105,"losses":354,"wins":79}}},"per_game_raw_elo_all":{"GB2-01":1407.09196338529,"GB2-03":1411.837681105234,"GB2-04":1401.5177940400729,"GB2-06":1515.163835455264,"GB2-07":1586.1697971002316,"GB2-08":1227.5814069457876},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1407.953737414123,"GB2-02":1433.3078551152962,"GB2-03":1560.8262590880133,"GB2-04":1423.4360965098103,"GB2-05":1800.045776009417,"GB2-06":1687.70246150215,"GB2-07":1878.0194134888413,"GB2-08":1179.6845364384803},"medium":{"GB2-01":1483.6299104395284,"GB2-02":1401.3257484478688,"GB2-03":1367.3752054116387,"GB2-04":1347.4192338133864,"GB2-05":1369.332055358503,"GB2-06":1252.6906477646482,"GB2-07":1783.005848020484,"GB2-08":1370.7264654823541},"none":{"GB2-01":1329.6922423022188,"GB2-03":1307.3115788160496,"GB2-04":1433.6980517970223,"GB2-06":1605.098397098994,"GB2-07":1097.4841297913695,"GB2-08":1132.3332189165283}},"per_game_tracks":{"highest":{"GB2-01":43.58353633785871,"GB2-02":45.022421426676964,"GB2-03":64.13066103380365,"GB2-04":43.33319700499054,"GB2-05":74.81201350070057,"GB2-06":66.33931517535959,"GB2-07":79.27457840265981,"GB2-08":30.843798288708303},"medium":{"GB2-01":51.52882128415899,"GB2-02":40.89995054217238,"GB2-03":43.08026465020685,"GB2-04":33.80482228941814,"GB2-05":44.53500355323505,"GB2-06":39.02304595041499,"GB2-07":74.0840341297721,"GB2-08":48.33276120799385},"none":{"GB2-01":35.58112687581995,"GB2-03":36.23182617727008,"GB2-04":44.65848911173256,"GB2-06":61.54592532752725,"GB2-07":23.406016232255876,"GB2-08":26.57768044646329}},"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":"2026-10-24T19:18:37Z","reasoning":{"highest":55.91744014634476,"medium":46.91108795092154,"none":28.500133021383622},"reasoning_agg":{"highest":{"max":79.27457840265981,"mean":55.91744014634476,"min":30.843798288708303},"medium":{"max":74.0840341297721,"mean":46.91108795092154,"min":33.80482228941814},"none":{"max":61.54592532752725,"mean":28.500133021383622,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.417307124961138},"working_program_strength":{"all":46.94290181970371,"highest":55.91744014634476,"medium":46.91108795092154,"none":38.00017736184483}},{"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":0.37262013029400004},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.20237245442100005},"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":0.9135725942489998}},"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":43.52783950686774,"highest":48.708988669738766,"medium":53.667004053189046,"none":28.20752579767543},"first_seen_at":null,"game_gaps":{"none":{"GB2-02":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":514138,"total_reasoning_output_tokens":410486,"total_visible_output_tokens":103652,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":39.65244020354163,"score":39.65244020354163},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.53512890742101,"score":28.356752604947342},"GB2-03":{"attempts":3,"playable":39.58544442636555,"score":39.58544442636555},"GB2-04":{"attempts":3,"playable":45.33701969516898,"score":45.33701969516898},"GB2-05":{"attempts":3,"playable":42.923426735963524,"score":42.923426735963524},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":63.688101908464226,"score":42.45873460564282},"GB2-07":{"attempts":3,"playable":66.88044783195903,"score":66.88044783195903},"GB2-08":{"attempts":3,"playable":43.0284499513531,"score":43.0284499513531}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.516500344886474,"score":27.516500344886474},"GB2-02":{"attempts":1,"playable":45.76043854681514,"score":45.76043854681514},"GB2-03":{"attempts":1,"playable":46.71655058071938,"score":46.71655058071938},"GB2-04":{"attempts":1,"playable":46.490509638186836,"score":46.490509638186836},"GB2-05":{"attempts":1,"playable":45.112094261816324,"score":45.112094261816324},"GB2-06":{"attempts":1,"playable":78.70569511408215,"score":78.70569511408215},"GB2-07":{"attempts":1,"playable":74.77864378963382,"score":74.77864378963382},"GB2-08":{"attempts":1,"playable":24.59147708177002,"score":24.59147708177002}},"medium":{"GB2-01":{"attempts":1,"playable":62.326046402047176,"score":62.326046402047176},"GB2-02":{"attempts":1,"playable":39.30981926802688,"score":39.30981926802688},"GB2-03":{"attempts":1,"playable":29.58652296151986,"score":29.58652296151986},"GB2-04":{"attempts":1,"playable":44.35281068247941,"score":44.35281068247941},"GB2-05":{"attempts":1,"playable":49.14568681479483,"score":49.14568681479483},"GB2-06":{"attempts":1,"playable":48.670508702846305,"score":48.670508702846305},"GB2-07":{"attempts":1,"playable":71.47140899698569,"score":71.47140899698569},"GB2-08":{"attempts":1,"playable":84.47322859681222,"score":84.47322859681222}},"none":{"GB2-01":{"attempts":1,"playable":29.11477386369124,"score":29.11477386369124},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.453259736857405,"score":42.453259736857405},"GB2-04":{"attempts":1,"playable":45.16773876484072,"score":45.16773876484072},"GB2-05":{"attempts":1,"playable":34.512499131279434,"score":34.512499131279434},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":54.39129070925759,"score":54.39129070925759},"GB2-08":{"attempts":1,"playable":20.020644175477056,"score":20.020644175477056}}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-10-26T01:40:16Z","match_totals_all":{"draws":2579,"losses":4860,"wins":3842},"match_totals_tracks":{"highest":{"draws":999,"losses":1681,"wins":1407},"medium":{"draws":811,"losses":1557,"wins":1720},"none":{"draws":769,"losses":1622,"wins":715}},"model_slug":"deepseek-deepseek-v4-pro","official_rank_by_reasoning":{"highest":45,"medium":30,"none":69},"overall":{"max":84.47322859681222,"mean":43.52783950686774,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":47,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.516500344886474,"GB2-02":45.76043854681514,"GB2-03":46.71655058071938,"GB2-04":46.490509638186836,"GB2-05":45.112094261816324,"GB2-06":78.70569511408215,"GB2-07":74.77864378963382,"GB2-08":24.59147708177002},"per_game_all":{"GB2-01":39.65244020354163,"GB2-03":39.58544442636555,"GB2-04":45.33701969516898,"GB2-05":42.923426735963524,"GB2-07":66.88044783195903,"GB2-08":43.0284499513531},"per_game_match_totals_all":{"GB2-01":{"draws":213,"losses":856,"wins":479},"GB2-02":{"draws":699,"losses":218,"wins":43},"GB2-03":{"draws":450,"losses":724,"wins":308},"GB2-04":{"draws":944,"losses":370,"wins":180},"GB2-05":{"draws":0,"losses":931,"wins":659},"GB2-06":{"draws":19,"losses":388,"wins":596},"GB2-07":{"draws":0,"losses":551,"wins":1039},"GB2-08":{"draws":254,"losses":822,"wins":538}},"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":194,"wins":123},"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":139,"wins":391},"GB2-08":{"draws":117,"losses":358,"wins":63}},"medium":{"GB2-01":{"draws":37,"losses":187,"wins":292},"GB2-02":{"draws":346,"losses":126,"wins":8},"GB2-03":{"draws":109,"losses":309,"wins":76},"GB2-04":{"draws":313,"losses":129,"wins":56},"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":0,"losses":93,"wins":445}},"none":{"GB2-01":{"draws":133,"losses":308,"wins":75},"GB2-03":{"draws":164,"losses":221,"wins":109},"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":137,"losses":371,"wins":30}}},"per_game_raw_elo_all":{"GB2-01":1365.2295093963155,"GB2-03":1335.6140573806326,"GB2-04":1438.9375749418862,"GB2-05":1347.198023877783,"GB2-07":1679.3945431866075,"GB2-08":1387.8102972661143},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1244.2658044035877,"GB2-02":1439.000195026472,"GB2-03":1398.940589651182,"GB2-04":1447.845104509816,"GB2-05":1376.5660796623793,"GB2-06":1918.312247468047,"GB2-07":1794.8147015710883,"GB2-08":1109.3974269303371},"medium":{"GB2-01":1589.4123396928994,"GB2-02":1388.8376101825722,"GB2-03":1245.9698832213853,"GB2-04":1431.3339387145681,"GB2-05":1426.788072870283,"GB2-06":1399.0679930462284,"GB2-07":1740.4477718400842,"GB2-08":2000.9254762548514},"none":{"GB2-01":1262.0103840924594,"GB2-03":1361.9316992693302,"GB2-04":1437.633681601274,"GB2-05":1238.239919100687,"GB2-07":1502.9211561486504,"GB2-08":1053.1079886131538}},"per_game_tracks":{"highest":{"GB2-01":27.516500344886474,"GB2-02":45.76043854681514,"GB2-03":46.71655058071938,"GB2-04":46.490509638186836,"GB2-05":45.112094261816324,"GB2-06":78.70569511408215,"GB2-07":74.77864378963382,"GB2-08":24.59147708177002},"medium":{"GB2-01":62.326046402047176,"GB2-02":39.30981926802688,"GB2-03":29.58652296151986,"GB2-04":44.35281068247941,"GB2-05":49.14568681479483,"GB2-06":48.670508702846305,"GB2-07":71.47140899698569,"GB2-08":84.47322859681222},"none":{"GB2-01":29.11477386369124,"GB2-03":42.453259736857405,"GB2-04":45.16773876484072,"GB2-05":34.512499131279434,"GB2-07":54.39129070925759,"GB2-08":20.020644175477056}},"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":"2026-10-24T18:45:04Z","reasoning":{"highest":48.708988669738766,"medium":53.667004053189046,"none":28.20752579767543},"reasoning_agg":{"highest":{"max":78.70569511408215,"mean":48.708988669738766,"min":24.59147708177002},"medium":{"max":84.47322859681222,"mean":53.667004053189046,"min":29.58652296151986},"none":{"max":54.39129070925759,"mean":28.20752579767543,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.459478255513616},"working_program_strength":{"all":46.662009039942795,"highest":48.708988669738766,"medium":53.667004053189046,"none":37.61003439690057}},{"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":2.2561124999999995},"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":1.4205012499999998},"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":0.7793050000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.779305},"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":2.2561124999999995}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-10-09":19},"run_count":24,"token_priced_attempt_count":31,"total":4.4559187499999995},"codegen_latency_ms":{"attempt_count":19,"max_ms":452838,"mean_ms":201000.75,"min_ms":115295,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":452838,"mean_ms":260996.125,"min_ms":140461,"run_count":8},"medium":{"attempt_count":9,"max_ms":181508,"mean_ms":141005.375,"min_ms":115295,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43637,"output_mean":21815.875,"output_min":13286,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43637,"output_mean":26965.5,"output_min":16148,"run_count":8},"medium":{"attempt_count":9,"output_max":19618,"output_mean":16666.25,"output_min":13286,"run_count":8}},"display_name":"GPT-5","economics":{"all":43.199946457290686,"highest":49.452229432393345,"medium":38.628248717466356,"none":41.51936122201238},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed"},"none":{"GB2-04":"too_slow","GB2-06":"too_slow"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"total_output_tokens":349054},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":43.81384099393201,"score":43.81384099393201},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.47457594530332,"score":26.983050630202214},"GB2-03":{"attempts":3,"playable":28.405643914502928,"score":28.405643914502928},"GB2-04":{"attempts":2,"playable":41.44331354005614,"score":41.44331354005614},"GB2-05":{"attempts":3,"playable":61.7506949190068,"score":61.7506949190068},"GB2-06":{"attempts":2,"playable":59.530548523954785,"score":59.530548523954785},"GB2-07":{"attempts":3,"playable":52.412531555784916,"score":52.412531555784916},"GB2-08":{"attempts":3,"playable":37.23832745421451,"score":37.23832745421451}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":39.73790526536497,"score":39.73790526536497},"GB2-02":{"attempts":1,"playable":42.27605906017271,"score":42.27605906017271},"GB2-03":{"attempts":1,"playable":37.611301069122675,"score":37.611301069122675},"GB2-04":{"attempts":1,"playable":40.06362607016069,"score":40.06362607016069},"GB2-05":{"attempts":1,"playable":75.91303436651312,"score":75.91303436651312},"GB2-06":{"attempts":1,"playable":69.90573731056207,"score":69.90573731056207},"GB2-07":{"attempts":1,"playable":52.93541386858993,"score":52.93541386858993},"GB2-08":{"attempts":1,"playable":37.17475844866062,"score":37.17475844866062}},"medium":{"GB2-01":{"attempts":1,"playable":21.095558671137997,"score":21.095558671137997},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.742066078343424,"score":31.742066078343424},"GB2-04":{"attempts":1,"playable":42.82300100995158,"score":42.82300100995158},"GB2-05":{"attempts":1,"playable":61.53661978064131,"score":61.53661978064131},"GB2-06":{"attempts":1,"playable":49.155359737347496,"score":49.155359737347496},"GB2-07":{"attempts":1,"playable":62.838415616371904,"score":62.838415616371904},"GB2-08":{"attempts":1,"playable":39.83496884593718,"score":39.83496884593718}},"none":{"GB2-01":{"attempts":1,"playable":70.60805904529305,"score":70.60805904529305},"GB2-02":{"attempts":1,"playable":38.67309283043393,"score":38.67309283043393},"GB2-03":{"attempts":1,"playable":15.863564596042682,"score":15.863564596042682},"GB2-05":{"attempts":1,"playable":47.80243060986596,"score":47.80243060986596},"GB2-07":{"attempts":1,"playable":41.463765182392905,"score":41.463765182392905},"GB2-08":{"attempts":1,"playable":34.70525506804573,"score":34.70525506804573}}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-10-26T00:59:53Z","match_totals_all":{"draws":2406,"losses":4916,"wins":3462},"match_totals_tracks":{"highest":{"draws":1156,"losses":1578,"wins":1354},"medium":{"draws":652,"losses":1772,"wins":1184},"none":{"draws":598,"losses":1566,"wins":924}},"model_slug":"gpt-5","official_rank_by_reasoning":{"highest":44,"medium":56,"none":37},"overall":{"max":75.91303436651312,"mean":43.199946457290686,"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":39.73790526536497,"GB2-02":42.27605906017271,"GB2-03":37.611301069122675,"GB2-04":40.06362607016069,"GB2-05":75.91303436651312,"GB2-06":69.90573731056207,"GB2-07":52.93541386858993,"GB2-08":37.17475844866062},"per_game_all":{"GB2-01":43.81384099393201,"GB2-03":28.405643914502928,"GB2-05":61.7506949190068,"GB2-07":52.412531555784916,"GB2-08":37.23832745421451},"per_game_match_totals_all":{"GB2-01":{"draws":208,"losses":794,"wins":546},"GB2-02":{"draws":706,"losses":234,"wins":20},"GB2-03":{"draws":417,"losses":897,"wins":168},"GB2-04":{"draws":599,"losses":300,"wins":97},"GB2-05":{"draws":0,"losses":634,"wins":956},"GB2-06":{"draws":24,"losses":432,"wins":548},"GB2-07":{"draws":0,"losses":793,"wins":797},"GB2-08":{"draws":452,"losses":832,"wins":330}},"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":218,"losses":244,"wins":76}},"medium":{"GB2-01":{"draws":65,"losses":382,"wins":69},"GB2-03":{"draws":191,"losses":258,"wins":45},"GB2-04":{"draws":268,"losses":159,"wins":71},"GB2-05":{"draws":0,"losses":213,"wins":317},"GB2-06":{"draws":17,"losses":269,"wins":216},"GB2-07":{"draws":0,"losses":207,"wins":323},"GB2-08":{"draws":111,"losses":284,"wins":143}},"none":{"GB2-01":{"draws":57,"losses":134,"wins":325},"GB2-02":{"draws":346,"losses":129,"wins":5},"GB2-03":{"draws":72,"losses":390,"wins":32},"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":1405.3104160849723,"GB2-03":1225.4315626857358,"GB2-05":1606.1150200836921,"GB2-07":1479.9594376400266,"GB2-08":1248.3743486249934},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1370.8333995749038,"GB2-02":1412.051507468645,"GB2-03":1319.5692003972233,"GB2-04":1397.9111624927277,"GB2-05":1822.3505374105973,"GB2-06":1751.6214695332815,"GB2-07":1484.4227597982008,"GB2-08":1247.6632746784537},"medium":{"GB2-01":1166.625798088919,"GB2-03":1266.390719129744,"GB2-04":1419.475544761744,"GB2-05":1585.892242767181,"GB2-06":1406.5330625368624,"GB2-07":1614.2268976080036,"GB2-08":1276.1859110704497},"none":{"GB2-01":1678.4720505910939,"GB2-02":1383.8023519694618,"GB2-03":1090.3347685302401,"GB2-05":1410.1022800732985,"GB2-07":1341.2286555138758,"GB2-08":1221.2738601260767}},"per_game_tracks":{"highest":{"GB2-01":39.73790526536497,"GB2-02":42.27605906017271,"GB2-03":37.611301069122675,"GB2-04":40.06362607016069,"GB2-05":75.91303436651312,"GB2-06":69.90573731056207,"GB2-07":52.93541386858993,"GB2-08":37.17475844866062},"medium":{"GB2-01":21.095558671137997,"GB2-03":31.742066078343424,"GB2-04":42.82300100995158,"GB2-05":61.53661978064131,"GB2-06":49.155359737347496,"GB2-07":62.838415616371904,"GB2-08":39.83496884593718},"none":{"GB2-01":70.60805904529305,"GB2-02":38.67309283043393,"GB2-03":15.863564596042682,"GB2-05":47.80243060986596,"GB2-07":41.463765182392905,"GB2-08":34.70525506804573}},"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":49.452229432393345,"medium":38.628248717466356,"none":41.51936122201238},"reasoning_agg":{"highest":{"max":75.91303436651312,"mean":49.452229432393345,"min":37.17475844866062},"medium":{"max":62.838415616371904,"mean":38.628248717466356,"min":0.0},"none":{"max":70.60805904529305,"mean":41.51936122201238,"min":15.863564596042682}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":10.82398071492699},"working_program_strength":{"all":45.03938687240814,"highest":49.452229432393345,"medium":44.146569962818695,"none":41.51936122201238}},{"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":0.05054444999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0367878}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"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":0.036787799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.24666659999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.3339988500000001},"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":41.581349766272766,"highest":55.862096065373166,"medium":43.030258555037776,"none":25.851694678407355},"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":51.3498744762477,"score":51.3498744762477},"GB2-02":{"attempts":3,"playable":43.71985904429773,"score":43.71985904429773},"GB2-03":{"attempts":3,"playable":38.58202493672601,"score":38.58202493672601},"GB2-04":{"attempts":3,"playable":41.75912050300873,"score":41.75912050300873},"GB2-05":{"attempts":3,"playable":40.09466295264844,"score":40.09466295264844},"GB2-06":{"attempts":3,"playable":52.569411071694226,"score":52.569411071694226},"GB2-07":{"attempts":3,"playable":38.80257986929555,"score":38.80257986929555},"GB2-08":{"attempts":3,"playable":25.773265276263725,"score":25.773265276263725}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.401125129377,"score":81.401125129377},"GB2-02":{"attempts":1,"playable":45.338788424049355,"score":45.338788424049355},"GB2-03":{"attempts":1,"playable":41.72041770372514,"score":41.72041770372514},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":51.25358631759123,"score":51.25358631759123},"GB2-06":{"attempts":1,"playable":83.72858164014411,"score":83.72858164014411},"GB2-07":{"attempts":1,"playable":72.69221573249251,"score":72.69221573249251},"GB2-08":{"attempts":1,"playable":32.13196509707394,"score":32.13196509707394}},"medium":{"GB2-01":{"attempts":1,"playable":46.53271418856003,"score":46.53271418856003},"GB2-02":{"attempts":1,"playable":43.43895423021337,"score":43.43895423021337},"GB2-03":{"attempts":1,"playable":44.33108968183731,"score":44.33108968183731},"GB2-04":{"attempts":1,"playable":47.7098452152136,"score":47.7098452152136},"GB2-05":{"attempts":1,"playable":44.53500355323505,"score":44.53500355323505},"GB2-06":{"attempts":1,"playable":54.80342947849586,"score":54.80342947849586},"GB2-07":{"attempts":1,"playable":28.680284444924364,"score":28.680284444924364},"GB2-08":{"attempts":1,"playable":34.210747647822636,"score":34.210747647822636}},"none":{"GB2-01":{"attempts":1,"playable":26.115784110806082,"score":26.115784110806082},"GB2-02":{"attempts":1,"playable":42.38183447863047,"score":42.38183447863047},"GB2-03":{"attempts":1,"playable":29.69456742461558,"score":29.69456742461558},"GB2-04":{"attempts":1,"playable":38.93742781528057,"score":38.93742781528057},"GB2-05":{"attempts":1,"playable":24.49539898711905,"score":24.49539898711905},"GB2-06":{"attempts":1,"playable":19.176222096442736,"score":19.176222096442736},"GB2-07":{"attempts":1,"playable":15.03523943046976,"score":15.03523943046976},"GB2-08":{"attempts":1,"playable":10.977083083894604,"score":10.977083083894604}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:42Z","match_totals_all":{"draws":3511,"losses":5686,"wins":3067},"match_totals_tracks":{"highest":{"draws":1186,"losses":1290,"wins":1612},"medium":{"draws":1222,"losses":1827,"wins":1039},"none":{"draws":1103,"losses":2569,"wins":416}},"model_slug":"gpt-5-6-luna","official_rank_by_reasoning":{"highest":39,"medium":50,"none":75},"overall":{"max":83.72858164014411,"mean":41.581349766272766,"min":10.977083083894604},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.401125129377,"GB2-02":45.338788424049355,"GB2-03":41.72041770372514,"GB2-04":38.63008847853202,"GB2-05":51.25358631759123,"GB2-06":83.72858164014411,"GB2-07":72.69221573249251,"GB2-08":32.13196509707394},"per_game_all":{"GB2-01":51.3498744762477,"GB2-02":43.71985904429773,"GB2-03":38.58202493672601,"GB2-04":41.75912050300873,"GB2-05":40.09466295264844,"GB2-06":52.569411071694226,"GB2-07":38.80257986929555,"GB2-08":25.773265276263725},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":697,"wins":682},"GB2-02":{"draws":1127,"losses":271,"wins":42},"GB2-03":{"draws":581,"losses":673,"wins":228},"GB2-04":{"draws":949,"losses":420,"wins":125},"GB2-05":{"draws":0,"losses":975,"wins":615},"GB2-06":{"draws":74,"losses":722,"wins":710},"GB2-07":{"draws":0,"losses":1002,"wins":588},"GB2-08":{"draws":611,"losses":926,"wins":77}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":105,"wins":410},"GB2-02":{"draws":357,"losses":92,"wins":31},"GB2-03":{"draws":211,"losses":201,"wins":82},"GB2-04":{"draws":293,"losses":167,"wins":38},"GB2-05":{"draws":0,"losses":267,"wins":263},"GB2-06":{"draws":35,"losses":73,"wins":394},"GB2-07":{"draws":0,"losses":151,"wins":379},"GB2-08":{"draws":289,"losses":234,"wins":15}},"medium":{"GB2-01":{"draws":67,"losses":253,"wins":196},"GB2-02":{"draws":385,"losses":87,"wins":8},"GB2-03":{"draws":156,"losses":216,"wins":122},"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":250,"losses":243,"wins":45}},"none":{"GB2-01":{"draws":101,"losses":339,"wins":76},"GB2-02":{"draws":385,"losses":92,"wins":3},"GB2-03":{"draws":214,"losses":256,"wins":24},"GB2-04":{"draws":310,"losses":157,"wins":31},"GB2-05":{"draws":0,"losses":406,"wins":124},"GB2-06":{"draws":21,"losses":410,"wins":71},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":72,"losses":449,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1494.6392174035363,"GB2-02":1423.2310077399836,"GB2-03":1326.9326377049736,"GB2-04":1410.949743032915,"GB2-05":1303.3302421867045,"GB2-06":1487.9887710102691,"GB2-07":1295.1726896919088,"GB2-08":1107.1507074038407},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1819.5517682901786,"GB2-02":1435.7485726887123,"GB2-03":1355.562626207137,"GB2-04":1386.5783876383734,"GB2-05":1452.998625286702,"GB2-06":2021.909206530001,"GB2-07":1759.9950092189056,"GB2-08":1193.642685909422},"medium":{"GB2-01":1436.0892558975147,"GB2-02":1421.0710505964687,"GB2-03":1378.2267530540141,"GB2-04":1457.2536446119695,"GB2-05":1369.332055358503,"GB2-06":1494.8662622825464,"GB2-07":1174.6588104115167,"GB2-08":1215.9815680881559},"none":{"GB2-01":1228.276628022916,"GB2-02":1412.8733999347703,"GB2-03":1247.0085338537692,"GB2-04":1389.0171968484015,"GB2-05":1087.660045914908,"GB2-06":947.1908442182599,"GB2-07":950.8642494453044,"GB2-08":911.8278682139444}},"per_game_tracks":{"highest":{"GB2-01":81.401125129377,"GB2-02":45.338788424049355,"GB2-03":41.72041770372514,"GB2-04":38.63008847853202,"GB2-05":51.25358631759123,"GB2-06":83.72858164014411,"GB2-07":72.69221573249251,"GB2-08":32.13196509707394},"medium":{"GB2-01":46.53271418856003,"GB2-02":43.43895423021337,"GB2-03":44.33108968183731,"GB2-04":47.7098452152136,"GB2-05":44.53500355323505,"GB2-06":54.80342947849586,"GB2-07":28.680284444924364,"GB2-08":34.210747647822636},"none":{"GB2-01":26.115784110806082,"GB2-02":42.38183447863047,"GB2-03":29.69456742461558,"GB2-04":38.93742781528057,"GB2-05":24.49539898711905,"GB2-06":19.176222096442736,"GB2-07":15.03523943046976,"GB2-08":10.977083083894604}},"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":"2026-10-24T19:07:02Z","reasoning":{"highest":55.862096065373166,"medium":43.030258555037776,"none":25.851694678407355},"reasoning_agg":{"highest":{"max":83.72858164014411,"mean":55.862096065373166,"min":32.13196509707394},"medium":{"max":54.80342947849586,"mean":43.030258555037776,"min":28.680284444924364},"none":{"max":42.38183447863047,"mean":25.851694678407355,"min":10.977083083894604}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":30.01040138696581},"working_program_strength":{"all":41.581349766272766,"highest":55.862096065373166,"medium":43.030258555037776,"none":25.851694678407355}},{"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":38.07123278679902,"highest":40.00369844821555,"medium":42.67169063123324,"none":31.538309280948283},"economics_best_value":{"per_model":{"all":true,"highest":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-08":"failed"},"medium":{"GB2-02":"failed"},"none":{"GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":35,"effective_max_output_tokens":[524288],"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"requested_max_output_token_observations":35,"requested_max_output_tokens":[524288],"total_output_tokens":399154,"total_reasoning_output_tokens":282019,"total_visible_output_tokens":117135,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":524288,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":37.984877796527435,"score":37.984877796527435},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.42939693014983,"score":27.619597953433217},"GB2-03":{"attempts":3,"playable":34.826379796640076,"score":34.826379796640076},"GB2-04":{"attempts":3,"playable":39.68806985319623,"score":39.68806985319623},"GB2-05":{"attempts":3,"playable":48.93470138678226,"score":48.93470138678226},"GB2-06":{"attempts":3,"playable":51.182489328590215,"score":51.182489328590215},"GB2-07":{"attempts":3,"playable":54.64746639978847,"score":54.64746639978847},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":29.05883933830283,"score":9.686279779434276}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":14.931506354971024,"score":14.931506354971024},"GB2-02":{"attempts":1,"playable":41.111782530814864,"score":41.111782530814864},"GB2-03":{"attempts":1,"playable":49.13808216264724,"score":49.13808216264724},"GB2-04":{"attempts":1,"playable":39.65423019410055,"score":39.65423019410055},"GB2-05":{"attempts":1,"playable":72.78229423571837,"score":72.78229423571837},"GB2-06":{"attempts":1,"playable":32.163984579948654,"score":32.163984579948654},"GB2-07":{"attempts":1,"playable":70.24770752752374,"score":70.24770752752374},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":68.11346235814054,"score":68.11346235814054},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.849547148522728,"score":31.849547148522728},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":50.48751301185782,"score":50.48751301185782},"GB2-06":{"attempts":1,"playable":51.660210126745696,"score":51.660210126745696},"GB2-07":{"attempts":1,"playable":71.47140899698569,"score":71.47140899698569},"GB2-08":{"attempts":1,"playable":29.05883933830283,"score":29.05883933830283}},"none":{"GB2-01":{"attempts":1,"playable":30.909664676470744,"score":30.909664676470744},"GB2-02":{"attempts":1,"playable":41.74701132948479,"score":41.74701132948479},"GB2-03":{"attempts":1,"playable":23.49151007875027,"score":23.49151007875027},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":23.534296912770603,"score":23.534296912770603},"GB2-06":{"attempts":1,"playable":69.7232732790763,"score":69.7232732790763},"GB2-07":{"attempts":1,"playable":22.22328267485598,"score":22.22328267485598},"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":51,"none":57},"overall":{"max":72.78229423571837,"mean":38.07123278679902,"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":14.931506354971024,"GB2-02":41.111782530814864,"GB2-03":49.13808216264724,"GB2-04":39.65423019410055,"GB2-05":72.78229423571837,"GB2-06":32.163984579948654,"GB2-07":70.24770752752374},"per_game_all":{"GB2-01":37.984877796527435,"GB2-03":34.826379796640076,"GB2-04":39.68806985319623,"GB2-05":48.93470138678226,"GB2-06":51.182489328590215,"GB2-07":54.64746639978847},"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":1336.1131719010002,"GB2-03":1290.4674775631347,"GB2-04":1394.9368522398438,"GB2-05":1425.5165900748232,"GB2-06":1447.7750047762793,"GB2-07":1513.5929447291321},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1076.4431811485538,"GB2-02":1402.9812080843883,"GB2-03":1420.0829206933058,"GB2-04":1394.685396465057,"GB2-05":1761.4113291594228,"GB2-06":1149.6591580353102,"GB2-07":1721.3774930411432},"medium":{"GB2-01":1650.5071520267834,"GB2-03":1267.3935978692582,"GB2-04":1387.3919879141274,"GB2-05":1443.4625680267284,"GB2-06":1445.364446605583,"GB2-07":1740.4477718400842,"GB2-08":1160.1230178144444},"none":{"GB2-01":1281.3891825276637,"GB2-02":1407.9355934071364,"GB2-03":1183.92591412684,"GB2-04":1402.7331723403474,"GB2-05":1071.6758730383183,"GB2-06":1748.3014096879447,"GB2-07":1078.953569306169}},"per_game_tracks":{"highest":{"GB2-01":14.931506354971024,"GB2-02":41.111782530814864,"GB2-03":49.13808216264724,"GB2-04":39.65423019410055,"GB2-05":72.78229423571837,"GB2-06":32.163984579948654,"GB2-07":70.24770752752374},"medium":{"GB2-01":68.11346235814054,"GB2-03":31.849547148522728,"GB2-04":38.73254406931057,"GB2-05":50.48751301185782,"GB2-06":51.660210126745696,"GB2-07":71.47140899698569,"GB2-08":29.05883933830283},"none":{"GB2-01":30.909664676470744,"GB2-02":41.74701132948479,"GB2-03":23.49151007875027,"GB2-04":40.67743529617756,"GB2-05":23.534296912770603,"GB2-06":69.7232732790763,"GB2-07":22.22328267485598}},"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":40.00369844821555,"medium":42.67169063123324,"none":31.538309280948283},"reasoning_agg":{"highest":{"max":72.78229423571837,"mean":40.00369844821555,"min":0.0},"medium":{"max":71.47140899698569,"mean":42.67169063123324,"min":0.0},"none":{"max":69.7232732790763,"mean":31.538309280948283,"min":0.0}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":11.133381350284957},"working_program_strength":{"all":43.509980327770315,"highest":45.71851251224634,"medium":48.767646435695134,"none":36.04378203536947}},{"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":0.40576999999999996},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.42810400000000004},"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":0.428104},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760899999999998},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.0014829999999997},"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":36.437202664448485,"highest":43.02828227925883,"medium":40.135867311216444,"none":26.147458402870175},"first_seen_at":null,"game_gaps":{"medium":{"GB2-07":"failed"},"none":{"GB2-02":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":157,"total_output_tokens":288440,"total_reasoning_output_tokens":204471,"total_visible_output_tokens":83969,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":38.689791152987624,"score":38.689791152987624},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.26392443461065,"score":26.842616289740434},"GB2-03":{"attempts":3,"playable":42.68953433131849,"score":42.68953433131849},"GB2-04":{"attempts":3,"playable":40.67602002741477,"score":40.67602002741477},"GB2-05":{"attempts":3,"playable":38.36891427996026,"score":38.36891427996026},"GB2-06":{"attempts":3,"playable":17.503696495344197,"score":17.503696495344197},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":37.04158353467015,"score":24.694389023113434},"GB2-08":{"attempts":3,"playable":62.032659715708654,"score":62.032659715708654}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.31722481191092,"score":41.31722481191092},"GB2-02":{"attempts":1,"playable":41.00587206875293,"score":41.00587206875293},"GB2-03":{"attempts":1,"playable":41.61560876606564,"score":41.61560876606564},"GB2-04":{"attempts":1,"playable":38.527623776115156,"score":38.527623776115156},"GB2-05":{"attempts":1,"playable":49.912626901458104,"score":49.912626901458104},"GB2-06":{"attempts":1,"playable":20.304515731648973,"score":20.304515731648973},"GB2-07":{"attempts":1,"playable":45.0151740935915,"score":45.0151740935915},"GB2-08":{"attempts":1,"playable":66.52761208452745,"score":66.52761208452745}},"medium":{"GB2-01":{"attempts":1,"playable":50.942176921604464,"score":50.942176921604464},"GB2-02":{"attempts":1,"playable":39.52197680046837,"score":39.52197680046837},"GB2-03":{"attempts":1,"playable":40.46078193506135,"score":40.46078193506135},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":48.37827969173142,"score":48.37827969173142},"GB2-06":{"attempts":1,"playable":14.163085520441673,"score":14.163085520441673},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":86.94320232424666,"score":86.94320232424666}},"none":{"GB2-01":{"attempts":1,"playable":23.809971725447504,"score":23.809971725447504},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.99221229282847,"score":45.99221229282847},"GB2-04":{"attempts":1,"playable":42.82300100995158,"score":42.82300100995158},"GB2-05":{"attempts":1,"playable":16.815836246691234,"score":16.815836246691234},"GB2-06":{"attempts":1,"playable":18.043488233941947,"score":18.043488233941947},"GB2-07":{"attempts":1,"playable":29.0679929757488,"score":29.0679929757488},"GB2-08":{"attempts":1,"playable":32.62716473835184,"score":32.62716473835184}}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:43Z","match_totals_all":{"draws":2800,"losses":5615,"wins":2839},"match_totals_tracks":{"highest":{"draws":1126,"losses":1855,"wins":1107},"medium":{"draws":831,"losses":1565,"wins":1162},"none":{"draws":843,"losses":2195,"wins":570}},"model_slug":"bytedance-seed-seed-2-0-code","official_rank_by_reasoning":{"highest":49,"medium":54,"none":73},"overall":{"max":86.94320232424666,"mean":36.437202664448485,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.31722481191092,"GB2-02":41.00587206875293,"GB2-03":41.61560876606564,"GB2-04":38.527623776115156,"GB2-05":49.912626901458104,"GB2-06":20.304515731648973,"GB2-07":45.0151740935915,"GB2-08":66.52761208452745},"per_game_all":{"GB2-01":38.689791152987624,"GB2-03":42.68953433131849,"GB2-04":40.67602002741477,"GB2-05":38.36891427996026,"GB2-06":17.503696495344197,"GB2-08":62.032659715708654},"per_game_match_totals_all":{"GB2-01":{"draws":392,"losses":782,"wins":374},"GB2-02":{"draws":708,"losses":235,"wins":17},"GB2-03":{"draws":337,"losses":737,"wins":408},"GB2-04":{"draws":987,"losses":417,"wins":90},"GB2-05":{"draws":0,"losses":1002,"wins":588},"GB2-06":{"draws":9,"losses":1279,"wins":218},"GB2-07":{"draws":0,"losses":694,"wins":366},"GB2-08":{"draws":367,"losses":469,"wins":778}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":208,"losses":209,"wins":99},"GB2-02":{"draws":362,"losses":110,"wins":8},"GB2-03":{"draws":134,"losses":240,"wins":120},"GB2-04":{"draws":316,"losses":156,"wins":26},"GB2-05":{"draws":0,"losses":274,"wins":256},"GB2-06":{"draws":3,"losses":414,"wins":85},"GB2-07":{"draws":0,"losses":305,"wins":225},"GB2-08":{"draws":103,"losses":147,"wins":288}},"medium":{"GB2-01":{"draws":68,"losses":230,"wins":218},"GB2-02":{"draws":346,"losses":125,"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":3,"losses":441,"wins":58},"GB2-08":{"draws":0,"losses":78,"wins":460}},"none":{"GB2-01":{"draws":116,"losses":343,"wins":57},"GB2-03":{"draws":102,"losses":235,"wins":157},"GB2-04":{"draws":358,"losses":114,"wins":26},"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":264,"losses":244,"wins":30}}},"per_game_raw_elo_all":{"GB2-01":1355.0333293514138,"GB2-03":1363.9614563315197,"GB2-04":1402.657609750663,"GB2-05":1267.6314244120451,"GB2-06":917.085084530138,"GB2-08":1630.0691015501761},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1386.1598088145818,"GB2-02":1402.1537380681266,"GB2-03":1354.6509784254854,"GB2-04":1385.7641121498975,"GB2-05":1436.3156100355102,"GB2-06":965.9262059683973,"GB2-07":1385.4338142203014,"GB2-08":1624.3657984374445},"medium":{"GB2-01":1478.0348355100698,"GB2-02":1390.5106332137198,"GB2-03":1344.589577549028,"GB2-04":1402.7331723403474,"GB2-05":1417.2568345658124,"GB2-06":857.3820054439727,"GB2-08":2066.860001818117},"none":{"GB2-01":1200.9053437295897,"GB2-03":1392.6438130200452,"GB2-04":1419.475544761744,"GB2-05":949.321828634813,"GB2-06":927.9470421780442,"GB2-07":1180.0505604090772,"GB2-08":1198.9815043949666}},"per_game_tracks":{"highest":{"GB2-01":41.31722481191092,"GB2-02":41.00587206875293,"GB2-03":41.61560876606564,"GB2-04":38.527623776115156,"GB2-05":49.912626901458104,"GB2-06":20.304515731648973,"GB2-07":45.0151740935915,"GB2-08":66.52761208452745},"medium":{"GB2-01":50.942176921604464,"GB2-02":39.52197680046837,"GB2-03":40.46078193506135,"GB2-04":40.67743529617756,"GB2-05":48.37827969173142,"GB2-06":14.163085520441673,"GB2-08":86.94320232424666},"none":{"GB2-01":23.809971725447504,"GB2-03":45.99221229282847,"GB2-04":42.82300100995158,"GB2-05":16.815836246691234,"GB2-06":18.043488233941947,"GB2-07":29.0679929757488,"GB2-08":32.62716473835184}},"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":1,"rank_movement_baseline_at":"2026-10-24T19:21:15Z","reasoning":{"highest":43.02828227925883,"medium":40.135867311216444,"none":26.147458402870175},"reasoning_agg":{"highest":{"max":66.52761208452745,"mean":43.02828227925883,"min":20.304515731648973},"medium":{"max":86.94320232424666,"mean":40.135867311216444,"min":0.0},"none":{"max":45.99221229282847,"mean":26.147458402870175,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":16.880823876388657},"working_program_strength":{"all":39.59355150797642,"highest":43.02828227925883,"medium":45.869562641390225,"none":29.8828096032802}},{"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":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.345102}},"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":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_cost_usd":{"admitted_cell_count":33,"cell_count":24,"cost_basis_counts":{"estimated":32,"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":15,"max":0.1097735,"mean":0.06116525,"median":0.054719000000000004,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":58},"recorded_attempt_count":32,"run_count":48,"token_priced_attempt_count":26,"total":3.663629999999999},"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":36.235655526526436,"highest":32.05428032485568,"medium":34.30300012709623,"none":42.349686127627386},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"too_slow","GB2-04":"failed"},"medium":{"GB2-02":"failed","GB2-03":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[100000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":82,"output_token_observations":58,"provider_post_attempt_observations":10,"provider_post_attempts":10,"reasoning_token_observations":10,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[100000],"total_output_tokens":345212,"total_reasoning_output_tokens":5824,"total_visible_output_tokens":17542,"visible_token_observations":10},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":45.37979239589587,"score":40.31176576452305},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.487598451954895,"score":21.243799225977448},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":39.080886955246186,"score":16.99596809251327},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":42.9235838167643,"score":28.615722544509534},"GB2-05":{"attempts":6,"playable":48.397945071952115,"score":48.397945071952115},"GB2-06":{"attempts":6,"playable":44.87884802518503,"score":44.87884802518503},"GB2-07":{"attempts":6,"playable":47.08329360060379,"score":47.08329360060379},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":42.7400443845234,"score":38.754408187321175}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":60.81631957647386,"score":45.612239682355394},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":36.23182617727008,"score":9.05795654431752},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":49.02142322077218,"score":49.02142322077218},"GB2-06":{"attempts":4,"playable":41.49880946747784,"score":41.49880946747784},"GB2-07":{"attempts":4,"playable":43.3188075842468,"score":43.3188075842468},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":47.827634366426736,"score":35.87072577482005}},"medium":{"GB2-01":{"attempts":1,"playable":37.46358856237706,"score":37.46358856237706},"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":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":1,"playable":44.72738826431963,"score":44.72738826431963},"GB2-06":{"attempts":1,"playable":45.24522447749243,"score":45.24522447749243},"GB2-07":{"attempts":1,"playable":58.72681136385298,"score":58.72681136385298},"GB2-08":{"attempts":1,"playable":47.07230982693174,"score":47.07230982693174}},"none":{"GB2-01":{"attempts":1,"playable":37.859469048836694,"score":37.859469048836694},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"playable":41.92994773322229,"score":41.92994773322229},"GB2-04":{"attempts":1,"playable":44.65848911173256,"score":44.65848911173256},"GB2-05":{"attempts":1,"playable":51.44502373076455,"score":51.44502373076455},"GB2-06":{"attempts":1,"playable":47.89251013058481,"score":47.89251013058481},"GB2-07":{"attempts":1,"playable":39.204261853711586,"score":39.204261853711586},"GB2-08":{"attempts":1,"playable":33.32018896021172,"score":33.32018896021172}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:04Z","match_totals_all":{"draws":2202,"losses":8608,"wins":6296},"match_totals_tracks":{"highest":{"draws":540,"losses":5212,"wins":4152},"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":58.72681136385298,"mean":36.235655526526436,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.81631957647386,"GB2-03":36.23182617727008,"GB2-05":49.02142322077218,"GB2-06":41.49880946747784,"GB2-07":43.3188075842468,"GB2-08":47.827634366426736},"per_game_all":{"GB2-01":45.37979239589587,"GB2-05":48.397945071952115,"GB2-06":44.87884802518503,"GB2-07":47.08329360060379,"GB2-08":42.7400443845234},"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":52,"losses":1812,"wins":1148},"GB2-07":{"draws":0,"losses":1820,"wins":1360},"GB2-08":{"draws":613,"losses":1254,"wins":823}},"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":15,"losses":1249,"wins":744},"GB2-07":{"draws":0,"losses":1254,"wins":866},"GB2-08":{"draws":241,"losses":765,"wins":608}},"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":1425.6752822056744,"GB2-05":1417.4069236392236,"GB2-06":1341.1941777714185,"GB2-07":1411.6676398364627,"GB2-08":1322.3194112323315},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1576.1274405875865,"GB2-03":1307.3115788160496,"GB2-05":1425.0904955901367,"GB2-06":1289.7597655910458,"GB2-07":1363.0664476686502,"GB2-08":1404.3470710006798},"medium":{"GB2-01":1348.491421078167,"GB2-04":1406.7373394219212,"GB2-05":1371.7457633487018,"GB2-06":1346.703099816814,"GB2-07":1559.0396727162702,"GB2-08":1356.1780614070835},"none":{"GB2-01":1352.4069849512698,"GB2-02":1413.6948813920858,"GB2-03":1357.3845406048026,"GB2-04":1433.6980517970223,"GB2-05":1455.384511978832,"GB2-06":1387.119667906396,"GB2-07":1312.896799124468,"GB2-08":1206.4331012892305}},"per_game_tracks":{"highest":{"GB2-01":60.81631957647386,"GB2-03":36.23182617727008,"GB2-05":49.02142322077218,"GB2-06":41.49880946747784,"GB2-07":43.3188075842468,"GB2-08":47.827634366426736},"medium":{"GB2-01":37.46358856237706,"GB2-04":41.18867852179604,"GB2-05":44.72738826431963,"GB2-06":45.24522447749243,"GB2-07":58.72681136385298,"GB2-08":47.07230982693174},"none":{"GB2-01":37.859469048836694,"GB2-02":42.487598451954895,"GB2-03":41.92994773322229,"GB2-04":44.65848911173256,"GB2-05":51.44502373076455,"GB2-06":47.89251013058481,"GB2-07":39.204261853711586,"GB2-08":33.32018896021172}},"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":-1,"rank_movement_baseline_at":"2026-10-24T18:09:41Z","reasoning":{"highest":32.05428032485568,"medium":34.30300012709623,"none":42.349686127627386},"reasoning_agg":{"highest":{"max":49.02142322077218,"mean":32.05428032485568,"min":0.0},"medium":{"max":58.72681136385298,"mean":34.30300012709623,"min":0.0},"none":{"max":51.44502373076455,"mean":42.349686127627386,"min":33.32018896021172}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.295405802771704},"working_program_strength":{"all":44.84649656528898,"highest":46.45247006544458,"medium":45.737333502794975,"none":42.349686127627386}},{"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":2.0928052},"codegen_latency_ms":{"attempt_count":38,"max_ms":2128037,"mean_ms":537328.375,"min_ms":33625,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":2128037,"mean_ms":1259891.875,"min_ms":809012,"run_count":8},"medium":{"attempt_count":13,"max_ms":394009,"mean_ms":249918.25,"min_ms":106640,"run_count":8},"none":{"attempt_count":14,"max_ms":139550,"mean_ms":102175.0,"min_ms":33625,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":142524,"output_mean":33293.458333333336,"output_min":2177,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":142524,"output_mean":77872.0,"output_min":45409,"run_count":8},"medium":{"attempt_count":13,"output_max":24263,"output_mean":15845.5,"output_min":6781,"run_count":8},"none":{"attempt_count":14,"output_max":9194,"output_mean":6162.875,"output_min":2177,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"all":34.59326083819388,"highest":45.45528204178371,"medium":40.828320729133,"none":17.49617974366492},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-08":"failed"},"none":{"GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[131072],"finish_reason_observations":38,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":41,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"reconciliation_get_attempts":53,"requested_max_output_token_observations":27,"requested_max_output_tokens":[131072],"total_output_tokens":799043,"total_reasoning_output_tokens":636129,"total_visible_output_tokens":162914,"visible_token_observations":38},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-27b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":50.90554664525774,"score":50.90554664525774},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.06446832874224,"score":28.04297888582816},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":45.82290792279751,"score":30.548605281865008},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":55.62007741806809,"score":37.080051612045395},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.262151563671,"score":39.50810104244733},"GB2-06":{"attempts":3,"playable":40.46175290498238,"score":40.46175290498238},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":49.638088061840136,"score":33.09205870789342},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":51.320974875694716,"score":17.106991625231572}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.71142886560035,"score":74.71142886560035},"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":71.07420340446123,"score":71.07420340446123},"GB2-05":{"attempts":1,"playable":59.262151563671,"score":59.262151563671},"GB2-06":{"attempts":1,"playable":29.033746354786555,"score":29.033746354786555},"GB2-07":{"attempts":1,"playable":78.23975127005579,"score":78.23975127005579},"GB2-08":{"attempts":1,"playable":51.320974875694716,"score":51.320974875694716}},"medium":{"GB2-01":{"attempts":1,"playable":53.091730974515094,"score":53.091730974515094},"GB2-02":{"attempts":1,"playable":42.1702722263371,"score":42.1702722263371},"GB2-03":{"attempts":1,"playable":48.983436825560815,"score":48.983436825560815},"GB2-04":{"attempts":1,"playable":40.16595143167495,"score":40.16595143167495},"GB2-05":{"attempts":1,"playable":59.262151563671,"score":59.262151563671},"GB2-06":{"attempts":1,"playable":61.916597957680565,"score":61.916597957680565},"GB2-07":{"attempts":1,"playable":21.036424853624478,"score":21.036424853624478},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"playable":24.91348009565777,"score":24.91348009565777},"GB2-02":{"attempts":1,"playable":41.95866443114737,"score":41.95866443114737},"GB2-03":{"attempts":1,"playable":42.6623790200342,"score":42.6623790200342},"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":30.434914402480022,"score":30.434914402480022},"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":1876,"losses":3690,"wins":3090},"match_totals_tracks":{"highest":{"draws":239,"losses":1174,"wins":1701},"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":46,"medium":53},"overall":{"max":78.23975127005579,"mean":34.59326083819388,"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":74.71142886560035,"GB2-04":71.07420340446123,"GB2-05":59.262151563671,"GB2-06":29.033746354786555,"GB2-07":78.23975127005579,"GB2-08":51.320974875694716},"per_game_all":{"GB2-01":50.90554664525774,"GB2-06":40.46175290498238},"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":63,"losses":249,"wins":226}},"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":63,"losses":249,"wins":226}},"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":1480.0824382755388,"GB2-06":1279.1243935457294},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1727.489417939916,"GB2-04":1653.9482456893322,"GB2-05":1555.2450737850634,"GB2-06":1102.414252292945,"GB2-07":1857.6458692209237,"GB2-08":1406.283065893548},"medium":{"GB2-01":1498.5767111965495,"GB2-02":1411.229195836158,"GB2-03":1418.727152417578,"GB2-04":1398.7161843538827,"GB2-05":1555.2450737850634,"GB2-06":1611.3518049296445,"GB2-07":1059.7832929100819},"none":{"GB2-01":1214.1811856901504,"GB2-02":1409.5832822880382,"GB2-03":1363.747703223939,"GB2-06":1123.6071234145984}},"per_game_tracks":{"highest":{"GB2-01":74.71142886560035,"GB2-04":71.07420340446123,"GB2-05":59.262151563671,"GB2-06":29.033746354786555,"GB2-07":78.23975127005579,"GB2-08":51.320974875694716},"medium":{"GB2-01":53.091730974515094,"GB2-02":42.1702722263371,"GB2-03":48.983436825560815,"GB2-04":40.16595143167495,"GB2-05":59.262151563671,"GB2-06":61.916597957680565,"GB2-07":21.036424853624478},"none":{"GB2-01":24.91348009565777,"GB2-02":41.95866443114737,"GB2-03":42.6623790200342,"GB2-06":30.434914402480022}},"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":45.45528204178371,"medium":40.828320729133,"none":17.49617974366492},"reasoning_agg":{"highest":{"max":78.23975127005579,"mean":45.45528204178371,"min":0.0},"medium":{"max":61.916597957680565,"mean":40.828320729133,"min":0.0},"none":{"max":42.6623790200342,"mean":17.49617974366492,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":27.95910229811879},"working_program_strength":{"all":47.420113395286705,"highest":60.60704272237828,"medium":46.660937976152,"none":34.99235948732984}},{"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":0.09094043002},"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":0.010671596919999998}},"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":0.03996709936},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.05097333066},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.01067159692},"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":34.20082731285799,"highest":36.57606113748682,"medium":34.886324002744516,"none":31.14009679834263},"first_seen_at":null,"game_gaps":{"highest":{"GB2-05":"failed"},"none":{"GB2-04":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":339820,"total_reasoning_output_tokens":258096,"total_visible_output_tokens":81724,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":24.865429877193744,"score":24.865429877193744},"GB2-02":{"attempts":5,"playable":41.48573833052928,"score":41.48573833052928},"GB2-03":{"attempts":4,"playable":37.86568196557769,"score":37.86568196557769},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.59709508256233,"score":27.731396721708222},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":35.32858348369627,"score":23.552388989130847},"GB2-06":{"attempts":5,"playable":54.83006983594731,"score":54.83006983594731},"GB2-07":{"attempts":5,"playable":27.97527869177901,"score":27.97527869177901},"GB2-08":{"attempts":5,"playable":35.3006340909978,"score":35.3006340909978}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":15.64110811112249,"score":15.64110811112249},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":34.7408210165092,"score":34.7408210165092},"GB2-04":{"attempts":1,"playable":42.41466060211229,"score":42.41466060211229},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":82.0934769045649,"score":82.0934769045649},"GB2-07":{"attempts":1,"playable":39.01539001530872,"score":39.01539001530872},"GB2-08":{"attempts":1,"playable":35.792493154349145,"score":35.792493154349145}},"medium":{"GB2-01":{"attempts":3,"playable":38.262472664348486,"score":38.262472664348486},"GB2-02":{"attempts":3,"playable":39.69383216676119,"score":39.69383216676119},"GB2-03":{"attempts":2,"playable":43.79543121746261,"score":43.79543121746261},"GB2-04":{"attempts":2,"playable":40.77952956301237,"score":40.77952956301237},"GB2-05":{"attempts":3,"playable":25.737415005182402,"score":25.737415005182402},"GB2-06":{"attempts":3,"playable":25.89396726889154,"score":25.89396726889154},"GB2-07":{"attempts":3,"playable":25.662333306361614,"score":25.662333306361614},"GB2-08":{"attempts":3,"playable":39.26561082993595,"score":39.26561082993595}},"none":{"GB2-01":{"attempts":1,"playable":20.692708856110247,"score":20.692708856110247},"GB2-02":{"attempts":1,"playable":41.852843528898845,"score":41.852843528898845},"GB2-03":{"attempts":1,"playable":35.06079366276128,"score":35.06079366276128},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.919751962210135,"score":44.919751962210135},"GB2-06":{"attempts":1,"playable":56.50276533438551,"score":56.50276533438551},"GB2-07":{"attempts":1,"playable":19.248112753666703,"score":19.248112753666703},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T02:04:59Z","match_totals_all":{"draws":4601,"losses":9936,"wins":3884},"match_totals_tracks":{"highest":{"draws":1165,"losses":1572,"wins":821},"medium":{"draws":2623,"losses":6366,"wins":2284},"none":{"draws":813,"losses":1998,"wins":779}},"model_slug":"deepseek-deepseek-v4-flash","official_rank_by_reasoning":{"highest":52,"medium":61,"none":58},"overall":{"max":82.0934769045649,"mean":34.20082731285799,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":15.64110811112249,"GB2-02":42.910539295927805,"GB2-03":34.7408210165092,"GB2-04":42.41466060211229,"GB2-06":82.0934769045649,"GB2-07":39.01539001530872,"GB2-08":35.792493154349145},"per_game_all":{"GB2-01":24.865429877193744,"GB2-02":41.48573833052928,"GB2-03":37.86568196557769,"GB2-06":54.83006983594731,"GB2-07":27.97527869177901,"GB2-08":35.3006340909978},"per_game_match_totals_all":{"GB2-01":{"draws":401,"losses":1640,"wins":539},"GB2-02":{"draws":1789,"losses":566,"wins":45},"GB2-03":{"draws":563,"losses":990,"wins":424},"GB2-04":{"draws":982,"losses":410,"wins":102},"GB2-05":{"draws":0,"losses":1499,"wins":621},"GB2-06":{"draws":59,"losses":1471,"wins":980},"GB2-07":{"draws":0,"losses":1993,"wins":657},"GB2-08":{"draws":807,"losses":1367,"wins":516}},"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":143,"losses":268,"wins":83},"GB2-04":{"draws":296,"losses":147,"wins":55},"GB2-06":{"draws":37,"losses":81,"wins":384},"GB2-07":{"draws":0,"losses":337,"wins":193},"GB2-08":{"draws":238,"losses":241,"wins":59}},"medium":{"GB2-01":{"draws":189,"losses":888,"wins":471},"GB2-02":{"draws":1059,"losses":362,"wins":19},"GB2-03":{"draws":282,"losses":453,"wins":254},"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":393,"losses":829,"wins":392}},"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":8,"losses":235,"wins":259},"GB2-07":{"draws":0,"losses":439,"wins":91},"GB2-08":{"draws":176,"losses":297,"wins":65}}},"per_game_raw_elo_all":{"GB2-01":1197.0673053337075,"GB2-02":1405.7744529517242,"GB2-03":1321.4313199560536,"GB2-06":1515.925284743007,"GB2-07":1149.825041818697,"GB2-08":1229.073717480784},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1088.0018238894809,"GB2-02":1416.9768592403107,"GB2-03":1293.918570041053,"GB2-04":1416.3007191678437,"GB2-06":1987.1082422919399,"GB2-07":1310.5166702806316,"GB2-08":1232.8949922586762},"medium":{"GB2-01":1341.8878003990555,"GB2-02":1391.5868357130064,"GB2-03":1373.568432347583,"GB2-04":1403.5259079598877,"GB2-05":1064.6223088128977,"GB2-06":1038.5951382938842,"GB2-07":1109.3141954480682,"GB2-08":1274.6416237451947},"none":{"GB2-01":1161.3122917125856,"GB2-02":1408.7596639018554,"GB2-03":1296.806957479525,"GB2-05":1374.1570739105443,"GB2-06":1522.0724736431973,"GB2-07":1029.6442597273913,"GB2-08":1179.6845364384803}},"per_game_tracks":{"highest":{"GB2-01":15.64110811112249,"GB2-02":42.910539295927805,"GB2-03":34.7408210165092,"GB2-04":42.41466060211229,"GB2-06":82.0934769045649,"GB2-07":39.01539001530872,"GB2-08":35.792493154349145},"medium":{"GB2-01":38.262472664348486,"GB2-02":39.69383216676119,"GB2-03":43.79543121746261,"GB2-04":40.77952956301237,"GB2-05":25.737415005182402,"GB2-06":25.89396726889154,"GB2-07":25.662333306361614,"GB2-08":39.26561082993595},"none":{"GB2-01":20.692708856110247,"GB2-02":41.852843528898845,"GB2-03":35.06079366276128,"GB2-05":44.919751962210135,"GB2-06":56.50276533438551,"GB2-07":19.248112753666703,"GB2-08":30.843798288708303}},"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":"2026-10-24T19:06:59Z","reasoning":{"highest":36.57606113748682,"medium":34.886324002744516,"none":31.14009679834263},"reasoning_agg":{"highest":{"max":82.0934769045649,"mean":36.57606113748682,"min":0.0},"medium":{"max":43.79543121746261,"mean":34.886324002744516,"min":25.662333306361614},"none":{"max":56.50276533438551,"mean":31.14009679834263,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.4359643391441885},"working_program_strength":{"all":37.4254062621832,"highest":41.801212728556365,"medium":34.886324002744516,"none":35.58868205524872}},{"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":33.428596175704534,"highest":36.845604935949716,"medium":35.7991725745788,"none":27.64101101658508},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":42,"effective_max_output_tokens":[262144],"finish_reason_observations":42,"finish_reasons":["stop"],"indexed_attempts":42,"output_token_observations":42,"provider_post_attempt_observations":42,"provider_post_attempts":42,"reasoning_token_observations":42,"reconciliation_get_attempt_observations":42,"requested_max_output_token_observations":42,"requested_max_output_tokens":[262144],"total_output_tokens":341271,"total_visible_output_tokens":341271,"visible_token_observations":42},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":56.5764097745617,"score":37.71760651637447},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.79952124297172,"score":27.866347495314482},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":40.90207894746507,"score":27.268052631643382},"GB2-04":{"attempts":3,"playable":41.18664500659943,"score":41.18664500659943},"GB2-05":{"attempts":3,"playable":34.14413371354145,"score":34.14413371354145},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":48.505551651737775,"score":32.33703443449185},"GB2-07":{"attempts":3,"playable":45.52100312227699,"score":45.52100312227699},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.08191972809129,"score":21.387946485394195}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.77650188114862,"score":63.77650188114862},"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":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":45.688988962286096,"score":45.688988962286096},"GB2-06":{"attempts":1,"playable":38.81864854033569,"score":38.81864854033569},"GB2-07":{"attempts":1,"playable":74.43144469769753,"score":74.43144469769753},"GB2-08":{"attempts":1,"playable":33.41916692759776,"score":33.41916692759776}},"medium":{"GB2-01":{"attempts":1,"playable":49.37631766797478,"score":49.37631766797478},"GB2-02":{"attempts":1,"playable":42.69909194377107,"score":42.69909194377107},"GB2-03":{"attempts":1,"playable":45.78498915227661,"score":45.78498915227661},"GB2-04":{"attempts":1,"playable":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":1,"playable":13.170633701862291,"score":13.170633701862291},"GB2-06":{"attempts":1,"playable":58.192454763139864,"score":58.192454763139864},"GB2-07":{"attempts":1,"playable":35.98121484580971,"score":35.98121484580971},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":40.89995054217238,"score":40.89995054217238},"GB2-03":{"attempts":1,"playable":36.019168742653534,"score":36.019168742653534},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":1,"playable":43.57277847647596,"score":43.57277847647596},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.150349823323733,"score":26.150349823323733},"GB2-08":{"attempts":1,"playable":30.744672528584836,"score":30.744672528584836}}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:58Z","match_totals_all":{"draws":2396,"losses":4653,"wins":2685},"match_totals_tracks":{"highest":{"draws":542,"losses":1379,"wins":1193},"medium":{"draws":912,"losses":1735,"wins":903},"none":{"draws":942,"losses":1539,"wins":589}},"model_slug":"stealth-space-bunny-alpha","official_rank_by_reasoning":{"highest":51,"medium":59,"none":71},"overall":{"max":74.43144469769753,"mean":33.428596175704534,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.77650188114862,"GB2-04":38.63008847853202,"GB2-05":45.688988962286096,"GB2-06":38.81864854033569,"GB2-07":74.43144469769753,"GB2-08":33.41916692759776},"per_game_all":{"GB2-04":41.18664500659943,"GB2-05":34.14413371354145,"GB2-07":45.52100312227699},"per_game_match_totals_all":{"GB2-01":{"draws":248,"losses":346,"wins":438},"GB2-02":{"draws":749,"losses":200,"wins":11},"GB2-03":{"draws":219,"losses":511,"wins":258},"GB2-04":{"draws":952,"losses":427,"wins":115},"GB2-05":{"draws":0,"losses":1068,"wins":522},"GB2-06":{"draws":11,"losses":554,"wins":439},"GB2-07":{"draws":0,"losses":898,"wins":692},"GB2-08":{"draws":217,"losses":649,"wins":210}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":154,"losses":121,"wins":241},"GB2-04":{"draws":291,"losses":168,"wins":39},"GB2-05":{"draws":0,"losses":296,"wins":234},"GB2-06":{"draws":5,"losses":327,"wins":170},"GB2-07":{"draws":0,"losses":141,"wins":389},"GB2-08":{"draws":92,"losses":326,"wins":120}},"medium":{"GB2-01":{"draws":94,"losses":225,"wins":197},"GB2-02":{"draws":378,"losses":94,"wins":8},"GB2-03":{"draws":102,"losses":236,"wins":156},"GB2-04":{"draws":332,"losses":135,"wins":31},"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":371,"losses":106,"wins":3},"GB2-03":{"draws":117,"losses":275,"wins":102},"GB2-04":{"draws":329,"losses":124,"wins":45},"GB2-05":{"draws":0,"losses":307,"wins":223},"GB2-07":{"draws":0,"losses":404,"wins":126},"GB2-08":{"draws":125,"losses":323,"wins":90}}},"per_game_raw_elo_all":{"GB2-04":1406.6381439418303,"GB2-05":1204.2906173913395,"GB2-07":1399.8103916769535},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1604.3168595739435,"GB2-04":1386.5783876383734,"GB2-05":1383.7801956738601,"GB2-06":1249.6170592520937,"GB2-07":1788.8832935983105,"GB2-08":1207.495686188623},"medium":{"GB2-01":1463.1277080560324,"GB2-02":1415.3366437603197,"GB2-03":1390.8438863987412,"GB2-04":1406.7373394219212,"GB2-05":871.867338237239,"GB2-06":1549.4853190832127,"GB2-07":1271.9318931743353},"none":{"GB2-02":1401.3257484478688,"GB2-03":1305.4112530196908,"GB2-04":1426.598704765196,"GB2-05":1357.2243182629188,"GB2-07":1138.615988258215,"GB2-08":1178.6055589508921}},"per_game_tracks":{"highest":{"GB2-01":63.77650188114862,"GB2-04":38.63008847853202,"GB2-05":45.688988962286096,"GB2-06":38.81864854033569,"GB2-07":74.43144469769753,"GB2-08":33.41916692759776},"medium":{"GB2-01":49.37631766797478,"GB2-02":42.69909194377107,"GB2-03":45.78498915227661,"GB2-04":41.18867852179604,"GB2-05":13.170633701862291,"GB2-06":58.192454763139864,"GB2-07":35.98121484580971},"none":{"GB2-02":40.89995054217238,"GB2-03":36.019168742653534,"GB2-04":43.74116801947021,"GB2-05":43.57277847647596,"GB2-07":26.150349823323733,"GB2-08":30.744672528584836}},"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":"2026-10-24T19:02:40Z","reasoning":{"highest":36.845604935949716,"medium":35.7991725745788,"none":27.64101101658508},"reasoning_agg":{"highest":{"max":74.43144469769753,"mean":36.845604935949716,"min":0.0},"medium":{"max":58.192454763139864,"mean":35.7991725745788,"min":0.0},"none":{"max":43.74116801947021,"mean":27.64101101658508,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.204593919364637},"working_program_strength":{"all":42.29849822953754,"highest":49.127473247932954,"medium":40.91334008523291,"none":36.85468135544677}},{"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":0.9722945},"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":0.2715711}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093000000001},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.27157109999999995},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000002}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519749},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":33.09758335111059,"highest":32.89978538978541,"medium":27.225511649199216,"none":39.16745301434716},"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":37.705424753578335,"score":31.841360231998504},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":43.13507341987674,"score":28.338718830081707},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":48.293481127523016,"score":39.09496197417404},"GB2-04":{"attempts":6,"playable":43.08944591636314,"score":43.08944591636314},"GB2-05":{"attempts":6,"playable":15.248357952159784,"score":15.248357952159784},"GB2-06":{"attempts":6,"playable":37.239279692158796,"score":37.239279692158796},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":42.558152791836825,"score":39.085118603835596},"GB2-08":{"attempts":6,"playable":30.843423608113195,"score":30.843423608113195}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":35.18438712947898,"score":17.59219356473949},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":45.12788935224403,"score":22.563944676122016},"GB2-03":{"attempts":2,"playable":47.550334569425274,"score":47.550334569425274},"GB2-04":{"attempts":2,"playable":39.755391022817186,"score":39.755391022817186},"GB2-05":{"attempts":2,"playable":18.06278094308005,"score":18.06278094308005},"GB2-06":{"attempts":2,"playable":41.404123575210555,"score":41.404123575210555},"GB2-07":{"attempts":2,"playable":44.73197677868093,"score":44.73197677868093},"GB2-08":{"attempts":2,"playable":31.53753798820775,"score":31.53753798820775}},"medium":{"GB2-01":{"attempts":2,"playable":41.02127603100788,"score":41.02127603100788},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.65023818652617,"score":21.825119093263083},"GB2-03":{"attempts":2,"playable":42.13899389304992,"score":42.13899389304992},"GB2-04":{"attempts":2,"playable":42.46492327063312,"score":42.46492327063312},"GB2-05":{"attempts":2,"playable":15.760817483559318,"score":15.760817483559318},"GB2-06":{"attempts":2,"playable":13.87579640274205,"score":13.87579640274205},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.838205128007385,"score":10.419102564003692},"GB2-08":{"attempts":2,"playable":30.298064455334675,"score":30.298064455334675}},"none":{"GB2-01":{"attempts":2,"playable":36.91061110024815,"score":36.91061110024815},"GB2-02":{"attempts":2,"playable":40.62709272086003,"score":40.62709272086003},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":55.191114920093845,"score":27.595557460046923},"GB2-04":{"attempts":2,"playable":47.048023455639125,"score":47.048023455639125},"GB2-05":{"attempts":2,"playable":11.921475429839985,"score":11.921475429839985},"GB2-06":{"attempts":2,"playable":56.43791909852378,"score":56.43791909852378},"GB2-07":{"attempts":2,"playable":62.104276468822164,"score":62.104276468822164},"GB2-08":{"attempts":2,"playable":30.694668380797154,"score":30.694668380797154}}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:49Z","match_totals_all":{"draws":5335,"losses":11373,"wins":4781},"match_totals_tracks":{"highest":{"draws":1459,"losses":3553,"wins":1630},"medium":{"draws":1904,"losses":4151,"wins":1111},"none":{"draws":1972,"losses":3669,"wins":2040}},"model_slug":"google-gemini-3-5-flash-lite","official_rank_by_reasoning":{"highest":57,"medium":69,"none":46},"overall":{"max":62.104276468822164,"mean":33.09758335111059,"min":10.419102564003692},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":56,"overall_ranking_status":"ranked","per_game":{"GB2-01":35.18438712947898,"GB2-02":45.12788935224403,"GB2-03":47.550334569425274,"GB2-04":39.755391022817186,"GB2-05":18.06278094308005,"GB2-06":41.404123575210555,"GB2-07":44.73197677868093,"GB2-08":31.53753798820775},"per_game_all":{"GB2-01":37.705424753578335,"GB2-02":43.13507341987674,"GB2-03":48.293481127523016,"GB2-04":43.08944591636314,"GB2-05":15.248357952159784,"GB2-06":37.239279692158796,"GB2-07":42.558152791836825,"GB2-08":30.843423608113195},"per_game_match_totals_all":{"GB2-01":{"draws":465,"losses":1411,"wins":704},"GB2-02":{"draws":1498,"losses":386,"wins":35},"GB2-03":{"draws":541,"losses":1135,"wins":794},"GB2-04":{"draws":1836,"losses":832,"wins":320},"GB2-05":{"draws":0,"losses":2725,"wins":455},"GB2-06":{"draws":36,"losses":1970,"wins":1006},"GB2-07":{"draws":0,"losses":1465,"wins":1185},"GB2-08":{"draws":959,"losses":1449,"wins":282}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":100,"losses":294,"wins":122},"GB2-02":{"draws":359,"losses":92,"wins":29},"GB2-03":{"draws":145,"losses":483,"wins":360},"GB2-04":{"draws":596,"losses":318,"wins":82},"GB2-05":{"draws":0,"losses":879,"wins":181},"GB2-06":{"draws":22,"losses":611,"wins":371},"GB2-07":{"draws":0,"losses":613,"wins":447},"GB2-08":{"draws":237,"losses":263,"wins":38}},"medium":{"GB2-01":{"draws":170,"losses":544,"wins":318},"GB2-02":{"draws":397,"losses":80,"wins":3},"GB2-03":{"draws":308,"losses":455,"wins":225},"GB2-04":{"draws":661,"losses":259,"wins":76},"GB2-05":{"draws":0,"losses":903,"wins":157},"GB2-06":{"draws":5,"losses":885,"wins":114},"GB2-07":{"draws":0,"losses":431,"wins":99},"GB2-08":{"draws":363,"losses":594,"wins":119}},"none":{"GB2-01":{"draws":195,"losses":573,"wins":264},"GB2-02":{"draws":742,"losses":214,"wins":3},"GB2-03":{"draws":88,"losses":197,"wins":209},"GB2-04":{"draws":579,"losses":255,"wins":162},"GB2-05":{"draws":0,"losses":943,"wins":117},"GB2-06":{"draws":9,"losses":474,"wins":521},"GB2-07":{"draws":0,"losses":421,"wins":639},"GB2-08":{"draws":359,"losses":592,"wins":125}}},"per_game_raw_elo_all":{"GB2-01":1350.410536923411,"GB2-02":1418.6642575976555,"GB2-03":1413.6478584028962,"GB2-04":1421.411307049392,"GB2-05":913.588255639372,"GB2-06":1222.3372410108245,"GB2-07":1350.056483813799,"GB2-08":1179.616540325039},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1325.688344566556,"GB2-02":1434.121633179476,"GB2-03":1407.573623073482,"GB2-04":1395.4178588466386,"GB2-05":973.4856765781382,"GB2-06":1293.7051934423037,"GB2-07":1381.9067780752562,"GB2-08":1187.2154450503033},"medium":{"GB2-01":1383.2977132679694,"GB2-02":1422.7063547595108,"GB2-03":1359.1993408247122,"GB2-04":1416.6680220935586,"GB2-05":927.9203646429773,"GB2-06":851.6169393616087,"GB2-07":1056.5204537768536,"GB2-08":1173.6448368065712},"none":{"GB2-01":1342.2455529357076,"GB2-02":1399.1647848539794,"GB2-03":1474.1706113104947,"GB2-04":1452.1480402079787,"GB2-05":839.3587256970004,"GB2-06":1521.689590228561,"GB2-07":1611.7422195892875,"GB2-08":1177.9893391182427}},"per_game_tracks":{"highest":{"GB2-01":35.18438712947898,"GB2-02":45.12788935224403,"GB2-03":47.550334569425274,"GB2-04":39.755391022817186,"GB2-05":18.06278094308005,"GB2-06":41.404123575210555,"GB2-07":44.73197677868093,"GB2-08":31.53753798820775},"medium":{"GB2-01":41.02127603100788,"GB2-02":43.65023818652617,"GB2-03":42.13899389304992,"GB2-04":42.46492327063312,"GB2-05":15.760817483559318,"GB2-06":13.87579640274205,"GB2-07":20.838205128007385,"GB2-08":30.298064455334675},"none":{"GB2-01":36.91061110024815,"GB2-02":40.62709272086003,"GB2-03":55.191114920093845,"GB2-04":47.048023455639125,"GB2-05":11.921475429839985,"GB2-06":56.43791909852378,"GB2-07":62.104276468822164,"GB2-08":30.694668380797154}},"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":"2026-10-24T19:12:16Z","reasoning":{"highest":32.89978538978541,"medium":27.225511649199216,"none":39.16745301434716},"reasoning_agg":{"highest":{"max":47.550334569425274,"mean":32.89978538978541,"min":17.59219356473949},"medium":{"max":42.46492327063312,"mean":27.225511649199216,"min":10.419102564003692},"none":{"max":62.104276468822164,"mean":39.16745301434716,"min":11.921475429839985}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.941941365147944},"working_program_strength":{"all":37.26407990770122,"highest":37.91930266989309,"medium":31.25603935635757,"none":42.61689769685302}},{"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":0.072064},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761485}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373185999999999},"codegen_latency_ms":{"attempt_count":43,"max_ms":599272,"mean_ms":125847.07142857143,"min_ms":18961,"run_count":28},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":599272,"mean_ms":283663.1,"min_ms":69866,"run_count":10},"medium":{"attempt_count":15,"max_ms":68712,"mean_ms":42566.11111111111,"min_ms":22862,"run_count":9},"none":{"attempt_count":14,"max_ms":63236,"mean_ms":33776.88888888889,"min_ms":18961,"run_count":9}},"codegen_output_tokens":{"attempt_count":43,"output_max":49133,"output_mean":11683.67857142857,"output_min":894,"run_count":28},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":49133,"output_mean":28182.1,"output_min":11882,"run_count":10},"medium":{"attempt_count":15,"output_max":4066,"output_mean":2679.6666666666665,"output_min":1736,"run_count":9},"none":{"attempt_count":14,"output_max":5147,"output_mean":2356.1111111111113,"output_min":894,"run_count":9}},"display_name":"Inkling Small","economics":{"all":31.794526070879414,"highest":36.154355295356524,"medium":29.78379569122899,"none":29.44542722605273},"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":21.47918166611663,"score":21.47918166611663},"GB2-02":{"attempts":3,"playable":41.74687276729588,"score":41.74687276729588},"GB2-03":{"attempts":3,"playable":47.54102928298632,"score":47.54102928298632},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":43.77451720646989,"score":36.722425501752},"GB2-05":{"attempts":3,"playable":19.136076121949344,"score":19.136076121949344},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":29.671586185149867,"score":23.922328633066357},"GB2-07":{"attempts":3,"playable":35.47872248762044,"score":35.47872248762044},"GB2-08":{"attempts":3,"playable":28.329572106248346,"score":28.329572106248346}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":33.19839222532428,"score":33.19839222532428},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":45.57764655257097,"score":45.57764655257097},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.31255022830733,"score":21.156275114153665},"GB2-05":{"attempts":1,"playable":41.839633609815536,"score":41.839633609815536},"GB2-06":{"attempts":1,"playable":54.51921324294854,"score":54.51921324294854},"GB2-07":{"attempts":1,"playable":18.4501050975686,"score":18.4501050975686},"GB2-08":{"attempts":1,"playable":32.429102513673,"score":32.429102513673}},"medium":{"GB2-01":{"attempts":1,"playable":9.439054404701363,"score":9.439054404701363},"GB2-02":{"attempts":1,"playable":42.1702722263371,"score":42.1702722263371},"GB2-03":{"attempts":1,"playable":40.14521690712411,"score":40.14521690712411},"GB2-04":{"attempts":1,"playable":45.06591040934613,"score":45.06591040934613},"GB2-05":{"attempts":1,"playable":10.097402999951962,"score":10.097402999951962},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.70284515345578,"score":8.85142257672789},"GB2-07":{"attempts":1,"playable":56.02269229466545,"score":56.02269229466545},"GB2-08":{"attempts":1,"playable":26.478393710977922,"score":26.478393710977922}},"none":{"GB2-01":{"attempts":1,"playable":21.800098368324253,"score":21.800098368324253},"GB2-02":{"attempts":1,"playable":41.00587206875293,"score":41.00587206875293},"GB2-03":{"attempts":1,"playable":56.9002243892639,"score":56.9002243892639},"GB2-04":{"attempts":1,"playable":43.945090981756195,"score":43.945090981756195},"GB2-05":{"attempts":1,"playable":5.47119175608054,"score":5.47119175608054},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.792700159045285,"score":8.396350079522643},"GB2-07":{"attempts":1,"playable":31.963370070627274,"score":31.963370070627274},"GB2-08":{"attempts":1,"playable":26.081220094094103,"score":26.081220094094103}}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:44Z","match_totals_all":{"draws":3379,"losses":6774,"wins":2111},"match_totals_tracks":{"highest":{"draws":1214,"losses":2002,"wins":872},"medium":{"draws":1063,"losses":2382,"wins":643},"none":{"draws":1102,"losses":2390,"wins":596}},"model_slug":"thinkingmachines-inkling-small","official_rank_by_reasoning":{"highest":53,"medium":68,"none":66},"overall":{"max":56.9002243892639,"mean":31.794526070879414,"min":5.47119175608054},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":57,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.19839222532428,"GB2-02":42.06447400679762,"GB2-03":45.57764655257097,"GB2-04":42.31255022830733,"GB2-05":41.839633609815536,"GB2-06":54.51921324294854,"GB2-07":18.4501050975686,"GB2-08":32.429102513673},"per_game_all":{"GB2-01":21.47918166611663,"GB2-02":41.74687276729588,"GB2-03":47.54102928298632,"GB2-04":43.77451720646989,"GB2-05":19.136076121949344,"GB2-06":29.671586185149867,"GB2-07":35.47872248762044,"GB2-08":28.329572106248346},"per_game_match_totals_all":{"GB2-01":{"draws":262,"losses":1106,"wins":180},"GB2-02":{"draws":1149,"losses":288,"wins":3},"GB2-03":{"draws":443,"losses":613,"wins":426},"GB2-04":{"draws":952,"losses":389,"wins":153},"GB2-05":{"draws":0,"losses":1302,"wins":288},"GB2-06":{"draws":19,"losses":1098,"wins":389},"GB2-07":{"draws":0,"losses":1062,"wins":528},"GB2-08":{"draws":554,"losses":916,"wins":144}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":140,"losses":284,"wins":92},"GB2-02":{"draws":388,"losses":92,"wins":0},"GB2-03":{"draws":94,"losses":241,"wins":159},"GB2-04":{"draws":311,"losses":140,"wins":47},"GB2-05":{"draws":0,"losses":316,"wins":214},"GB2-06":{"draws":15,"losses":242,"wins":245},"GB2-07":{"draws":0,"losses":443,"wins":87},"GB2-08":{"draws":266,"losses":244,"wins":28}},"medium":{"GB2-01":{"draws":60,"losses":442,"wins":14},"GB2-02":{"draws":387,"losses":92,"wins":1},"GB2-03":{"draws":130,"losses":249,"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":182,"losses":316,"wins":40}},"none":{"GB2-01":{"draws":62,"losses":380,"wins":74},"GB2-02":{"draws":374,"losses":104,"wins":2},"GB2-03":{"draws":219,"losses":123,"wins":152},"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":1150.1335460339644,"GB2-02":1407.9297969177924,"GB2-03":1406.943411869818,"GB2-04":1426.8437548960364,"GB2-05":924.5240554954358,"GB2-06":1106.166204312158,"GB2-07":1252.9599893217116,"GB2-08":1151.5722571563113},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1305.391904574051,"GB2-02":1410.4064568490924,"GB2-03":1389.0434625562089,"GB2-04":1415.5060664905627,"GB2-05":1335.2367315179742,"GB2-06":1490.3486807465188,"GB2-07":1015.6403469798747,"GB2-08":1196.8477269401258},"medium":{"GB2-01":969.2401613078958,"GB2-02":1411.229195836158,"GB2-03":1341.8339683434406,"GB2-04":1436.8469801675587,"GB2-05":795.9167645632368,"GB2-06":922.062259283025,"GB2-07":1523.8368473609687,"GB2-08":1131.2030453967263},"none":{"GB2-01":1175.7685722199465,"GB2-02":1402.1537380681266,"GB2-03":1489.9528047098042,"GB2-04":1428.1782180299879,"GB2-05":642.4186704050967,"GB2-06":906.0876729069307,"GB2-07":1219.402773624292,"GB2-08":1126.665999132082}},"per_game_tracks":{"highest":{"GB2-01":33.19839222532428,"GB2-02":42.06447400679762,"GB2-03":45.57764655257097,"GB2-04":42.31255022830733,"GB2-05":41.839633609815536,"GB2-06":54.51921324294854,"GB2-07":18.4501050975686,"GB2-08":32.429102513673},"medium":{"GB2-01":9.439054404701363,"GB2-02":42.1702722263371,"GB2-03":40.14521690712411,"GB2-04":45.06591040934613,"GB2-05":10.097402999951962,"GB2-06":17.70284515345578,"GB2-07":56.02269229466545,"GB2-08":26.478393710977922},"none":{"GB2-01":21.800098368324253,"GB2-02":41.00587206875293,"GB2-03":56.9002243892639,"GB2-04":43.945090981756195,"GB2-05":5.47119175608054,"GB2-06":16.792700159045285,"GB2-07":31.963370070627274,"GB2-08":26.081220094094103}},"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":"2026-10-24T19:01:26Z","reasoning":{"highest":36.154355295356524,"medium":29.78379569122899,"none":29.44542722605273},"reasoning_agg":{"highest":{"max":54.51921324294854,"mean":36.154355295356524,"min":18.4501050975686},"medium":{"max":56.02269229466545,"mean":29.78379569122899,"min":8.85142257672789},"none":{"max":56.9002243892639,"mean":29.44542722605273,"min":5.47119175608054}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.708928069303795},"working_program_strength":{"all":33.39469472797959,"highest":38.798889684625735,"medium":30.890223513319974,"none":30.49497098599306}},{"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":0.05850166000000001}},"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":0.05850166},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":30.308188774555305,"highest":35.883597102379156,"medium":31.36286013831701,"none":23.678109082969737},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"failed"},"none":{"GB2-02":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":164,"total_output_tokens":154154,"total_reasoning_output_tokens":105962,"total_visible_output_tokens":48432,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-glimmer-30b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":29.995757715173156,"score":29.995757715173156},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.22759991228898,"score":28.818399941525985},"GB2-03":{"attempts":3,"playable":40.65907175548377,"score":40.65907175548377},"GB2-04":{"attempts":3,"playable":46.08079421319206,"score":46.08079421319206},"GB2-05":{"attempts":3,"playable":23.047355482438387,"score":23.047355482438387},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":17.1342988476045,"score":5.711432949201501},"GB2-07":{"attempts":3,"playable":37.474346284011766,"score":37.474346284011766},"GB2-08":{"attempts":3,"playable":30.678351855415784,"score":30.678351855415784}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":31.71092374401135,"score":31.71092374401135},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"GB2-03":{"attempts":1,"playable":37.399390391057594,"score":37.399390391057594},"GB2-04":{"attempts":1,"playable":49.231658345772594,"score":49.231658345772594},"GB2-05":{"attempts":1,"playable":45.88124187411278,"score":45.88124187411278},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":47.79640907135037,"score":47.79640907135037},"GB2-08":{"attempts":1,"playable":32.032907798363944,"score":32.032907798363944}},"medium":{"GB2-01":{"attempts":1,"playable":22.001291370452723,"score":22.001291370452723},"GB2-02":{"attempts":1,"playable":43.43895423021337,"score":43.43895423021337},"GB2-03":{"attempts":1,"playable":39.9346947850152,"score":39.9346947850152},"GB2-04":{"attempts":1,"playable":45.26955627433336,"score":45.26955627433336},"GB2-05":{"attempts":1,"playable":15.473079984383576,"score":15.473079984383576},"GB2-06":{"attempts":1,"playable":17.1342988476045,"score":17.1342988476045},"GB2-07":{"attempts":1,"playable":37.501187377236114,"score":37.501187377236114},"GB2-08":{"attempts":1,"playable":30.149818237297243,"score":30.149818237297243}},"none":{"GB2-01":{"attempts":1,"playable":36.275058031055394,"score":36.275058031055394},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.643130090378534,"score":44.643130090378534},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":1,"playable":7.787744588818808,"score":7.787744588818808},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":27.12544240344881,"score":27.12544240344881},"GB2-08":{"attempts":1,"playable":29.852329530586164,"score":29.852329530586164}}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:42Z","match_totals_all":{"draws":3163,"losses":5716,"wins":1900},"match_totals_tracks":{"highest":{"draws":1191,"losses":1599,"wins":795},"medium":{"draws":1179,"losses":2312,"wins":597},"none":{"draws":793,"losses":1805,"wins":508}},"model_slug":"meta-muse-glimmer-30b","official_rank_by_reasoning":{"highest":54,"medium":65,"none":78},"overall":{"max":49.231658345772594,"mean":30.308188774555305,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.71092374401135,"GB2-02":43.016245594364584,"GB2-03":37.399390391057594,"GB2-04":49.231658345772594,"GB2-05":45.88124187411278,"GB2-07":47.79640907135037,"GB2-08":32.032907798363944},"per_game_all":{"GB2-01":29.995757715173156,"GB2-03":40.65907175548377,"GB2-04":46.08079421319206,"GB2-05":23.047355482438387,"GB2-07":37.474346284011766,"GB2-08":30.678351855415784},"per_game_match_totals_all":{"GB2-01":{"draws":320,"losses":949,"wins":278},"GB2-02":{"draws":786,"losses":168,"wins":6},"GB2-03":{"draws":451,"losses":709,"wins":322},"GB2-04":{"draws":984,"losses":339,"wins":171},"GB2-05":{"draws":0,"losses":1241,"wins":349},"GB2-06":{"draws":1,"losses":429,"wins":72},"GB2-07":{"draws":0,"losses":1034,"wins":556},"GB2-08":{"draws":621,"losses":847,"wins":146}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":293,"wins":87},"GB2-02":{"draws":387,"losses":88,"wins":5},"GB2-03":{"draws":156,"losses":249,"wins":89},"GB2-04":{"draws":287,"losses":118,"wins":93},"GB2-05":{"draws":0,"losses":295,"wins":235},"GB2-07":{"draws":0,"losses":290,"wins":240},"GB2-08":{"draws":226,"losses":266,"wins":46}},"medium":{"GB2-01":{"draws":90,"losses":365,"wins":61},"GB2-02":{"draws":399,"losses":80,"wins":1},"GB2-03":{"draws":130,"losses":250,"wins":114},"GB2-04":{"draws":342,"losses":110,"wins":46},"GB2-05":{"draws":0,"losses":453,"wins":77},"GB2-06":{"draws":1,"losses":429,"wins":72},"GB2-07":{"draws":0,"losses":345,"wins":185},"GB2-08":{"draws":217,"losses":280,"wins":41}},"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":178,"losses":301,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1268.2934106893792,"GB2-03":1346.2070026613294,"GB2-04":1444.675682200698,"GB2-05":1012.0170073203926,"GB2-07":1288.0169122877996,"GB2-08":1177.847464944905},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1289.8753963093654,"GB2-02":1417.796406980097,"GB2-03":1317.6935100666856,"GB2-04":1469.0081577109459,"GB2-05":1386.18091031784,"GB2-07":1420.0044853745724,"GB2-08":1192.5731157294144},"medium":{"GB2-01":1178.3459514523217,"GB2-02":1421.0710505964687,"GB2-03":1339.9938761618187,"GB2-04":1438.420184125952,"GB2-05":921.9879838261603,"GB2-06":912.1283051685773,"GB2-07":1291.3505187570638,"GB2-08":1172.1137289836033},"none":{"GB2-01":1336.6588843064505,"GB2-03":1380.933621755484,"GB2-04":1426.598704765196,"GB2-05":727.8821278171777,"GB2-07":1152.6957327317625,"GB2-08":1168.855550121697}},"per_game_tracks":{"highest":{"GB2-01":31.71092374401135,"GB2-02":43.016245594364584,"GB2-03":37.399390391057594,"GB2-04":49.231658345772594,"GB2-05":45.88124187411278,"GB2-07":47.79640907135037,"GB2-08":32.032907798363944},"medium":{"GB2-01":22.001291370452723,"GB2-02":43.43895423021337,"GB2-03":39.9346947850152,"GB2-04":45.26955627433336,"GB2-05":15.473079984383576,"GB2-06":17.1342988476045,"GB2-07":37.501187377236114,"GB2-08":30.149818237297243},"none":{"GB2-01":36.275058031055394,"GB2-03":44.643130090378534,"GB2-04":43.74116801947021,"GB2-05":7.787744588818808,"GB2-07":27.12544240344881,"GB2-08":29.852329530586164}},"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":"2026-10-24T18:34:55Z","reasoning":{"highest":35.883597102379156,"medium":31.36286013831701,"none":23.678109082969737},"reasoning_agg":{"highest":{"max":49.231658345772594,"mean":35.883597102379156,"min":0.0},"medium":{"max":45.26955627433336,"mean":31.36286013831701,"min":15.473079984383576},"none":{"max":44.643130090378534,"mean":23.678109082969737,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.205488019409419},"working_program_strength":{"all":34.647832502935074,"highest":41.00982525986189,"medium":31.36286013831701,"none":31.570812110626317}},{"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":0.05953976200000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855890999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085672999999999},"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":0.07848132600000002},"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":30.214315420234474,"highest":35.08481708241417,"medium":31.234603233380938,"none":24.323525944908326},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"},"none":{"GB2-04":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":33,"finish_reasons":["stop"],"indexed_attempts":33,"output_token_observations":33,"provider_post_attempt_observations":33,"provider_post_attempts":33,"reasoning_token_observations":33,"reconciliation_get_attempt_observations":33,"reconciliation_get_attempts":158,"total_output_tokens":223323,"total_reasoning_output_tokens":139050,"total_visible_output_tokens":87482,"visible_token_observations":33},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":38.49949571858879,"score":25.666330479059194},"GB2-02":{"attempts":3,"playable":43.22745599184024,"score":43.22745599184024},"GB2-03":{"attempts":3,"playable":39.55240287209788,"score":39.55240287209788},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":40.72709435494931,"score":27.151396236632873},"GB2-05":{"attempts":3,"playable":29.880770757423324,"score":29.880770757423324},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":24.759964175155375,"score":16.506642783436916},"GB2-07":{"attempts":3,"playable":28.06058758590523,"score":28.06058758590523},"GB2-08":{"attempts":3,"playable":31.668936655480177,"score":31.668936655480177}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":46.40629965489456,"score":46.40629965489456},"GB2-04":{"attempts":1,"playable":42.516760894618045,"score":42.516760894618045},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":22.88129159889048,"score":22.88129159889048},"GB2-07":{"attempts":1,"playable":34.07304809595744,"score":34.07304809595744},"GB2-08":{"attempts":1,"playable":32.62716473835184,"score":32.62716473835184}},"medium":{"GB2-01":{"attempts":1,"playable":35.97771540616969,"score":35.97771540616969},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"playable":35.91279705643585,"score":35.91279705643585},"GB2-04":{"attempts":1,"playable":38.93742781528057,"score":38.93742781528057},"GB2-05":{"attempts":1,"playable":15.66490775172327,"score":15.66490775172327},"GB2-06":{"attempts":1,"playable":26.638636751420268,"score":26.638636751420268},"GB2-07":{"attempts":1,"playable":21.23452636920462,"score":21.23452636920462},"GB2-08":{"attempts":1,"playable":33.02321626485831,"score":33.02321626485831}},"none":{"GB2-01":{"attempts":1,"playable":41.02127603100788,"score":41.02127603100788},"GB2-02":{"attempts":1,"playable":43.33329461578827,"score":43.33329461578827},"GB2-03":{"attempts":1,"playable":36.33811190496322,"score":36.33811190496322},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":15.66490775172327,"score":15.66490775172327},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":28.874188292553626,"score":28.874188292553626},"GB2-08":{"attempts":1,"playable":29.356428963230368,"score":29.356428963230368}}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:43Z","match_totals_all":{"draws":2950,"losses":5827,"wins":1971},"match_totals_tracks":{"highest":{"draws":946,"losses":1756,"wins":870},"medium":{"draws":1180,"losses":2322,"wins":586},"none":{"draws":824,"losses":1749,"wins":515}},"model_slug":"openai-gpt-oss-120b","official_rank_by_reasoning":{"highest":55,"medium":67,"none":76},"overall":{"max":58.31249676882345,"mean":30.214315420234474,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":59,"overall_ranking_status":"ranked","per_game":{"GB2-02":43.861474907777556,"GB2-03":46.40629965489456,"GB2-04":42.516760894618045,"GB2-05":58.31249676882345,"GB2-06":22.88129159889048,"GB2-07":34.07304809595744,"GB2-08":32.62716473835184},"per_game_all":{"GB2-02":43.22745599184024,"GB2-03":39.55240287209788,"GB2-05":29.880770757423324,"GB2-07":28.06058758590523,"GB2-08":31.668936655480177},"per_game_match_totals_all":{"GB2-01":{"draws":179,"losses":565,"wins":288},"GB2-02":{"draws":1161,"losses":261,"wins":18},"GB2-03":{"draws":358,"losses":771,"wins":353},"GB2-04":{"draws":655,"losses":279,"wins":62},"GB2-05":{"draws":0,"losses":1134,"wins":456},"GB2-06":{"draws":8,"losses":787,"wins":209},"GB2-07":{"draws":0,"losses":1182,"wins":408},"GB2-08":{"draws":589,"losses":848,"wins":177}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":381,"losses":87,"wins":12},"GB2-03":{"draws":118,"losses":225,"wins":151},"GB2-04":{"draws":327,"losses":131,"wins":40},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":2,"losses":403,"wins":97},"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":273,"wins":99},"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":248,"losses":250,"wins":40}},"none":{"GB2-01":{"draws":85,"losses":272,"wins":159},"GB2-02":{"draws":398,"losses":81,"wins":1},"GB2-03":{"draws":118,"losses":273,"wins":103},"GB2-05":{"draws":0,"losses":452,"wins":78},"GB2-07":{"draws":0,"losses":390,"wins":140},"GB2-08":{"draws":223,"losses":281,"wins":34}}},"per_game_raw_elo_all":{"GB2-02":1419.4293949761943,"GB2-03":1336.320731114704,"GB2-05":1131.5557501721694,"GB2-07":1162.5394742459052,"GB2-08":1188.5432094916157},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1424.340397604501,"GB2-03":1396.2424379077477,"GB2-04":1417.09498613261,"GB2-05":1542.7288818013874,"GB2-06":1007.4567347307886,"GB2-07":1247.2329502650728,"GB2-08":1198.9815043949666},"medium":{"GB2-01":1333.6792793054642,"GB2-02":1413.6948813920858,"GB2-03":1304.4595395887322,"GB2-04":1389.0171968484015,"GB2-05":925.9691843575606,"GB2-06":1065.9153455307319,"GB2-07":1063.026103631255,"GB2-08":1203.242561572809},"none":{"GB2-01":1383.2977132679694,"GB2-02":1420.252905931996,"GB2-03":1308.2602158476316,"GB2-05":925.9691843575606,"GB2-07":1177.359368841388,"GB2-08":1163.4055625070712}},"per_game_tracks":{"highest":{"GB2-02":43.861474907777556,"GB2-03":46.40629965489456,"GB2-04":42.516760894618045,"GB2-05":58.31249676882345,"GB2-06":22.88129159889048,"GB2-07":34.07304809595744,"GB2-08":32.62716473835184},"medium":{"GB2-01":35.97771540616969,"GB2-02":42.487598451954895,"GB2-03":35.91279705643585,"GB2-04":38.93742781528057,"GB2-05":15.66490775172327,"GB2-06":26.638636751420268,"GB2-07":21.23452636920462,"GB2-08":33.02321626485831},"none":{"GB2-01":41.02127603100788,"GB2-02":43.33329461578827,"GB2-03":36.33811190496322,"GB2-05":15.66490775172327,"GB2-07":28.874188292553626,"GB2-08":29.356428963230368}},"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":"2026-10-24T19:06:59Z","reasoning":{"highest":35.08481708241417,"medium":31.234603233380938,"none":24.323525944908326},"reasoning_agg":{"highest":{"max":58.31249676882345,"mean":35.08481708241417,"min":0.0},"medium":{"max":42.487598451954895,"mean":31.234603233380938,"min":15.66490775172327},"none":{"max":43.33329461578827,"mean":24.323525944908326,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.761291137505843},"working_program_strength":{"all":34.58763498946624,"highest":40.09693380847334,"medium":31.234603233380938,"none":32.43136792654443}},{"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":0.50472065},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.31772779999999995},"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":1.2116408500000002},"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":27.332375234422283,"highest":23.96319850648898,"medium":27.713147011663132,"none":30.320780185114735},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed","GB2-07":"failed"},"medium":{"GB2-03":"failed","GB2-04":"failed","GB2-05":"infra_excluded"},"none":{"GB2-02":"failed"}},"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":46.01209872760595,"score":41.74292947169953},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.97888885415118,"score":27.319259236100788},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":30.557911384038643,"score":10.185970461346214},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.75061437505168,"score":27.833742916701123},"GB2-05":{"attempts":3,"playable":46.09757293123491,"score":46.09757293123491},"GB2-06":{"attempts":3,"playable":35.635890749024405,"score":35.635890749024405},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":7.444611419960019,"score":4.13784593552744},"GB2-08":{"attempts":4,"playable":31.833932146934472,"score":31.833932146934472}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":25.615015535438562,"score":12.807507767719281},"GB2-02":{"attempts":2,"playable":40.95190563954942,"score":40.95190563954942},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":2,"playable":30.280124901292105,"score":30.280124901292105},"GB2-06":{"attempts":1,"playable":34.048295254900594,"score":34.048295254900594},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":32.42907596665441,"score":32.42907596665441}},"medium":{"GB2-01":{"attempts":1,"playable":57.184068748285824,"score":57.184068748285824},"GB2-02":{"attempts":1,"playable":41.00587206875293,"score":41.00587206875293},"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":56.4086180600745,"score":56.4086180600745},"GB2-07":{"attempts":1,"playable":9.9378527732446,"score":9.9378527732446},"GB2-08":{"attempts":1,"playable":29.455617431284093,"score":29.455617431284093}},"none":{"GB2-01":{"attempts":1,"playable":55.237211899093474,"score":55.237211899093474},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":30.557911384038643,"score":30.557911384038643},"GB2-04":{"attempts":1,"playable":42.31255022830733,"score":42.31255022830733},"GB2-05":{"attempts":1,"playable":61.9150209611777,"score":61.9150209611777},"GB2-06":{"attempts":1,"playable":16.45075893209812,"score":16.45075893209812},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":4.951370066675437,"score":2.4756850333377187},"GB2-08":{"attempts":1,"playable":33.61710304286491,"score":33.61710304286491}}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:48Z","match_totals_all":{"draws":3041,"losses":5673,"wins":2072},"match_totals_tracks":{"highest":{"draws":1638,"losses":2315,"wins":659},"medium":{"draws":589,"losses":1345,"wins":632},"none":{"draws":814,"losses":2013,"wins":781}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","official_rank_by_reasoning":{"highest":61,"none":61},"overall":{"max":61.9150209611777,"mean":27.332375234422283,"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":25.615015535438562,"GB2-02":40.95190563954942,"GB2-04":41.18867852179604,"GB2-05":30.280124901292105,"GB2-06":34.048295254900594,"GB2-08":32.42907596665441},"per_game_all":{"GB2-01":46.01209872760595,"GB2-06":35.635890749024405,"GB2-08":31.833932146934472},"per_game_match_totals_all":{"GB2-01":{"draws":286,"losses":723,"wins":539},"GB2-02":{"draws":1103,"losses":322,"wins":15},"GB2-03":{"draws":180,"losses":269,"wins":45},"GB2-04":{"draws":693,"losses":250,"wins":53},"GB2-05":{"draws":0,"losses":963,"wins":627},"GB2-06":{"draws":35,"losses":1007,"wins":464},"GB2-07":{"draws":0,"losses":994,"wins":66},"GB2-08":{"draws":744,"losses":1145,"wins":263}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":106,"losses":339,"wins":71},"GB2-02":{"draws":727,"losses":219,"wins":14},"GB2-04":{"draws":352,"losses":125,"wins":21},"GB2-05":{"draws":0,"losses":752,"wins":308},"GB2-06":{"draws":23,"losses":341,"wins":138},"GB2-08":{"draws":430,"losses":539,"wins":107}},"medium":{"GB2-01":{"draws":102,"losses":181,"wins":233},"GB2-02":{"draws":376,"losses":103,"wins":1},"GB2-06":{"draws":7,"losses":236,"wins":259},"GB2-07":{"draws":0,"losses":485,"wins":45},"GB2-08":{"draws":104,"losses":340,"wins":94}},"none":{"GB2-01":{"draws":78,"losses":203,"wins":235},"GB2-03":{"draws":180,"losses":269,"wins":45},"GB2-04":{"draws":341,"losses":125,"wins":32},"GB2-05":{"draws":0,"losses":211,"wins":319},"GB2-06":{"draws":5,"losses":430,"wins":67},"GB2-07":{"draws":0,"losses":509,"wins":21},"GB2-08":{"draws":210,"losses":266,"wins":62}}},"per_game_raw_elo_all":{"GB2-01":1426.6115779794611,"GB2-06":1199.5054351548767,"GB2-08":1190.3207578440458},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1222.4499201496415,"GB2-02":1401.692016574245,"GB2-04":1406.7373394219212,"GB2-05":1169.118428184885,"GB2-06":1177.9772023816904,"GB2-08":1196.8451230327664},"medium":{"GB2-01":1538.1556493495507,"GB2-02":1402.1537380681266,"GB2-06":1520.5560203120851,"GB2-07":831.9421758897495,"GB2-08":1164.4976067405998},"none":{"GB2-01":1519.2291644391912,"GB2-03":1255.2484908977012,"GB2-04":1415.5060664905627,"GB2-05":1591.0961351434594,"GB2-06":899.9830827708553,"GB2-07":657.7597795758323,"GB2-08":1209.6195437587714}},"per_game_tracks":{"highest":{"GB2-01":25.615015535438562,"GB2-02":40.95190563954942,"GB2-04":41.18867852179604,"GB2-05":30.280124901292105,"GB2-06":34.048295254900594,"GB2-08":32.42907596665441},"medium":{"GB2-01":57.184068748285824,"GB2-02":41.00587206875293,"GB2-06":56.4086180600745,"GB2-07":9.9378527732446,"GB2-08":29.455617431284093},"none":{"GB2-01":55.237211899093474,"GB2-03":30.557911384038643,"GB2-04":42.31255022830733,"GB2-05":61.9150209611777,"GB2-06":16.45075893209812,"GB2-07":4.951370066675437,"GB2-08":33.61710304286491}},"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":23.96319850648898,"medium":27.713147011663132,"none":30.320780185114735},"reasoning_agg":{"highest":{"max":41.18867852179604,"mean":23.96319850648898,"min":0.0},"medium":{"max":57.184068748285824,"mean":27.713147011663132,"min":0.0},"none":{"max":61.9150209611777,"mean":30.320780185114735,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.357581678625756},"working_program_strength":{"all":35.963303762767815,"highest":34.08551596993852,"medium":38.79840581632838,"none":35.00598950203652}},{"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":0.24908164000000002},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":60},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.261503015,"mean":0.224623670625,"median":0.22750746833333335,"min":0.17735088333333335,"recorded_attempt_count":60,"run_count":22,"total":4.90638056}},"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":5.74391615},"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":26.673701383390227,"highest":33.07380471903819,"medium":19.21577888046587,"none":27.73152055066662},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":20,"effective_max_output_tokens":[262144],"finish_reason_observations":112,"finish_reasons":["length","stop"],"indexed_attempts":112,"output_token_observations":112,"provider_post_attempt_observations":20,"provider_post_attempts":23,"reasoning_token_observations":85,"reconciliation_get_attempt_observations":20,"reconciliation_get_attempts":33,"requested_max_output_token_observations":20,"requested_max_output_tokens":[262144],"total_output_tokens":1224013,"total_reasoning_output_tokens":793927,"total_visible_output_tokens":126602,"visible_token_observations":82},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":25.980649336302065,"score":25.980649336302065},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":42.936414729034176,"score":21.296430573015243},"GB2-03":{"attempts":5,"playable":44.74522943810561,"score":44.74522943810561},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":42.34534240435115,"score":35.0041696164127},"GB2-05":{"attempts":5,"playable":19.284277946521605,"score":19.284277946521605},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":35.0826287198967,"score":21.558643744116495},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":23.743081235160133,"score":19.809290204031043},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":56.74783978639129,"score":25.710920208617022}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":40.0905826031761,"score":40.0905826031761},"GB2-02":{"attempts":2,"playable":41.90575398002311,"score":41.90575398002311},"GB2-03":{"attempts":2,"playable":47.90330464403783,"score":47.90330464403783},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.04703672763066,"score":22.02351836381533},"GB2-05":{"attempts":2,"playable":16.240371999207255,"score":16.240371999207255},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":53.75985489041197,"score":26.879927445205986},"GB2-07":{"attempts":2,"playable":28.777137037920316,"score":28.777137037920316},"GB2-08":{"attempts":2,"playable":40.76984167891956,"score":40.76984167891956}},"medium":{"GB2-01":{"attempts":1,"playable":17.867482377220473,"score":17.867482377220473},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":37.07559594034441,"score":37.07559594034441},"GB2-04":{"attempts":1,"playable":41.69967780442835,"score":41.69967780442835},"GB2-05":{"attempts":1,"playable":14.130138135939301,"score":14.130138135939301},"GB2-06":{"attempts":1,"playable":24.10397630500886,"score":24.10397630500886},"GB2-07":{"attempts":1,"playable":18.849360480785553,"score":18.849360480785553},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":2,"playable":19.983883028509617,"score":19.983883028509617},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.967075478045246,"score":21.983537739022623},"GB2-03":{"attempts":2,"playable":49.256787729934594,"score":49.256787729934594},"GB2-04":{"attempts":2,"playable":41.28931268099445,"score":41.28931268099445},"GB2-05":{"attempts":2,"playable":27.48232370441826,"score":27.48232370441826},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":27.38405496426927,"score":13.692027482134636},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":23.602746186774525,"score":11.801373093387262},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":72.72583789386302,"score":36.36291894693151}}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:25Z","match_totals_all":{"draws":4195,"losses":8912,"wins":3265},"match_totals_tracks":{"highest":{"draws":1895,"losses":3704,"wins":1577},"medium":{"draws":692,"losses":2012,"wins":367},"none":{"draws":1608,"losses":3196,"wins":1321}},"model_slug":"thinkingmachines-inkling","official_rank_by_reasoning":{"highest":56,"medium":77,"none":70},"overall":{"max":49.256787729934594,"mean":26.673701383390227,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":61,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.0905826031761,"GB2-02":41.90575398002311,"GB2-03":47.90330464403783,"GB2-04":44.04703672763066,"GB2-05":16.240371999207255,"GB2-06":53.75985489041197,"GB2-07":28.777137037920316,"GB2-08":40.76984167891956},"per_game_all":{"GB2-01":25.980649336302065,"GB2-03":44.74522943810561,"GB2-04":42.34534240435115,"GB2-05":19.284277946521605,"GB2-06":35.0826287198967,"GB2-07":23.743081235160133},"per_game_match_totals_all":{"GB2-01":{"draws":629,"losses":1594,"wins":357},"GB2-02":{"draws":1149,"losses":276,"wins":15},"GB2-03":{"draws":772,"losses":1035,"wins":664},"GB2-04":{"draws":1275,"losses":549,"wins":168},"GB2-05":{"draws":0,"losses":2139,"wins":511},"GB2-06":{"draws":26,"losses":1022,"wins":457},"GB2-07":{"draws":0,"losses":1639,"wins":481},"GB2-08":{"draws":344,"losses":658,"wins":612}},"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":211,"losses":448,"wins":329},"GB2-04":{"draws":316,"losses":129,"wins":53},"GB2-05":{"draws":0,"losses":898,"wins":162},"GB2-06":{"draws":9,"losses":249,"wins":244},"GB2-07":{"draws":0,"losses":781,"wins":279},"GB2-08":{"draws":324,"losses":505,"wins":247}},"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":262,"losses":407,"wins":319},"GB2-04":{"draws":630,"losses":286,"wins":80},"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":20,"losses":153,"wins":365}}},"per_game_raw_elo_all":{"GB2-01":1214.689722662111,"GB2-03":1382.8689968499227,"GB2-04":1415.7193787123724,"GB2-05":987.6214368379457,"GB2-06":1194.112781024223,"GB2-07":1099.7360204130057},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1371.5268259881168,"GB2-02":1409.1714730949468,"GB2-03":1409.2812399810568,"GB2-04":1428.9675511405587,"GB2-05":937.6455064961868,"GB2-06":1478.3216468499102,"GB2-07":1175.999636498725,"GB2-08":1295.0868130434897},"medium":{"GB2-01":1122.028124905464,"GB2-03":1314.8226196392684,"GB2-04":1410.7296430882634,"GB2-05":893.3167916593192,"GB2-06":1026.6959185097726,"GB2-07":1022.6929303508891},"none":{"GB2-01":1150.5142170927522,"GB2-02":1425.1569655307137,"GB2-03":1424.5031309294432,"GB2-04":1407.4609419082951,"GB2-05":1131.902012358331,"GB2-06":1077.3207777129862,"GB2-07":1100.5154943894029,"GB2-08":1738.3756747661203}},"per_game_tracks":{"highest":{"GB2-01":40.0905826031761,"GB2-02":41.90575398002311,"GB2-03":47.90330464403783,"GB2-04":44.04703672763066,"GB2-05":16.240371999207255,"GB2-06":53.75985489041197,"GB2-07":28.777137037920316,"GB2-08":40.76984167891956},"medium":{"GB2-01":17.867482377220473,"GB2-03":37.07559594034441,"GB2-04":41.69967780442835,"GB2-05":14.130138135939301,"GB2-06":24.10397630500886,"GB2-07":18.849360480785553},"none":{"GB2-01":19.983883028509617,"GB2-02":43.967075478045246,"GB2-03":49.256787729934594,"GB2-04":41.28931268099445,"GB2-05":27.48232370441826,"GB2-06":27.38405496426927,"GB2-07":23.602746186774525,"GB2-08":72.72583789386302}},"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":"2026-10-24T19:04:18Z","reasoning":{"highest":33.07380471903819,"medium":19.21577888046587,"none":27.73152055066662},"reasoning_agg":{"highest":{"max":47.90330464403783,"mean":33.07380471903819,"min":16.240371999207255},"medium":{"max":41.69967780442835,"mean":19.21577888046587,"min":0.0},"none":{"max":49.256787729934594,"mean":27.73152055066662,"min":11.801373093387262}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":13.858025838572324},"working_program_strength":{"all":34.33975888693493,"highest":39.18673544516585,"medium":25.621038507287825,"none":38.21150270835112}},{"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":0.13713908},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1134224},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005}},"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":0.73661958},"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":24.183897516367892,"highest":15.536652343348086,"medium":26.435328954651105,"none":30.579711251104477},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed","GB2-04":"failed"},"medium":{"GB2-02":"failed","GB2-04":"failed"},"none":{"GB2-05":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[230400],"finish_reason_observations":46,"finish_reasons":["stop"],"indexed_attempts":46,"output_token_observations":46,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[230400],"total_output_tokens":577622,"total_visible_output_tokens":183088,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":17.700345925244225,"score":17.700345925244225},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":43.54460209735465,"score":14.514867365784882},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":36.123448745573626,"score":24.08229916371575},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.16595143167495,"score":13.388650477224983},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":45.00661836879158,"score":30.00441224586105},"GB2-06":{"attempts":3,"playable":42.56506207885854,"score":42.56506207885854},"GB2-07":{"attempts":3,"playable":35.089379817859665,"score":35.089379817859665},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":24.189244584591044,"score":16.12616305639403}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":9.74494813775178,"score":9.74494813775178},"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":39.33415746968565,"score":39.33415746968565},"GB2-06":{"attempts":1,"playable":33.09908901644075,"score":33.09908901644075},"GB2-07":{"attempts":1,"playable":24.97678665828656,"score":24.97678665828656},"GB2-08":{"attempts":1,"playable":17.13823746461996,"score":17.13823746461996}},"medium":{"GB2-01":{"attempts":1,"playable":10.356509846524498,"score":10.356509846524498},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":34.847507100089665,"score":34.847507100089665},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":50.6790792678975,"score":50.6790792678975},"GB2-06":{"attempts":1,"playable":45.34389370282634,"score":45.34389370282634},"GB2-07":{"attempts":1,"playable":39.01539001530872,"score":39.01539001530872},"GB2-08":{"attempts":1,"playable":31.240251704562134,"score":31.240251704562134}},"none":{"GB2-01":{"attempts":1,"playable":32.99957979145639,"score":32.99957979145639},"GB2-02":{"attempts":1,"playable":43.54460209735465,"score":43.54460209735465},"GB2-03":{"attempts":1,"playable":37.399390391057594,"score":37.399390391057594},"GB2-04":{"attempts":1,"playable":40.16595143167495,"score":40.16595143167495},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":49.252203517308516,"score":49.252203517308516},"GB2-07":{"attempts":1,"playable":41.275962779983715,"score":41.275962779983715},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T23:55:10Z","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":50.6790792678975,"mean":24.183897516367892,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":62,"overall_ranking_status":"ranked","per_game":{"GB2-01":9.74494813775178,"GB2-05":39.33415746968565,"GB2-06":33.09908901644075,"GB2-07":24.97678665828656,"GB2-08":17.13823746461996},"per_game_all":{"GB2-01":17.700345925244225,"GB2-06":42.56506207885854,"GB2-07":35.089379817859665},"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":1089.9050477903982,"GB2-06":1306.6494171372735,"GB2-07":1256.9055846576287},"per_game_raw_elo_tracks":{"highest":{"GB2-01":976.3457736325589,"GB2-05":1302.9191963517355,"GB2-06":1163.7185939205642,"GB2-07":1121.317794758378,"GB2-08":1013.8608351462723},"medium":{"GB2-01":990.0346525947057,"GB2-03":1294.8825411781243,"GB2-05":1445.8456581752926,"GB2-06":1348.203703570001,"GB2-07":1310.5166702806316,"GB2-08":1183.9924609992147},"none":{"GB2-01":1303.33471714393,"GB2-02":1421.8888642543418,"GB2-03":1317.6935100666856,"GB2-04":1398.7161843538827,"GB2-06":1408.0259539212557,"GB2-07":1338.8822889338762}},"per_game_tracks":{"highest":{"GB2-01":9.74494813775178,"GB2-05":39.33415746968565,"GB2-06":33.09908901644075,"GB2-07":24.97678665828656,"GB2-08":17.13823746461996},"medium":{"GB2-01":10.356509846524498,"GB2-03":34.847507100089665,"GB2-05":50.6790792678975,"GB2-06":45.34389370282634,"GB2-07":39.01539001530872,"GB2-08":31.240251704562134},"none":{"GB2-01":32.99957979145639,"GB2-02":43.54460209735465,"GB2-03":37.399390391057594,"GB2-04":40.16595143167495,"GB2-06":49.252203517308516,"GB2-07":41.275962779983715}},"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":"2026-10-24T16:58:20Z","reasoning":{"highest":15.536652343348086,"medium":26.4353289546511,"none":30.57971125110448},"reasoning_agg":{"highest":{"max":39.33415746968565,"mean":15.536652343348086,"min":0.0},"medium":{"max":50.6790792678975,"mean":26.4353289546511,"min":0.0},"none":{"max":49.252203517308516,"mean":30.57971125110448,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":15.043058907756395},"working_program_strength":{"all":33.62623245234368,"highest":24.858643749356936,"medium":35.24710527286814,"none":40.77294833480597}},{"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":0.010578220000000001},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122239999999998},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.00761251}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.007612510000000001},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.028312970000000003},"codegen_latency_ms":{"attempt_count":37,"max_ms":49328,"mean_ms":21505.916666666668,"min_ms":9355,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":47445,"mean_ms":22491.5,"min_ms":13295,"run_count":8},"medium":{"attempt_count":12,"max_ms":49328,"mean_ms":23044.25,"min_ms":13295,"run_count":8},"none":{"attempt_count":14,"max_ms":24913,"mean_ms":18982.0,"min_ms":9355,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":11394,"output_mean":4854.291666666667,"output_min":1030,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":11185,"output_mean":6150.25,"output_min":2902,"run_count":8},"medium":{"attempt_count":12,"output_max":11394,"output_mean":5469.5,"output_min":3022,"run_count":8},"none":{"attempt_count":14,"output_max":4416,"output_mean":2943.125,"output_min":1030,"run_count":8}},"display_name":"Mercury 2.5 Preview","economics":{"all":21.89213988063352,"highest":21.136130199536197,"medium":20.329380187971026,"none":24.21090925439333},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed","GB2-05":"failed"},"medium":{"GB2-01":"failed","GB2-03":"failed"},"none":{"GB2-01":"failed","GB2-07":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"provider_post_attempt_observations":37,"provider_post_attempts":37,"reasoning_token_observations":37,"reconciliation_get_attempt_observations":37,"reconciliation_get_attempts":176,"total_output_tokens":116503,"total_reasoning_output_tokens":61584,"total_visible_output_tokens":54919,"visible_token_observations":37},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-2.5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":27.416518712100512,"score":9.13883957070017},"GB2-02":{"attempts":3,"playable":42.66376026560186,"score":42.66376026560186},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.99221229282847,"score":15.330737430942824},"GB2-04":{"attempts":3,"playable":41.28886531507201,"score":41.28886531507201},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":28.267788382598997,"score":18.845192255066},"GB2-06":{"attempts":3,"playable":18.258488418785124,"score":18.258488418785124},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.186252699594592,"score":8.124168466396394},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.23060098375562,"score":21.487067322503748}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.416518712100512,"score":27.416518712100512},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.039855920000804,"score":39.039855920000804},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":15.079751586405402,"score":15.079751586405402},"GB2-07":{"attempts":1,"playable":14.023281885914468,"score":14.023281885914468},"GB2-08":{"attempts":1,"playable":31.0420350399135,"score":31.0420350399135}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.227623284677975,"score":43.227623284677975},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.779703297584575,"score":40.779703297584575},"GB2-05":{"attempts":1,"playable":16.815836246691234,"score":16.815836246691234},"GB2-06":{"attempts":1,"playable":18.043488233941947,"score":18.043488233941947},"GB2-07":{"attempts":1,"playable":10.349223513274715,"score":10.349223513274715},"GB2-08":{"attempts":1,"playable":33.41916692759774,"score":33.41916692759774}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.27605906017271,"score":42.27605906017271},"GB2-03":{"attempts":1,"playable":45.99221229282847,"score":45.99221229282847},"GB2-04":{"attempts":1,"playable":44.04703672763066,"score":44.04703672763066},"GB2-05":{"attempts":1,"playable":39.71974051850676,"score":39.71974051850676},"GB2-06":{"attempts":1,"playable":21.652225436008024,"score":21.652225436008024},"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":"2026-10-26T02:00:13Z","match_totals_all":{"draws":2957,"losses":4692,"wins":997},"match_totals_tracks":{"highest":{"draws":1052,"losses":1740,"wins":272},"medium":{"draws":1024,"losses":1798,"wins":256},"none":{"draws":881,"losses":1154,"wins":469}},"model_slug":"inception-mercury-2-5-preview","official_rank_by_reasoning":{"highest":62,"medium":75,"none":77},"overall":{"max":45.99221229282847,"mean":21.89213988063352,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":63,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.416518712100512,"GB2-02":42.487598451954895,"GB2-04":39.039855920000804,"GB2-06":15.079751586405402,"GB2-07":14.023281885914468,"GB2-08":31.0420350399135},"per_game_all":{"GB2-02":42.66376026560186,"GB2-04":41.28886531507201,"GB2-06":18.258488418785124},"per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":324,"wins":74},"GB2-02":{"draws":1175,"losses":262,"wins":3},"GB2-03":{"draws":116,"losses":228,"wins":150},"GB2-04":{"draws":1057,"losses":373,"wins":64},"GB2-05":{"draws":0,"losses":773,"wins":287},"GB2-06":{"draws":9,"losses":1269,"wins":228},"GB2-07":{"draws":0,"losses":948,"wins":112},"GB2-08":{"draws":482,"losses":515,"wins":79}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":118,"losses":324,"wins":74},"GB2-02":{"draws":388,"losses":90,"wins":2},"GB2-04":{"draws":349,"losses":137,"wins":12},"GB2-06":{"draws":3,"losses":437,"wins":62},"GB2-07":{"draws":0,"losses":465,"wins":65},"GB2-08":{"draws":194,"losses":287,"wins":57}},"medium":{"GB2-02":{"draws":397,"losses":82,"wins":1},"GB2-04":{"draws":336,"losses":135,"wins":27},"GB2-05":{"draws":0,"losses":446,"wins":84},"GB2-06":{"draws":3,"losses":424,"wins":75},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":288,"losses":228,"wins":22}},"none":{"GB2-02":{"draws":390,"losses":90,"wins":0},"GB2-03":{"draws":116,"losses":228,"wins":150},"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":1415.0602704142077,"GB2-04":1407.4437913452095,"GB2-06":930.2133532593713},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1243.138779298394,"GB2-02":1413.6948813920858,"GB2-04":1389.8288224054152,"GB2-06":874.8555154461964,"GB2-07":929.8068168528538,"GB2-08":1181.8400651828306},"medium":{"GB2-02":1419.4344223818925,"GB2-04":1403.535000489655,"GB2-05":949.321828634813,"GB2-06":927.9470421780442,"GB2-07":842.984588352401,"GB2-08":1207.4956861886228},"none":{"GB2-02":1412.051507468645,"GB2-03":1392.6438130200452,"GB2-04":1428.9675511405587,"GB2-05":1307.940731168561,"GB2-06":987.8375021538733}},"per_game_tracks":{"highest":{"GB2-01":27.416518712100512,"GB2-02":42.487598451954895,"GB2-04":39.039855920000804,"GB2-06":15.079751586405402,"GB2-07":14.023281885914468,"GB2-08":31.0420350399135},"medium":{"GB2-02":43.227623284677975,"GB2-04":40.779703297584575,"GB2-05":16.815836246691234,"GB2-06":18.043488233941947,"GB2-07":10.349223513274715,"GB2-08":33.41916692759774},"none":{"GB2-02":42.27605906017271,"GB2-03":45.99221229282847,"GB2-04":44.04703672763066,"GB2-05":39.71974051850676,"GB2-06":21.652225436008024}},"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":"2026-10-24T19:02:08Z","reasoning":{"highest":21.136130199536197,"medium":20.329380187971026,"none":24.21090925439333},"reasoning_agg":{"highest":{"max":42.487598451954895,"mean":21.136130199536197,"min":0.0},"medium":{"max":43.227623284677975,"mean":20.329380187971026,"min":0.0},"none":{"max":45.99221229282847,"mean":24.21090925439333,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":3.8815290664223028},"working_program_strength":{"all":31.341600663457427,"highest":28.181506932714928,"medium":27.105840250628034,"none":38.73745480702932}},{"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":0.081084},"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":16.196035802854244,"highest":17.367332157839826,"medium":20.11480637467599,"none":11.105968876046907},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-02":"failed","GB2-03":"failed"},"none":{"GB2-03":"failed","GB2-04":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":150003},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":23.296932550117198,"score":15.531288366744798},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.804821402339726,"score":14.268273800779909},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":43.33319183978524,"score":28.88879455985683},"GB2-05":{"attempts":3,"playable":11.244304065555825,"score":11.244304065555825},"GB2-06":{"attempts":3,"playable":22.050018355488657,"score":22.050018355488657},"GB2-07":{"attempts":3,"playable":14.186395681841859,"score":14.186395681841859},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":35.098817388849056,"score":23.399211592566036}},"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":43.2311783551885,"score":43.2311783551885},"GB2-05":{"attempts":1,"playable":10.674072031668008,"score":10.674072031668008},"GB2-06":{"attempts":1,"playable":18.61039249601762,"score":18.61039249601762},"GB2-07":{"attempts":1,"playable":33.49880171248045,"score":33.49880171248045},"GB2-08":{"attempts":1,"playable":32.92421266736403,"score":32.92421266736403}},"medium":{"GB2-01":{"attempts":1,"playable":33.79459575009096,"score":33.79459575009096},"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":43.43520532438199,"score":43.43520532438199},"GB2-05":{"attempts":1,"playable":17.007657862391902,"score":17.007657862391902},"GB2-06":{"attempts":1,"playable":22.99271296083545,"score":22.99271296083545},"GB2-07":{"attempts":1,"playable":6.414856989373502,"score":6.414856989373502},"GB2-08":{"attempts":1,"playable":37.27342211033409,"score":37.27342211033409}},"none":{"GB2-01":{"attempts":1,"playable":12.799269350143435,"score":12.799269350143435},"GB2-02":{"attempts":1,"playable":42.804821402339726,"score":42.804821402339726},"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":6.051182302607571,"score":6.051182302607571},"GB2-06":{"attempts":1,"playable":24.54694960961289,"score":24.54694960961289},"GB2-07":{"attempts":1,"playable":2.645528343671625,"score":2.645528343671625},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-25T23:46:16Z","match_totals_all":{"draws":1802,"losses":5532,"wins":936},"match_totals_tracks":{"highest":{"draws":621,"losses":1622,"wins":355},"medium":{"draws":708,"losses":1990,"wins":416},"none":{"draws":473,"losses":1920,"wins":165}},"model_slug":"google-gemini-3-1-flash-lite","official_rank_by_reasoning":{"highest":63,"medium":76,"none":84},"overall":{"max":43.43520532438199,"mean":16.196035802854244,"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":43.2311783551885,"GB2-05":10.674072031668008,"GB2-06":18.61039249601762,"GB2-07":33.49880171248045,"GB2-08":32.92421266736403},"per_game_all":{"GB2-05":11.244304065555825,"GB2-06":22.050018355488657,"GB2-07":14.186395681841859},"per_game_match_totals_all":{"GB2-01":{"draws":331,"losses":641,"wins":60},"GB2-02":{"draws":379,"losses":93,"wins":8},"GB2-04":{"draws":690,"losses":236,"wins":70},"GB2-05":{"draws":0,"losses":1425,"wins":165},"GB2-06":{"draws":8,"losses":1219,"wins":279},"GB2-07":{"draws":0,"losses":1388,"wins":202},"GB2-08":{"draws":394,"losses":530,"wins":152}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":362,"losses":110,"wins":26},"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":259,"losses":245,"wins":34}},"medium":{"GB2-01":{"draws":242,"losses":230,"wins":44},"GB2-04":{"draws":328,"losses":126,"wins":44},"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":135,"losses":285,"wins":118}},"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":5,"losses":394,"wins":103},"GB2-07":{"draws":0,"losses":520,"wins":10}}},"per_game_raw_elo_all":{"GB2-05":810.1525148880088,"GB2-06":993.4888059475694,"GB2-07":826.0887145243018},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1422.6446576786338,"GB2-05":811.1947709137768,"GB2-06":937.6375204175217,"GB2-07":1239.717391763284,"GB2-08":1202.1780750028308},"medium":{"GB2-01":1311.532111939778,"GB2-04":1424.2272136509296,"GB2-05":953.1303321188425,"GB2-06":1009.2205949435478,"GB2-07":719.4861296230508,"GB2-08":1248.717968116956},"none":{"GB2-01":1039.1091691954784,"GB2-02":1416.1569408377225,"GB2-05":666.1324416314072,"GB2-06":1033.6083024816392,"GB2-07":519.0626221865706}},"per_game_tracks":{"highest":{"GB2-04":43.2311783551885,"GB2-05":10.674072031668008,"GB2-06":18.61039249601762,"GB2-07":33.49880171248045,"GB2-08":32.92421266736403},"medium":{"GB2-01":33.79459575009096,"GB2-04":43.43520532438199,"GB2-05":17.007657862391902,"GB2-06":22.99271296083545,"GB2-07":6.414856989373502,"GB2-08":37.27342211033409},"none":{"GB2-01":12.799269350143435,"GB2-02":42.804821402339726,"GB2-05":6.051182302607571,"GB2-06":24.54694960961289,"GB2-07":2.645528343671625}},"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":17.367332157839826,"medium":20.11480637467599,"none":11.105968876046907},"reasoning_agg":{"highest":{"max":43.2311783551885,"mean":17.367332157839826,"min":0.0},"medium":{"max":43.43520532438199,"mean":20.11480637467599,"min":0.0},"none":{"max":42.804821402339726,"mean":11.105968876046907,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":9.008837498629083},"working_program_strength":{"all":24.125674495706694,"highest":27.78773145254372,"medium":26.819741832901318,"none":17.769550201675052}},{"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":0.012156649999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0023752,"mean":0.0015195812500000002,"median":0.00138595,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":0.012156650000000001},"historical-provider-setting-intensive":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069025}},"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":0.20104779999999997},"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":8.179035323783117,"highest":13.810100956617422,"medium":5.655110306064714,"none":5.071894708667212},"first_seen_at":null,"game_gaps":{"all":{"GB2-02":"failed","GB2-03":"failed","GB2-08":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-08":"failed"},"medium":{"GB2-02":"infra_excluded","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":49,"effective_max_output_tokens":[131072],"finish_reason_observations":48,"finish_reasons":["stop"],"indexed_attempts":49,"output_token_observations":49,"provider_post_attempt_observations":49,"provider_post_attempts":51,"reasoning_token_observations":49,"reconciliation_get_attempt_observations":49,"requested_max_output_token_observations":49,"requested_max_output_tokens":[131072],"total_output_tokens":913760,"total_reasoning_output_tokens":808441,"total_visible_output_tokens":105319,"visible_token_observations":49},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":19.28125641080402,"score":6.427085470268007},"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":40.5751576693377,"score":13.5250525564459},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":46.073471504282615,"score":15.357823834760872},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.7981729684762,"score":17.198781978984133},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":33.11550594335333,"score":11.038501981117776},"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":46.073471504282615,"score":46.073471504282615},"GB2-06":{"attempts":1,"playable":31.291830205303434,"score":31.291830205303434},"GB2-07":{"attempts":1,"playable":33.11550594335333,"score":33.11550594335333},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":19.28125641080402,"score":19.28125641080402},"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":20.304515731648973,"score":20.304515731648973},"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":40.5751576693377,"score":40.5751576693377},"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":46.073471504282615,"mean":8.179035323783117,"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":46.073471504282615,"GB2-06":31.291830205303434,"GB2-07":33.11550594335333},"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":1388.5797847546953,"GB2-06":1136.529290084248,"GB2-07":1234.6771572333178},"medium":{"GB2-01":1142.157774662837,"GB2-06":965.9262059683973},"none":{"GB2-04":1401.9308314236346}},"per_game_tracks":{"highest":{"GB2-05":46.073471504282615,"GB2-06":31.291830205303434,"GB2-07":33.11550594335333},"medium":{"GB2-01":19.28125641080402,"GB2-06":20.304515731648973},"none":{"GB2-04":40.5751576693377}},"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":13.810100956617424,"medium":5.655110306064714,"none":5.071894708667212},"reasoning_agg":{"highest":{"max":46.073471504282615,"mean":13.810100956617424,"min":0.0},"medium":{"max":20.304515731648973,"mean":5.655110306064714,"min":0.0},"none":{"max":40.5751576693377,"mean":5.071894708667212,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.738206247950211},"working_program_strength":{"all":32.39832654162577,"highest":36.82693588431312,"medium":19.792886071226498,"none":40.5751576693377}},{"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":0.06705538000000001},"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":0.06705538}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":24,"cost_basis_counts":{"provider_reported":56},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":23,"max":0.01113168,"mean":0.00448752,"median":0.002935335,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":37},"recorded_attempt_count":56,"run_count":24,"total":0.10770048000000002},"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":1.6181246051373426,"highest":0.0,"medium":4.8543738154120275,"none":0.0},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"medium":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":37,"effective_max_output_tokens":[117964],"finish_reason_observations":56,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":56,"provider_post_attempt_observations":56,"provider_post_attempts":56,"reasoning_token_observations":56,"reconciliation_get_attempt_observations":56,"reconciliation_get_attempts":88,"requested_max_output_token_observations":37,"requested_max_output_tokens":[117964],"total_output_tokens":331648,"total_reasoning_output_tokens":194609,"total_visible_output_tokens":137039,"visible_token_observations":56},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"ibm","provider_model":"ibm-granite/granite-4.2-8b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":38.83499052329622,"score":12.94499684109874},"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":38.83499052329622,"score":38.83499052329622},"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":38.83499052329622,"mean":1.6181246051373426,"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":1388.2049214936515}},"per_game_tracks":{"medium":{"GB2-04":38.83499052329622}},"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":4.8543738154120275,"none":0.0},"reasoning_agg":{"highest":{"max":0.0,"mean":0.0,"min":0.0},"medium":{"max":38.83499052329622,"mean":4.8543738154120275,"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":4.8543738154120275},"working_program_strength":{"all":38.83499052329622,"medium":38.83499052329622}},{"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":90.60945754866256,"none":90.60945754866256},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":8,"effective_max_output_tokens":[131072],"finish_reason_observations":8,"finish_reasons":["stop"],"indexed_attempts":8,"output_token_observations":8,"provider_post_attempt_observations":8,"provider_post_attempts":8,"reasoning_token_observations":8,"reconciliation_get_attempt_observations":8,"requested_max_output_token_observations":8,"requested_max_output_tokens":[131072],"total_output_tokens":57747,"total_visible_output_tokens":57747,"visible_token_observations":8},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":91.44446337962175,"score":91.44446337962175},"GB2-02":{"attempts":1,"playable":79.50804434894312,"score":79.50804434894312},"GB2-03":{"attempts":1,"playable":96.4292719023919,"score":96.4292719023919},"GB2-04":{"attempts":1,"playable":85.65291386041439,"score":85.65291386041439},"GB2-05":{"attempts":1,"playable":91.90017957529739,"score":91.90017957529739},"GB2-06":{"attempts":1,"playable":93.60240885205931,"score":93.60240885205931},"GB2-07":{"attempts":1,"playable":95.14792430503898,"score":95.14792430503898},"GB2-08":{"attempts":1,"playable":91.19045416553365,"score":91.19045416553365}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":91.44446337962175,"score":91.44446337962175},"GB2-02":{"attempts":1,"playable":79.50804434894312,"score":79.50804434894312},"GB2-03":{"attempts":1,"playable":96.4292719023919,"score":96.4292719023919},"GB2-04":{"attempts":1,"playable":85.65291386041439,"score":85.65291386041439},"GB2-05":{"attempts":1,"playable":91.90017957529739,"score":91.90017957529739},"GB2-06":{"attempts":1,"playable":93.60240885205931,"score":93.60240885205931},"GB2-07":{"attempts":1,"playable":95.14792430503898,"score":95.14792430503898},"GB2-08":{"attempts":1,"playable":91.19045416553365,"score":91.19045416553365}}},"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":96.4292719023919,"mean":90.60945754866256,"min":79.50804434894312},"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":2022.6274529380141,"GB2-02":1747.516188906536,"GB2-03":2299.385104080095,"GB2-04":1837.1416694699278,"GB2-05":2335.4137783675424,"GB2-06":2292.6807046393565,"GB2-07":2445.2365326244108,"GB2-08":2199.177119230384}},"per_game_tracks":{"none":{"GB2-01":91.44446337962175,"GB2-02":79.50804434894312,"GB2-03":96.4292719023919,"GB2-04":85.65291386041439,"GB2-05":91.90017957529739,"GB2-06":93.60240885205931,"GB2-07":95.14792430503898,"GB2-08":91.19045416553365}},"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":90.60945754866256},"reasoning_agg":{"none":{"max":96.4292719023919,"mean":90.60945754866256,"min":79.50804434894312}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":90.60945754866256,"none":90.60945754866256}},{"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":0.24543760000000003}},"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":89.68138346863117,"none":89.68138346863117},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[131072],"finish_reason_observations":9,"finish_reasons":["stop"],"indexed_attempts":9,"output_token_observations":9,"provider_post_attempt_observations":9,"provider_post_attempts":9,"reasoning_token_observations":9,"reconciliation_get_attempt_observations":9,"requested_max_output_token_observations":9,"requested_max_output_tokens":[131072],"total_output_tokens":57710,"total_visible_output_tokens":57710,"visible_token_observations":9},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":73.75996925502372,"score":73.75996925502372},"GB2-02":{"attempts":1,"playable":91.55797471857755,"score":91.55797471857755},"GB2-03":{"attempts":1,"playable":93.77026540100348,"score":93.77026540100348},"GB2-04":{"attempts":1,"playable":86.40302268825785,"score":86.40302268825785},"GB2-05":{"attempts":1,"playable":94.26076154257755,"score":94.26076154257755},"GB2-06":{"attempts":1,"playable":87.53442921211186,"score":87.53442921211186},"GB2-07":{"attempts":1,"playable":95.89865809396942,"score":95.89865809396942},"GB2-08":{"attempts":1,"playable":94.26598683752802,"score":94.26598683752802}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":73.75996925502372,"score":73.75996925502372},"GB2-02":{"attempts":1,"playable":91.55797471857755,"score":91.55797471857755},"GB2-03":{"attempts":1,"playable":93.77026540100348,"score":93.77026540100348},"GB2-04":{"attempts":1,"playable":86.40302268825785,"score":86.40302268825785},"GB2-05":{"attempts":1,"playable":94.26076154257755,"score":94.26076154257755},"GB2-06":{"attempts":1,"playable":87.53442921211186,"score":87.53442921211186},"GB2-07":{"attempts":1,"playable":95.89865809396942,"score":95.89865809396942},"GB2-08":{"attempts":1,"playable":94.26598683752802,"score":94.26598683752802}}},"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":95.89865809396942,"mean":89.68138346863117,"min":73.75996925502372},"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":1715.7320965704523,"GB2-02":1970.7239821707371,"GB2-03":2144.3289813812207,"GB2-04":1850.0289484641544,"GB2-05":2461.9131391675596,"GB2-06":2109.526347100161,"GB2-07":2495.810403977528,"GB2-08":2324.896267561036}},"per_game_tracks":{"none":{"GB2-01":73.75996925502372,"GB2-02":91.55797471857755,"GB2-03":93.77026540100348,"GB2-04":86.40302268825785,"GB2-05":94.26076154257755,"GB2-06":87.53442921211186,"GB2-07":95.89865809396942,"GB2-08":94.26598683752802}},"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":89.68138346863117},"reasoning_agg":{"none":{"max":95.89865809396942,"mean":89.68138346863117,"min":73.75996925502372}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":89.68138346863117,"none":89.68138346863117}},{"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":0.05751309}},"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":62.083765326494536,"medium":73.15756430631654,"none":51.00996634667253},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":19,"effective_max_output_tokens":[131072],"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"provider_post_attempt_observations":19,"provider_post_attempts":20,"reasoning_token_observations":19,"reconciliation_get_attempt_observations":19,"requested_max_output_token_observations":19,"requested_max_output_tokens":[131072],"total_output_tokens":513762,"total_reasoning_output_tokens":447944,"total_visible_output_tokens":65818,"visible_token_observations":19},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":46.803893037375076,"score":46.803893037375076},"GB2-02":{"attempts":2,"playable":60.47446741056632,"score":60.47446741056632},"GB2-03":{"attempts":2,"playable":65.43384966484501,"score":65.43384966484501},"GB2-04":{"attempts":2,"playable":50.5320659191903,"score":50.5320659191903},"GB2-05":{"attempts":2,"playable":65.34674349348201,"score":65.34674349348201},"GB2-06":{"attempts":2,"playable":56.643631163108175,"score":56.643631163108175},"GB2-07":{"attempts":2,"playable":66.55602876764627,"score":66.55602876764627},"GB2-08":{"attempts":2,"playable":84.87944315574313,"score":84.87944315574313}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":54.06745685878506,"score":54.06745685878506},"GB2-02":{"attempts":1,"playable":80.79074236697731,"score":80.79074236697731},"GB2-03":{"attempts":1,"playable":85.91279600396095,"score":85.91279600396095},"GB2-04":{"attempts":1,"playable":45.371362908471355,"score":45.371362908471355},"GB2-05":{"attempts":1,"playable":85.00449802467791,"score":85.00449802467791},"GB2-06":{"attempts":1,"playable":57.0670286353555,"score":57.0670286353555},"GB2-07":{"attempts":1,"playable":89.77514727559289,"score":89.77514727559289},"GB2-08":{"attempts":1,"playable":87.27148237671136,"score":87.27148237671136}},"none":{"GB2-01":{"attempts":1,"playable":39.5403292159651,"score":39.5403292159651},"GB2-02":{"attempts":1,"playable":40.15819245415532,"score":40.15819245415532},"GB2-03":{"attempts":1,"playable":44.95490332572907,"score":44.95490332572907},"GB2-04":{"attempts":1,"playable":55.69276892990924,"score":55.69276892990924},"GB2-05":{"attempts":1,"playable":45.688988962286096,"score":45.688988962286096},"GB2-06":{"attempts":1,"playable":56.22023369086085,"score":56.22023369086085},"GB2-07":{"attempts":1,"playable":43.33691025969965,"score":43.33691025969965},"GB2-08":{"attempts":1,"playable":82.48740393477489,"score":82.48740393477489}}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:21Z","match_totals_all":{"draws":1402,"losses":2546,"wins":4228},"match_totals_tracks":{"medium":{"draws":386,"losses":961,"wins":2741},"none":{"draws":1016,"losses":1585,"wins":1487}},"model_slug":"xiaomi-mimo-v2-6-pro","official_rank_by_reasoning":{"medium":9,"none":21},"overall":{"max":89.77514727559289,"mean":62.083765326494536,"min":39.5403292159651},"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":96,"losses":322,"wins":570},"GB2-04":{"draws":506,"losses":257,"wins":233},"GB2-05":{"draws":0,"losses":381,"wins":679},"GB2-06":{"draws":53,"losses":450,"wins":501},"GB2-07":{"draws":0,"losses":366,"wins":694},"GB2-08":{"draws":0,"losses":181,"wins":895}},"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":94,"losses":244,"wins":156},"GB2-04":{"draws":321,"losses":69,"wins":108},"GB2-05":{"draws":0,"losses":296,"wins":234},"GB2-06":{"draws":23,"losses":229,"wins":250},"GB2-07":{"draws":0,"losses":314,"wins":216},"GB2-08":{"draws":0,"losses":105,"wins":433}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1507.9465543718034,"GB2-02":1764.7432878641234,"GB2-03":1883.9521051730376,"GB2-04":1439.2064943902606,"GB2-05":2059.6387087218595,"GB2-06":1531.184883722592,"GB2-07":2170.793606201848,"GB2-08":2076.0948451377317},"none":{"GB2-01":1368.9061791396339,"GB2-02":1395.514545018261,"GB2-03":1383.638544775471,"GB2-04":1519.5660051862353,"GB2-05":1383.7801956738601,"GB2-06":1517.524998695506,"GB2-07":1364.5732520099505,"GB2-08":1951.5118621291194}},"per_game_tracks":{"medium":{"GB2-01":54.06745685878506,"GB2-02":80.79074236697731,"GB2-03":85.91279600396095,"GB2-04":45.371362908471355,"GB2-05":85.00449802467791,"GB2-06":57.0670286353555,"GB2-07":89.77514727559289,"GB2-08":87.27148237671136},"none":{"GB2-01":39.5403292159651,"GB2-02":40.15819245415532,"GB2-03":44.95490332572907,"GB2-04":55.69276892990924,"GB2-05":45.688988962286096,"GB2-06":56.22023369086085,"GB2-07":43.33691025969965,"GB2-08":82.48740393477489}},"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":73.15756430631654,"none":51.00996634667253},"reasoning_agg":{"medium":{"max":89.77514727559289,"mean":73.15756430631654,"min":45.371362908471355},"none":{"max":82.48740393477489,"mean":51.00996634667253,"min":39.5403292159651}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":22.147597959644017},"working_program_strength":{"all":62.083765326494536,"medium":73.15756430631654,"none":51.00996634667253}},{"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":58.647177301731844,"medium":82.98469083668653,"none":34.30966376677716},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"}},"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":58.647177301731844,"score":58.647177301731844}},"headline_games_tracks":{"medium":{"GB2-08":{"attempts":1,"playable":82.98469083668653,"score":82.98469083668653}},"none":{"GB2-08":{"attempts":1,"playable":34.30966376677716,"score":34.30966376677716}}},"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":82.98469083668653,"mean":58.647177301731844,"min":34.30966376677716},"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":1963.6358207439525},"none":{"GB2-08":1217.0406498419302}},"per_game_tracks":{"medium":{"GB2-08":82.98469083668653},"none":{"GB2-08":34.30966376677716}},"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":82.98469083668653,"none":34.30966376677716},"reasoning_agg":{"medium":{"max":82.98469083668653,"mean":82.98469083668653,"min":82.98469083668653},"none":{"max":34.30966376677716,"mean":34.30966376677716,"min":34.30966376677716}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":48.67502706990936},"working_program_strength":{"all":58.647177301731844,"medium":82.98469083668653,"none":34.30966376677716}},{"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":0.16601801999999996},"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":50.368992387307614,"medium":60.1913228654651,"none":40.546661909150124},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-04":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[131072],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":23,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[131072],"total_output_tokens":500838,"total_reasoning_output_tokens":411817,"total_visible_output_tokens":89021,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":61.039510471904926,"score":61.039510471904926},"GB2-02":{"attempts":2,"playable":54.66579903193971,"score":54.66579903193971},"GB2-03":{"attempts":2,"playable":51.45163928679864,"score":51.45163928679864},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":58.70174355075301,"score":29.350871775376504},"GB2-05":{"attempts":2,"playable":56.40260350984238,"score":56.40260350984238},"GB2-06":{"attempts":2,"playable":58.7140786077428,"score":58.7140786077428},"GB2-07":{"attempts":2,"playable":61.97110724277714,"score":61.97110724277714},"GB2-08":{"attempts":2,"playable":29.356329172078745,"score":29.356329172078745}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":53.677267651639525,"score":53.677267651639525},"GB2-02":{"attempts":1,"playable":66.84399961192453,"score":66.84399961192453},"GB2-03":{"attempts":1,"playable":62.758061666473175,"score":62.758061666473175},"GB2-04":{"attempts":1,"playable":58.70174355075301,"score":58.70174355075301},"GB2-05":{"attempts":1,"playable":60.021061787878295,"score":60.021061787878295},"GB2-06":{"attempts":1,"playable":66.24759668126995,"score":66.24759668126995},"GB2-07":{"attempts":1,"playable":83.23019220896973,"score":83.23019220896973},"GB2-08":{"attempts":1,"playable":30.050659764812487,"score":30.050659764812487}},"none":{"GB2-01":{"attempts":1,"playable":68.40175329217033,"score":68.40175329217033},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"playable":40.14521690712411,"score":40.14521690712411},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":52.784145231806455,"score":52.784145231806455},"GB2-06":{"attempts":1,"playable":51.180560534215644,"score":51.180560534215644},"GB2-07":{"attempts":1,"playable":40.71202227658455,"score":40.71202227658455},"GB2-08":{"attempts":1,"playable":28.661998579345,"score":28.661998579345}}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:26Z","match_totals_all":{"draws":1394,"losses":3046,"wins":3238},"match_totals_tracks":{"medium":{"draws":524,"losses":1459,"wins":2105},"none":{"draws":870,"losses":1587,"wins":1133}},"model_slug":"xiaomi-mimo-v2-6-flash","official_rank_by_reasoning":{"medium":22,"none":43},"overall":{"max":83.23019220896973,"mean":50.368992387307614,"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":564,"losses":169,"wins":227},"GB2-03":{"draws":182,"losses":426,"wins":380},"GB2-04":{"draws":51,"losses":189,"wins":258},"GB2-05":{"draws":0,"losses":480,"wins":580},"GB2-06":{"draws":35,"losses":436,"wins":533},"GB2-07":{"draws":0,"losses":418,"wins":642},"GB2-08":{"draws":378,"losses":596,"wins":102}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":20,"losses":240,"wins":256},"GB2-02":{"draws":206,"losses":64,"wins":210},"GB2-03":{"draws":30,"losses":188,"wins":276},"GB2-04":{"draws":51,"losses":189,"wins":258},"GB2-05":{"draws":0,"losses":221,"wins":309},"GB2-06":{"draws":15,"losses":179,"wins":308},"GB2-07":{"draws":0,"losses":90,"wins":440},"GB2-08":{"draws":202,"losses":288,"wins":48}},"none":{"GB2-01":{"draws":164,"losses":92,"wins":260},"GB2-02":{"draws":358,"losses":105,"wins":17},"GB2-03":{"draws":152,"losses":238,"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":176,"losses":308,"wins":54}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1504.1954855105625,"GB2-02":1610.9407701594707,"GB2-03":1546.7399694154274,"GB2-04":1543.817721577298,"GB2-05":1565.358762307084,"GB2-06":1686.0861310033283,"GB2-07":1965.6189393673296,"GB2-08":1171.0286153641355},"none":{"GB2-01":1653.6799692997133,"GB2-02":1413.6948813920858,"GB2-03":1341.8339683434406,"GB2-05":1472.1179776231863,"GB2-06":1437.8911540552695,"GB2-07":1331.8283552700786,"GB2-08":1155.730681884457}},"per_game_tracks":{"medium":{"GB2-01":53.677267651639525,"GB2-02":66.84399961192453,"GB2-03":62.758061666473175,"GB2-04":58.70174355075301,"GB2-05":60.021061787878295,"GB2-06":66.24759668126995,"GB2-07":83.23019220896973,"GB2-08":30.050659764812487},"none":{"GB2-01":68.40175329217033,"GB2-02":42.487598451954895,"GB2-03":40.14521690712411,"GB2-05":52.784145231806455,"GB2-06":51.180560534215644,"GB2-07":40.71202227658455,"GB2-08":28.661998579345}},"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":60.1913228654651,"none":40.546661909150124},"reasoning_agg":{"medium":{"max":83.23019220896973,"mean":60.1913228654651,"min":30.050659764812487},"none":{"max":68.40175329217033,"mean":40.546661909150124,"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":19.644660956314972},"working_program_strength":{"all":53.26518252367548,"medium":60.1913228654651,"none":46.33904218188586}},{"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":0.3015096},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.027488630000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.020562389374999997,"median":0.015992453,"min":0.0021123,"recorded_attempt_count":22,"run_count":16,"total":0.32899823},"codegen_latency_ms":{"attempt_count":22,"max_ms":1377805,"mean_ms":526774.25,"min_ms":30630,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1377805,"mean_ms":998592.5,"min_ms":680734,"run_count":8},"none":{"attempt_count":11,"max_ms":104368,"mean_ms":54956.0,"min_ms":30630,"run_count":8}},"codegen_output_tokens":{"attempt_count":22,"output_max":125053,"output_mean":40030.0625,"output_min":2070,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":125053,"output_mean":76276.375,"output_min":52513,"run_count":8},"none":{"attempt_count":11,"output_max":7265,"output_mean":3783.75,"output_min":2070,"run_count":8}},"display_name":"Qwen3.8 Flash","economics":{"all":48.42275314767305,"medium":63.08758585684125,"none":33.75792043850485},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":22,"finish_reasons":["stop"],"indexed_attempts":22,"output_token_observations":22,"provider_post_attempt_observations":22,"provider_post_attempts":22,"reasoning_token_observations":22,"reconciliation_get_attempt_observations":22,"reconciliation_get_attempts":100,"total_output_tokens":640481,"total_reasoning_output_tokens":544948,"total_visible_output_tokens":95533,"visible_token_observations":22},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":43.10777914544832,"score":43.10777914544832},"GB2-02":{"attempts":2,"playable":50.92272137182435,"score":50.92272137182435},"GB2-03":{"attempts":2,"playable":55.91884437113908,"score":55.91884437113908},"GB2-04":{"attempts":2,"playable":44.24324769256978,"score":44.24324769256978},"GB2-05":{"attempts":2,"playable":44.43466723481594,"score":44.43466723481594},"GB2-06":{"attempts":2,"playable":68.18876206730721,"score":68.18876206730721},"GB2-07":{"attempts":2,"playable":42.721336026580595,"score":42.721336026580595},"GB2-08":{"attempts":2,"playable":37.84466727169907,"score":37.84466727169907}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":51.62656602805672,"score":51.62656602805672},"GB2-02":{"attempts":1,"playable":58.61781945897073,"score":58.61781945897073},"GB2-03":{"attempts":1,"playable":66.46750411509237,"score":66.46750411509237},"GB2-04":{"attempts":1,"playable":48.115921740853715,"score":48.115921740853715},"GB2-05":{"attempts":1,"playable":71.66985312607504,"score":71.66985312607504},"GB2-06":{"attempts":1,"playable":80.91204535467794,"score":80.91204535467794},"GB2-07":{"attempts":1,"playable":75.29905289404675,"score":75.29905289404675},"GB2-08":{"attempts":1,"playable":51.99192413695668,"score":51.99192413695668}},"none":{"GB2-01":{"attempts":1,"playable":34.588992262839916,"score":34.588992262839916},"GB2-02":{"attempts":1,"playable":43.227623284677975,"score":43.227623284677975},"GB2-03":{"attempts":1,"playable":45.37018462718579,"score":45.37018462718579},"GB2-04":{"attempts":1,"playable":40.37057364428585,"score":40.37057364428585},"GB2-05":{"attempts":1,"playable":17.199481343556844,"score":17.199481343556844},"GB2-06":{"attempts":1,"playable":55.465478779936475,"score":55.465478779936475},"GB2-07":{"attempts":1,"playable":10.143619159114431,"score":10.143619159114431},"GB2-08":{"attempts":1,"playable":23.697410406441467,"score":23.697410406441467}}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:06Z","match_totals_all":{"draws":2151,"losses":3336,"wins":2689},"match_totals_tracks":{"medium":{"draws":1021,"losses":1086,"wins":1981},"none":{"draws":1130,"losses":2250,"wins":708}},"model_slug":"qwen-qwen3-8-flash","official_rank_by_reasoning":{"medium":19,"none":54},"overall":{"max":80.91204535467794,"mean":48.42275314767305,"min":10.143619159114431},"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":639,"losses":168,"wins":153},"GB2-03":{"draws":252,"losses":347,"wins":389},"GB2-04":{"draws":626,"losses":259,"wins":111},"GB2-05":{"draws":0,"losses":603,"wins":457},"GB2-06":{"draws":47,"losses":327,"wins":630},"GB2-07":{"draws":0,"losses":620,"wins":440},"GB2-08":{"draws":294,"losses":551,"wins":231}},"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":126,"losses":121,"wins":247},"GB2-04":{"draws":292,"losses":121,"wins":85},"GB2-05":{"draws":0,"losses":159,"wins":371},"GB2-06":{"draws":40,"losses":86,"wins":376},"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":375,"losses":93,"wins":12},"GB2-03":{"draws":126,"losses":226,"wins":142},"GB2-04":{"draws":334,"losses":138,"wins":26},"GB2-05":{"draws":0,"losses":444,"wins":86},"GB2-06":{"draws":7,"losses":241,"wins":254},"GB2-07":{"draws":0,"losses":484,"wins":46},"GB2-08":{"draws":176,"losses":333,"wins":29}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1484.5628456821335,"GB2-02":1539.955207728861,"GB2-03":1585.6874663493816,"GB2-04":1460.3881063570461,"GB2-05":1741.4342273060984,"GB2-06":1962.6826721465886,"GB2-07":1803.8178665487517,"GB2-08":1414.502443354476},"none":{"GB2-01":1319.6494177104776,"GB2-02":1419.4344223818925,"GB2-03":1387.2424753401822,"GB2-04":1400.3245802126385,"GB2-05":956.9163787690927,"GB2-06":1505.4248690390898,"GB2-07":837.5067316085596,"GB2-08":1098.8186472735092}},"per_game_tracks":{"medium":{"GB2-01":51.62656602805672,"GB2-02":58.61781945897073,"GB2-03":66.46750411509237,"GB2-04":48.115921740853715,"GB2-05":71.66985312607504,"GB2-06":80.91204535467794,"GB2-07":75.29905289404675,"GB2-08":51.99192413695668},"none":{"GB2-01":34.588992262839916,"GB2-02":43.227623284677975,"GB2-03":45.37018462718579,"GB2-04":40.37057364428585,"GB2-05":17.199481343556844,"GB2-06":55.465478779936475,"GB2-07":10.143619159114431,"GB2-08":23.697410406441467}},"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":63.08758585684125,"none":33.75792043850485},"reasoning_agg":{"medium":{"max":80.91204535467794,"mean":63.08758585684125,"min":48.115921740853715},"none":{"max":55.465478779936475,"mean":33.75792043850485,"min":10.143619159114431}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":29.329665418336404},"working_program_strength":{"all":48.42275314767305,"medium":63.08758585684125,"none":33.75792043850485}},{"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":1.5289414000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.33846634,"mean":0.10613685812499998,"median":0.05239252,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.69818973},"codegen_latency_ms":{"attempt_count":23,"max_ms":2372746,"mean_ms":755436.1875,"min_ms":27078,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2372746,"mean_ms":1420193.375,"min_ms":412995,"run_count":8},"none":{"attempt_count":13,"max_ms":165291,"mean_ms":90679.0,"min_ms":27078,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":159550,"output_mean":46908.8125,"output_min":3069,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":159550,"output_mean":88125.0,"output_min":32501,"run_count":8},"none":{"attempt_count":13,"output_max":9287,"output_mean":5692.625,"output_min":3069,"run_count":8}},"display_name":"Mistral Large 4","economics":{"all":46.74401401365521,"highest":57.85279997474128,"none":35.63522805256914},"first_seen_at":null,"game_gaps":{"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[262144],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[262144],"total_output_tokens":750541,"total_reasoning_output_tokens":655796,"total_visible_output_tokens":94745,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":47.15376995777604,"score":47.15376995777604},"GB2-02":{"attempts":2,"playable":54.267767154668206,"score":54.267767154668206},"GB2-03":{"attempts":2,"playable":37.02602529219823,"score":37.02602529219823},"GB2-04":{"attempts":2,"playable":52.09864250433918,"score":52.09864250433918},"GB2-05":{"attempts":2,"playable":56.66657652051722,"score":56.66657652051722},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":79.63955354616625,"score":39.81977677308313},"GB2-07":{"attempts":2,"playable":44.486370931647215,"score":44.486370931647215},"GB2-08":{"attempts":2,"playable":42.43318297501246,"score":42.43318297501246}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":34.98596030617719,"score":34.98596030617719},"GB2-02":{"attempts":1,"playable":65.41359404194165,"score":65.41359404194165},"GB2-03":{"attempts":1,"playable":43.60195874561567,"score":43.60195874561567},"GB2-04":{"attempts":1,"playable":65.56719653014635,"score":65.56719653014635},"GB2-05":{"attempts":1,"playable":49.52921654279083,"score":49.52921654279083},"GB2-06":{"attempts":1,"playable":79.63955354616625,"score":79.63955354616625},"GB2-07":{"attempts":1,"playable":79.44691027123345,"score":79.44691027123345},"GB2-08":{"attempts":1,"playable":44.63800981385882,"score":44.63800981385882}},"none":{"GB2-01":{"attempts":1,"playable":59.32157960937489,"score":59.32157960937489},"GB2-02":{"attempts":1,"playable":43.12194026739476,"score":43.12194026739476},"GB2-03":{"attempts":1,"playable":30.450091838780786,"score":30.450091838780786},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":63.80393649824361,"score":63.80393649824361},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.52583159206098,"score":9.52583159206098},"GB2-08":{"attempts":1,"playable":40.228356136166084,"score":40.228356136166084}}},"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":36,"none":52},"overall":{"max":79.63955354616625,"mean":46.74401401365521,"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":34.98596030617719,"GB2-02":65.41359404194165,"GB2-03":43.60195874561567,"GB2-04":65.56719653014635,"GB2-05":49.52921654279083,"GB2-06":79.63955354616625,"GB2-07":79.44691027123345,"GB2-08":44.63800981385882},"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":1323.6798648493855,"GB2-02":1597.955907005048,"GB2-03":1371.9018676500107,"GB2-04":1602.2382254283004,"GB2-05":1431.5519176268197,"GB2-06":1936.917844233639,"GB2-07":1881.4979424000703,"GB2-08":1328.6947556729865},"none":{"GB2-01":1559.2049805323863,"GB2-02":1418.6155920415097,"GB2-03":1254.225045427533,"GB2-04":1386.5783876383734,"GB2-05":1617.6005239638205,"GB2-07":820.5386297402082,"GB2-08":1280.4264338855992}},"per_game_tracks":{"highest":{"GB2-01":34.98596030617719,"GB2-02":65.41359404194165,"GB2-03":43.60195874561567,"GB2-04":65.56719653014635,"GB2-05":49.52921654279083,"GB2-06":79.63955354616625,"GB2-07":79.44691027123345,"GB2-08":44.63800981385882},"none":{"GB2-01":59.32157960937489,"GB2-02":43.12194026739476,"GB2-03":30.450091838780786,"GB2-04":38.63008847853202,"GB2-05":63.80393649824361,"GB2-07":9.52583159206098,"GB2-08":40.228356136166084}},"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":57.85279997474128,"none":35.63522805256914},"reasoning_agg":{"highest":{"max":79.63955354616625,"mean":57.85279997474128,"min":34.98596030617719},"none":{"max":63.80393649824361,"mean":35.63522805256914,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":22.21757192217214},"working_program_strength":{"all":49.289387445981575,"highest":57.85279997474128,"none":40.725974917221876}},{"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":0.18443460000000003}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.224169,"mean":0.0821287125,"median":0.0481557,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.3140593999999999},"codegen_latency_ms":{"attempt_count":23,"max_ms":561371,"mean_ms":157083.3125,"min_ms":8331,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":10,"max_ms":561371,"mean_ms":286804.25,"min_ms":88263,"run_count":8},"none":{"attempt_count":13,"max_ms":43454,"mean_ms":27362.375,"min_ms":8331,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":73204,"output_mean":25017.0625,"output_min":2066,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":10,"output_max":73204,"output_mean":44953.5,"output_min":17269,"run_count":8},"none":{"attempt_count":13,"output_max":8678,"output_mean":5080.625,"output_min":2066,"run_count":8}},"display_name":"Glimpse","economics":{"all":42.659018217797566,"medium":65.83738011304924,"none":19.480656322545897},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-02":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[235929],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":23,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[235929],"total_output_tokens":400273,"total_reasoning_output_tokens":316594,"total_visible_output_tokens":83679,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"elorian/glimpse","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":47.88533845613112,"score":47.88533845613112},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.861474907777556,"score":21.930737453888778},"GB2-03":{"attempts":2,"playable":45.51502997852399,"score":45.51502997852399},"GB2-04":{"attempts":2,"playable":48.23535880825,"score":48.23535880825},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.69249200332186,"score":29.34624600166093},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":84.63629825457303,"score":42.31814912728652},"GB2-07":{"attempts":2,"playable":45.78585099453851,"score":45.78585099453851},"GB2-08":{"attempts":2,"playable":60.25543492210068,"score":60.25543492210068}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":83.07306782963423,"score":83.07306782963423},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":36.44436895903613,"score":36.44436895903613},"GB2-04":{"attempts":1,"playable":55.79328232032243,"score":55.79328232032243},"GB2-05":{"attempts":1,"playable":58.69249200332186,"score":58.69249200332186},"GB2-06":{"attempts":1,"playable":84.63629825457303,"score":84.63629825457303},"GB2-07":{"attempts":1,"playable":75.12563458860022,"score":75.12563458860022},"GB2-08":{"attempts":1,"playable":89.07242204112839,"score":89.07242204112839}},"none":{"GB2-01":{"attempts":1,"playable":12.697609082628016,"score":12.697609082628016},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":54.58569099801185,"score":54.58569099801185},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"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":16.446067400476796,"score":16.446067400476796},"GB2-08":{"attempts":1,"playable":31.43844780307297,"score":31.43844780307297}}},"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":15,"none":81},"overall":{"max":89.07242204112839,"mean":42.659018217797566,"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":1846.0872737655034,"GB2-02":1424.340397604501,"GB2-03":1309.207851941514,"GB2-04":1520.366656604706,"GB2-05":1547.7194986563513,"GB2-06":2041.8414387673147,"GB2-07":1800.802285791785,"GB2-08":2129.304447878063},"none":{"GB2-01":1037.2169012356349,"GB2-03":1468.6453138867805,"GB2-04":1402.7331723403474,"GB2-07":978.6860665791575,"GB2-08":1186.1418450171386}},"per_game_tracks":{"medium":{"GB2-01":83.07306782963423,"GB2-02":43.861474907777556,"GB2-03":36.44436895903613,"GB2-04":55.79328232032243,"GB2-05":58.69249200332186,"GB2-06":84.63629825457303,"GB2-07":75.12563458860022,"GB2-08":89.07242204112839},"none":{"GB2-01":12.697609082628016,"GB2-03":54.58569099801185,"GB2-04":40.67743529617756,"GB2-07":16.446067400476796,"GB2-08":31.43844780307297}},"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":65.83738011304924,"none":19.480656322545897},"reasoning_agg":{"medium":{"max":89.07242204112839,"mean":65.83738011304924,"min":36.44436895903613},"none":{"max":54.58569099801185,"mean":19.480656322545897,"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":46.35672379050334},"working_program_strength":{"all":48.503215114561335,"medium":65.83738011304924,"none":31.169050116073436}},{"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":42.397549164017946,"none":42.397549164017946},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":11,"finish_reasons":["stop"],"indexed_attempts":11,"output_token_observations":11,"total_output_tokens":35469},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":61.84206851689213,"score":61.84206851689213},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":39.302431406504134,"score":39.302431406504134},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":13.93825891291957,"score":13.93825891291957},"GB2-06":{"attempts":1,"playable":50.13315219774284,"score":50.13315219774284},"GB2-07":{"attempts":1,"playable":47.98112150477692,"score":47.98112150477692},"GB2-08":{"attempts":1,"playable":44.442732998848115,"score":44.442732998848115}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":61.84206851689213,"score":61.84206851689213},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":39.302431406504134,"score":39.302431406504134},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":13.93825891291957,"score":13.93825891291957},"GB2-06":{"attempts":1,"playable":50.13315219774284,"score":50.13315219774284},"GB2-07":{"attempts":1,"playable":47.98112150477692,"score":47.98112150477692},"GB2-08":{"attempts":1,"playable":44.442732998848115,"score":44.442732998848115}}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:10Z","match_totals_all":{"draws":1090,"losses":1914,"wins":1083},"match_totals_tracks":{"none":{"draws":1090,"losses":1914,"wins":1083}},"model_slug":"gpt-4-1","official_rank_by_reasoning":{"none":34},"overall":{"max":61.84206851689213,"mean":42.397549164017946,"min":13.93825891291957},"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":5,"losses":269,"wins":227},"GB2-07":{"draws":0,"losses":289,"wins":241},"GB2-08":{"draws":226,"losses":203,"wins":109}},"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":5,"losses":269,"wins":227},"GB2-07":{"draws":0,"losses":289,"wins":241},"GB2-08":{"draws":226,"losses":203,"wins":109}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1584.489312468309,"GB2-02":1416.9768592403107,"GB2-03":1334.4582272497535,"GB2-04":1386.5783876383734,"GB2-05":889.0965364024593,"GB2-06":1421.6356233932645,"GB2-07":1422.3040522984802,"GB2-08":1326.5206078985866}},"per_game_tracks":{"none":{"GB2-01":61.84206851689213,"GB2-02":42.910539295927805,"GB2-03":39.302431406504134,"GB2-04":38.63008847853202,"GB2-05":13.93825891291957,"GB2-06":50.13315219774284,"GB2-07":47.98112150477692,"GB2-08":44.442732998848115}},"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":42.397549164017946},"reasoning_agg":{"none":{"max":61.84206851689213,"mean":42.397549164017946,"min":13.93825891291957}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"working_program_strength":{"all":42.397549164017946,"none":42.397549164017946}},{"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":1.2830031540000002}},"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":1.2830031540000002},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"all":40.61844090162918,"medium":40.61844090162918},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"infra_excluded","GB2-06":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"infra_excluded","GB2-06":"failed"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"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":38.51497559923496,"score":38.51497559923496},"GB2-02":{"attempts":1,"playable":42.59335095030837,"score":42.59335095030837},"GB2-04":{"attempts":1,"playable":38.42514998716071,"score":38.42514998716071},"GB2-05":{"attempts":1,"playable":52.9753103538752,"score":52.9753103538752},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.523737593579355,"score":43.523737593579355},"GB2-08":{"attempts":1,"playable":68.29656182724565,"score":68.29656182724565}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":38.51497559923496,"score":38.51497559923496},"GB2-02":{"attempts":1,"playable":42.59335095030837,"score":42.59335095030837},"GB2-04":{"attempts":1,"playable":38.42514998716071,"score":38.42514998716071},"GB2-05":{"attempts":1,"playable":52.9753103538752,"score":52.9753103538752},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.523737593579355,"score":43.523737593579355},"GB2-08":{"attempts":1,"playable":68.29656182724565,"score":68.29656182724565}}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-10-25T23:51:26Z","match_totals_all":{"draws":694,"losses":1337,"wins":1060},"match_totals_tracks":{"medium":{"draws":694,"losses":1337,"wins":1060}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":68.29656182724565,"mean":40.61844090162918,"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":291,"losses":169,"wins":38},"GB2-05":{"draws":0,"losses":258,"wins":272},"GB2-07":{"draws":0,"losses":313,"wins":217},"GB2-08":{"draws":33,"losses":172,"wins":333}},"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":291,"losses":169,"wins":38},"GB2-05":{"draws":0,"losses":258,"wins":272},"GB2-07":{"draws":0,"losses":313,"wins":217},"GB2-08":{"draws":33,"losses":172,"wins":333}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1358.8645870426485,"GB2-02":1414.5159599680042,"GB2-04":1384.9491528865444,"GB2-05":1474.5143083563207,"GB2-07":1366.8972011272233,"GB2-08":1655.2337563552296}},"per_game_tracks":{"medium":{"GB2-01":38.51497559923496,"GB2-02":42.59335095030837,"GB2-04":38.42514998716071,"GB2-05":52.9753103538752,"GB2-07":43.523737593579355,"GB2-08":68.29656182724565}},"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":40.61844090162918},"reasoning_agg":{"medium":{"max":68.29656182724565,"mean":40.61844090162918,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":47.38818105190071,"medium":47.38818105190071}},{"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":5.168810400000001},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"all":38.91232848757102,"medium":48.27784746950317,"none":29.546809505638855},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":21,"finish_reasons":["incomplete","stop"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":2,"total_output_tokens":1096010,"total_reasoning_output_tokens":255888,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":51.819752220671134,"score":51.819752220671134},"GB2-02":{"attempts":2,"playable":41.53531315649431,"score":41.53531315649431},"GB2-03":{"attempts":2,"playable":45.52569905546824,"score":45.52569905546824},"GB2-04":{"attempts":2,"playable":43.89404994594723,"score":43.89404994594723},"GB2-05":{"attempts":2,"playable":29.526397279769263,"score":29.526397279769263},"GB2-06":{"attempts":2,"playable":39.334269029551784,"score":39.334269029551784},"GB2-07":{"attempts":2,"playable":26.179655135772354,"score":26.179655135772354},"GB2-08":{"attempts":2,"playable":33.483492076893796,"score":33.483492076893796}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":69.74557538933259,"score":69.74557538933259},"GB2-02":{"attempts":1,"playable":41.53531315649431,"score":41.53531315649431},"GB2-03":{"attempts":1,"playable":45.78498915227661,"score":45.78498915227661},"GB2-04":{"attempts":1,"playable":44.25089660655846,"score":44.25089660655846},"GB2-05":{"attempts":1,"playable":47.994407605115654,"score":47.994407605115654},"GB2-06":{"attempts":1,"playable":47.69757081673043,"score":47.69757081673043},"GB2-07":{"attempts":1,"playable":45.9444532821712,"score":45.9444532821712},"GB2-08":{"attempts":1,"playable":43.26957374734612,"score":43.26957374734612}},"none":{"GB2-01":{"attempts":1,"playable":33.893929052009675,"score":33.893929052009675},"GB2-02":{"attempts":1,"playable":41.53531315649431,"score":41.53531315649431},"GB2-03":{"attempts":1,"playable":45.26640895865987,"score":45.26640895865987},"GB2-04":{"attempts":1,"playable":43.537203285336005,"score":43.537203285336005},"GB2-05":{"attempts":1,"playable":11.058386954422868,"score":11.058386954422868},"GB2-06":{"attempts":1,"playable":30.97096724237314,"score":30.97096724237314},"GB2-07":{"attempts":1,"playable":6.4148569893735035,"score":6.4148569893735035},"GB2-08":{"attempts":1,"playable":23.697410406441467,"score":23.697410406441467}}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:58Z","match_totals_all":{"draws":2449,"losses":3979,"wins":1748},"match_totals_tracks":{"medium":{"draws":1041,"losses":1699,"wins":1348},"none":{"draws":1408,"losses":2280,"wins":400}},"model_slug":"gpt-5-4-mini","official_rank_by_reasoning":{"medium":42,"none":65},"overall":{"max":69.74557538933259,"mean":38.91232848757102,"min":6.4148569893735035},"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":547,"losses":303,"wins":138},"GB2-04":{"draws":611,"losses":270,"wins":115},"GB2-05":{"draws":0,"losses":760,"wins":300},"GB2-06":{"draws":34,"losses":635,"wins":335},"GB2-07":{"draws":0,"losses":802,"wins":258},"GB2-08":{"draws":316,"losses":585,"wins":175}},"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":166,"losses":204,"wins":124},"GB2-04":{"draws":322,"losses":125,"wins":51},"GB2-05":{"draws":0,"losses":284,"wins":246},"GB2-06":{"draws":24,"losses":273,"wins":205},"GB2-07":{"draws":0,"losses":300,"wins":230},"GB2-08":{"draws":128,"losses":258,"wins":152}},"none":{"GB2-01":{"draws":159,"losses":271,"wins":86},"GB2-02":{"draws":381,"losses":98,"wins":1},"GB2-03":{"draws":381,"losses":99,"wins":14},"GB2-04":{"draws":289,"losses":145,"wins":64},"GB2-05":{"draws":0,"losses":476,"wins":54},"GB2-06":{"draws":10,"losses":362,"wins":130},"GB2-07":{"draws":0,"losses":502,"wins":28},"GB2-08":{"draws":188,"losses":327,"wins":23}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1668.667942224696,"GB2-02":1406.286062793837,"GB2-03":1390.8438863987412,"GB2-04":1430.545404647071,"GB2-05":1412.4879057892756,"GB2-06":1384.1313499201208,"GB2-07":1396.9782916784195,"GB2-08":1313.541019698037},"none":{"GB2-01":1312.551032716877,"GB2-02":1406.286062793837,"GB2-03":1386.3417497190121,"GB2-04":1425.0180160962746,"GB2-05":821.0782730220733,"GB2-06":1131.6935712883765,"GB2-07":719.4861296230509,"GB2-08":1098.8186472735092}},"per_game_tracks":{"medium":{"GB2-01":69.74557538933259,"GB2-02":41.53531315649431,"GB2-03":45.78498915227661,"GB2-04":44.25089660655846,"GB2-05":47.994407605115654,"GB2-06":47.69757081673043,"GB2-07":45.9444532821712,"GB2-08":43.26957374734612},"none":{"GB2-01":33.893929052009675,"GB2-02":41.53531315649431,"GB2-03":45.26640895865987,"GB2-04":43.537203285336005,"GB2-05":11.058386954422868,"GB2-06":30.97096724237314,"GB2-07":6.4148569893735035,"GB2-08":23.697410406441467}},"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":48.27784746950317,"none":29.546809505638855},"reasoning_agg":{"medium":{"max":69.74557538933259,"mean":48.27784746950317,"min":41.53531315649431},"none":{"max":45.26640895865987,"mean":29.546809505638855,"min":6.4148569893735035}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":18.731037963864317},"working_program_strength":{"all":38.91232848757102,"medium":48.27784746950317,"none":29.546809505638855}},{"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":1.0777302952},"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":1.3313309783999998},"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":38.29903149795016,"medium":46.785793220027806,"none":29.812269775872515},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-02":"infra_excluded","GB2-03":"infra_excluded"},"none":{"GB2-04":"failed"}},"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":54.319662771015324,"score":54.319662771015324},"GB2-02":{"attempts":1,"playable":39.09761928198411,"score":39.09761928198411},"GB2-03":{"attempts":1,"playable":34.527363294170684,"score":34.527363294170684},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":47.60829699628472,"score":23.80414849814236},"GB2-05":{"attempts":2,"playable":22.383379426712345,"score":22.383379426712345},"GB2-06":{"attempts":2,"playable":52.78660997199282,"score":52.78660997199282},"GB2-07":{"attempts":2,"playable":45.55537993569061,"score":45.55537993569061},"GB2-08":{"attempts":2,"playable":23.94478687194261,"score":23.94478687194261}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":71.37373256693535,"score":71.37373256693535},"GB2-04":{"attempts":1,"playable":47.60829699628472,"score":47.60829699628472},"GB2-05":{"attempts":1,"playable":25.456917724816257,"score":25.456917724816257},"GB2-06":{"attempts":1,"playable":67.16410028755743,"score":67.16410028755743},"GB2-07":{"attempts":1,"playable":41.83910358067528,"score":41.83910358067528},"GB2-08":{"attempts":1,"playable":27.272608163897793,"score":27.272608163897793}},"none":{"GB2-01":{"attempts":1,"playable":37.2655929750953,"score":37.2655929750953},"GB2-02":{"attempts":1,"playable":39.09761928198411,"score":39.09761928198411},"GB2-03":{"attempts":1,"playable":34.527363294170684,"score":34.527363294170684},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.309841128608433,"score":19.309841128608433},"GB2-06":{"attempts":1,"playable":38.409119656428196,"score":38.409119656428196},"GB2-07":{"attempts":1,"playable":49.27165629070595,"score":49.27165629070595},"GB2-08":{"attempts":1,"playable":20.616965579987426,"score":20.616965579987426}}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:54Z","match_totals_all":{"draws":1333,"losses":3526,"wins":1845},"match_totals_tracks":{"medium":{"draws":577,"losses":1447,"wins":1090},"none":{"draws":756,"losses":2079,"wins":755}},"model_slug":"xiaomi-mimo-v2-5-pro","official_rank_by_reasoning":{"none":64},"overall":{"max":71.37373256693535,"mean":38.29903149795016,"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":320,"losses":140,"wins":20},"GB2-03":{"draws":183,"losses":249,"wins":62},"GB2-04":{"draws":251,"losses":144,"wins":103},"GB2-05":{"draws":0,"losses":834,"wins":226},"GB2-06":{"draws":20,"losses":503,"wins":481},"GB2-07":{"draws":0,"losses":604,"wins":456},"GB2-08":{"draws":369,"losses":655,"wins":52}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":63,"losses":127,"wins":326},"GB2-04":{"draws":251,"losses":144,"wins":103},"GB2-05":{"draws":0,"losses":401,"wins":129},"GB2-06":{"draws":15,"losses":174,"wins":313},"GB2-07":{"draws":0,"losses":322,"wins":208},"GB2-08":{"draws":248,"losses":279,"wins":11}},"none":{"GB2-01":{"draws":127,"losses":270,"wins":119},"GB2-02":{"draws":320,"losses":140,"wins":20},"GB2-03":{"draws":183,"losses":249,"wins":62},"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":1687.307132213646,"GB2-04":1456.4699533843047,"GB2-05":1103.3385818564211,"GB2-06":1702.3000007458459,"GB2-07":1345.9143749883358,"GB2-08":1140.2010425388262},"none":{"GB2-01":1346.5284597257478,"GB2-02":1387.1619387321743,"GB2-03":1291.987034432538,"GB2-05":997.2079150455615,"GB2-06":1243.4605735523548,"GB2-07":1438.3940758739384,"GB2-08":1060.80549548712}},"per_game_tracks":{"medium":{"GB2-01":71.37373256693535,"GB2-04":47.60829699628472,"GB2-05":25.456917724816257,"GB2-06":67.16410028755743,"GB2-07":41.83910358067528,"GB2-08":27.272608163897793},"none":{"GB2-01":37.2655929750953,"GB2-02":39.09761928198411,"GB2-03":34.527363294170684,"GB2-05":19.309841128608433,"GB2-06":38.409119656428196,"GB2-07":49.27165629070595,"GB2-08":20.616965579987426}},"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":46.785793220027806,"none":29.812269775872515},"reasoning_agg":{"medium":{"max":71.37373256693535,"mean":46.785793220027806,"min":25.456917724816257},"none":{"max":49.27165629070595,"mean":29.812269775872515,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.97352344415529},"working_program_strength":{"all":40.42847933908391,"medium":46.785793220027806,"none":34.071165458140015}},{"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":0.7288237500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875000000003}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999998},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"all":37.59802533964688,"medium":39.90533142143005,"none":35.290719257863714},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"total_output_tokens":178317},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":42.23484043727251,"score":42.23484043727251},"GB2-02":{"attempts":2,"playable":45.127589240945326,"score":45.127589240945326},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":29.690595943558773,"score":14.845297971779386},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.63919085975499,"score":21.819595429877495},"GB2-05":{"attempts":2,"playable":38.080608175054834,"score":38.080608175054834},"GB2-06":{"attempts":2,"playable":38.78084228192538,"score":38.78084228192538},"GB2-07":{"attempts":2,"playable":68.61058634647813,"score":68.61058634647813},"GB2-08":{"attempts":2,"playable":31.28484283384198,"score":31.28484283384198}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.47367135694114,"score":18.47367135694114},"GB2-02":{"attempts":1,"playable":44.38935843142217,"score":44.38935843142217},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.63919085975499,"score":43.63919085975499},"GB2-05":{"attempts":1,"playable":39.52695378355019,"score":39.52695378355019},"GB2-06":{"attempts":1,"playable":61.45320043406526,"score":61.45320043406526},"GB2-07":{"attempts":1,"playable":76.16539028897841,"score":76.16539028897841},"GB2-08":{"attempts":1,"playable":35.59488621672822,"score":35.59488621672822}},"none":{"GB2-01":{"attempts":1,"playable":65.99600951760388,"score":65.99600951760388},"GB2-02":{"attempts":1,"playable":45.86582005046848,"score":45.86582005046848},"GB2-03":{"attempts":1,"playable":29.690595943558773,"score":29.690595943558773},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":36.63426256655947,"score":36.63426256655947},"GB2-06":{"attempts":1,"playable":16.1084841297855,"score":16.1084841297855},"GB2-07":{"attempts":1,"playable":61.05578240397785,"score":61.05578240397785},"GB2-08":{"attempts":1,"playable":26.974799450955743,"score":26.974799450955743}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:54Z","match_totals_all":{"draws":1878,"losses":3302,"wins":2005},"match_totals_tracks":{"medium":{"draws":982,"losses":1533,"wins":1079},"none":{"draws":896,"losses":1769,"wins":926}},"model_slug":"qwen-qwen3-7-max","official_rank_by_reasoning":{"medium":55,"none":53},"overall":{"max":76.16539028897841,"mean":37.59802533964688,"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":692,"losses":197,"wins":71},"GB2-03":{"draws":194,"losses":267,"wins":34},"GB2-04":{"draws":270,"losses":154,"wins":74},"GB2-05":{"draws":0,"losses":671,"wins":389},"GB2-06":{"draws":41,"losses":626,"wins":337},"GB2-07":{"draws":0,"losses":348,"wins":712},"GB2-08":{"draws":459,"losses":536,"wins":81}},"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":270,"losses":154,"wins":74},"GB2-05":{"draws":0,"losses":328,"wins":202},"GB2-06":{"draws":37,"losses":194,"wins":271},"GB2-07":{"draws":0,"losses":131,"wins":399},"GB2-08":{"draws":244,"losses":239,"wins":55}},"none":{"GB2-01":{"draws":153,"losses":110,"wins":253},"GB2-02":{"draws":330,"losses":103,"wins":47},"GB2-03":{"draws":194,"losses":267,"wins":34},"GB2-05":{"draws":0,"losses":343,"wins":187},"GB2-06":{"draws":4,"losses":432,"wins":66},"GB2-07":{"draws":0,"losses":217,"wins":313},"GB2-08":{"draws":215,"losses":297,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1130.7845634338496,"GB2-02":1428.4203946875823,"GB2-04":1425.8085108177343,"GB2-05":1305.4324010050284,"GB2-06":1603.5375135852112,"GB2-07":1819.1259736797747,"GB2-08":1230.783780377737},"none":{"GB2-01":1627.618501970005,"GB2-02":1439.8126739813636,"GB2-03":1246.9703855261146,"GB2-05":1267.1716606890257,"GB2-06":893.811223076742,"GB2-07":1590.016445528597,"GB2-08":1136.8382066154281}},"per_game_tracks":{"medium":{"GB2-01":18.47367135694114,"GB2-02":44.38935843142217,"GB2-04":43.63919085975499,"GB2-05":39.52695378355019,"GB2-06":61.45320043406526,"GB2-07":76.16539028897841,"GB2-08":35.59488621672822},"none":{"GB2-01":65.99600951760388,"GB2-02":45.86582005046848,"GB2-03":29.690595943558773,"GB2-05":36.63426256655947,"GB2-06":16.1084841297855,"GB2-07":61.05578240397785,"GB2-08":26.974799450955743}},"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":39.90533142143005,"none":35.290719257863714},"reasoning_agg":{"medium":{"max":76.16539028897841,"mean":39.90533142143005,"min":0.0},"none":{"max":65.99600951760388,"mean":35.290719257863714,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":4.614612163566335},"working_program_strength":{"all":42.96917181673929,"medium":45.606093053062914,"none":40.332250580415675}},{"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":0.48528460000000007}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"all":34.91176220956577,"medium":34.91176220956577},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":17,"finish_reasons":["stop"],"indexed_attempts":17,"output_token_observations":17,"total_output_tokens":179458},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":37.36459538989437,"score":37.36459538989437},"GB2-02":{"attempts":1,"playable":43.54460209735465,"score":43.54460209735465},"GB2-03":{"attempts":1,"playable":29.04587972921168,"score":29.04587972921168},"GB2-04":{"attempts":1,"playable":40.98421031880623,"score":40.98421031880623},"GB2-05":{"attempts":1,"playable":50.295915322236574,"score":50.295915322236574},"GB2-06":{"attempts":1,"playable":32.6755337727175,"score":32.6755337727175},"GB2-07":{"attempts":1,"playable":15.03523943046976,"score":15.03523943046976},"GB2-08":{"attempts":1,"playable":30.34812161583544,"score":30.34812161583544}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":37.36459538989437,"score":37.36459538989437},"GB2-02":{"attempts":1,"playable":43.54460209735465,"score":43.54460209735465},"GB2-03":{"attempts":1,"playable":29.04587972921168,"score":29.04587972921168},"GB2-04":{"attempts":1,"playable":40.98421031880623,"score":40.98421031880623},"GB2-05":{"attempts":1,"playable":50.295915322236574,"score":50.295915322236574},"GB2-06":{"attempts":1,"playable":32.6755337727175,"score":32.6755337727175},"GB2-07":{"attempts":1,"playable":15.03523943046976,"score":15.03523943046976},"GB2-08":{"attempts":1,"playable":30.34812161583544,"score":30.34812161583544}}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-10-26T01:35:05Z","match_totals_all":{"draws":1191,"losses":2163,"wins":734},"match_totals_tracks":{"medium":{"draws":1191,"losses":2163,"wins":734}},"model_slug":"x-ai-grok-build-0-1","official_rank_by_reasoning":{"medium":60},"overall":{"max":50.295915322236574,"mean":34.91176220956577,"min":15.03523943046976},"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":132,"losses":300,"wins":62},"GB2-04":{"draws":340,"losses":132,"wins":26},"GB2-05":{"draws":0,"losses":272,"wins":258},"GB2-06":{"draws":6,"losses":356,"wins":140},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":231,"losses":272,"wins":35}},"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":132,"losses":300,"wins":62},"GB2-04":{"draws":340,"losses":132,"wins":26},"GB2-05":{"draws":0,"losses":272,"wins":258},"GB2-06":{"draws":6,"losses":356,"wins":140},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":231,"losses":272,"wins":35}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1347.510379640592,"GB2-02":1421.8888642543418,"GB2-03":1240.746357159253,"GB2-04":1405.1371493550557,"GB2-05":1441.079928899763,"GB2-06":1157.352294610677,"GB2-07":950.8642494453044,"GB2-08":1174.281199256321}},"per_game_tracks":{"medium":{"GB2-01":37.36459538989437,"GB2-02":43.54460209735465,"GB2-03":29.04587972921168,"GB2-04":40.98421031880623,"GB2-05":50.295915322236574,"GB2-06":32.6755337727175,"GB2-07":15.03523943046976,"GB2-08":30.34812161583544}},"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":34.91176220956577},"reasoning_agg":{"medium":{"max":50.295915322236574,"mean":34.91176220956577,"min":15.03523943046976}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":34.91176220956577,"medium":34.91176220956577}},{"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":33.32018896021172,"none":33.32018896021172},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"}},"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":33.32018896021172,"score":33.32018896021172}},"headline_games_tracks":{"none":{"GB2-08":{"attempts":1,"playable":33.32018896021172,"score":33.32018896021172}}},"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":33.32018896021172,"mean":33.32018896021172,"min":33.32018896021172},"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":1206.4331012892305}},"per_game_tracks":{"none":{"GB2-08":33.32018896021172}},"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":33.32018896021172},"reasoning_agg":{"none":{"max":33.32018896021172,"mean":33.32018896021172,"min":33.32018896021172}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"},"working_program_strength":{"all":33.32018896021172,"none":33.32018896021172}},{"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":0.04176386}},"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":31.634760981160213,"medium":31.335161634682557,"none":31.934360327637865},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-07":"too_slow"},"none":{"GB2-04":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"poolside","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":45.61939485793179,"score":35.38874268276867},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":42.01104720613089,"score":31.75957918894266},"GB2-03":{"attempts":4,"playable":39.102529841730124,"score":39.102529841730124},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.37057364428585,"score":20.185286822142924},"GB2-05":{"attempts":4,"playable":38.24152371387998,"score":38.24152371387998},"GB2-06":{"attempts":2,"playable":20.246889034093414,"score":20.246889034093414},"GB2-07":{"attempts":2,"playable":45.21795121798449,"score":45.21795121798449},"GB2-08":{"attempts":4,"playable":29.876980139390394,"score":29.876980139390394}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":40.92260870065246,"score":20.46130435032623},"GB2-02":{"attempts":2,"playable":43.01622234350885,"score":43.01622234350885},"GB2-03":{"attempts":2,"playable":38.761728989351525,"score":38.761728989351525},"GB2-04":{"attempts":1,"playable":40.37057364428585,"score":40.37057364428585},"GB2-05":{"attempts":2,"playable":28.07691920678637,"score":28.07691920678637},"GB2-06":{"attempts":1,"playable":19.402244997158455,"score":19.402244997158455},"GB2-08":{"attempts":2,"playable":29.25713791136063,"score":29.25713791136063}},"none":{"GB2-01":{"attempts":2,"playable":50.316181015211114,"score":50.316181015211114},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":41.00587206875293,"score":20.502936034376464},"GB2-03":{"attempts":2,"playable":39.443330694108724,"score":39.443330694108724},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":48.406128220973585,"score":48.406128220973585},"GB2-06":{"attempts":1,"playable":21.09153307102837,"score":21.09153307102837},"GB2-07":{"attempts":2,"playable":45.21795121798449,"score":45.21795121798449},"GB2-08":{"attempts":2,"playable":30.496822367420158,"score":30.496822367420158}}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:39Z","match_totals_all":{"draws":2985,"losses":6123,"wins":2690},"match_totals_tracks":{"medium":{"draws":1773,"losses":2918,"wins":909},"none":{"draws":1212,"losses":3205,"wins":1781}},"model_slug":"poolside-laguna-s-2-1","official_rank_by_reasoning":{"medium":66,"none":55},"overall":{"max":50.316181015211114,"mean":31.634760981160213,"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":1132,"losses":288,"wins":20},"GB2-03":{"draws":651,"losses":950,"wins":375},"GB2-04":{"draws":298,"losses":156,"wins":44},"GB2-05":{"draws":0,"losses":1335,"wins":785},"GB2-06":{"draws":9,"losses":827,"wins":168},"GB2-07":{"draws":0,"losses":606,"wins":454},"GB2-08":{"draws":643,"losses":1238,"wins":271}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":86,"losses":272,"wins":158},"GB2-02":{"draws":790,"losses":168,"wins":2},"GB2-03":{"draws":302,"losses":490,"wins":196},"GB2-04":{"draws":298,"losses":156,"wins":44},"GB2-05":{"draws":0,"losses":775,"wins":285},"GB2-06":{"draws":3,"losses":418,"wins":81},"GB2-08":{"draws":294,"losses":639,"wins":143}},"none":{"GB2-01":{"draws":166,"losses":451,"wins":415},"GB2-02":{"draws":342,"losses":120,"wins":18},"GB2-03":{"draws":349,"losses":460,"wins":179},"GB2-05":{"draws":0,"losses":560,"wins":500},"GB2-06":{"draws":6,"losses":409,"wins":87},"GB2-07":{"draws":0,"losses":606,"wins":454},"GB2-08":{"draws":349,"losses":599,"wins":128}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1382.342552783333,"GB2-02":1417.7956816098076,"GB2-03":1329.4912940002264,"GB2-04":1400.3245802126385,"GB2-05":1123.397938920052,"GB2-06":950.9761047836756,"GB2-08":1162.2861269550663},"none":{"GB2-01":1472.702979449688,"GB2-02":1402.1537380681266,"GB2-03":1335.4409906484757,"GB2-05":1428.7536175606908,"GB2-06":978.7773112568484,"GB2-07":1387.7029189444747,"GB2-08":1175.9017385996221}},"per_game_tracks":{"medium":{"GB2-01":40.92260870065246,"GB2-02":43.01622234350885,"GB2-03":38.761728989351525,"GB2-04":40.37057364428585,"GB2-05":28.07691920678637,"GB2-06":19.402244997158455,"GB2-08":29.25713791136063},"none":{"GB2-01":50.316181015211114,"GB2-02":41.00587206875293,"GB2-03":39.443330694108724,"GB2-05":48.406128220973585,"GB2-06":21.09153307102837,"GB2-07":45.21795121798449,"GB2-08":30.496822367420158}},"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":31.335161634682553,"none":31.934360327637865},"reasoning_agg":{"medium":{"max":43.01622234350885,"mean":31.335161634682553,"min":19.402244997158455},"none":{"max":50.316181015211114,"mean":31.934360327637865,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.5991986929553121},"working_program_strength":{"all":36.84180388918454,"medium":34.2582051133006,"none":39.42540266506848}},{"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":0.031586438999999994},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139173999999999}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725612999999995},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"all":31.43946221352207,"highest":32.56208971571559,"none":30.31683471132855},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-06":"failed","GB2-07":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"total_output_tokens":130744},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":71.81343806792842,"score":71.81343806792842},"GB2-02":{"attempts":2,"playable":38.40745949264775,"score":38.40745949264775},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":32.17182072697564,"score":16.08591036348782},"GB2-04":{"attempts":2,"playable":45.97928982336829,"score":45.97928982336829},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":37.74596101507403,"score":22.693292624814305},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":14.277776758291424,"score":7.138888379145712},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":25.564044191476587,"score":12.782022095738293},"GB2-08":{"attempts":2,"playable":36.61539686104595,"score":36.61539686104595}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":65.22465150047583,"score":65.22465150047583},"GB2-02":{"attempts":1,"playable":39.09761928198411,"score":39.09761928198411},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":60.21067356103889,"score":30.105336780519444},"GB2-06":{"attempts":1,"playable":14.277776758291424,"score":14.277776758291424},"GB2-07":{"attempts":1,"playable":25.564044191476587,"score":25.564044191476587},"GB2-08":{"attempts":1,"playable":42.48612119350707,"score":42.48612119350707}},"none":{"GB2-01":{"attempts":1,"playable":78.40222463538099,"score":78.40222463538099},"GB2-02":{"attempts":1,"playable":37.7172997033114,"score":37.7172997033114},"GB2-03":{"attempts":1,"playable":32.17182072697564,"score":32.17182072697564},"GB2-04":{"attempts":1,"playable":48.21741162726638,"score":48.21741162726638},"GB2-05":{"attempts":1,"playable":15.281248469109165,"score":15.281248469109165},"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":30.744672528584836,"score":30.744672528584836}}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:13Z","match_totals_all":{"draws":1971,"losses":3074,"wins":1605},"match_totals_tracks":{"highest":{"draws":902,"losses":1723,"wins":969},"none":{"draws":1069,"losses":1351,"wins":636}},"model_slug":"tencent-hy3-preview","official_rank_by_reasoning":{"highest":58,"none":62},"overall":{"max":78.40222463538099,"mean":31.43946221352207,"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":65.22465150047583,"GB2-02":39.09761928198411,"GB2-04":43.74116801947021,"GB2-05":60.21067356103889,"GB2-06":14.277776758291424,"GB2-07":25.564044191476587,"GB2-08":42.48612119350707},"per_game_match_totals_all":{"GB2-01":{"draws":158,"losses":233,"wins":641},"GB2-02":{"draws":691,"losses":261,"wins":8},"GB2-03":{"draws":119,"losses":292,"wins":83},"GB2-04":{"draws":660,"losses":225,"wins":111},"GB2-05":{"draws":0,"losses":674,"wins":386},"GB2-06":{"draws":6,"losses":439,"wins":57},"GB2-07":{"draws":0,"losses":407,"wins":123},"GB2-08":{"draws":337,"losses":543,"wins":196}},"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":6,"losses":439,"wins":57},"GB2-07":{"draws":0,"losses":407,"wins":123},"GB2-08":{"draws":114,"losses":269,"wins":155}},"none":{"GB2-01":{"draws":79,"losses":82,"wins":355},"GB2-02":{"draws":347,"losses":133,"wins":0},"GB2-03":{"draws":119,"losses":292,"wins":83},"GB2-04":{"draws":301,"losses":116,"wins":81},"GB2-05":{"draws":0,"losses":454,"wins":76},"GB2-08":{"draws":223,"losses":274,"wins":41}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1619.4466997702934,"GB2-02":1387.1619387321743,"GB2-04":1426.598704765196,"GB2-05":1567.9023033024068,"GB2-06":859.6015105664538,"GB2-07":1130.0245300615766,"GB2-08":1304.9441959132437},"none":{"GB2-01":1775.9288847944135,"GB2-02":1376.20030038151,"GB2-03":1270.3926998084164,"GB2-04":1461.1716777068912,"GB2-05":917.9796077524041,"GB2-08":1178.6055589508921}},"per_game_tracks":{"highest":{"GB2-01":65.22465150047583,"GB2-02":39.09761928198411,"GB2-04":43.74116801947021,"GB2-05":60.21067356103889,"GB2-06":14.277776758291424,"GB2-07":25.564044191476587,"GB2-08":42.48612119350707},"none":{"GB2-01":78.40222463538099,"GB2-02":37.7172997033114,"GB2-03":32.17182072697564,"GB2-04":48.21741162726638,"GB2-05":15.281248469109165,"GB2-08":30.744672528584836}},"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":32.56208971571559,"none":30.31683471132855},"reasoning_agg":{"highest":{"max":65.22465150047583,"mean":32.56208971571559,"min":0.0},"none":{"max":78.40222463538099,"mean":30.31683471132855,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":2.2452550043870367},"working_program_strength":{"all":40.968512748474566,"highest":41.51457921517773,"none":40.4224462817714}},{"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":0.02850254}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.017223799999999997,"mean":0.00762354625,"median":0.00630875,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":26,"run_count":16,"total":0.12197674},"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":30.937961819602904,"medium":50.174554112269085,"none":11.701369526936721},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[235929],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[235929],"total_output_tokens":253398,"total_reasoning_output_tokens":186412,"total_visible_output_tokens":66986,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3.5-super-vl","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":66.18873786369763,"score":33.09436893184881},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.81144895648299,"score":22.405724478241495},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":36.23182617727008,"score":18.11591308863504},"GB2-04":{"attempts":2,"playable":42.209823145404926,"score":42.209823145404926},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.31249676882345,"score":29.156248384411725},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":46.81810703397261,"score":23.409053516986305},"GB2-07":{"attempts":2,"playable":40.452956593532484,"score":40.452956593532484},"GB2-08":{"attempts":2,"playable":38.65960641776244,"score":38.65960641776244}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":66.18873786369763,"score":66.18873786369763},"GB2-02":{"attempts":1,"playable":44.81144895648299,"score":44.81144895648299},"GB2-03":{"attempts":1,"playable":36.23182617727008,"score":36.23182617727008},"GB2-04":{"attempts":1,"playable":41.08644928581932,"score":41.08644928581932},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":46.81810703397261,"score":46.81810703397261},"GB2-07":{"attempts":1,"playable":57.10654768753967,"score":57.10654768753967},"GB2-08":{"attempts":1,"playable":50.840819124546954,"score":50.840819124546954}},"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":43.33319700499054,"score":43.33319700499054},"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":23.7993654995253,"score":23.7993654995253},"GB2-08":{"attempts":1,"playable":26.478393710977922,"score":26.478393710977922}}},"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":66.18873786369763,"mean":30.937961819602904,"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":1629.6733884109735,"GB2-02":1431.67964470658,"GB2-03":1307.3115788160496,"GB2-04":1405.9374854214225,"GB2-05":1542.7288818013874,"GB2-06":1370.6751707666133,"GB2-07":1537.8595131779418,"GB2-08":1400.4575417617962},"none":{"GB2-04":1423.4360965098103,"GB2-07":1103.5313841029026,"GB2-08":1131.2030453967263}},"per_game_tracks":{"medium":{"GB2-01":66.18873786369763,"GB2-02":44.81144895648299,"GB2-03":36.23182617727008,"GB2-04":41.08644928581932,"GB2-05":58.31249676882345,"GB2-06":46.81810703397261,"GB2-07":57.10654768753967,"GB2-08":50.840819124546954},"none":{"GB2-04":43.33319700499054,"GB2-07":23.7993654995253,"GB2-08":26.478393710977922}},"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":50.174554112269085,"none":11.701369526936721},"reasoning_agg":{"medium":{"max":66.18873786369763,"mean":50.174554112269085,"min":36.23182617727008},"none":{"max":43.33319700499054,"mean":11.701369526936721,"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":38.47318458533236},"working_program_strength":{"all":40.689103092050175,"medium":50.174554112269085,"none":31.203652071831257}},{"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":0.1973610844},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03062629,"mean":0.020124273158333334,"median":0.017895481666666668,"min":0.012095886733333333,"recorded_attempt_count":52,"run_count":24,"total":0.486187507},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.0016912200000000002,"recorded_attempt_count":37,"run_count":24,"total":0.0689052158}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0265755425,"mean":0.018416099712499998,"median":0.017703669999999998,"min":0.0109615788,"recorded_attempt_count":32,"run_count":15,"total":0.2720731754},"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":0.0306854728},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.0016912200000000002,"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":30.69843243636994,"highest":35.85861319556868,"medium":30.18633380077896,"none":26.050350312762177},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"infra_excluded","GB2-05":"infra_excluded","GB2-07":"infra_excluded"},"medium":{"GB2-03":"infra_excluded"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["length","stop"],"indexed_attempts":32,"output_token_observations":32,"total_output_tokens":734523},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":32.04332823775294,"score":32.04332823775294},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":42.56898646593197,"score":33.409501599366195},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.68133277644017,"score":15.227110925480057},"GB2-04":{"attempts":6,"playable":40.11943352075965,"score":40.11943352075965},"GB2-05":{"attempts":5,"playable":26.060840488137124,"score":26.060840488137124},"GB2-06":{"attempts":5,"playable":34.63021706681293,"score":34.63021706681293},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":25.58105206875522,"score":22.17761998775572},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":29.49415097817078,"score":22.229577311350877}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":23.508780088691488,"score":23.508780088691488},"GB2-02":{"attempts":1,"playable":44.07266414671792,"score":44.07266414671792},"GB2-04":{"attempts":1,"playable":39.55185774658149,"score":39.55185774658149},"GB2-06":{"attempts":1,"playable":49.05847406271931,"score":49.05847406271931},"GB2-08":{"attempts":1,"playable":23.10128993313319,"score":23.10128993313319}},"medium":{"GB2-01":{"attempts":2,"playable":29.90918046140999,"score":29.90918046140999},"GB2-02":{"attempts":3,"playable":42.416613351532014,"score":42.416613351532014},"GB2-04":{"attempts":3,"playable":38.8002889097337,"score":38.8002889097337},"GB2-05":{"attempts":2,"playable":24.40175676370076,"score":24.40175676370076},"GB2-06":{"attempts":1,"playable":21.87615289214184,"score":21.87615289214184},"GB2-07":{"attempts":2,"playable":30.741511651513424,"score":30.741511651513424},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":34.73824886313145,"score":23.15883257542097}},"none":{"GB2-01":{"attempts":3,"playable":42.71202416315733,"score":42.71202416315733},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":41.21768189954597,"score":13.739227299848658},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.68133277644017,"score":15.227110925480057},"GB2-04":{"attempts":2,"playable":42.006153905963735,"score":42.006153905963735},"GB2-05":{"attempts":3,"playable":27.71992421257349,"score":27.71992421257349},"GB2-06":{"attempts":3,"playable":32.95602424557764,"score":32.95602424557764},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":20.42059248599702,"score":13.613728323998012},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":30.642914138247697,"score":20.428609425498465}}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:11Z","match_totals_all":{"draws":5481,"losses":10144,"wins":3323},"match_totals_tracks":{"highest":{"draws":1108,"losses":1136,"wins":290},"medium":{"draws":2456,"losses":4015,"wins":1193},"none":{"draws":1917,"losses":4993,"wins":1840}},"model_slug":"xiaomi-mimo-v2-5","official_rank_by_reasoning":{"none":74},"overall":{"max":49.05847406271931,"mean":30.69843243636994,"min":13.613728323998012},"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":23.508780088691488,"GB2-02":44.07266414671792,"GB2-04":39.55185774658149,"GB2-06":49.05847406271931,"GB2-08":23.10128993313319},"per_game_all":{"GB2-01":32.04332823775294,"GB2-02":42.56898646593197,"GB2-04":40.11943352075965,"GB2-06":34.630217066812925,"GB2-08":29.49415097817078},"per_game_match_totals_all":{"GB2-01":{"draws":639,"losses":1741,"wins":716},"GB2-02":{"draws":1863,"losses":488,"wins":49},"GB2-03":{"draws":181,"losses":197,"wins":116},"GB2-04":{"draws":1848,"losses":917,"wins":223},"GB2-05":{"draws":0,"losses":1981,"wins":669},"GB2-06":{"draws":45,"losses":1722,"wins":743},"GB2-07":{"draws":0,"losses":1625,"wins":495},"GB2-08":{"draws":905,"losses":1473,"wins":312}},"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":182,"losses":333,"wins":23}},"medium":{"GB2-01":{"draws":132,"losses":675,"wins":225},"GB2-02":{"draws":1110,"losses":298,"wins":32},"GB2-04":{"draws":932,"losses":472,"wins":90},"GB2-05":{"draws":0,"losses":813,"wins":247},"GB2-06":{"draws":13,"losses":402,"wins":87},"GB2-07":{"draws":0,"losses":760,"wins":300},"GB2-08":{"draws":269,"losses":595,"wins":212}},"none":{"GB2-01":{"draws":292,"losses":771,"wins":485},"GB2-02":{"draws":368,"losses":106,"wins":6},"GB2-03":{"draws":181,"losses":197,"wins":116},"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":865,"wins":195},"GB2-08":{"draws":454,"losses":545,"wins":77}}},"per_game_raw_elo_all":{"GB2-01":1288.5571263638988,"GB2-02":1414.3041222924176,"GB2-04":1398.2974788327158,"GB2-06":1185.720605822243,"GB2-08":1162.1492678567759},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1197.2207150255585,"GB2-02":1425.9732414779407,"GB2-04":1393.8774951379276,"GB2-06":1405.0401418812698,"GB2-08":1091.6634509039557},"medium":{"GB2-01":1270.0410434647779,"GB2-02":1413.1309583410293,"GB2-04":1387.8954271352661,"GB2-05":1084.181441466143,"GB2-06":991.4356031808871,"GB2-07":1198.3397637218952,"GB2-08":1217.7236946653688},"none":{"GB2-01":1398.4096206013603,"GB2-02":1403.8081670582826,"GB2-03":1389.943740758311,"GB2-04":1413.119514224954,"GB2-05":1106.5914747227632,"GB2-06":1160.686072404572,"GB2-07":1028.4685422367759,"GB2-08":1177.0606580010037}},"per_game_tracks":{"highest":{"GB2-01":23.508780088691488,"GB2-02":44.07266414671792,"GB2-04":39.55185774658149,"GB2-06":49.05847406271931,"GB2-08":23.10128993313319},"medium":{"GB2-01":29.90918046140999,"GB2-02":42.416613351532014,"GB2-04":38.80028890973371,"GB2-05":24.40175676370076,"GB2-06":21.87615289214184,"GB2-07":30.741511651513424,"GB2-08":34.73824886313145},"none":{"GB2-01":42.71202416315733,"GB2-02":41.21768189954597,"GB2-03":45.68133277644017,"GB2-04":42.006153905963735,"GB2-05":27.719924212573485,"GB2-06":32.95602424557763,"GB2-07":20.42059248599702,"GB2-08":30.642914138247697}},"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":35.85861319556868,"medium":30.18633380077896,"none":26.050350312762177},"reasoning_agg":{"highest":{"max":49.05847406271931,"mean":35.85861319556868,"min":23.10128993313319},"medium":{"max":42.416613351532014,"mean":30.18633380077896,"min":21.87615289214184},"none":{"max":42.71202416315733,"mean":26.050350312762177,"min":13.613728323998012}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":9.808262882806503},"working_program_strength":{"all":34.37291010053377,"highest":35.85861319556868,"medium":31.840536127594742,"none":35.419580978437885}},{"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":0.39544914999999997},"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":0.14744575}},"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":29.524258958147882,"medium":32.454648107314846,"none":26.59386980898092},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["incomplete","stop"],"indexed_attempts":57,"output_token_observations":57,"reasoning_token_observations":2,"total_output_tokens":752982,"total_reasoning_output_tokens":128000,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":31.310180073622785,"score":31.310180073622785},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.290682020547486,"score":30.224634362579067},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":34.634106411260305,"score":8.658526602815076},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":51.559785454938435,"score":12.889946363734609},"GB2-05":{"attempts":4,"playable":29.54827040042975,"score":29.54827040042975},"GB2-06":{"attempts":4,"playable":50.87951085446464,"score":50.87951085446464},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":28.186873213149653,"score":22.878241620848495},"GB2-08":{"attempts":4,"playable":49.804761386688625,"score":49.804761386688625}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"playable":16.249501432738306,"score":16.249501432738306},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.26419063187367,"score":20.132095315936834},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":51.559785454938435,"score":25.779892727469218},"GB2-05":{"attempts":2,"playable":50.73086039977494,"score":50.73086039977494},"GB2-06":{"attempts":2,"playable":60.18176763434397,"score":60.18176763434397},"GB2-07":{"attempts":2,"playable":35.13922005709468,"score":35.13922005709468},"GB2-08":{"attempts":2,"playable":51.423847291160804,"score":51.423847291160804}},"none":{"GB2-01":{"attempts":2,"playable":46.370858714507264,"score":46.370858714507264},"GB2-02":{"attempts":2,"playable":40.317173409221304,"score":40.317173409221304},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":34.634106411260305,"score":17.317053205630152},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":8.365680401084564,"score":8.365680401084564},"GB2-06":{"attempts":2,"playable":41.57725407458532,"score":41.57725407458532},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":21.23452636920462,"score":10.61726318460231},"GB2-08":{"attempts":2,"playable":48.185675482216446,"score":48.185675482216446}}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:23Z","match_totals_all":{"draws":2169,"losses":6678,"wins":3519},"match_totals_tracks":{"medium":{"draws":894,"losses":3201,"wins":2115},"none":{"draws":1275,"losses":3477,"wins":1404}},"model_slug":"gpt-5-4-nano","official_rank_by_reasoning":{"medium":64,"none":72},"overall":{"max":60.18176763434397,"mean":29.524258958147882,"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":340,"wins":14},"GB2-03":{"draws":142,"losses":269,"wins":83},"GB2-04":{"draws":238,"losses":131,"wins":129},"GB2-05":{"draws":0,"losses":1514,"wins":606},"GB2-06":{"draws":37,"losses":1039,"wins":932},"GB2-07":{"draws":0,"losses":1135,"wins":455},"GB2-08":{"draws":282,"losses":991,"wins":879}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":161,"losses":796,"wins":75},"GB2-02":{"draws":367,"losses":111,"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":93,"losses":502,"wins":481}},"none":{"GB2-01":{"draws":223,"losses":463,"wins":346},"GB2-02":{"draws":719,"losses":229,"wins":12},"GB2-03":{"draws":142,"losses":269,"wins":83},"GB2-05":{"draws":0,"losses":980,"wins":80},"GB2-06":{"draws":2,"losses":618,"wins":384},"GB2-07":{"draws":0,"losses":429,"wins":101},"GB2-08":{"draws":189,"losses":489,"wins":398}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1059.8576691294293,"GB2-02":1396.3464148070134,"GB2-04":1487.0643276002747,"GB2-05":1488.8245591256305,"GB2-06":1583.1928160699406,"GB2-07":1206.1863992156182,"GB2-08":1472.5839642268652},"none":{"GB2-01":1434.3516380682704,"GB2-02":1396.761483196034,"GB2-03":1292.9534056499733,"GB2-05":746.1243856603305,"GB2-06":1296.9372801767295,"GB2-07":1063.026103631255,"GB2-08":1421.984482696871}},"per_game_tracks":{"medium":{"GB2-01":16.249501432738306,"GB2-02":40.26419063187367,"GB2-04":51.559785454938435,"GB2-05":50.73086039977494,"GB2-06":60.18176763434397,"GB2-07":35.13922005709468,"GB2-08":51.423847291160804},"none":{"GB2-01":46.370858714507264,"GB2-02":40.317173409221304,"GB2-03":34.634106411260305,"GB2-05":8.365680401084564,"GB2-06":41.57725407458532,"GB2-07":21.23452636920462,"GB2-08":48.185675482216446}},"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":32.454648107314846,"none":26.593869808980923},"reasoning_agg":{"medium":{"max":60.18176763434397,"mean":32.454648107314846,"min":0.0},"none":{"max":48.185675482216446,"mean":26.593869808980923,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":5.860778298333923},"working_program_strength":{"all":39.016746268857474,"medium":43.649881843132114,"none":34.38361069458283}},{"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":0.04566446},"codegen_latency_ms":{"attempt_count":25,"max_ms":425398,"mean_ms":137358.0,"min_ms":22859,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":14,"max_ms":425398,"mean_ms":207893.5,"min_ms":65353,"run_count":8},"none":{"attempt_count":11,"max_ms":256957,"mean_ms":66822.5,"min_ms":22859,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":12120,"output_mean":4888.4375,"output_min":1108,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":14,"output_max":12120,"output_mean":7438.375,"output_min":3314,"run_count":8},"none":{"attempt_count":11,"output_max":4877,"output_mean":2338.5,"output_min":1108,"run_count":8}},"display_name":"Gemma 4 31B","economics":{"all":29.21567327142973,"medium":38.09245916181765,"none":20.338887381041808},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-03":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[16384],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":26,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[16384],"total_output_tokens":78215,"total_reasoning_output_tokens":27437,"total_visible_output_tokens":50778,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":16384,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":22.403539400699408,"score":11.201769700349704},"GB2-02":{"attempts":2,"playable":41.69255892351879,"score":41.69255892351879},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":43.91462092939784,"score":21.95731046469892},"GB2-04":{"attempts":2,"playable":44.65758484118679,"score":44.65758484118679},"GB2-05":{"attempts":2,"playable":44.42844288715342,"score":44.42844288715342},"GB2-06":{"attempts":2,"playable":22.316293585053337,"score":22.316293585053337},"GB2-07":{"attempts":2,"playable":14.299755195825217,"score":14.299755195825217},"GB2-08":{"attempts":2,"playable":33.171670573651696,"score":33.171670573651696}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":22.403539400699408,"score":22.403539400699408},"GB2-02":{"attempts":1,"playable":43.43895423021337,"score":43.43895423021337},"GB2-03":{"attempts":1,"playable":43.91462092939784,"score":43.91462092939784},"GB2-04":{"attempts":1,"playable":43.33319700499054,"score":43.33319700499054},"GB2-05":{"attempts":1,"playable":72.04104952761561,"score":72.04104952761561},"GB2-06":{"attempts":1,"playable":27.839887011061393,"score":27.839887011061393},"GB2-07":{"attempts":1,"playable":18.250286878375718,"score":18.250286878375718},"GB2-08":{"attempts":1,"playable":33.518138312187396,"score":33.518138312187396}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":39.94616361682421,"score":39.94616361682421},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":45.981972677383034,"score":45.981972677383034},"GB2-05":{"attempts":1,"playable":16.815836246691234,"score":16.815836246691234},"GB2-06":{"attempts":1,"playable":16.792700159045285,"score":16.792700159045285},"GB2-07":{"attempts":1,"playable":10.349223513274715,"score":10.349223513274715},"GB2-08":{"attempts":1,"playable":32.82520283511599,"score":32.82520283511599}}},"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":57,"none":80},"overall":{"max":72.04104952761561,"mean":29.21567327142973,"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":1183.456260709713,"GB2-02":1421.0710505964687,"GB2-03":1374.6141714805544,"GB2-04":1423.4360965098103,"GB2-05":1748.0138022162296,"GB2-06":1084.2730719729932,"GB2-07":1012.0746524727718,"GB2-08":1208.5578292458827},"none":{"GB2-02":1393.8490280412934,"GB2-04":1443.9206888876554,"GB2-05":949.321828634813,"GB2-06":906.0876729069307,"GB2-07":842.984588352401,"GB2-08":1201.1130790993504}},"per_game_tracks":{"medium":{"GB2-01":22.403539400699408,"GB2-02":43.43895423021337,"GB2-03":43.91462092939784,"GB2-04":43.33319700499054,"GB2-05":72.04104952761561,"GB2-06":27.839887011061393,"GB2-07":18.250286878375718,"GB2-08":33.518138312187396},"none":{"GB2-02":39.94616361682421,"GB2-04":45.981972677383034,"GB2-05":16.815836246691234,"GB2-06":16.792700159045285,"GB2-07":10.349223513274715,"GB2-08":32.82520283511599}},"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":38.09245916181765,"none":20.338887381041808},"reasoning_agg":{"medium":{"max":72.04104952761561,"mean":38.09245916181765,"min":18.250286878375718},"none":{"max":45.981972677383034,"mean":20.338887381041808,"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":17.753571780775843},"working_program_strength":{"all":32.605487834936696,"medium":38.09245916181765,"none":27.118516508055745}},{"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":1.3863592560000002},"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":0.21404720400000002}},"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":28.195392850666572,"medium":26.954783938526667,"none":29.436001762806473},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meituan","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":42.64792367967752,"score":21.32396183983876},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":41.85188882448263,"score":20.925944412241314},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":37.182016067043776,"score":27.27734264352464},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":42.417917992853646,"score":30.795290583306937},"GB2-05":{"attempts":4,"playable":22.786710049563965,"score":22.786710049563965},"GB2-06":{"attempts":4,"playable":31.071116089179398,"score":31.071116089179398},"GB2-07":{"attempts":4,"playable":36.35384226617667,"score":36.35384226617667},"GB2-08":{"attempts":4,"playable":35.02893492150086,"score":35.02893492150086}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.227623284677975,"score":21.613811642338987},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.61869369407654,"score":19.80934684703827},"GB2-04":{"attempts":2,"playable":38.345326347520455,"score":38.345326347520455},"GB2-05":{"attempts":2,"playable":33.459854477038505,"score":33.459854477038505},"GB2-06":{"attempts":2,"playable":25.080195711838712,"score":25.080195711838712},"GB2-07":{"attempts":2,"playable":37.718099359302876,"score":37.718099359302876},"GB2-08":{"attempts":2,"playable":39.61163712313554,"score":39.61163712313554}},"none":{"GB2-01":{"attempts":2,"playable":42.64792367967752,"score":42.64792367967752},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.47615436428729,"score":20.238077182143645},"GB2-03":{"attempts":2,"playable":34.74533844001101,"score":34.74533844001101},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":46.490509638186836,"score":23.245254819093418},"GB2-05":{"attempts":2,"playable":12.113565622089428,"score":12.113565622089428},"GB2-06":{"attempts":2,"playable":37.062036466520084,"score":37.062036466520084},"GB2-07":{"attempts":2,"playable":34.98958517305047,"score":34.98958517305047},"GB2-08":{"attempts":2,"playable":30.446232719866195,"score":30.446232719866195}}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:43Z","match_totals_all":{"draws":2882,"losses":7614,"wins":2871},"match_totals_tracks":{"medium":{"draws":1320,"losses":3431,"wins":1418},"none":{"draws":1562,"losses":4183,"wins":1453}},"model_slug":"meituan-longcat-2-0","official_rank_by_reasoning":{"medium":70,"none":67},"overall":{"max":42.64792367967752,"mean":28.195392850666572,"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":768,"losses":190,"wins":2},"GB2-03":{"draws":440,"losses":775,"wins":267},"GB2-04":{"draws":832,"losses":488,"wins":173},"GB2-05":{"draws":0,"losses":1660,"wins":460},"GB2-06":{"draws":61,"losses":1431,"wins":516},"GB2-07":{"draws":0,"losses":1396,"wins":724},"GB2-08":{"draws":534,"losses":1185,"wins":433}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":397,"losses":82,"wins":1},"GB2-03":{"draws":149,"losses":242,"wins":103},"GB2-04":{"draws":544,"losses":357,"wins":94},"GB2-05":{"draws":0,"losses":719,"wins":341},"GB2-06":{"draws":30,"losses":773,"wins":201},"GB2-07":{"draws":0,"losses":680,"wins":380},"GB2-08":{"draws":200,"losses":578,"wins":298}},"none":{"GB2-01":{"draws":247,"losses":489,"wins":296},"GB2-02":{"draws":371,"losses":108,"wins":1},"GB2-03":{"draws":291,"losses":533,"wins":164},"GB2-04":{"draws":288,"losses":131,"wins":79},"GB2-05":{"draws":0,"losses":941,"wins":119},"GB2-06":{"draws":31,"losses":658,"wins":315},"GB2-07":{"draws":0,"losses":716,"wins":344},"GB2-08":{"draws":334,"losses":607,"wins":135}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1419.4344223818925,"GB2-03":1337.2290097072948,"GB2-04":1384.0624086574148,"GB2-05":1192.5489810766576,"GB2-06":1041.3685236169135,"GB2-07":1262.3180973483472,"GB2-08":1282.007051496246},"none":{"GB2-01":1398.9767097708523,"GB2-02":1398.0084213738069,"GB2-03":1292.3206309715479,"GB2-04":1447.845104509816,"GB2-05":844.0989015266994,"GB2-06":1223.4014944680284,"GB2-07":1257.438694329189,"GB2-08":1175.1695000941818}},"per_game_tracks":{"medium":{"GB2-02":43.227623284677975,"GB2-03":39.61869369407654,"GB2-04":38.345326347520455,"GB2-05":33.459854477038505,"GB2-06":25.080195711838712,"GB2-07":37.718099359302876,"GB2-08":39.61163712313554},"none":{"GB2-01":42.64792367967752,"GB2-02":40.47615436428729,"GB2-03":34.74533844001101,"GB2-04":46.490509638186836,"GB2-05":12.113565622089428,"GB2-06":37.062036466520084,"GB2-07":34.98958517305047,"GB2-08":30.446232719866195}},"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":26.954783938526663,"none":29.436001762806473},"reasoning_agg":{"medium":{"max":39.61163712313554,"mean":26.954783938526663,"min":0.0},"none":{"max":42.64792367967752,"mean":29.436001762806473,"min":12.113565622089428}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":2.4812178242798097},"working_program_strength":{"all":35.79723984559416,"medium":36.72306142822723,"none":34.8714182629611}},{"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":0.20304798}},"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":0.7875583200000003},"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":26.749955635359438,"medium":23.122569274783885,"none":30.37734199593499},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"total_output_tokens":596080},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":38.656854763493286,"score":38.656854763493286},"GB2-02":{"attempts":2,"playable":39.78711233554944,"score":39.78711233554944},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.9346947850152,"score":19.9673473925076},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.37057364428585,"score":20.185286822142924},"GB2-05":{"attempts":2,"playable":15.448223122742842,"score":15.448223122742842},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.1342988476045,"score":8.56714942380225},"GB2-07":{"attempts":2,"playable":33.00209595040792,"score":33.00209595040792},"GB2-08":{"attempts":2,"playable":38.38557527222924,"score":38.38557527222924}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.574661114006865,"score":18.574661114006865},"GB2-02":{"attempts":1,"playable":39.840133013450746,"score":39.840133013450746},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.37057364428585,"score":40.37057364428585},"GB2-05":{"attempts":1,"playable":2.1672981238426035,"score":2.1672981238426035},"GB2-06":{"attempts":1,"playable":17.1342988476045,"score":17.1342988476045},"GB2-07":{"attempts":1,"playable":42.40144571404132,"score":42.40144571404132},"GB2-08":{"attempts":1,"playable":24.49214374103919,"score":24.49214374103919}},"none":{"GB2-01":{"attempts":1,"playable":58.7390484129797,"score":58.7390484129797},"GB2-02":{"attempts":1,"playable":39.73409165764812,"score":39.73409165764812},"GB2-03":{"attempts":1,"playable":39.9346947850152,"score":39.9346947850152},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":28.72914812164308,"score":28.72914812164308},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.602746186774525,"score":23.602746186774525},"GB2-08":{"attempts":1,"playable":52.27900680341929,"score":52.27900680341929}}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:01Z","match_totals_all":{"draws":1375,"losses":3941,"wins":1366},"match_totals_tracks":{"medium":{"draws":812,"losses":2310,"wins":472},"none":{"draws":563,"losses":1631,"wins":894}},"model_slug":"minimax-minimax-m3","official_rank_by_reasoning":{"medium":74,"none":60},"overall":{"max":58.7390484129797,"mean":26.749955635359438,"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":725,"losses":231,"wins":4},"GB2-03":{"draws":104,"losses":263,"wins":127},"GB2-04":{"draws":322,"losses":144,"wins":32},"GB2-05":{"draws":0,"losses":906,"wins":154},"GB2-06":{"draws":3,"losses":428,"wins":71},"GB2-07":{"draws":0,"losses":736,"wins":324},"GB2-08":{"draws":117,"losses":634,"wins":325}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":22,"losses":416,"wins":78},"GB2-02":{"draws":365,"losses":114,"wins":1},"GB2-04":{"draws":322,"losses":144,"wins":32},"GB2-05":{"draws":0,"losses":522,"wins":8},"GB2-06":{"draws":3,"losses":428,"wins":71},"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":17,"losses":267,"wins":254}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1132.224588047275,"GB2-02":1393.01536297024,"GB2-04":1400.3245802126385,"GB2-05":441.491805143713,"GB2-06":912.1283051685773,"GB2-07":1352.9264051160994,"GB2-08":1108.2306154654827},"none":{"GB2-01":1553.4364910832232,"GB2-02":1392.1810815166534,"GB2-03":1339.9938761618187,"GB2-05":1154.5553362022792,"GB2-07":1100.5154943894029,"GB2-08":1418.0484745920562}},"per_game_tracks":{"medium":{"GB2-01":18.574661114006865,"GB2-02":39.840133013450746,"GB2-04":40.37057364428585,"GB2-05":2.1672981238426035,"GB2-06":17.1342988476045,"GB2-07":42.40144571404132,"GB2-08":24.49214374103919},"none":{"GB2-01":58.7390484129797,"GB2-02":39.73409165764812,"GB2-03":39.9346947850152,"GB2-05":28.72914812164308,"GB2-07":23.602746186774525,"GB2-08":52.27900680341929}},"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":23.12256927478389,"none":30.377341995934994},"reasoning_agg":{"medium":{"max":42.40144571404132,"mean":23.12256927478389,"min":0.0},"none":{"max":58.7390484129797,"mean":30.377341995934994,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":7.254772721151106},"working_program_strength":{"all":33.46445805907126,"medium":26.425793456895867,"none":40.50312266124666}},{"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":0.8197712500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.40579925},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"all":26.46607328838344,"medium":15.896084969094579,"none":37.0360616076723},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"infra_excluded"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"infra_excluded","GB2-02":"infra_excluded","GB2-04":"failed"},"none":{"GB2-01":"infra_excluded"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":53,"finish_reasons":["length","stop"],"indexed_attempts":53,"output_token_observations":53,"total_output_tokens":2639964},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":36.228874289897526,"score":36.228874289897526},"GB2-03":{"attempts":2,"playable":33.08013719052168,"score":33.08013719052168},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.006158892138465,"score":21.003079446069233},"GB2-05":{"attempts":2,"playable":21.049285237346275,"score":21.049285237346275},"GB2-06":{"attempts":2,"playable":13.411822362801868,"score":13.411822362801868},"GB2-07":{"attempts":2,"playable":44.20649012084516,"score":44.20649012084516},"GB2-08":{"attempts":2,"playable":26.449219031603803,"score":26.449219031603803}},"headline_games_tracks":{"medium":{"GB2-03":{"attempts":1,"playable":31.41945336453417,"score":31.41945336453417},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":11.4426069613079,"score":11.4426069613079},"GB2-06":{"attempts":1,"playable":15.65161477192967,"score":15.65161477192967},"GB2-07":{"attempts":1,"playable":23.7993654995253,"score":23.7993654995253},"GB2-08":{"attempts":1,"playable":13.063469217270422,"score":13.063469217270422}},"none":{"GB2-02":{"attempts":1,"playable":36.228874289897526,"score":36.228874289897526},"GB2-03":{"attempts":1,"playable":34.7408210165092,"score":34.7408210165092},"GB2-04":{"attempts":1,"playable":42.006158892138465,"score":42.006158892138465},"GB2-05":{"attempts":1,"playable":30.65596351338465,"score":30.65596351338465},"GB2-06":{"attempts":1,"playable":11.172029953674063,"score":11.172029953674063},"GB2-07":{"attempts":1,"playable":64.61361474216501,"score":64.61361474216501},"GB2-08":{"attempts":1,"playable":39.83496884593718,"score":39.83496884593718}}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:28Z","match_totals_all":{"draws":1313,"losses":3815,"wins":1038},"match_totals_tracks":{"medium":{"draws":199,"losses":2056,"wins":339},"none":{"draws":1114,"losses":1759,"wins":699}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":64.61361474216501,"mean":26.46607328838344,"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":152,"wins":5},"GB2-03":{"draws":399,"losses":495,"wins":94},"GB2-04":{"draws":358,"losses":118,"wins":22},"GB2-05":{"draws":0,"losses":848,"wins":212},"GB2-06":{"draws":25,"losses":879,"wins":100},"GB2-07":{"draws":0,"losses":613,"wins":447},"GB2-08":{"draws":208,"losses":710,"wins":158}},"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":19,"losses":465,"wins":54}},"none":{"GB2-02":{"draws":323,"losses":152,"wins":5},"GB2-03":{"draws":237,"losses":221,"wins":36},"GB2-04":{"draws":358,"losses":118,"wins":22},"GB2-05":{"draws":0,"losses":374,"wins":156},"GB2-06":{"draws":7,"losses":452,"wins":43},"GB2-07":{"draws":0,"losses":197,"wins":333},"GB2-08":{"draws":189,"losses":245,"wins":104}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1263.3723118022003,"GB2-05":830.740714088723,"GB2-06":885.4712997355064,"GB2-07":1103.5313841029026,"GB2-08":950.1944104681861},"none":{"GB2-02":1364.2421781697037,"GB2-03":1293.918570041053,"GB2-04":1413.119721643807,"GB2-05":1183.31854970504,"GB2-06":795.238382165832,"GB2-07":1638.8446960322851,"GB2-08":1276.1859110704497}},"per_game_tracks":{"medium":{"GB2-03":31.41945336453417,"GB2-05":11.4426069613079,"GB2-06":15.65161477192967,"GB2-07":23.7993654995253,"GB2-08":13.063469217270422},"none":{"GB2-02":36.228874289897526,"GB2-03":34.7408210165092,"GB2-04":42.006158892138465,"GB2-05":30.65596351338465,"GB2-06":11.172029953674063,"GB2-07":64.61361474216501,"GB2-08":39.83496884593718}},"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":15.896084969094579,"none":37.0360616076723},"reasoning_agg":{"medium":{"max":31.41945336453417,"mean":15.896084969094579,"min":0.0},"none":{"max":64.61361474216501,"mean":37.0360616076723,"min":11.172029953674063}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.13997663857772},"working_program_strength":{"all":28.055681785292897,"medium":19.075301962913493,"none":37.0360616076723}},{"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":1.397542663983281},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167187}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167188},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.27741402547937455,"mean":0.12115799999999999,"median":0.10979066017348882,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":16,"token_priced_attempt_count":25,"total":1.9385280000000003},"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":25.878922390770086,"highest":28.921715353062087,"none":22.836129428478085},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-07":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[209715],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":34,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[209715],"total_output_tokens":220326,"total_visible_output_tokens":220326,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":209715,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":12.087417348913485,"score":6.0437086744567425},"GB2-02":{"attempts":2,"playable":42.856105202140256,"score":42.856105202140256},"GB2-03":{"attempts":2,"playable":36.12228825217767,"score":36.12228825217767},"GB2-04":{"attempts":2,"playable":36.83188462793162,"score":36.83188462793162},"GB2-05":{"attempts":2,"playable":25.192232570742284,"score":25.192232570742284},"GB2-06":{"attempts":2,"playable":21.845226910235482,"score":21.845226910235482},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":13.007677305839454,"score":6.503838652919727},"GB2-08":{"attempts":2,"playable":31.636094235556904,"score":31.636094235556904}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.600427873465655,"score":44.600427873465655},"GB2-03":{"attempts":1,"playable":37.717213210184646,"score":37.717213210184646},"GB2-04":{"attempts":1,"playable":39.8589469664451,"score":39.8589469664451},"GB2-05":{"attempts":1,"playable":37.405769033347546,"score":37.405769033347546},"GB2-06":{"attempts":1,"playable":25.760472170355964,"score":25.760472170355964},"GB2-07":{"attempts":1,"playable":13.007677305839454,"score":13.007677305839454},"GB2-08":{"attempts":1,"playable":33.02321626485831,"score":33.02321626485831}},"none":{"GB2-01":{"attempts":1,"playable":12.087417348913485,"score":12.087417348913485},"GB2-02":{"attempts":1,"playable":41.111782530814864,"score":41.111782530814864},"GB2-03":{"attempts":1,"playable":34.527363294170684,"score":34.527363294170684},"GB2-04":{"attempts":1,"playable":33.80482228941814,"score":33.80482228941814},"GB2-05":{"attempts":1,"playable":12.978696108137019,"score":12.978696108137019},"GB2-06":{"attempts":1,"playable":17.929981650115,"score":17.929981650115},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":30.248972206255498,"score":30.248972206255498}}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:36Z","match_totals_all":{"draws":1976,"losses":4200,"wins":954},"match_totals_tracks":{"highest":{"draws":1088,"losses":1937,"wins":547},"none":{"draws":888,"losses":2263,"wins":407}},"model_slug":"mistralai-mistral-medium-3-5","official_rank_by_reasoning":{"highest":60,"none":79},"overall":{"max":44.600427873465655,"mean":25.878922390770086,"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":44.600427873465655,"GB2-03":37.717213210184646,"GB2-04":39.8589469664451,"GB2-05":37.405769033347546,"GB2-06":25.760472170355964,"GB2-07":13.007677305839454,"GB2-08":33.02321626485831},"per_game_match_totals_all":{"GB2-01":{"draws":46,"losses":436,"wins":34},"GB2-02":{"draws":747,"losses":191,"wins":22},"GB2-03":{"draws":240,"losses":546,"wins":202},"GB2-04":{"draws":557,"losses":366,"wins":73},"GB2-05":{"draws":0,"losses":805,"wins":255},"GB2-06":{"draws":8,"losses":813,"wins":183},"GB2-07":{"draws":0,"losses":470,"wins":60},"GB2-08":{"draws":378,"losses":573,"wins":125}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":370,"losses":89,"wins":21},"GB2-03":{"draws":129,"losses":261,"wins":104},"GB2-04":{"draws":329,"losses":143,"wins":26},"GB2-05":{"draws":0,"losses":339,"wins":191},"GB2-06":{"draws":6,"losses":388,"wins":108},"GB2-07":{"draws":0,"losses":470,"wins":60},"GB2-08":{"draws":254,"losses":247,"wins":37}},"none":{"GB2-01":{"draws":46,"losses":436,"wins":34},"GB2-02":{"draws":377,"losses":102,"wins":1},"GB2-03":{"draws":111,"losses":285,"wins":98},"GB2-04":{"draws":228,"losses":223,"wins":47},"GB2-05":{"draws":0,"losses":466,"wins":64},"GB2-06":{"draws":2,"losses":425,"wins":75},"GB2-08":{"draws":124,"losses":326,"wins":88}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1430.050511493092,"GB2-03":1320.5057492969559,"GB2-04":1396.2994312073722,"GB2-05":1277.4990607741188,"GB2-06":1052.4119079532645,"GB2-07":907.5963135919784,"GB2-08":1203.242561572809},"none":{"GB2-01":1025.611348818781,"GB2-02":1402.9812080843883,"GB2-03":1291.987034432538,"GB2-04":1347.4192338133864,"GB2-05":867.4676191012508,"GB2-06":925.9915116426993,"GB2-08":1173.1979182483526}},"per_game_tracks":{"highest":{"GB2-02":44.600427873465655,"GB2-03":37.717213210184646,"GB2-04":39.8589469664451,"GB2-05":37.405769033347546,"GB2-06":25.760472170355964,"GB2-07":13.007677305839454,"GB2-08":33.02321626485831},"none":{"GB2-01":12.087417348913485,"GB2-02":41.111782530814864,"GB2-03":34.527363294170684,"GB2-04":33.80482228941814,"GB2-05":12.978696108137019,"GB2-06":17.929981650115,"GB2-08":30.248972206255498}},"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":28.921715353062087,"none":22.836129428478085},"reasoning_agg":{"highest":{"max":44.600427873465655,"mean":28.921715353062087,"min":0.0},"none":{"max":41.111782530814864,"mean":22.836129428478085,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":6.085585924584002},"working_program_strength":{"all":29.57591130373724,"highest":33.0533889749281,"none":26.09843363254638}},{"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":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"all":25.62359434353766,"medium":32.980358513691364,"none":18.266830173383955},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed","GB2-04":"failed"},"none":{"GB2-03":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"total_output_tokens":343242},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":34.960339027005084,"score":30.215713743903656},"GB2-02":{"attempts":2,"playable":40.84466921239925,"score":40.84466921239925},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.76186614472562,"score":21.88093307236281},"GB2-05":{"attempts":2,"playable":38.07797660311408,"score":38.07797660311408},"GB2-06":{"attempts":2,"playable":42.51225085250504,"score":42.51225085250504},"GB2-07":{"attempts":2,"playable":16.2335780591337,"score":16.2335780591337},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":30.447266409765394,"score":15.223633204882697}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":50.942176921604464,"score":50.942176921604464},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"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":43.95772723420936,"score":43.95772723420936},"GB2-06":{"attempts":1,"playable":71.09088716682969,"score":71.09088716682969},"GB2-07":{"attempts":1,"playable":24.38856478275738,"score":24.38856478275738},"GB2-08":{"attempts":1,"playable":30.447266409765394,"score":30.447266409765394}},"none":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":18.978501132405704,"score":9.489250566202852},"GB2-02":{"attempts":1,"playable":38.67309283043393,"score":38.67309283043393},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.76186614472562,"score":43.76186614472562},"GB2-05":{"attempts":1,"playable":32.19822597201881,"score":32.19822597201881},"GB2-06":{"attempts":1,"playable":13.933614538180397,"score":13.933614538180397},"GB2-07":{"attempts":1,"playable":8.07859133551002,"score":8.07859133551002},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-10-26T00:54:23Z","match_totals_all":{"draws":1505,"losses":3376,"wins":1270},"match_totals_tracks":{"medium":{"draws":705,"losses":1458,"wins":933},"none":{"draws":800,"losses":1918,"wins":337}},"model_slug":"qwen-qwen3-7-plus","official_rank_by_reasoning":{"medium":63,"none":83},"overall":{"max":71.09088716682969,"mean":25.62359434353766,"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":741,"losses":213,"wins":6},"GB2-04":{"draws":337,"losses":119,"wins":41},"GB2-05":{"draws":0,"losses":671,"wins":389},"GB2-06":{"draws":27,"losses":590,"wins":387},"GB2-07":{"draws":0,"losses":907,"wins":153},"GB2-08":{"draws":204,"losses":285,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":88,"losses":220,"wins":208},"GB2-02":{"draws":391,"losses":86,"wins":3},"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":204,"losses":285,"wins":49}},"none":{"GB2-01":{"draws":108,"losses":371,"wins":37},"GB2-02":{"draws":350,"losses":127,"wins":3},"GB2-04":{"draws":337,"losses":119,"wins":41},"GB2-05":{"draws":0,"losses":366,"wins":164},"GB2-06":{"draws":5,"losses":441,"wins":56},"GB2-07":{"draws":0,"losses":494,"wins":36}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1478.0348355100698,"GB2-02":1417.796406980097,"GB2-05":1362.0756219306095,"GB2-06":1773.3144722441912,"GB2-07":1112.4891173455744,"GB2-08":1175.3635879979417},"none":{"GB2-01":1137.9316004714572,"GB2-02":1383.8023519694618,"GB2-04":1426.7590628170276,"GB2-05":1205.6785219957096,"GB2-06":852.910810521267,"GB2-07":777.293429033093}},"per_game_tracks":{"medium":{"GB2-01":50.942176921604464,"GB2-02":43.016245594364584,"GB2-05":43.95772723420936,"GB2-06":71.09088716682969,"GB2-07":24.38856478275738,"GB2-08":30.447266409765394},"none":{"GB2-01":18.978501132405704,"GB2-02":38.67309283043393,"GB2-04":43.76186614472562,"GB2-05":32.19822597201881,"GB2-06":13.933614538180397,"GB2-07":8.07859133551002}},"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":32.980358513691364,"none":18.266830173383955},"reasoning_agg":{"medium":{"max":71.09088716682969,"mean":32.980358513691364,"min":0.0},"none":{"max":43.76186614472562,"mean":18.266830173383955,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":14.713528340307409},"working_program_strength":{"all":34.95556333856712,"medium":43.97381135158849,"none":25.93731532554575}},{"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":24.65642061462963,"medium":30.555504181654875,"none":18.75733704760439},"first_seen_at":null,"game_gaps":{"all":{"GB2-05":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"infra_excluded","GB2-05":"infra_excluded","GB2-08":"infra_excluded"},"none":{"GB2-05":"failed","GB2-07":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[32768],"finish_reason_observations":96,"finish_reasons":["length","stop","unknown"],"indexed_attempts":98,"output_token_observations":97,"provider_post_attempt_observations":4,"provider_post_attempts":5,"reasoning_token_observations":69,"reconciliation_get_attempt_observations":4,"requested_max_output_token_observations":4,"requested_max_output_tokens":[32768],"total_output_tokens":1115800,"total_reasoning_output_tokens":656294,"total_visible_output_tokens":120852,"visible_token_observations":59},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":27.575023019871132,"score":27.575023019871132},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.043454069275995,"score":28.897924103696923},"GB2-03":{"attempts":2,"playable":28.97412060092674,"score":28.97412060092674},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.309890175760486,"score":31.145267897827352},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":14.633638438814337,"score":14.633638438814337},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":35.974658495177195,"score":17.987329247588598},"GB2-08":{"attempts":3,"playable":33.38373127258608,"score":33.38373127258608}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":19.48303399859258,"score":19.48303399859258},"GB2-02":{"attempts":1,"playable":37.504788276235715,"score":37.504788276235715},"GB2-04":{"attempts":1,"playable":39.96129123978842,"score":39.96129123978842},"GB2-06":{"attempts":1,"playable":19.85374889848047,"score":19.85374889848047},"GB2-07":{"attempts":2,"playable":35.974658495177195,"score":35.974658495177195}},"none":{"GB2-01":{"attempts":2,"playable":35.66701204114969,"score":35.66701204114969},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.58211986231627,"score":20.291059931158134},"GB2-03":{"attempts":2,"playable":28.97412060092674,"score":28.97412060092674},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.65848911173256,"score":22.32924455586628},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":9.413527979148201,"score":9.413527979148201},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":3,"playable":33.38373127258608,"score":33.38373127258608}}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-10-26T02:03:01Z","match_totals_all":{"draws":2542,"losses":4925,"wins":1205},"match_totals_tracks":{"medium":{"draws":809,"losses":1756,"wins":491},"none":{"draws":1733,"losses":3169,"wins":714}},"model_slug":"inclusionai-ling-3-0-flash","official_rank_by_reasoning":{"none":82},"overall":{"max":39.96129123978842,"mean":24.65642061462963,"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":707,"losses":247,"wins":6},"GB2-03":{"draws":309,"losses":578,"wins":101},"GB2-04":{"draws":698,"losses":242,"wins":56},"GB2-06":{"draws":8,"losses":1340,"wins":158},"GB2-07":{"draws":0,"losses":706,"wins":354},"GB2-08":{"draws":497,"losses":868,"wins":249}},"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":416,"wins":83},"GB2-07":{"draws":0,"losses":706,"wins":354}},"none":{"GB2-01":{"draws":194,"losses":586,"wins":252},"GB2-02":{"draws":370,"losses":108,"wins":2},"GB2-03":{"draws":309,"losses":578,"wins":101},"GB2-04":{"draws":358,"losses":105,"wins":35},"GB2-06":{"draws":5,"losses":924,"wins":75},"GB2-08":{"draws":497,"losses":868,"wins":249}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1144.9503224551838,"GB2-02":1374.5023359792667,"GB2-04":1397.1055807696607,"GB2-06":958.4881917850041,"GB2-07":1271.5954494511245},"none":{"GB2-01":1329.2027577646109,"GB2-02":1398.8385757827054,"GB2-03":1238.8787454598303,"GB2-04":1433.6980517970223,"GB2-06":627.6274134894604,"GB2-08":1206.9830380188034}},"per_game_tracks":{"medium":{"GB2-01":19.48303399859258,"GB2-02":37.504788276235715,"GB2-04":39.96129123978842,"GB2-06":19.85374889848047,"GB2-07":35.974658495177195},"none":{"GB2-01":35.66701204114969,"GB2-02":40.58211986231627,"GB2-03":28.97412060092674,"GB2-04":44.65848911173256,"GB2-06":9.413527979148201,"GB2-08":33.38373127258608}},"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":30.55550418165488,"none":18.75733704760439},"reasoning_agg":{"medium":{"max":39.96129123978842,"mean":30.55550418165488,"min":19.48303399859258},"none":{"max":35.66701204114969,"mean":18.75733704760439,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":11.798167134050487},"working_program_strength":{"all":31.3343354964824,"medium":30.555504181654875,"none":32.113166811309924}},{"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":23.619168561994087,"medium":23.619168561994087},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":12,"effective_max_output_tokens":[235929],"finish_reason_observations":12,"finish_reasons":["stop"],"indexed_attempts":12,"output_token_observations":12,"provider_post_attempt_observations":12,"provider_post_attempts":12,"reasoning_token_observations":12,"reconciliation_get_attempt_observations":12,"requested_max_output_token_observations":12,"requested_max_output_tokens":[235929],"total_output_tokens":193763,"total_reasoning_output_tokens":181158,"total_visible_output_tokens":12944,"visible_token_observations":12},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"recursive/flint-v1.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":44.76413372751087,"score":44.76413372751087},"GB2-02":{"attempts":1,"playable":35.05804086751001,"score":35.05804086751001},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.75659327595914,"score":39.75659327595914},"GB2-05":{"attempts":1,"playable":13.93825891291957,"score":13.93825891291957},"GB2-06":{"attempts":1,"playable":17.020471221862483,"score":17.020471221862483},"GB2-07":{"attempts":1,"playable":10.34922351327472,"score":10.34922351327472},"GB2-08":{"attempts":1,"playable":28.066626976915888,"score":28.066626976915888}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":44.76413372751087,"score":44.76413372751087},"GB2-02":{"attempts":1,"playable":35.05804086751001,"score":35.05804086751001},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.75659327595914,"score":39.75659327595914},"GB2-05":{"attempts":1,"playable":13.93825891291957,"score":13.93825891291957},"GB2-06":{"attempts":1,"playable":17.020471221862483,"score":17.020471221862483},"GB2-07":{"attempts":1,"playable":10.34922351327472,"score":10.34922351327472},"GB2-08":{"attempts":1,"playable":28.066626976915888,"score":28.066626976915888}}},"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":44.76413372751087,"mean":23.619168561994087,"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":1419.2389484475627,"GB2-02":1354.7167425114787,"GB2-04":1395.4927057904952,"GB2-05":889.0965364024593,"GB2-06":910.1216715592267,"GB2-07":842.9845883524011,"GB2-08":1149.1064107710897}},"per_game_tracks":{"medium":{"GB2-01":44.76413372751087,"GB2-02":35.05804086751001,"GB2-04":39.75659327595914,"GB2-05":13.93825891291957,"GB2-06":17.020471221862483,"GB2-07":10.34922351327472,"GB2-08":28.066626976915888}},"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":23.619168561994087},"reasoning_agg":{"medium":{"max":44.76413372751087,"mean":23.619168561994087,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":26.993335499421814,"medium":26.993335499421814}},{"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":0.121453125},"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":19.636154322163883,"highest":20.637981389991857,"none":18.634327254335904},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed"},"highest":{"GB2-01":"infra_excluded","GB2-02":"infra_excluded","GB2-03":"failed","GB2-04":"infra_excluded","GB2-05":"infra_excluded","GB2-06":"infra_excluded","GB2-08":"infra_excluded"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":38,"effective_max_output_tokens":[235929],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":40,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"requested_max_output_token_observations":38,"requested_max_output_tokens":[235929],"total_output_tokens":1341414,"total_reasoning_output_tokens":1137994,"total_visible_output_tokens":203420,"visible_token_observations":38},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":37.504788276235715,"score":37.504788276235715},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":45.88861566334852,"score":22.94430783167426},"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":38.056689293189194,"score":38.056689293189194},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}},"headline_games_tracks":{"highest":{"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":41.275962779983715,"score":41.275962779983715}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":37.504788276235715,"score":37.504788276235715},"GB2-03":{"attempts":1,"playable":45.88861566334852,"score":45.88861566334852},"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":34.83741580639468,"score":34.83741580639468},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}}},"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":45.88861566334852,"mean":19.636154322163883,"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":41.275962779983715},"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":1338.8822889338762},"none":{"GB2-02":1374.5023359792667,"GB2-03":1391.743907737973,"GB2-07":1257.1747413357332,"GB2-08":1179.6845364384803}},"per_game_tracks":{"highest":{"GB2-07":41.275962779983715},"none":{"GB2-02":37.504788276235715,"GB2-03":45.88861566334852,"GB2-07":34.83741580639468,"GB2-08":30.843798288708303}},"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":20.637981389991857,"none":18.634327254335904},"reasoning_agg":{"highest":{"max":41.275962779983715,"mean":20.637981389991857,"min":0.0},"none":{"max":45.88861566334852,"mean":18.634327254335904,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":2.003654135655953},"working_program_strength":{"all":39.272308644327765,"highest":41.275962779983715,"none":37.26865450867181}},{"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":15.040537034838447,"medium":23.37591997563048,"none":6.705154094046412},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-02":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"failed","GB2-02":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[64000],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":15,"provider_post_attempts":15,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[64000],"total_output_tokens":270044,"total_visible_output_tokens":29197,"visible_token_observations":15},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":21.734159723041202,"score":10.867079861520601},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.18867852179604,"score":20.59433926089802},"GB2-05":{"attempts":2,"playable":33.17170468869959,"score":33.17170468869959},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.24808744063479,"score":8.624043720317395},"GB2-07":{"attempts":2,"playable":16.12436846729509,"score":16.12436846729509},"GB2-08":{"attempts":2,"playable":30.942760279976877,"score":30.942760279976877}},"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":21.734159723041202,"score":21.734159723041202},"GB2-04":{"attempts":1,"playable":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":1,"playable":46.457859448926094,"score":46.457859448926094},"GB2-06":{"attempts":1,"playable":17.24808744063479,"score":17.24808744063479},"GB2-07":{"attempts":1,"playable":30.22875643334849,"score":30.22875643334849},"GB2-08":{"attempts":1,"playable":30.149818237297243,"score":30.149818237297243}},"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":19.885549928473093,"score":19.885549928473093},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":2.019980501241687,"score":2.019980501241687},"GB2-08":{"attempts":1,"playable":31.73570232265651,"score":31.73570232265651}}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":815,"losses":3119,"wins":756},"match_totals_tracks":{"medium":{"draws":532,"losses":1927,"wins":633},"none":{"draws":283,"losses":1192,"wins":123}},"model_slug":"cohere-north-mini-code","official_rank_by_reasoning":{"medium":73},"overall":{"max":46.457859448926094,"mean":15.040537034838447,"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":342,"wins":37},"GB2-04":{"draws":304,"losses":149,"wins":45},"GB2-05":{"draws":0,"losses":722,"wins":338},"GB2-06":{"draws":2,"losses":428,"wins":72},"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":342,"wins":37},"GB2-04":{"draws":304,"losses":149,"wins":45},"GB2-05":{"draws":0,"losses":292,"wins":238},"GB2-06":{"draws":2,"losses":428,"wins":72},"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":1164.382163593048,"GB2-04":1406.7373394219212,"GB2-05":1393.3723861929614,"GB2-06":914.1281794407054,"GB2-07":1196.0102818399187,"GB2-08":1172.1137289836033},"none":{"GB2-05":1007.8054188734292,"GB2-07":462.97415265272025,"GB2-08":1189.3605352757763}},"per_game_tracks":{"medium":{"GB2-03":21.734159723041202,"GB2-04":41.18867852179604,"GB2-05":46.457859448926094,"GB2-06":17.24808744063479,"GB2-07":30.22875643334849,"GB2-08":30.149818237297243},"none":{"GB2-05":19.885549928473093,"GB2-07":2.019980501241687,"GB2-08":31.73570232265651}},"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":23.37591997563048,"none":6.705154094046411},"reasoning_agg":{"medium":{"max":46.457859448926094,"mean":23.37591997563048,"min":0.0},"none":{"max":31.73570232265651,"mean":6.705154094046411,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.67076588158407},"working_program_strength":{"all":24.524152109148872,"medium":31.167893300840642,"none":17.880410917457098}},{"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":11.802618239774382,"none":11.802618239774382},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[32768],"finish_reason_observations":13,"finish_reasons":["stop"],"indexed_attempts":13,"output_token_observations":13,"provider_post_attempt_observations":13,"provider_post_attempts":13,"reasoning_token_observations":13,"reconciliation_get_attempt_observations":13,"requested_max_output_token_observations":13,"requested_max_output_tokens":[32768],"total_output_tokens":20448,"total_visible_output_tokens":20448,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"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":41.32357014605849,"score":41.32357014605849},"GB2-03":{"attempts":1,"playable":35.16739412202156,"score":35.16739412202156},"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":17.929981650115,"score":17.929981650115},"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":41.32357014605849,"score":41.32357014605849},"GB2-03":{"attempts":1,"playable":35.16739412202156,"score":35.16739412202156},"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":17.929981650115,"score":17.929981650115},"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":41.32357014605849,"mean":11.802618239774382,"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":1404.6346235146577,"GB2-03":1297.7674292927354,"GB2-06":925.9915116426993}},"per_game_tracks":{"none":{"GB2-02":41.32357014605849,"GB2-03":35.16739412202156,"GB2-06":17.929981650115}},"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":11.802618239774382},"reasoning_agg":{"none":{"max":41.32357014605849,"mean":11.802618239774382,"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":31.473648639398352,"none":31.473648639398352}}],"public_release_id":"gb2-20261026-cb69502a12d9","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":"gb2-20261026-cb69502a12d9","schema_version":2,"snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-10-26 02:27 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":27},"claude-fable-5":{"draws":17,"losses":97,"wins":18},"claude-fable-5-1":{"draws":6,"losses":136,"wins":6},"claude-haiku-5-5":{"draws":27,"losses":74,"wins":25},"claude-opus-4-5":{"draws":70,"losses":92,"wins":52},"claude-opus-4-8":{"draws":32,"losses":68,"wins":20},"claude-opus-5":{"draws":27,"losses":177,"wins":22},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":39,"losses":68,"wins":25},"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":60,"losses":64,"wins":72},"deepseek/deepseek-v4-pro":{"draws":30,"losses":61,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":53,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":62,"wins":33},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":89,"wins":20},"elorian/glimpse":{"draws":16,"losses":34,"wins":22},"fireworks/ember-1":{"draws":36,"losses":70,"wins":26},"gemini-3.1-pro-preview":{"draws":36,"losses":59,"wins":37},"gemini-4-argon":{"draws":3,"losses":123,"wins":6},"google/gemini-3.1-flash-lite":{"draws":27,"losses":17,"wins":44},"google/gemini-3.5-flash":{"draws":35,"losses":82,"wins":49},"google/gemini-3.5-flash-lite":{"draws":76,"losses":72,"wins":86},"google/gemini-3.6-flash":{"draws":60,"losses":137,"wins":57},"google/gemini-3.8-flash":{"draws":26,"losses":83,"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":34,"losses":43,"wins":39},"gpt-5.4":{"draws":29,"losses":71,"wins":28},"gpt-5.4-mini":{"draws":32,"losses":25,"wins":31},"gpt-5.4-nano":{"draws":28,"losses":48,"wins":56},"gpt-5.5":{"draws":44,"losses":54,"wins":24},"gpt-5.6-luna":{"draws":43,"losses":42,"wins":47},"gpt-5.6-sol":{"draws":22,"losses":97,"wins":13},"gpt-5.6-terra":{"draws":35,"losses":65,"wins":26},"gpt-6-astra":{"draws":6,"losses":118,"wins":8},"gpt-6-luna":{"draws":40,"losses":53,"wins":39},"gpt-6-sol":{"draws":15,"losses":103,"wins":14},"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":23,"wins":33},"inception/mercury-3":{"draws":25,"losses":34,"wins":27},"inclusionai/ling-3.0-flash":{"draws":36,"losses":16,"wins":42},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":38,"losses":42,"wins":64},"meta/muse-glimmer-30b":{"draws":41,"losses":33,"wins":42},"meta/muse-spark-1.2":{"draws":31,"losses":64,"wins":31},"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":14,"wins":38},"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":32,"losses":18,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":8},"moonshotai/kimi-k3":{"draws":34,"losses":60,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":103,"wins":4},"nex-agi/nex-n2-pro":{"draws":16,"losses":13,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":34,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":22,"wins":16},"o3":{"draws":38,"losses":90,"wins":56},"openai/gpt-oss-120b":{"draws":38,"losses":32,"wins":44},"poolside/laguna-s-2.1":{"draws":42,"losses":40,"wins":46},"qwen/qwen3.7-max":{"draws":24,"losses":27,"wins":25},"qwen/qwen3.7-plus":{"draws":20,"losses":20,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":63,"wins":30},"qwen/qwen3.8-27b":{"draws":22,"losses":48,"wins":24},"qwen/qwen3.8-flash":{"draws":29,"losses":39,"wins":20},"qwen/qwen3.8-max":{"draws":43,"losses":53,"wins":36},"qwen/qwen3.8-max-0902":{"draws":33,"losses":76,"wins":23},"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":95,"losses":255,"wins":90},"stealth/space-bunny-alpha":{"draws":34,"losses":40,"wins":30},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":23,"losses":22,"wins":27},"tencent/hy4-preview":{"draws":40,"losses":71,"wins":17},"thinkingmachines/inkling":{"draws":59,"losses":47,"wins":72},"thinkingmachines/inkling-small":{"draws":46,"losses":29,"wins":57},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":15,"wins":14},"x-ai/grok-4.5":{"draws":30,"losses":85,"wins":17},"x-ai/grok-4.6":{"draws":33,"losses":83,"wins":16},"x-ai/grok-4.7":{"draws":6,"losses":93,"wins":15},"x-ai/grok-build-0.1":{"draws":14,"losses":10,"wins":20},"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":13,"losses":49,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":57,"wins":18},"z-ai/glm-5.2":{"draws":94,"losses":96,"wins":74},"z-ai/glm-5.3":{"draws":23,"losses":86,"wins":17},"z-ai/glm-5.3-flash":{"draws":28,"losses":74,"wins":30},"z-ai/glm-5.3-flashx":{"draws":24,"losses":83,"wins":25}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":18,"wins":97},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":9,"losses":135,"wins":18},"claude-haiku-5-5":{"draws":24,"losses":42,"wins":72},"claude-opus-4-5":{"draws":35,"losses":40,"wins":159},"claude-opus-4-8":{"draws":24,"losses":35,"wins":73},"claude-opus-5":{"draws":37,"losses":140,"wins":69},"claude-opus-5-5":{"draws":12,"losses":122,"wins":22},"claude-sonnet-5":{"draws":23,"losses":26,"wins":95},"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":35,"losses":15,"wins":166},"deepseek/deepseek-v4-pro":{"draws":23,"losses":27,"wins":82},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":27,"wins":87},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":36,"wins":74},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":53,"wins":65},"elorian/glimpse":{"draws":11,"losses":28,"wins":39},"fireworks/ember-1":{"draws":30,"losses":22,"wins":92},"gemini-3.1-pro-preview":{"draws":28,"losses":29,"wins":87},"gemini-4-argon":{"draws":13,"losses":101,"wins":30},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":85},"google/gemini-3.5-flash":{"draws":29,"losses":34,"wins":117},"google/gemini-3.5-flash-lite":{"draws":39,"losses":28,"wins":185},"google/gemini-3.6-flash":{"draws":40,"losses":84,"wins":152},"google/gemini-3.8-flash":{"draws":21,"losses":56,"wins":67},"google/gemma-4-31b-it":{"draws":18,"losses":8,"wins":58},"gpt-4.1":{"draws":7,"losses":12,"wins":29},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":20,"losses":21,"wins":85},"gpt-5.4":{"draws":31,"losses":40,"wins":67},"gpt-5.4-mini":{"draws":20,"losses":11,"wins":65},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":114},"gpt-5.5":{"draws":30,"losses":38,"wins":64},"gpt-5.6-luna":{"draws":29,"losses":18,"wins":97},"gpt-5.6-sol":{"draws":18,"losses":61,"wins":65},"gpt-5.6-terra":{"draws":32,"losses":20,"wins":86},"gpt-6-astra":{"draws":10,"losses":111,"wins":23},"gpt-6-luna":{"draws":29,"losses":27,"wins":88},"gpt-6-sol":{"draws":20,"losses":82,"wins":42},"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":17,"losses":4,"wins":81},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":15,"losses":20,"wins":121},"meta/muse-glimmer-30b":{"draws":21,"losses":7,"wins":98},"meta/muse-spark-1.2":{"draws":20,"losses":32,"wins":86},"meta/muse-spark-1.3":{"draws":22,"losses":43,"wins":79},"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":17,"losses":6,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":26},"moonshotai/kimi-k3":{"draws":25,"losses":27,"wins":86},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":97,"wins":30},"nex-agi/nex-n2-pro":{"draws":12,"losses":2,"wins":58},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":13,"wins":93},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":4,"wins":49},"o3":{"draws":16,"losses":29,"wins":153},"openai/gpt-oss-120b":{"draws":26,"losses":11,"wins":89},"poolside/laguna-s-2.1":{"draws":19,"losses":21,"wins":98},"qwen/qwen3.7-max":{"draws":12,"losses":13,"wins":59},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":36,"wins":77},"qwen/qwen3.8-27b":{"draws":20,"losses":16,"wins":66},"qwen/qwen3.8-flash":{"draws":21,"losses":20,"wins":55},"qwen/qwen3.8-max":{"draws":25,"losses":37,"wins":82},"qwen/qwen3.8-max-0902":{"draws":28,"losses":35,"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":74,"losses":122,"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":21,"losses":12,"wins":45},"tencent/hy4-preview":{"draws":19,"losses":30,"wins":89},"thinkingmachines/inkling":{"draws":36,"losses":12,"wins":144},"thinkingmachines/inkling-small":{"draws":22,"losses":14,"wins":108},"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":45,"wins":76},"x-ai/grok-4.6":{"draws":31,"losses":49,"wins":64},"x-ai/grok-4.7":{"draws":7,"losses":77,"wins":42},"x-ai/grok-build-0.1":{"draws":8,"losses":6,"wins":34},"xiaomi/mimo-v2.5":{"draws":38,"losses":6,"wins":178},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":66},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":22,"wins":53},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":41,"wins":47},"z-ai/glm-5.2":{"draws":56,"losses":42,"wins":190},"z-ai/glm-5.3":{"draws":20,"losses":64,"wins":54},"z-ai/glm-5.3-flash":{"draws":21,"losses":46,"wins":77},"z-ai/glm-5.3-flashx":{"draws":22,"losses":44,"wins":78}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":136},"claude-fable-5":{"draws":9,"losses":18,"wins":135},"claude-fable-5-1":{"draws":12,"losses":60,"wins":60},"claude-haiku-5-5":{"draws":8,"losses":8,"wins":138},"claude-opus-4-5":{"draws":13,"losses":11,"wins":238},"claude-opus-4-8":{"draws":6,"losses":11,"wins":129},"claude-opus-5":{"draws":25,"losses":79,"wins":174},"claude-opus-5-5":{"draws":15,"losses":95,"wins":64},"claude-sonnet-5":{"draws":8,"losses":6,"wins":148},"claude-sonnet-5-5":{"draws":6,"losses":36,"wins":120},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4-flash":{"draws":9,"losses":1,"wins":230},"deepseek/deepseek-v4-pro":{"draws":10,"losses":5,"wins":135},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":3,"wins":143},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":138},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":133},"elorian/glimpse":{"draws":7,"losses":9,"wins":74},"fireworks/ember-1":{"draws":5,"losses":10,"wins":147},"gemini-3.1-pro-preview":{"draws":8,"losses":4,"wins":150},"gemini-4-argon":{"draws":14,"losses":53,"wins":95},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":99},"google/gemini-3.5-flash":{"draws":14,"losses":6,"wins":182},"google/gemini-3.5-flash-lite":{"draws":14,"losses":2,"wins":268},"google/gemini-3.6-flash":{"draws":19,"losses":17,"wins":276},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":139},"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":8,"losses":16,"wins":132},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":103},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":152},"gpt-5.5":{"draws":4,"losses":18,"wins":128},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":147},"gpt-5.6-sol":{"draws":13,"losses":18,"wins":131},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":143},"gpt-6-astra":{"draws":16,"losses":85,"wins":61},"gpt-6-luna":{"draws":13,"losses":6,"wins":143},"gpt-6-sol":{"draws":15,"losses":38,"wins":109},"gpt-6.1-sol":{"draws":9,"losses":76,"wins":77},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":106},"inception/mercury-3":{"draws":4,"losses":1,"wins":101},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":108},"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":7,"losses":0,"wins":136},"meta/muse-spark-1.2":{"draws":7,"losses":9,"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":2,"losses":1,"wins":83},"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":4,"losses":1,"wins":89},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":37},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":139},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":43,"wins":96},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":77},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":128},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":71},"o3":{"draws":5,"losses":9,"wins":204},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":133},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":145},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":89},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":73},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":7,"wins":147},"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":7,"losses":15,"wins":140},"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":30,"losses":28,"wins":492},"stealth/space-bunny-alpha":{"draws":4,"losses":2,"wins":124},"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":8,"losses":13,"wins":135},"thinkingmachines/inkling":{"draws":10,"losses":0,"wins":208},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":152},"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":9,"losses":11,"wins":142},"x-ai/grok-4.6":{"draws":9,"losses":24,"wins":129},"x-ai/grok-4.7":{"draws":6,"losses":37,"wins":97},"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":4,"losses":9,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":11,"wins":83},"z-ai/glm-5.2":{"draws":19,"losses":7,"wins":298},"z-ai/glm-5.3":{"draws":12,"losses":21,"wins":123},"z-ai/glm-5.3-flash":{"draws":10,"losses":13,"wins":139},"z-ai/glm-5.3-flashx":{"draws":11,"losses":12,"wins":139}},"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":37,"losses":32,"wins":63},"claude-fable-5":{"draws":22,"losses":93,"wins":29},"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":39,"losses":55,"wins":38},"claude-opus-5":{"draws":39,"losses":185,"wins":22},"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":60,"losses":43,"wins":113},"deepseek/deepseek-v4-pro":{"draws":36,"losses":47,"wins":49},"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":47,"losses":56,"wins":41},"gemini-3.1-pro-preview":{"draws":34,"losses":47,"wins":63},"gemini-4-argon":{"draws":6,"losses":129,"wins":9},"google/gemini-3.1-flash-lite":{"draws":21,"losses":3,"wins":72},"google/gemini-3.5-flash":{"draws":45,"losses":73,"wins":62},"google/gemini-3.5-flash-lite":{"draws":83,"losses":50,"wins":119},"google/gemini-3.6-flash":{"draws":75,"losses":124,"wins":77},"google/gemini-3.8-flash":{"draws":39,"losses":73,"wins":32},"google/gemma-4-31b-it":{"draws":28,"losses":10,"wins":46},"gpt-4.1":{"draws":18,"losses":12,"wins":18},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":37,"losses":40,"wins":49},"gpt-5.4":{"draws":37,"losses":68,"wins":33},"gpt-5.4-mini":{"draws":40,"losses":18,"wins":38},"gpt-5.4-nano":{"draws":40,"losses":33,"wins":71},"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":97,"wins":25},"gpt-5.6-terra":{"draws":53,"losses":40,"wins":45},"gpt-6-astra":{"draws":9,"losses":124,"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":39,"losses":21,"wins":96},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":65},"meta/muse-spark-1.2":{"draws":35,"losses":65,"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":25,"losses":8,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":9,"wins":18},"moonshotai/kimi-k3":{"draws":47,"losses":48,"wins":43},"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":42,"losses":16,"wins":68},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":21,"wins":22},"o3":{"draws":25,"losses":54,"wins":119},"openai/gpt-oss-120b":{"draws":40,"losses":22,"wins":64},"poolside/laguna-s-2.1":{"draws":45,"losses":20,"wins":73},"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":47,"losses":59,"wins":38},"qwen/qwen3.8-27b":{"draws":29,"losses":37,"wins":36},"qwen/qwen3.8-flash":{"draws":33,"losses":32,"wins":31},"qwen/qwen3.8-max":{"draws":40,"losses":62,"wins":42},"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":126,"losses":202,"wins":146},"stealth/space-bunny-alpha":{"draws":33,"losses":27,"wins":54},"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":17,"wins":34},"tencent/hy4-preview":{"draws":35,"losses":62,"wins":41},"thinkingmachines/inkling":{"draws":58,"losses":31,"wins":103},"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":62,"wins":41},"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":7,"wins":24},"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":86,"losses":79,"wins":123},"z-ai/glm-5.3":{"draws":33,"losses":83,"wins":22},"z-ai/glm-5.3-flash":{"draws":32,"losses":74,"wins":38},"z-ai/glm-5.3-flashx":{"draws":36,"losses":75,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":20,"wins":68},"claude-fable-5":{"draws":24,"losses":73,"wins":35},"claude-fable-5-1":{"draws":6,"losses":129,"wins":11},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":57},"claude-opus-4-5":{"draws":66,"losses":54,"wins":98},"claude-opus-4-8":{"draws":16,"losses":34,"wins":34},"claude-opus-5":{"draws":32,"losses":156,"wins":34},"claude-opus-5-5":{"draws":12,"losses":115,"wins":17},"claude-sonnet-5":{"draws":37,"losses":38,"wins":57},"claude-sonnet-5-5":{"draws":29,"losses":62,"wins":41},"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":29,"losses":38,"wins":53},"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":42,"losses":37,"wins":53},"gemini-3.1-pro-preview":{"draws":32,"losses":34,"wins":66},"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":51,"wins":81},"google/gemini-3.5-flash-lite":{"draws":64,"losses":23,"wins":145},"google/gemini-3.6-flash":{"draws":58,"losses":104,"wins":90},"google/gemini-3.8-flash":{"draws":29,"losses":61,"wins":42},"google/gemma-4-31b-it":{"draws":23,"losses":10,"wins":47},"gpt-4.1":{"draws":14,"losses":5,"wins":25},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":30,"losses":30,"wins":54},"gpt-5.4":{"draws":29,"losses":55,"wins":42},"gpt-5.4-mini":{"draws":22,"losses":22,"wins":44},"gpt-5.4-nano":{"draws":25,"losses":31,"wins":84},"gpt-5.5":{"draws":37,"losses":48,"wins":35},"gpt-5.6-luna":{"draws":39,"losses":29,"wins":64},"gpt-5.6-sol":{"draws":19,"losses":73,"wins":40},"gpt-5.6-terra":{"draws":32,"losses":36,"wins":58},"gpt-6-astra":{"draws":8,"losses":114,"wins":10},"gpt-6-luna":{"draws":32,"losses":38,"wins":62},"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":33,"losses":9,"wins":56},"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":29,"losses":44,"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":17,"losses":10,"wins":47},"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":24,"losses":6,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":34,"losses":43,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":105,"wins":12},"nex-agi/nex-n2-pro":{"draws":15,"losses":3,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":18,"wins":76},"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":18,"losses":11,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":48,"wins":43},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":43},"qwen/qwen3.8-flash":{"draws":29,"losses":17,"wins":42},"qwen/qwen3.8-max":{"draws":26,"losses":45,"wins":61},"qwen/qwen3.8-max-0902":{"draws":31,"losses":50,"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":80,"losses":158,"wins":156},"stealth/space-bunny-alpha":{"draws":25,"losses":27,"wins":54},"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":19,"losses":16,"wins":39},"tencent/hy4-preview":{"draws":31,"losses":50,"wins":45},"thinkingmachines/inkling":{"draws":44,"losses":21,"wins":107},"thinkingmachines/inkling-small":{"draws":39,"losses":13,"wins":80},"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":15,"losses":15,"wins":44},"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":20,"losses":75,"wins":31},"z-ai/glm-5.3-flash":{"draws":19,"losses":61,"wins":52},"z-ai/glm-5.3-flashx":{"draws":25,"losses":49,"wins":58}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":22,"wins":177},"claude-fable-5":{"draws":37,"losses":69,"wins":140},"claude-fable-5-1":{"draws":25,"losses":174,"wins":79},"claude-haiku-5-5":{"draws":35,"losses":39,"wins":160},"claude-opus-4-5":{"draws":70,"losses":37,"wins":291},"claude-opus-4-8":{"draws":32,"losses":34,"wins":156},"claude-opus-5":{"draws":56,"losses":164,"wins":164},"claude-opus-5-5":{"draws":25,"losses":165,"wins":80},"claude-sonnet-5":{"draws":34,"losses":34,"wins":178},"claude-sonnet-5-5":{"draws":27,"losses":82,"wins":137},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":80},"deepseek/deepseek-v4-flash":{"draws":43,"losses":21,"wins":298},"deepseek/deepseek-v4-pro":{"draws":26,"losses":33,"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":45,"wins":175},"gemini-3.1-pro-preview":{"draws":24,"losses":36,"wins":186},"gemini-4-argon":{"draws":30,"losses":114,"wins":102},"google/gemini-3.1-flash-lite":{"draws":19,"losses":5,"wins":126},"google/gemini-3.5-flash":{"draws":36,"losses":30,"wins":238},"google/gemini-3.5-flash-lite":{"draws":49,"losses":33,"wins":342},"google/gemini-3.6-flash":{"draws":57,"losses":89,"wins":322},"google/gemini-3.8-flash":{"draws":25,"losses":53,"wins":168},"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":31,"losses":36,"wins":167},"gpt-5.4-mini":{"draws":31,"losses":13,"wins":120},"gpt-5.4-nano":{"draws":24,"losses":16,"wins":196},"gpt-5.5":{"draws":29,"losses":46,"wins":157},"gpt-5.6-luna":{"draws":26,"losses":24,"wins":196},"gpt-5.6-sol":{"draws":29,"losses":63,"wins":154},"gpt-5.6-terra":{"draws":26,"losses":23,"wins":185},"gpt-6-astra":{"draws":22,"losses":168,"wins":56},"gpt-6-luna":{"draws":43,"losses":26,"wins":177},"gpt-6-sol":{"draws":33,"losses":94,"wins":119},"gpt-6.1-sol":{"draws":33,"losses":138,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":128},"inception/mercury-3":{"draws":18,"losses":18,"wins":128},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":132},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":24,"losses":22,"wins":210},"meta/muse-glimmer-30b":{"draws":15,"losses":22,"wins":193},"meta/muse-spark-1.2":{"draws":31,"losses":36,"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":17,"losses":7,"wins":114},"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":21,"losses":12,"wins":111},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":3,"wins":59},"moonshotai/kimi-k3":{"draws":36,"losses":41,"wins":167},"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":26,"losses":6,"wins":182},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":81},"o3":{"draws":26,"losses":22,"wins":264},"openai/gpt-oss-120b":{"draws":29,"losses":11,"wins":180},"poolside/laguna-s-2.1":{"draws":26,"losses":13,"wins":209},"qwen/qwen3.7-max":{"draws":18,"losses":12,"wins":110},"qwen/qwen3.7-plus":{"draws":16,"losses":8,"wins":92},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":42,"wins":173},"qwen/qwen3.8-27b":{"draws":30,"losses":13,"wins":123},"qwen/qwen3.8-flash":{"draws":24,"losses":14,"wins":126},"qwen/qwen3.8-max":{"draws":36,"losses":32,"wins":178},"qwen/qwen3.8-max-0902":{"draws":34,"losses":43,"wins":169},"recursive/flint-v1.0":{"draws":7,"losses":1,"wins":62},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":23,"wins":180},"stealth/ox-alpha":{"draws":130,"losses":122,"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":24,"losses":35,"wins":175},"thinkingmachines/inkling":{"draws":49,"losses":30,"wins":259},"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":47,"wins":161},"x-ai/grok-4.6":{"draws":37,"losses":48,"wins":160},"x-ai/grok-4.7":{"draws":20,"losses":99,"wins":101},"x-ai/grok-build-0.1":{"draws":15,"losses":3,"wins":64},"xiaomi/mimo-v2.5":{"draws":57,"losses":23,"wins":298},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":5,"wins":110},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":17,"wins":119},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":39,"wins":99},"z-ai/glm-5.2":{"draws":73,"losses":34,"wins":385},"z-ai/glm-5.3":{"draws":31,"losses":65,"wins":138},"z-ai/glm-5.3-flash":{"draws":37,"losses":46,"wins":163},"z-ai/glm-5.3-flashx":{"draws":36,"losses":43,"wins":167}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":131},"claude-fable-5":{"draws":12,"losses":22,"wins":122},"claude-fable-5-1":{"draws":15,"losses":64,"wins":95},"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":12,"losses":17,"wins":115},"claude-opus-5":{"draws":25,"losses":80,"wins":165},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":10,"losses":9,"wins":137},"claude-sonnet-5-5":{"draws":14,"losses":31,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":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":12,"wins":136},"gemini-3.1-pro-preview":{"draws":10,"losses":10,"wins":136},"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":8,"wins":178},"google/gemini-3.5-flash-lite":{"draws":18,"losses":1,"wins":253},"google/gemini-3.6-flash":{"draws":21,"losses":24,"wins":251},"google/gemini-3.8-flash":{"draws":14,"losses":20,"wins":122},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":87},"gpt-4.1":{"draws":3,"losses":2,"wins":47},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":8,"losses":5,"wins":125},"gpt-5.4":{"draws":9,"losses":13,"wins":128},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":97},"gpt-5.4-nano":{"draws":7,"losses":2,"wins":151},"gpt-5.5":{"draws":13,"losses":15,"wins":116},"gpt-5.6-luna":{"draws":15,"losses":5,"wins":136},"gpt-5.6-sol":{"draws":11,"losses":22,"wins":123},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":138},"gpt-6-astra":{"draws":16,"losses":70,"wins":70},"gpt-6-luna":{"draws":13,"losses":4,"wins":139},"gpt-6-sol":{"draws":14,"losses":40,"wins":102},"gpt-6.1-sol":{"draws":19,"losses":62,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":102},"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":11,"losses":6,"wins":155},"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":11,"wins":134},"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":6,"losses":0,"wins":70},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":17,"wins":129},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":10,"losses":3,"wins":91},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":130},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":131},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":43},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":4,"wins":126},"stealth/ox-alpha":{"draws":45,"losses":27,"wins":434},"stealth/space-bunny-alpha":{"draws":6,"losses":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":12,"wins":126},"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":18,"losses":18,"wins":120},"x-ai/grok-4.6":{"draws":16,"losses":15,"wins":125},"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":8,"losses":2,"wins":88},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":81},"z-ai/glm-5.2":{"draws":18,"losses":12,"wins":282},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":114},"z-ai/glm-5.3-flash":{"draws":12,"losses":10,"wins":134},"z-ai/glm-5.3-flashx":{"draws":14,"losses":12,"wins":130}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":25,"wins":68},"claude-fable-5":{"draws":23,"losses":95,"wins":26},"claude-fable-5-1":{"draws":8,"losses":148,"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":37,"losses":57,"wins":38},"claude-opus-5":{"draws":34,"losses":178,"wins":34},"claude-opus-5-5":{"draws":10,"losses":137,"wins":9},"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":43,"losses":54,"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":38,"losses":61,"wins":45},"gemini-3.1-pro-preview":{"draws":40,"losses":49,"wins":55},"gemini-4-argon":{"draws":12,"losses":124,"wins":8},"google/gemini-3.1-flash-lite":{"draws":30,"losses":5,"wins":61},"google/gemini-3.5-flash":{"draws":49,"losses":77,"wins":54},"google/gemini-3.5-flash-lite":{"draws":70,"losses":56,"wins":126},"google/gemini-3.6-flash":{"draws":67,"losses":125,"wins":84},"google/gemini-3.8-flash":{"draws":32,"losses":77,"wins":35},"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":36,"wins":53},"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":57,"wins":27},"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":34,"losses":8,"wins":60},"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":37,"losses":64,"wins":37},"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":31,"losses":10,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":39,"losses":58,"wins":41},"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":44,"losses":29,"wins":53},"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":40,"losses":68,"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":106,"losses":233,"wins":135},"stealth/space-bunny-alpha":{"draws":24,"losses":40,"wins":50},"stepfun/step-3.7-flash":{"draws":21,"losses":27,"wins":54},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":25,"losses":22,"wins":31},"tencent/hy4-preview":{"draws":39,"losses":64,"wins":35},"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":89,"wins":25},"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":89,"wins":120},"z-ai/glm-5.3":{"draws":28,"losses":91,"wins":19},"z-ai/glm-5.3-flash":{"draws":24,"losses":79,"wins":41},"z-ai/glm-5.3-flashx":{"draws":39,"losses":72,"wins":33}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":79},"claude-fable-5":{"draws":26,"losses":61,"wins":57},"claude-fable-5-1":{"draws":6,"losses":120,"wins":36},"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":29,"losses":41,"wins":62},"claude-opus-5":{"draws":27,"losses":137,"wins":82},"claude-opus-5-5":{"draws":14,"losses":111,"wins":31},"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":31,"losses":34,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":41,"wins":74},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":60,"wins":60},"elorian/glimpse":{"draws":16,"losses":19,"wins":43},"fireworks/ember-1":{"draws":28,"losses":44,"wins":72},"gemini-3.1-pro-preview":{"draws":21,"losses":42,"wins":81},"gemini-4-argon":{"draws":12,"losses":88,"wins":44},"google/gemini-3.1-flash-lite":{"draws":15,"losses":13,"wins":68},"google/gemini-3.5-flash":{"draws":30,"losses":47,"wins":103},"google/gemini-3.5-flash-lite":{"draws":48,"losses":40,"wins":164},"google/gemini-3.6-flash":{"draws":50,"losses":97,"wins":129},"google/gemini-3.8-flash":{"draws":20,"losses":57,"wins":67},"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":14,"losses":73,"wins":57},"gpt-5.6-terra":{"draws":33,"losses":31,"wins":74},"gpt-6-astra":{"draws":11,"losses":103,"wins":30},"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":18,"losses":8,"wins":58},"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":50,"wins":63},"qwen/qwen3.8-27b":{"draws":17,"losses":26,"wins":59},"qwen/qwen3.8-flash":{"draws":17,"losses":30,"wins":49},"qwen/qwen3.8-max":{"draws":22,"losses":41,"wins":81},"qwen/qwen3.8-max-0902":{"draws":26,"losses":51,"wins":67},"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":82,"losses":165,"wins":227},"stealth/space-bunny-alpha":{"draws":21,"losses":24,"wins":69},"stepfun/step-3.7-flash":{"draws":11,"losses":26,"wins":65},"stepfun/step-5-preview":{"draws":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":54,"losses":66,"wins":168},"z-ai/glm-5.3":{"draws":22,"losses":63,"wins":53},"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":10,"losses":28,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":32,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":35,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":47,"wins":1},"elorian/glimpse":{"draws":3,"losses":21,"wins":6},"fireworks/ember-1":{"draws":10,"losses":35,"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":76,"wins":8},"google/gemini-3.8-flash":{"draws":8,"losses":40,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":18,"wins":6},"gpt-4.1":{"draws":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":42,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":41,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":7,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":39,"wins":9},"stealth/ox-alpha":{"draws":24,"losses":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":60,"losses":72,"wins":64},"claude-fable-5":{"draws":35,"losses":166,"wins":15},"claude-fable-5-1":{"draws":9,"losses":230,"wins":1},"claude-haiku-5-5":{"draws":57,"losses":121,"wins":30},"claude-opus-4-5":{"draws":104,"losses":183,"wins":65},"claude-opus-4-8":{"draws":49,"losses":125,"wins":26},"claude-opus-5":{"draws":43,"losses":298,"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":52,"losses":100,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":54,"losses":93,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":68,"losses":122,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":40,"losses":150,"wins":26},"elorian/glimpse":{"draws":25,"losses":61,"wins":30},"fireworks/ember-1":{"draws":63,"losses":110,"wins":43},"gemini-3.1-pro-preview":{"draws":61,"losses":97,"wins":58},"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":144,"wins":62},"google/gemini-3.5-flash-lite":{"draws":116,"losses":134,"wins":124},"google/gemini-3.6-flash":{"draws":98,"losses":255,"wins":59},"google/gemini-3.8-flash":{"draws":40,"losses":155,"wins":21},"google/gemma-4-31b-it":{"draws":58,"losses":22,"wins":46},"gpt-4.1":{"draws":22,"losses":34,"wins":16},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":55,"losses":93,"wins":42},"gpt-5.4":{"draws":53,"losses":123,"wins":30},"gpt-5.4-mini":{"draws":54,"losses":50,"wins":40},"gpt-5.4-nano":{"draws":49,"losses":94,"wins":83},"gpt-5.5":{"draws":64,"losses":111,"wins":21},"gpt-5.6-luna":{"draws":83,"losses":82,"wins":51},"gpt-5.6-sol":{"draws":29,"losses":166,"wins":21},"gpt-5.6-terra":{"draws":66,"losses":110,"wins":32},"gpt-6-astra":{"draws":10,"losses":201,"wins":5},"gpt-6-luna":{"draws":64,"losses":106,"wins":46},"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":59,"losses":43,"wins":56},"inclusionai/ling-3.1-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":63,"losses":77,"wins":94},"meta/muse-glimmer-30b":{"draws":78,"losses":47,"wins":61},"meta/muse-spark-1.2":{"draws":51,"losses":121,"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":32,"losses":45,"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":51,"losses":29,"wins":44},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":29,"wins":11},"moonshotai/kimi-k3":{"draws":58,"losses":106,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":187,"wins":3},"nex-agi/nex-n2-pro":{"draws":24,"losses":32,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":23,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":62,"losses":59,"wins":73},"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":69,"losses":72,"wins":69},"qwen/qwen3.7-max":{"draws":50,"losses":50,"wins":30},"qwen/qwen3.7-plus":{"draws":31,"losses":38,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":65,"losses":119,"wins":32},"qwen/qwen3.8-27b":{"draws":38,"losses":81,"wins":35},"qwen/qwen3.8-flash":{"draws":42,"losses":70,"wins":32},"qwen/qwen3.8-max":{"draws":65,"losses":116,"wins":35},"qwen/qwen3.8-max-0902":{"draws":61,"losses":123,"wins":32},"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":161,"losses":403,"wins":132},"stealth/space-bunny-alpha":{"draws":48,"losses":72,"wins":48},"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":51,"losses":117,"wins":38},"thinkingmachines/inkling":{"draws":93,"losses":98,"wins":93},"thinkingmachines/inkling-small":{"draws":85,"losses":48,"wins":83},"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":52,"losses":142,"wins":22},"x-ai/grok-4.7":{"draws":18,"losses":159,"wins":15},"x-ai/grok-build-0.1":{"draws":25,"losses":19,"wins":28},"xiaomi/mimo-v2.5":{"draws":115,"losses":108,"wins":111},"xiaomi/mimo-v2.5-pro":{"draws":32,"losses":46,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":83,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":95,"wins":24},"z-ai/glm-5.2":{"draws":144,"losses":183,"wins":105},"z-ai/glm-5.3":{"draws":44,"losses":150,"wins":12},"z-ai/glm-5.3-flash":{"draws":51,"losses":120,"wins":45},"z-ai/glm-5.3-flashx":{"draws":57,"losses":125,"wins":34}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":31,"wins":61},"claude-fable-5":{"draws":23,"losses":82,"wins":27},"claude-fable-5-1":{"draws":10,"losses":135,"wins":5},"claude-haiku-5-5":{"draws":35,"losses":50,"wins":41},"claude-opus-4-5":{"draws":62,"losses":76,"wins":76},"claude-opus-4-8":{"draws":28,"losses":55,"wins":37},"claude-opus-5":{"draws":26,"losses":173,"wins":33},"claude-opus-5-5":{"draws":11,"losses":128,"wins":5},"claude-sonnet-5":{"draws":40,"losses":45,"wins":47},"claude-sonnet-5-5":{"draws":31,"losses":67,"wins":34},"cohere/north-mini-code":{"draws":10,"losses":14,"wins":28},"deepseek/deepseek-v4-flash":{"draws":52,"losses":44,"wins":100},"deepseek/deepseek-v4-pro":{"draws":20,"losses":30,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":47,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":53,"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":36,"losses":56,"wins":40},"gemini-3.1-pro-preview":{"draws":30,"losses":51,"wins":51},"gemini-4-argon":{"draws":14,"losses":104,"wins":14},"google/gemini-3.1-flash-lite":{"draws":23,"losses":6,"wins":59},"google/gemini-3.5-flash":{"draws":37,"losses":74,"wins":55},"google/gemini-3.5-flash-lite":{"draws":59,"losses":67,"wins":106},"google/gemini-3.6-flash":{"draws":64,"losses":109,"wins":81},"google/gemini-3.8-flash":{"draws":25,"losses":74,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":14,"wins":34},"gpt-4.1":{"draws":13,"losses":9,"wins":22},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":28,"losses":38,"wins":52},"gpt-5.4":{"draws":27,"losses":63,"wins":38},"gpt-5.4-mini":{"draws":28,"losses":26,"wins":34},"gpt-5.4-nano":{"draws":15,"losses":48,"wins":67},"gpt-5.5":{"draws":37,"losses":60,"wins":27},"gpt-5.6-luna":{"draws":42,"losses":37,"wins":53},"gpt-5.6-sol":{"draws":16,"losses":88,"wins":28},"gpt-5.6-terra":{"draws":38,"losses":46,"wins":42},"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":35,"losses":9,"wins":46},"inception/mercury-3":{"draws":24,"losses":31,"wins":31},"inclusionai/ling-3.0-flash":{"draws":32,"losses":18,"wins":42},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":27,"losses":31,"wins":86},"meta/muse-glimmer-30b":{"draws":35,"losses":29,"wins":56},"meta/muse-spark-1.2":{"draws":23,"losses":59,"wins":46},"meta/muse-spark-1.3":{"draws":23,"losses":74,"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":19,"losses":11,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":12,"wins":15},"moonshotai/kimi-k3":{"draws":26,"losses":59,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":102,"wins":11},"nex-agi/nex-n2-pro":{"draws":15,"losses":14,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":23,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":20,"wins":25},"o3":{"draws":20,"losses":72,"wins":92},"openai/gpt-oss-120b":{"draws":33,"losses":28,"wins":55},"poolside/laguna-s-2.1":{"draws":30,"losses":47,"wins":51},"qwen/qwen3.7-max":{"draws":23,"losses":18,"wins":35},"qwen/qwen3.7-plus":{"draws":14,"losses":15,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":61,"wins":37},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":31},"qwen/qwen3.8-flash":{"draws":18,"losses":40,"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":102,"losses":209,"wins":131},"stealth/space-bunny-alpha":{"draws":29,"losses":30,"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":27,"losses":63,"wins":38},"thinkingmachines/inkling":{"draws":58,"losses":29,"wins":93},"thinkingmachines/inkling-small":{"draws":44,"losses":19,"wins":69},"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":33,"losses":61,"wins":38},"x-ai/grok-4.6":{"draws":32,"losses":73,"wins":27},"x-ai/grok-4.7":{"draws":10,"losses":85,"wins":21},"x-ai/grok-build-0.1":{"draws":17,"losses":9,"wins":18},"xiaomi/mimo-v2.5":{"draws":71,"losses":32,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":38,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":47,"wins":25},"z-ai/glm-5.2":{"draws":81,"losses":84,"wins":99},"z-ai/glm-5.3":{"draws":21,"losses":78,"wins":27},"z-ai/glm-5.3-flash":{"draws":21,"losses":73,"wins":38},"z-ai/glm-5.3-flashx":{"draws":30,"losses":60,"wins":42}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":36,"wins":53},"claude-fable-5":{"draws":18,"losses":87,"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":29,"losses":53,"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":51,"wins":93},"deepseek/deepseek-v4-pro":{"draws":34,"losses":41,"wins":47},"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":32,"losses":58,"wins":42},"gemini-3.1-pro-preview":{"draws":34,"losses":45,"wins":53},"gemini-4-argon":{"draws":13,"losses":111,"wins":8},"google/gemini-3.1-flash-lite":{"draws":24,"losses":10,"wins":54},"google/gemini-3.5-flash":{"draws":39,"losses":73,"wins":54},"google/gemini-3.5-flash-lite":{"draws":73,"losses":47,"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":53,"wins":39},"gpt-5.6-luna":{"draws":43,"losses":38,"wins":51},"gpt-5.6-sol":{"draws":16,"losses":89,"wins":27},"gpt-5.6-terra":{"draws":37,"losses":53,"wins":38},"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":7,"losses":122,"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":24,"losses":62,"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":20,"losses":13,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":34,"losses":41,"wins":51},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":104,"wins":10},"nex-agi/nex-n2-pro":{"draws":13,"losses":13,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":20,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":23,"wins":23},"o3":{"draws":26,"losses":58,"wins":100},"openai/gpt-oss-120b":{"draws":36,"losses":27,"wins":51},"poolside/laguna-s-2.1":{"draws":29,"losses":36,"wins":59},"qwen/qwen3.7-max":{"draws":27,"losses":17,"wins":32},"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":23,"losses":41,"wins":30},"qwen/qwen3.8-flash":{"draws":20,"losses":36,"wins":32},"qwen/qwen3.8-max":{"draws":37,"losses":55,"wins":40},"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":102,"losses":190,"wins":148},"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":58,"wins":43},"thinkingmachines/inkling":{"draws":58,"losses":43,"wins":75},"thinkingmachines/inkling-small":{"draws":39,"losses":26,"wins":67},"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":36,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":49,"wins":27},"z-ai/glm-5.2":{"draws":84,"losses":79,"wins":101},"z-ai/glm-5.3":{"draws":22,"losses":79,"wins":25},"z-ai/glm-5.3-flash":{"draws":18,"losses":78,"wins":36},"z-ai/glm-5.3-flashx":{"draws":27,"losses":66,"wins":39}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":33,"wins":62},"claude-fable-5":{"draws":34,"losses":74,"wins":36},"claude-fable-5-1":{"draws":11,"losses":138,"wins":13},"claude-haiku-5-5":{"draws":43,"losses":56,"wins":39},"claude-opus-4-5":{"draws":63,"losses":68,"wins":103},"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":43,"losses":47,"wins":54},"claude-sonnet-5-5":{"draws":29,"losses":74,"wins":41},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":35},"deepseek/deepseek-v4-flash":{"draws":68,"losses":26,"wins":122},"deepseek/deepseek-v4-pro":{"draws":37,"losses":42,"wins":53},"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":38,"losses":54,"wins":52},"gemini-3.1-pro-preview":{"draws":35,"losses":49,"wins":60},"gemini-4-argon":{"draws":12,"losses":114,"wins":18},"google/gemini-3.1-flash-lite":{"draws":34,"losses":9,"wins":53},"google/gemini-3.5-flash":{"draws":47,"losses":57,"wins":76},"google/gemini-3.5-flash-lite":{"draws":76,"losses":52,"wins":124},"google/gemini-3.6-flash":{"draws":75,"losses":115,"wins":86},"google/gemini-3.8-flash":{"draws":36,"losses":63,"wins":45},"google/gemma-4-31b-it":{"draws":34,"losses":12,"wins":38},"gpt-4.1":{"draws":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":36,"losses":20,"wins":40},"gpt-5.4-nano":{"draws":36,"losses":37,"wins":71},"gpt-5.5":{"draws":43,"losses":43,"wins":46},"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":53,"losses":33,"wins":52},"gpt-6-astra":{"draws":16,"losses":123,"wins":5},"gpt-6-luna":{"draws":46,"losses":40,"wins":58},"gpt-6-sol":{"draws":24,"losses":90,"wins":30},"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":43,"losses":9,"wins":50},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":34,"wins":89},"meta/muse-glimmer-30b":{"draws":52,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":33,"losses":53,"wins":52},"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":35,"losses":45,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":23,"losses":95,"wins":20},"nex-agi/nex-n2-pro":{"draws":16,"losses":8,"wins":48},"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":38,"losses":65,"wins":95},"openai/gpt-oss-120b":{"draws":39,"losses":25,"wins":62},"poolside/laguna-s-2.1":{"draws":54,"losses":24,"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":48,"wins":60},"qwen/qwen3.8-27b":{"draws":23,"losses":29,"wins":50},"qwen/qwen3.8-flash":{"draws":32,"losses":24,"wins":40},"qwen/qwen3.8-max":{"draws":40,"losses":50,"wins":54},"qwen/qwen3.8-max-0902":{"draws":46,"losses":49,"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":108,"losses":184,"wins":181},"stealth/space-bunny-alpha":{"draws":24,"losses":28,"wins":62},"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":40,"losses":57,"wins":41},"thinkingmachines/inkling":{"draws":62,"losses":30,"wins":100},"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":32,"losses":64,"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":17,"losses":5,"wins":26},"xiaomi/mimo-v2.5":{"draws":75,"losses":29,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":20,"wins":38},"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":101,"losses":64,"wins":123},"z-ai/glm-5.3":{"draws":25,"losses":86,"wins":27},"z-ai/glm-5.3-flash":{"draws":25,"losses":61,"wins":58},"z-ai/glm-5.3-flashx":{"draws":40,"losses":60,"wins":44}},"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":36,"losses":26,"wins":70},"claude-fable-5":{"draws":30,"losses":92,"wins":22},"claude-fable-5-1":{"draws":5,"losses":147,"wins":10},"claude-haiku-5-5":{"draws":36,"losses":64,"wins":38},"claude-opus-4-5":{"draws":77,"losses":67,"wins":90},"claude-opus-4-8":{"draws":42,"losses":53,"wins":37},"claude-opus-5":{"draws":26,"losses":175,"wins":45},"claude-opus-5-5":{"draws":8,"losses":136,"wins":12},"claude-sonnet-5":{"draws":38,"losses":45,"wins":61},"claude-sonnet-5-5":{"draws":28,"losses":72,"wins":44},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":35},"deepseek/deepseek-v4-flash":{"draws":63,"losses":43,"wins":110},"deepseek/deepseek-v4-pro":{"draws":36,"losses":40,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":42,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":52,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":34,"losses":78,"wins":32},"elorian/glimpse":{"draws":18,"losses":29,"wins":31},"fireworks/ember-1":{"draws":24,"losses":36,"wins":36},"gemini-3.1-pro-preview":{"draws":31,"losses":45,"wins":68},"gemini-4-argon":{"draws":10,"losses":118,"wins":16},"google/gemini-3.1-flash-lite":{"draws":17,"losses":9,"wins":70},"google/gemini-3.5-flash":{"draws":46,"losses":63,"wins":71},"google/gemini-3.5-flash-lite":{"draws":84,"losses":51,"wins":117},"google/gemini-3.6-flash":{"draws":74,"losses":99,"wins":103},"google/gemini-3.8-flash":{"draws":33,"losses":63,"wins":48},"google/gemma-4-31b-it":{"draws":31,"losses":12,"wins":41},"gpt-4.1":{"draws":11,"losses":16,"wins":21},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":8},"gpt-5":{"draws":31,"losses":35,"wins":60},"gpt-5.4":{"draws":36,"losses":62,"wins":40},"gpt-5.4-mini":{"draws":37,"losses":14,"wins":45},"gpt-5.4-nano":{"draws":33,"losses":31,"wins":80},"gpt-5.5":{"draws":38,"losses":50,"wins":44},"gpt-5.6-luna":{"draws":44,"losses":45,"wins":55},"gpt-5.6-sol":{"draws":22,"losses":87,"wins":35},"gpt-5.6-terra":{"draws":40,"losses":37,"wins":61},"gpt-6-astra":{"draws":10,"losses":129,"wins":5},"gpt-6-luna":{"draws":37,"losses":43,"wins":64},"gpt-6-sol":{"draws":20,"losses":101,"wins":23},"gpt-6.1-sol":{"draws":10,"losses":116,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":7,"wins":55},"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":38,"losses":30,"wins":88},"meta/muse-glimmer-30b":{"draws":38,"losses":19,"wins":69},"meta/muse-spark-1.2":{"draws":38,"losses":46,"wins":54},"meta/muse-spark-1.3":{"draws":34,"losses":67,"wins":43},"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":23,"losses":9,"wins":52},"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":42,"losses":23,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":19,"wins":29},"o3":{"draws":37,"losses":50,"wins":111},"openai/gpt-oss-120b":{"draws":43,"losses":18,"wins":65},"poolside/laguna-s-2.1":{"draws":46,"losses":26,"wins":66},"qwen/qwen3.7-max":{"draws":22,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":47,"wins":49},"qwen/qwen3.8-27b":{"draws":28,"losses":39,"wins":35},"qwen/qwen3.8-flash":{"draws":30,"losses":32,"wins":34},"qwen/qwen3.8-max":{"draws":41,"losses":43,"wins":60},"qwen/qwen3.8-max-0902":{"draws":37,"losses":63,"wins":44},"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":113,"losses":185,"wins":176},"stealth/space-bunny-alpha":{"draws":30,"losses":29,"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":29,"losses":14,"wins":35},"tencent/hy4-preview":{"draws":37,"losses":53,"wins":48},"thinkingmachines/inkling":{"draws":56,"losses":29,"wins":107},"thinkingmachines/inkling-small":{"draws":43,"losses":20,"wins":81},"unbiased/pareto-26.10":{"draws":2,"losses":45,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":23},"x-ai/grok-4.5":{"draws":32,"losses":72,"wins":40},"x-ai/grok-4.6":{"draws":37,"losses":64,"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":70,"losses":37,"wins":115},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":42,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":46,"wins":29},"z-ai/glm-5.2":{"draws":83,"losses":74,"wins":131},"z-ai/glm-5.3":{"draws":23,"losses":89,"wins":26},"z-ai/glm-5.3-flash":{"draws":25,"losses":73,"wins":46},"z-ai/glm-5.3-flashx":{"draws":28,"losses":67,"wins":49}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":37,"wins":59},"claude-fable-5":{"draws":28,"losses":87,"wins":29},"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":60,"losses":100,"wins":74},"claude-opus-4-8":{"draws":32,"losses":66,"wins":34},"claude-opus-5":{"draws":24,"losses":186,"wins":36},"claude-opus-5-5":{"draws":10,"losses":136,"wins":10},"claude-sonnet-5":{"draws":40,"losses":55,"wins":49},"claude-sonnet-5-5":{"draws":21,"losses":81,"wins":42},"cohere/north-mini-code":{"draws":11,"losses":16,"wins":27},"deepseek/deepseek-v4-flash":{"draws":61,"losses":58,"wins":97},"deepseek/deepseek-v4-pro":{"draws":30,"losses":51,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":53,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":60,"wins":49},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":81,"wins":37},"elorian/glimpse":{"draws":15,"losses":32,"wins":31},"fireworks/ember-1":{"draws":31,"losses":68,"wins":45},"gemini-3.1-pro-preview":{"draws":20,"losses":38,"wins":38},"gemini-4-argon":{"draws":11,"losses":118,"wins":15},"google/gemini-3.1-flash-lite":{"draws":20,"losses":19,"wins":57},"google/gemini-3.5-flash":{"draws":35,"losses":84,"wins":61},"google/gemini-3.5-flash-lite":{"draws":84,"losses":64,"wins":104},"google/gemini-3.6-flash":{"draws":67,"losses":123,"wins":86},"google/gemini-3.8-flash":{"draws":26,"losses":84,"wins":34},"google/gemma-4-31b-it":{"draws":30,"losses":15,"wins":39},"gpt-4.1":{"draws":13,"losses":17,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":40,"losses":35,"wins":51},"gpt-5.4":{"draws":32,"losses":67,"wins":39},"gpt-5.4-mini":{"draws":33,"losses":26,"wins":37},"gpt-5.4-nano":{"draws":32,"losses":41,"wins":71},"gpt-5.5":{"draws":34,"losses":64,"wins":34},"gpt-5.6-luna":{"draws":40,"losses":48,"wins":56},"gpt-5.6-sol":{"draws":18,"losses":95,"wins":31},"gpt-5.6-terra":{"draws":44,"losses":46,"wins":48},"gpt-6-astra":{"draws":7,"losses":133,"wins":4},"gpt-6-luna":{"draws":34,"losses":47,"wins":63},"gpt-6-sol":{"draws":14,"losses":102,"wins":28},"gpt-6.1-sol":{"draws":3,"losses":129,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":38,"losses":23,"wins":41},"inception/mercury-3":{"draws":32,"losses":39,"wins":25},"inclusionai/ling-3.0-flash":{"draws":31,"losses":18,"wins":53},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":38,"losses":47,"wins":71},"meta/muse-glimmer-30b":{"draws":48,"losses":18,"wins":60},"meta/muse-spark-1.2":{"draws":33,"losses":58,"wins":47},"meta/muse-spark-1.3":{"draws":24,"losses":80,"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":22,"wins":39},"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":27,"losses":13,"wins":44},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":18},"moonshotai/kimi-k3":{"draws":33,"losses":64,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":103,"wins":20},"nex-agi/nex-n2-pro":{"draws":19,"losses":11,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":8,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":30,"wins":51},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":25,"wins":26},"o3":{"draws":29,"losses":92,"wins":77},"openai/gpt-oss-120b":{"draws":37,"losses":32,"wins":57},"poolside/laguna-s-2.1":{"draws":44,"losses":33,"wins":61},"qwen/qwen3.7-max":{"draws":24,"losses":29,"wins":31},"qwen/qwen3.7-plus":{"draws":24,"losses":14,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":65,"wins":44},"qwen/qwen3.8-27b":{"draws":22,"losses":48,"wins":32},"qwen/qwen3.8-flash":{"draws":35,"losses":30,"wins":31},"qwen/qwen3.8-max":{"draws":38,"losses":59,"wins":47},"qwen/qwen3.8-max-0902":{"draws":34,"losses":70,"wins":40},"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":97,"losses":231,"wins":146},"stealth/space-bunny-alpha":{"draws":25,"losses":41,"wins":48},"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":21,"losses":23,"wins":34},"tencent/hy4-preview":{"draws":32,"losses":64,"wins":42},"thinkingmachines/inkling":{"draws":58,"losses":49,"wins":85},"thinkingmachines/inkling-small":{"draws":44,"losses":28,"wins":72},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":3},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":13,"wins":18},"x-ai/grok-4.5":{"draws":30,"losses":71,"wins":43},"x-ai/grok-4.6":{"draws":38,"losses":79,"wins":27},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":15,"losses":13,"wins":20},"xiaomi/mimo-v2.5":{"draws":72,"losses":55,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":28,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":45,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":57,"wins":24},"z-ai/glm-5.2":{"draws":82,"losses":94,"wins":112},"z-ai/glm-5.3":{"draws":26,"losses":84,"wins":28},"z-ai/glm-5.3-flash":{"draws":34,"losses":67,"wins":43},"z-ai/glm-5.3-flashx":{"draws":32,"losses":72,"wins":40}},"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":27,"losses":44,"wins":17},"claude-fable-5":{"draws":8,"losses":85,"wins":3},"claude-fable-5-1":{"draws":7,"losses":99,"wins":0},"claude-haiku-5-5":{"draws":22,"losses":66,"wins":8},"claude-opus-4-5":{"draws":37,"losses":116,"wins":7},"claude-opus-4-8":{"draws":20,"losses":71,"wins":5},"claude-opus-5":{"draws":19,"losses":126,"wins":5},"claude-opus-5-5":{"draws":8,"losses":96,"wins":0},"claude-sonnet-5":{"draws":30,"losses":61,"wins":5},"claude-sonnet-5-5":{"draws":15,"losses":68,"wins":13},"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":23,"losses":59,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":54,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":53,"wins":9},"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":70,"wins":9},"gemini-3.1-pro-preview":{"draws":20,"losses":57,"wins":19},"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":29,"losses":83,"wins":14},"google/gemini-3.5-flash-lite":{"draws":47,"losses":93,"wins":34},"google/gemini-3.6-flash":{"draws":42,"losses":129,"wins":15},"google/gemini-3.8-flash":{"draws":22,"losses":72,"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":23,"losses":56,"wins":5},"gpt-5.4":{"draws":18,"losses":68,"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":59,"wins":4},"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":30,"losses":54,"wins":6},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":27,"losses":59,"wins":10},"gpt-6-sol":{"draws":14,"losses":80,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":93,"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":22,"losses":24,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":63,"wins":29},"meta/muse-glimmer-30b":{"draws":32,"losses":31,"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":16,"losses":23,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":21,"wins":0},"moonshotai/kimi-k3":{"draws":24,"losses":56,"wins":10},"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":25,"losses":42,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":31,"wins":6},"o3":{"draws":22,"losses":124,"wins":12},"openai/gpt-oss-120b":{"draws":26,"losses":37,"wins":19},"poolside/laguna-s-2.1":{"draws":26,"losses":42,"wins":18},"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":23,"losses":66,"wins":7},"qwen/qwen3.8-27b":{"draws":15,"losses":46,"wins":9},"qwen/qwen3.8-flash":{"draws":22,"losses":33,"wins":9},"qwen/qwen3.8-max":{"draws":27,"losses":68,"wins":1},"qwen/qwen3.8-max-0902":{"draws":26,"losses":68,"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":55,"losses":189,"wins":28},"stealth/space-bunny-alpha":{"draws":16,"losses":50,"wins":14},"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":18,"losses":21,"wins":13},"tencent/hy4-preview":{"draws":23,"losses":68,"wins":3},"thinkingmachines/inkling":{"draws":36,"losses":58,"wins":32},"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":17,"losses":76,"wins":3},"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":12,"losses":44,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":44,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":50,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":126,"wins":23},"z-ai/glm-5.3":{"draws":12,"losses":79,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":64,"wins":13},"z-ai/glm-5.3-flashx":{"draws":24,"losses":64,"wins":8}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":49,"wins":82},"claude-fable-5":{"draws":29,"losses":117,"wins":34},"claude-fable-5-1":{"draws":14,"losses":182,"wins":6},"claude-haiku-5-5":{"draws":39,"losses":77,"wins":58},"claude-opus-4-5":{"draws":81,"losses":100,"wins":113},"claude-opus-4-8":{"draws":36,"losses":81,"wins":51},"claude-opus-5":{"draws":36,"losses":238,"wins":30},"claude-opus-5-5":{"draws":10,"losses":178,"wins":8},"claude-sonnet-5":{"draws":49,"losses":54,"wins":77},"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":62,"wins":144},"deepseek/deepseek-v4-pro":{"draws":37,"losses":55,"wins":74},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":54,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":47,"losses":76,"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":46,"losses":71,"wins":63},"gemini-3.1-pro-preview":{"draws":35,"losses":61,"wins":84},"gemini-4-argon":{"draws":12,"losses":160,"wins":8},"google/gemini-3.1-flash-lite":{"draws":29,"losses":14,"wins":83},"google/gemini-3.5-flash":{"draws":28,"losses":70,"wins":70},"google/gemini-3.5-flash-lite":{"draws":75,"losses":81,"wins":162},"google/gemini-3.6-flash":{"draws":74,"losses":142,"wins":130},"google/gemini-3.8-flash":{"draws":29,"losses":108,"wins":43},"google/gemma-4-31b-it":{"draws":31,"losses":22,"wins":53},"gpt-4.1":{"draws":14,"losses":16,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":11},"gpt-5":{"draws":36,"losses":55,"wins":67},"gpt-5.4":{"draws":26,"losses":98,"wins":50},"gpt-5.4-mini":{"draws":35,"losses":31,"wins":54},"gpt-5.4-nano":{"draws":27,"losses":51,"wins":106},"gpt-5.5":{"draws":42,"losses":75,"wins":49},"gpt-5.6-luna":{"draws":50,"losses":51,"wins":79},"gpt-5.6-sol":{"draws":19,"losses":122,"wins":39},"gpt-5.6-terra":{"draws":49,"losses":68,"wins":55},"gpt-6-astra":{"draws":9,"losses":164,"wins":7},"gpt-6-luna":{"draws":49,"losses":61,"wins":70},"gpt-6-sol":{"draws":26,"losses":126,"wins":28},"gpt-6.1-sol":{"draws":11,"losses":150,"wins":19},"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":35,"losses":16,"wins":77},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":37,"losses":38,"wins":123},"meta/muse-glimmer-30b":{"draws":47,"losses":24,"wins":87},"meta/muse-spark-1.2":{"draws":37,"losses":80,"wins":55},"meta/muse-spark-1.3":{"draws":35,"losses":99,"wins":46},"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":27,"losses":15,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":16,"wins":19},"moonshotai/kimi-k3":{"draws":46,"losses":65,"wins":61},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":147,"wins":15},"nex-agi/nex-n2-pro":{"draws":20,"losses":19,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":35,"wins":83},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":35},"o3":{"draws":31,"losses":91,"wins":136},"openai/gpt-oss-120b":{"draws":43,"losses":36,"wins":77},"poolside/laguna-s-2.1":{"draws":32,"losses":33,"wins":105},"qwen/qwen3.7-max":{"draws":30,"losses":36,"wins":40},"qwen/qwen3.7-plus":{"draws":18,"losses":21,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":79,"wins":54},"qwen/qwen3.8-27b":{"draws":19,"losses":51,"wins":58},"qwen/qwen3.8-flash":{"draws":30,"losses":41,"wins":49},"qwen/qwen3.8-max":{"draws":54,"losses":66,"wins":60},"qwen/qwen3.8-max-0902":{"draws":45,"losses":87,"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":98,"losses":273,"wins":205},"stealth/space-bunny-alpha":{"draws":39,"losses":38,"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":35,"losses":87,"wins":52},"thinkingmachines/inkling":{"draws":54,"losses":47,"wins":139},"thinkingmachines/inkling-small":{"draws":46,"losses":34,"wins":100},"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":32,"losses":87,"wins":61},"x-ai/grok-4.6":{"draws":46,"losses":96,"wins":38},"x-ai/grok-4.7":{"draws":14,"losses":120,"wins":24},"x-ai/grok-build-0.1":{"draws":16,"losses":8,"wins":36},"xiaomi/mimo-v2.5":{"draws":81,"losses":50,"wins":153},"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":90,"losses":112,"wins":158},"z-ai/glm-5.3":{"draws":31,"losses":106,"wins":35},"z-ai/glm-5.3-flash":{"draws":22,"losses":97,"wins":61},"z-ai/glm-5.3-flashx":{"draws":36,"losses":94,"wins":50}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":76,"losses":86,"wins":72},"claude-fable-5":{"draws":39,"losses":185,"wins":28},"claude-fable-5-1":{"draws":14,"losses":268,"wins":2},"claude-haiku-5-5":{"draws":53,"losses":149,"wins":40},"claude-opus-4-5":{"draws":133,"losses":187,"wins":90},"claude-opus-4-8":{"draws":64,"losses":145,"wins":23},"claude-opus-5":{"draws":49,"losses":342,"wins":33},"claude-opus-5-5":{"draws":18,"losses":253,"wins":1},"claude-sonnet-5":{"draws":70,"losses":126,"wins":56},"claude-sonnet-5-5":{"draws":48,"losses":164,"wins":40},"cohere/north-mini-code":{"draws":32,"losses":31,"wins":35},"deepseek/deepseek-v4-flash":{"draws":116,"losses":124,"wins":134},"deepseek/deepseek-v4-pro":{"draws":59,"losses":106,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":73,"losses":112,"wins":47},"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":84,"losses":117,"wins":51},"gemini-3.1-pro-preview":{"draws":84,"losses":104,"wins":64},"gemini-4-argon":{"draws":14,"losses":227,"wins":11},"google/gemini-3.1-flash-lite":{"draws":47,"losses":34,"wins":93},"google/gemini-3.5-flash":{"draws":75,"losses":162,"wins":81},"google/gemini-3.5-flash-lite":{"draws":110,"losses":127,"wins":127},"google/gemini-3.6-flash":{"draws":131,"losses":257,"wins":98},"google/gemini-3.8-flash":{"draws":45,"losses":187,"wins":20},"google/gemma-4-31b-it":{"draws":55,"losses":35,"wins":58},"gpt-4.1":{"draws":28,"losses":28,"wins":28},"gpt-4.1-nano":{"draws":18,"losses":3,"wins":9},"gpt-5":{"draws":60,"losses":101,"wins":59},"gpt-5.4":{"draws":57,"losses":146,"wins":41},"gpt-5.4-mini":{"draws":59,"losses":58,"wins":51},"gpt-5.4-nano":{"draws":50,"losses":99,"wins":103},"gpt-5.5":{"draws":84,"losses":112,"wins":36},"gpt-5.6-luna":{"draws":82,"losses":95,"wins":75},"gpt-5.6-sol":{"draws":35,"losses":195,"wins":22},"gpt-5.6-terra":{"draws":72,"losses":120,"wins":48},"gpt-6-astra":{"draws":15,"losses":237,"wins":0},"gpt-6-luna":{"draws":76,"losses":116,"wins":60},"gpt-6-sol":{"draws":38,"losses":191,"wins":23},"gpt-6.1-sol":{"draws":16,"losses":234,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":75,"losses":39,"wins":66},"inception/mercury-3":{"draws":47,"losses":84,"wins":31},"inclusionai/ling-3.0-flash":{"draws":57,"losses":39,"wins":80},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":78,"losses":83,"wins":117},"meta/muse-glimmer-30b":{"draws":89,"losses":53,"wins":78},"meta/muse-spark-1.2":{"draws":61,"losses":134,"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":35,"losses":46,"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":47,"losses":36,"wins":65},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":32,"wins":14},"moonshotai/kimi-k3":{"draws":74,"losses":119,"wins":47},"moonshotai/kimi-k3.1-pro":{"draws":31,"losses":208,"wins":3},"nex-agi/nex-n2-pro":{"draws":29,"losses":38,"wins":61},"nex-agi/nex-n2.5-pro":{"draws":13,"losses":17,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":80,"losses":69,"wins":71},"nvidia/nemotron-3.5-super-vl":{"draws":36,"losses":55,"wins":25},"o3":{"draws":57,"losses":201,"wins":98},"openai/gpt-oss-120b":{"draws":69,"losses":74,"wins":75},"poolside/laguna-s-2.1":{"draws":71,"losses":101,"wins":66},"qwen/qwen3.7-max":{"draws":43,"losses":64,"wins":39},"qwen/qwen3.7-plus":{"draws":36,"losses":40,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":77,"losses":132,"wins":43},"qwen/qwen3.8-27b":{"draws":34,"losses":103,"wins":43},"qwen/qwen3.8-flash":{"draws":56,"losses":81,"wins":31},"qwen/qwen3.8-max":{"draws":79,"losses":126,"wins":47},"qwen/qwen3.8-max-0902":{"draws":67,"losses":147,"wins":38},"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":177,"losses":481,"wins":168},"stealth/space-bunny-alpha":{"draws":53,"losses":89,"wins":60},"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":50,"losses":58,"wins":28},"tencent/hy4-preview":{"draws":64,"losses":132,"wins":48},"thinkingmachines/inkling":{"draws":93,"losses":116,"wins":129},"thinkingmachines/inkling-small":{"draws":81,"losses":73,"wins":98},"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":62,"losses":144,"wins":46},"x-ai/grok-4.6":{"draws":62,"losses":158,"wins":32},"x-ai/grok-4.7":{"draws":20,"losses":170,"wins":28},"x-ai/grok-build-0.1":{"draws":33,"losses":25,"wins":26},"xiaomi/mimo-v2.5":{"draws":126,"losses":130,"wins":136},"xiaomi/mimo-v2.5-pro":{"draws":41,"losses":49,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":29,"losses":107,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":118,"wins":29},"z-ai/glm-5.2":{"draws":160,"losses":201,"wins":143},"z-ai/glm-5.3":{"draws":40,"losses":185,"wins":17},"z-ai/glm-5.3-flash":{"draws":46,"losses":158,"wins":48},"z-ai/glm-5.3-flashx":{"draws":63,"losses":142,"wins":47}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":60,"losses":57,"wins":137},"claude-fable-5":{"draws":40,"losses":152,"wins":84},"claude-fable-5-1":{"draws":19,"losses":276,"wins":17},"claude-haiku-5-5":{"draws":65,"losses":100,"wins":99},"claude-opus-4-5":{"draws":128,"losses":117,"wins":203},"claude-opus-4-8":{"draws":58,"losses":90,"wins":104},"claude-opus-5":{"draws":57,"losses":322,"wins":89},"claude-opus-5-5":{"draws":21,"losses":251,"wins":24},"claude-sonnet-5":{"draws":67,"losses":84,"wins":125},"claude-sonnet-5-5":{"draws":50,"losses":129,"wins":97},"cohere/north-mini-code":{"draws":20,"losses":8,"wins":76},"deepseek/deepseek-v4-flash":{"draws":98,"losses":59,"wins":255},"deepseek/deepseek-v4-pro":{"draws":64,"losses":81,"wins":109},"deepseek/deepseek-v4-pro-0813":{"draws":57,"losses":77,"wins":120},"deepseek/deepseek-v4.1-flash":{"draws":75,"losses":86,"wins":115},"deepseek/deepseek-v4.1-flash-1017":{"draws":42,"losses":133,"wins":101},"elorian/glimpse":{"draws":30,"losses":58,"wins":62},"fireworks/ember-1":{"draws":74,"losses":103,"wins":99},"gemini-3.1-pro-preview":{"draws":67,"losses":86,"wins":123},"gemini-4-argon":{"draws":18,"losses":226,"wins":32},"google/gemini-3.1-flash-lite":{"draws":42,"losses":15,"wins":129},"google/gemini-3.5-flash":{"draws":74,"losses":130,"wins":142},"google/gemini-3.5-flash-lite":{"draws":131,"losses":98,"wins":257},"google/gemini-3.6-flash":{"draws":92,"losses":174,"wins":174},"google/gemini-3.8-flash":{"draws":57,"losses":138,"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":49,"losses":79,"wins":114},"gpt-5.4":{"draws":55,"losses":114,"wins":97},"gpt-5.4-mini":{"draws":55,"losses":31,"wins":98},"gpt-5.4-nano":{"draws":50,"losses":59,"wins":165},"gpt-5.5":{"draws":68,"losses":100,"wins":86},"gpt-5.6-luna":{"draws":82,"losses":58,"wins":136},"gpt-5.6-sol":{"draws":38,"losses":164,"wins":74},"gpt-5.6-terra":{"draws":78,"losses":66,"wins":120},"gpt-6-astra":{"draws":21,"losses":238,"wins":17},"gpt-6-luna":{"draws":79,"losses":73,"wins":124},"gpt-6-sol":{"draws":34,"losses":183,"wins":59},"gpt-6.1-sol":{"draws":17,"losses":234,"wins":25},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":67,"losses":12,"wins":115},"inception/mercury-3":{"draws":45,"losses":48,"wins":87},"inclusionai/ling-3.0-flash":{"draws":62,"losses":22,"wins":110},"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":77,"losses":35,"wins":130},"meta/muse-spark-1.2":{"draws":54,"losses":105,"wins":105},"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":51,"losses":16,"wins":93},"moonshotai/kimi-k2.7-code":{"draws":20,"losses":15,"wins":33},"moonshotai/kimi-k3":{"draws":68,"losses":90,"wins":106},"moonshotai/kimi-k3.1-pro":{"draws":29,"losses":203,"wins":33},"nex-agi/nex-n2-pro":{"draws":25,"losses":19,"wins":94},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":14,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":72,"losses":36,"wins":130},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":31,"wins":62},"o3":{"draws":50,"losses":127,"wins":207},"openai/gpt-oss-120b":{"draws":72,"losses":33,"wins":135},"poolside/laguna-s-2.1":{"draws":70,"losses":54,"wins":138},"qwen/qwen3.7-max":{"draws":45,"losses":38,"wins":77},"qwen/qwen3.7-plus":{"draws":38,"losses":22,"wins":78},"qwen/qwen3.8-2.4t-a95b":{"draws":66,"losses":95,"wins":115},"qwen/qwen3.8-27b":{"draws":40,"losses":66,"wins":92},"qwen/qwen3.8-flash":{"draws":55,"losses":47,"wins":82},"qwen/qwen3.8-max":{"draws":64,"losses":94,"wins":118},"qwen/qwen3.8-max-0902":{"draws":73,"losses":106,"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":184,"losses":364,"wins":368},"stealth/space-bunny-alpha":{"draws":55,"losses":51,"wins":114},"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":45,"losses":30,"wins":73},"tencent/hy4-preview":{"draws":61,"losses":100,"wins":105},"thinkingmachines/inkling":{"draws":103,"losses":54,"wins":215},"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":58,"losses":114,"wins":104},"x-ai/grok-4.6":{"draws":70,"losses":124,"wins":82},"x-ai/grok-4.7":{"draws":15,"losses":168,"wins":57},"x-ai/grok-build-0.1":{"draws":31,"losses":6,"wins":55},"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":146,"losses":151,"wins":255},"z-ai/glm-5.3":{"draws":51,"losses":152,"wins":61},"z-ai/glm-5.3-flash":{"draws":41,"losses":143,"wins":92},"z-ai/glm-5.3-flashx":{"draws":68,"losses":112,"wins":96}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":83},"claude-fable-5":{"draws":21,"losses":67,"wins":56},"claude-fable-5-1":{"draws":9,"losses":139,"wins":14},"claude-haiku-5-5":{"draws":33,"losses":43,"wins":62},"claude-opus-4-5":{"draws":68,"losses":47,"wins":119},"claude-opus-4-8":{"draws":29,"losses":42,"wins":61},"claude-opus-5":{"draws":25,"losses":168,"wins":53},"claude-opus-5-5":{"draws":14,"losses":122,"wins":20},"claude-sonnet-5":{"draws":32,"losses":35,"wins":77},"claude-sonnet-5-5":{"draws":20,"losses":67,"wins":57},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":40},"deepseek/deepseek-v4-flash":{"draws":40,"losses":21,"wins":155},"deepseek/deepseek-v4-pro":{"draws":25,"losses":33,"wins":74},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":34,"wins":70},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":45,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":71,"wins":47},"elorian/glimpse":{"draws":13,"losses":30,"wins":35},"fireworks/ember-1":{"draws":33,"losses":48,"wins":63},"gemini-3.1-pro-preview":{"draws":26,"losses":34,"wins":84},"gemini-4-argon":{"draws":15,"losses":108,"wins":21},"google/gemini-3.1-flash-lite":{"draws":22,"losses":2,"wins":72},"google/gemini-3.5-flash":{"draws":29,"losses":43,"wins":108},"google/gemini-3.5-flash-lite":{"draws":45,"losses":20,"wins":187},"google/gemini-3.6-flash":{"draws":57,"losses":81,"wins":138},"google/gemini-3.8-flash":{"draws":20,"losses":38,"wins":38},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":52},"gpt-4.1":{"draws":14,"losses":8,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":23,"losses":31,"wins":72},"gpt-5.4":{"draws":24,"losses":51,"wins":63},"gpt-5.4-mini":{"draws":21,"losses":12,"wins":63},"gpt-5.4-nano":{"draws":25,"losses":24,"wins":95},"gpt-5.5":{"draws":41,"losses":47,"wins":44},"gpt-5.6-luna":{"draws":31,"losses":26,"wins":87},"gpt-5.6-sol":{"draws":19,"losses":75,"wins":50},"gpt-5.6-terra":{"draws":35,"losses":41,"wins":62},"gpt-6-astra":{"draws":14,"losses":119,"wins":11},"gpt-6-luna":{"draws":40,"losses":34,"wins":70},"gpt-6-sol":{"draws":22,"losses":91,"wins":31},"gpt-6.1-sol":{"draws":18,"losses":109,"wins":17},"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":26,"losses":2,"wins":74},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":112},"meta/muse-glimmer-30b":{"draws":29,"losses":15,"wins":82},"meta/muse-spark-1.2":{"draws":24,"losses":55,"wins":59},"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":7,"wins":57},"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":17,"losses":6,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":17,"wins":14},"moonshotai/kimi-k3":{"draws":31,"losses":35,"wins":72},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":22},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":9,"wins":84},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":38},"o3":{"draws":20,"losses":45,"wins":133},"openai/gpt-oss-120b":{"draws":26,"losses":8,"wins":92},"poolside/laguna-s-2.1":{"draws":22,"losses":17,"wins":99},"qwen/qwen3.7-max":{"draws":24,"losses":20,"wins":40},"qwen/qwen3.7-plus":{"draws":15,"losses":7,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":45,"wins":69},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":64},"qwen/qwen3.8-flash":{"draws":18,"losses":28,"wins":50},"qwen/qwen3.8-max":{"draws":33,"losses":49,"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":93,"losses":155,"wins":226},"stealth/space-bunny-alpha":{"draws":23,"losses":19,"wins":72},"stepfun/step-3.7-flash":{"draws":16,"losses":9,"wins":77},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":31,"losses":8,"wins":39},"tencent/hy4-preview":{"draws":29,"losses":54,"wins":55},"thinkingmachines/inkling":{"draws":48,"losses":19,"wins":125},"thinkingmachines/inkling-small":{"draws":35,"losses":19,"wins":90},"unbiased/pareto-26.10":{"draws":4,"losses":39,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":24,"losses":69,"wins":51},"x-ai/grok-4.6":{"draws":40,"losses":51,"wins":53},"x-ai/grok-4.7":{"draws":12,"losses":89,"wins":25},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5":{"draws":58,"losses":20,"wins":144},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":13,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":29,"wins":41},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":46,"wins":30},"z-ai/glm-5.2":{"draws":68,"losses":60,"wins":160},"z-ai/glm-5.3":{"draws":28,"losses":71,"wins":39},"z-ai/glm-5.3-flash":{"draws":18,"losses":55,"wins":71},"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":7,"losses":29,"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":28,"losses":33,"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":3,"losses":47,"wins":2},"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":11,"losses":21,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"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":30,"wins":16},"google/gemini-3.5-flash-lite":{"draws":28,"losses":28,"wins":28},"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":18,"losses":13,"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":12,"losses":5,"wins":11},"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":11,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":24,"wins":8},"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":18,"losses":16,"wins":14},"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":79,"wins":38},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":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":15,"wins":18},"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":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":5,"losses":28,"wins":15},"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":34,"losses":39,"wins":43},"claude-fable-5":{"draws":20,"losses":85,"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":63,"losses":75,"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":8,"losses":125,"wins":5},"claude-sonnet-5":{"draws":37,"losses":53,"wins":36},"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":55,"losses":42,"wins":93},"deepseek/deepseek-v4-pro":{"draws":28,"losses":52,"wins":38},"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":31,"losses":60,"wins":35},"gemini-3.1-pro-preview":{"draws":40,"losses":51,"wins":35},"gemini-4-argon":{"draws":4,"losses":113,"wins":9},"google/gemini-3.1-flash-lite":{"draws":23,"losses":5,"wins":56},"google/gemini-3.5-flash":{"draws":36,"losses":67,"wins":55},"google/gemini-3.5-flash-lite":{"draws":60,"losses":59,"wins":101},"google/gemini-3.6-flash":{"draws":49,"losses":114,"wins":79},"google/gemini-3.8-flash":{"draws":23,"losses":72,"wins":31},"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":23,"losses":28,"wins":33},"gpt-5.4-nano":{"draws":16,"losses":44,"wins":68},"gpt-5.5":{"draws":39,"losses":52,"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":28,"losses":52,"wins":40},"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":29,"losses":20,"wins":39},"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":36,"losses":24,"wins":54},"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":21,"losses":15,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":29,"losses":50,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":102,"wins":9},"nex-agi/nex-n2-pro":{"draws":12,"losses":20,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":19,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":22,"wins":23},"o3":{"draws":23,"losses":68,"wins":89},"openai/gpt-oss-120b":{"draws":35,"losses":21,"wins":56},"poolside/laguna-s-2.1":{"draws":32,"losses":39,"wins":55},"qwen/qwen3.7-max":{"draws":27,"losses":18,"wins":29},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":55,"wins":35},"qwen/qwen3.8-27b":{"draws":17,"losses":41,"wins":30},"qwen/qwen3.8-flash":{"draws":16,"losses":36,"wins":32},"qwen/qwen3.8-max":{"draws":35,"losses":62,"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":90,"losses":201,"wins":133},"stealth/space-bunny-alpha":{"draws":20,"losses":39,"wins":41},"stepfun/step-3.7-flash":{"draws":21,"losses":18,"wins":53},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":27,"wins":21},"tencent/hy4-preview":{"draws":32,"losses":50,"wins":40},"thinkingmachines/inkling":{"draws":38,"losses":39,"wins":95},"thinkingmachines/inkling-small":{"draws":42,"losses":22,"wins":62},"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":34,"losses":73,"wins":19},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":18},"x-ai/grok-build-0.1":{"draws":13,"losses":9,"wins":20},"xiaomi/mimo-v2.5":{"draws":56,"losses":39,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":21,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":41,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":22},"z-ai/glm-5.2":{"draws":74,"losses":75,"wins":103},"z-ai/glm-5.3":{"draws":16,"losses":82,"wins":22},"z-ai/glm-5.3-flash":{"draws":18,"losses":73,"wins":35},"z-ai/glm-5.3-flashx":{"draws":32,"losses":62,"wins":32}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":28,"wins":71},"claude-fable-5":{"draws":31,"losses":67,"wins":40},"claude-fable-5-1":{"draws":8,"losses":132,"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":29,"losses":42,"wins":55},"claude-opus-5":{"draws":31,"losses":167,"wins":36},"claude-opus-5-5":{"draws":9,"losses":128,"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":32,"losses":39,"wins":67},"gemini-4-argon":{"draws":13,"losses":103,"wins":22},"google/gemini-3.1-flash-lite":{"draws":18,"losses":8,"wins":68},"google/gemini-3.5-flash":{"draws":26,"losses":50,"wins":98},"google/gemini-3.5-flash-lite":{"draws":57,"losses":41,"wins":146},"google/gemini-3.6-flash":{"draws":55,"losses":97,"wins":114},"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":22,"losses":13,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":25,"losses":38,"wins":69},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":99,"wins":21},"nex-agi/nex-n2-pro":{"draws":16,"losses":16,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":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":48,"wins":58},"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":32,"losses":31,"wins":25},"claude-fable-5":{"draws":20,"losses":65,"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":58,"losses":65,"wins":33},"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":54,"losses":40,"wins":50},"deepseek/deepseek-v4-pro":{"draws":28,"losses":34,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":40,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":40,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":64,"wins":9},"elorian/glimpse":{"draws":15,"losses":24,"wins":13},"fireworks/ember-1":{"draws":37,"losses":45,"wins":14},"gemini-3.1-pro-preview":{"draws":33,"losses":37,"wins":26},"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":35,"losses":54,"wins":31},"google/gemini-3.5-flash-lite":{"draws":59,"losses":51,"wins":58},"google/gemini-3.6-flash":{"draws":55,"losses":98,"wins":31},"google/gemini-3.8-flash":{"draws":21,"losses":63,"wins":12},"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":23,"losses":33,"wins":28},"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":43,"wins":27},"gpt-5.5":{"draws":39,"losses":34,"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":42,"losses":40,"wins":14},"gpt-6-sol":{"draws":13,"losses":72,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":88,"wins":5},"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":26,"losses":16,"wins":26},"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":22,"losses":10,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":29,"losses":42,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":81,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":13,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":25,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":24,"wins":6},"o3":{"draws":23,"losses":74,"wins":35},"openai/gpt-oss-120b":{"draws":32,"losses":21,"wins":31},"poolside/laguna-s-2.1":{"draws":34,"losses":26,"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":31,"losses":52,"wins":13},"qwen/qwen3.8-27b":{"draws":17,"losses":34,"wins":17},"qwen/qwen3.8-flash":{"draws":21,"losses":29,"wins":14},"qwen/qwen3.8-max":{"draws":36,"losses":40,"wins":20},"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":88,"losses":168,"wins":60},"stealth/space-bunny-alpha":{"draws":23,"losses":36,"wins":17},"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":47,"losses":37,"wins":44},"thinkingmachines/inkling-small":{"draws":41,"losses":25,"wins":30},"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":31,"losses":51,"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":11,"losses":18,"wins":23},"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":81,"losses":74,"wins":37},"z-ai/glm-5.3":{"draws":21,"losses":62,"wins":9},"z-ai/glm-5.3-flash":{"draws":21,"losses":54,"wins":21},"z-ai/glm-5.3-flashx":{"draws":26,"losses":57,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":56,"wins":48},"claude-fable-5":{"draws":16,"losses":114,"wins":14},"claude-fable-5-1":{"draws":2,"losses":152,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":76,"wins":39},"claude-opus-4-5":{"draws":63,"losses":111,"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":49,"losses":83,"wins":94},"deepseek/deepseek-v4-pro":{"draws":15,"losses":67,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":64,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":71,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":96,"wins":27},"elorian/glimpse":{"draws":13,"losses":39,"wins":22},"fireworks/ember-1":{"draws":33,"losses":80,"wins":31},"gemini-3.1-pro-preview":{"draws":32,"losses":71,"wins":41},"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":27,"losses":106,"wins":51},"google/gemini-3.5-flash-lite":{"draws":50,"losses":103,"wins":99},"google/gemini-3.6-flash":{"draws":50,"losses":165,"wins":59},"google/gemini-3.8-flash":{"draws":25,"losses":95,"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":16,"losses":68,"wins":44},"gpt-5.4":{"draws":15,"losses":91,"wins":32},"gpt-5.4-mini":{"draws":26,"losses":27,"wins":43},"gpt-5.4-nano":{"draws":16,"losses":52,"wins":52},"gpt-5.5":{"draws":29,"losses":69,"wins":32},"gpt-5.6-luna":{"draws":34,"losses":61,"wins":49},"gpt-5.6-sol":{"draws":10,"losses":117,"wins":17},"gpt-5.6-terra":{"draws":25,"losses":73,"wins":38},"gpt-6-astra":{"draws":3,"losses":139,"wins":2},"gpt-6-luna":{"draws":29,"losses":71,"wins":44},"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":24,"losses":30,"wins":50},"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":29,"losses":40,"wins":53},"meta/muse-spark-1.2":{"draws":23,"losses":69,"wins":44},"meta/muse-spark-1.3":{"draws":23,"losses":92,"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":16,"losses":17,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":17,"wins":13},"moonshotai/kimi-k3":{"draws":32,"losses":70,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":127,"wins":4},"nex-agi/nex-n2-pro":{"draws":12,"losses":25,"wins":35},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":14,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":46,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":29,"wins":24},"o3":{"draws":17,"losses":106,"wins":103},"openai/gpt-oss-120b":{"draws":35,"losses":47,"wins":44},"poolside/laguna-s-2.1":{"draws":31,"losses":54,"wins":59},"qwen/qwen3.7-max":{"draws":24,"losses":38,"wins":30},"qwen/qwen3.7-plus":{"draws":17,"losses":32,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":84,"wins":26},"qwen/qwen3.8-27b":{"draws":19,"losses":51,"wins":34},"qwen/qwen3.8-flash":{"draws":20,"losses":50,"wins":26},"qwen/qwen3.8-max":{"draws":32,"losses":75,"wins":37},"qwen/qwen3.8-max-0902":{"draws":36,"losses":73,"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":73,"losses":229,"wins":122},"stealth/space-bunny-alpha":{"draws":23,"losses":50,"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":21,"losses":89,"wins":28},"thinkingmachines/inkling":{"draws":41,"losses":70,"wins":77},"thinkingmachines/inkling-small":{"draws":44,"losses":40,"wins":60},"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":23,"losses":96,"wins":25},"x-ai/grok-4.7":{"draws":15,"losses":106,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":26},"xiaomi/mimo-v2.5":{"draws":54,"losses":74,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":37,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":52,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":66,"wins":17},"z-ai/glm-5.2":{"draws":63,"losses":127,"wins":98},"z-ai/glm-5.3":{"draws":19,"losses":96,"wins":21},"z-ai/glm-5.3-flash":{"draws":20,"losses":84,"wins":40},"z-ai/glm-5.3-flashx":{"draws":28,"losses":81,"wins":35}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":44,"losses":24,"wins":54},"claude-fable-5":{"draws":30,"losses":64,"wins":38},"claude-fable-5-1":{"draws":4,"losses":128,"wins":18},"claude-haiku-5-5":{"draws":46,"losses":45,"wins":35},"claude-opus-4-5":{"draws":88,"losses":47,"wins":79},"claude-opus-4-8":{"draws":37,"losses":35,"wins":48},"claude-opus-5":{"draws":29,"losses":157,"wins":46},"claude-opus-5-5":{"draws":13,"losses":116,"wins":15},"claude-sonnet-5":{"draws":48,"losses":27,"wins":57},"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":64,"losses":21,"wins":111},"deepseek/deepseek-v4-pro":{"draws":37,"losses":27,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":39,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":46,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":39,"losses":50,"wins":43},"elorian/glimpse":{"draws":17,"losses":24,"wins":33},"fireworks/ember-1":{"draws":38,"losses":44,"wins":50},"gemini-3.1-pro-preview":{"draws":34,"losses":34,"wins":64},"gemini-4-argon":{"draws":9,"losses":100,"wins":23},"google/gemini-3.1-flash-lite":{"draws":25,"losses":4,"wins":59},"google/gemini-3.5-flash":{"draws":42,"losses":49,"wins":75},"google/gemini-3.5-flash-lite":{"draws":84,"losses":36,"wins":112},"google/gemini-3.6-flash":{"draws":68,"losses":86,"wins":100},"google/gemini-3.8-flash":{"draws":41,"losses":44,"wins":47},"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":39,"losses":27,"wins":52},"gpt-5.4":{"draws":34,"losses":49,"wins":45},"gpt-5.4-mini":{"draws":39,"losses":15,"wins":34},"gpt-5.4-nano":{"draws":29,"losses":32,"wins":69},"gpt-5.5":{"draws":32,"losses":24,"wins":24},"gpt-5.6-luna":{"draws":48,"losses":23,"wins":61},"gpt-5.6-sol":{"draws":24,"losses":64,"wins":44},"gpt-5.6-terra":{"draws":47,"losses":29,"wins":50},"gpt-6-astra":{"draws":5,"losses":117,"wins":10},"gpt-6-luna":{"draws":48,"losses":30,"wins":54},"gpt-6-sol":{"draws":19,"losses":83,"wins":30},"gpt-6.1-sol":{"draws":7,"losses":103,"wins":22},"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":38,"losses":9,"wins":45},"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":46,"losses":16,"wins":58},"meta/muse-spark-1.2":{"draws":25,"losses":45,"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":24,"losses":9,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":12},"moonshotai/kimi-k3":{"draws":35,"losses":46,"wins":47},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":93,"wins":23},"nex-agi/nex-n2-pro":{"draws":17,"losses":6,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":10,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":10,"wins":29},"o3":{"draws":35,"losses":44,"wins":105},"openai/gpt-oss-120b":{"draws":44,"losses":16,"wins":56},"poolside/laguna-s-2.1":{"draws":44,"losses":24,"wins":60},"qwen/qwen3.7-max":{"draws":26,"losses":14,"wins":36},"qwen/qwen3.7-plus":{"draws":24,"losses":6,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":46,"wins":47},"qwen/qwen3.8-27b":{"draws":26,"losses":28,"wins":38},"qwen/qwen3.8-flash":{"draws":31,"losses":20,"wins":37},"qwen/qwen3.8-max":{"draws":43,"losses":40,"wins":49},"qwen/qwen3.8-max-0902":{"draws":46,"losses":42,"wins":44},"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":117,"losses":165,"wins":160},"stealth/space-bunny-alpha":{"draws":38,"losses":21,"wins":47},"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":41,"losses":45,"wins":42},"thinkingmachines/inkling":{"draws":55,"losses":27,"wins":98},"thinkingmachines/inkling-small":{"draws":45,"losses":20,"wins":67},"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":54,"wins":43},"x-ai/grok-4.6":{"draws":39,"losses":55,"wins":38},"x-ai/grok-4.7":{"draws":10,"losses":69,"wins":37},"x-ai/grok-build-0.1":{"draws":21,"losses":7,"wins":16},"xiaomi/mimo-v2.5":{"draws":83,"losses":20,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":15,"wins":37},"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":97,"losses":49,"wins":118},"z-ai/glm-5.3":{"draws":28,"losses":75,"wins":23},"z-ai/glm-5.3-flash":{"draws":24,"losses":58,"wins":50},"z-ai/glm-5.3-flashx":{"draws":40,"losses":48,"wins":44}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":47,"wins":42},"claude-fable-5":{"draws":29,"losses":97,"wins":18},"claude-fable-5-1":{"draws":9,"losses":147,"wins":6},"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":83,"losses":51,"wins":82},"deepseek/deepseek-v4-pro":{"draws":42,"losses":53,"wins":37},"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":44,"losses":55,"wins":45},"gemini-3.1-pro-preview":{"draws":40,"losses":56,"wins":48},"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":50,"losses":79,"wins":51},"google/gemini-3.5-flash-lite":{"draws":82,"losses":75,"wins":95},"google/gemini-3.6-flash":{"draws":82,"losses":136,"wins":58},"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":34,"losses":49,"wins":61},"gpt-5.5":{"draws":48,"losses":61,"wins":23},"gpt-5.6-luna":{"draws":40,"losses":28,"wins":28},"gpt-5.6-sol":{"draws":21,"losses":98,"wins":25},"gpt-5.6-terra":{"draws":46,"losses":51,"wins":41},"gpt-6-astra":{"draws":12,"losses":128,"wins":4},"gpt-6-luna":{"draws":48,"losses":57,"wins":39},"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":46,"losses":48,"wins":62},"meta/muse-glimmer-30b":{"draws":52,"losses":32,"wins":42},"meta/muse-spark-1.2":{"draws":37,"losses":65,"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":47,"losses":62,"wins":29},"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":90,"wins":68},"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":47,"losses":68,"wins":29},"qwen/qwen3.8-max-0902":{"draws":47,"losses":63,"wins":34},"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":33,"losses":45,"wins":36},"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":44,"losses":69,"wins":25},"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":38,"losses":78,"wins":28},"z-ai/glm-5.3-flashx":{"draws":42,"losses":73,"wins":29}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":13,"wins":97},"claude-fable-5":{"draws":18,"losses":65,"wins":61},"claude-fable-5-1":{"draws":13,"losses":131,"wins":18},"claude-haiku-5-5":{"draws":21,"losses":41,"wins":76},"claude-opus-4-5":{"draws":44,"losses":38,"wins":152},"claude-opus-4-8":{"draws":19,"losses":40,"wins":73},"claude-opus-5":{"draws":29,"losses":154,"wins":63},"claude-opus-5-5":{"draws":11,"losses":123,"wins":22},"claude-sonnet-5":{"draws":20,"losses":19,"wins":105},"claude-sonnet-5-5":{"draws":14,"losses":57,"wins":73},"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":28,"wins":88},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":27,"wins":89},"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":22,"losses":35,"wins":87},"gemini-3.1-pro-preview":{"draws":18,"losses":31,"wins":95},"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":19,"losses":39,"wins":122},"google/gemini-3.5-flash-lite":{"draws":35,"losses":22,"wins":195},"google/gemini-3.6-flash":{"draws":38,"losses":74,"wins":164},"google/gemini-3.8-flash":{"draws":19,"losses":50,"wins":75},"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":10,"losses":17,"wins":117},"gpt-5.5":{"draws":24,"losses":44,"wins":64},"gpt-5.6-luna":{"draws":21,"losses":25,"wins":98},"gpt-5.6-sol":{"draws":8,"losses":44,"wins":44},"gpt-5.6-terra":{"draws":26,"losses":25,"wins":87},"gpt-6-astra":{"draws":14,"losses":117,"wins":13},"gpt-6-luna":{"draws":27,"losses":25,"wins":92},"gpt-6-sol":{"draws":13,"losses":85,"wins":46},"gpt-6.1-sol":{"draws":12,"losses":109,"wins":23},"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":5,"wins":85},"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":18,"losses":33,"wins":87},"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":4,"losses":7,"wins":25},"moonshotai/kimi-k3":{"draws":23,"losses":31,"wins":84},"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":12,"losses":31,"wins":155},"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":21,"losses":37,"wins":86},"qwen/qwen3.8-27b":{"draws":15,"losses":17,"wins":70},"qwen/qwen3.8-flash":{"draws":16,"losses":18,"wins":62},"qwen/qwen3.8-max":{"draws":25,"losses":31,"wins":88},"qwen/qwen3.8-max-0902":{"draws":21,"losses":34,"wins":89},"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":68,"losses":113,"wins":293},"stealth/space-bunny-alpha":{"draws":19,"losses":14,"wins":81},"stepfun/step-3.7-flash":{"draws":11,"losses":6,"wins":85},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":56},"tencent/hy4-preview":{"draws":19,"losses":47,"wins":72},"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":41,"wins":84},"x-ai/grok-4.6":{"draws":28,"losses":58,"wins":58},"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":20,"wins":61},"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":22,"losses":54,"wins":62},"z-ai/glm-5.3-flash":{"draws":24,"losses":47,"wins":73},"z-ai/glm-5.3-flashx":{"draws":24,"losses":41,"wins":79}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":26,"wins":65},"claude-fable-5":{"draws":32,"losses":86,"wins":20},"claude-fable-5-1":{"draws":7,"losses":143,"wins":6},"claude-haiku-5-5":{"draws":39,"losses":56,"wins":37},"claude-opus-4-5":{"draws":79,"losses":77,"wins":68},"claude-opus-4-8":{"draws":32,"losses":58,"wins":36},"claude-opus-5":{"draws":26,"losses":185,"wins":23},"claude-opus-5-5":{"draws":8,"losses":138,"wins":4},"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":66,"losses":32,"wins":110},"deepseek/deepseek-v4-pro":{"draws":38,"losses":42,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":38,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":53,"losses":52,"wins":33},"deepseek/deepseek-v4.1-flash-1017":{"draws":33,"losses":80,"wins":25},"elorian/glimpse":{"draws":19,"losses":32,"wins":25},"fireworks/ember-1":{"draws":40,"losses":61,"wins":37},"gemini-3.1-pro-preview":{"draws":44,"losses":48,"wins":46},"gemini-4-argon":{"draws":14,"losses":116,"wins":8},"google/gemini-3.1-flash-lite":{"draws":30,"losses":6,"wins":54},"google/gemini-3.5-flash":{"draws":49,"losses":55,"wins":68},"google/gemini-3.5-flash-lite":{"draws":72,"losses":48,"wins":120},"google/gemini-3.6-flash":{"draws":78,"losses":120,"wins":66},"google/gemini-3.8-flash":{"draws":35,"losses":62,"wins":41},"google/gemma-4-31b-it":{"draws":32,"losses":9,"wins":39},"gpt-4.1":{"draws":18,"losses":15,"wins":13},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":28,"losses":40,"wins":52},"gpt-5.4":{"draws":33,"losses":61,"wins":38},"gpt-5.4-mini":{"draws":39,"losses":21,"wins":32},"gpt-5.4-nano":{"draws":25,"losses":38,"wins":73},"gpt-5.5":{"draws":47,"losses":50,"wins":29},"gpt-5.6-luna":{"draws":46,"losses":41,"wins":51},"gpt-5.6-sol":{"draws":26,"losses":87,"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":24,"losses":98,"wins":16},"gpt-6.1-sol":{"draws":9,"losses":122,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":42,"losses":7,"wins":49},"inception/mercury-3":{"draws":29,"losses":33,"wins":32},"inclusionai/ling-3.0-flash":{"draws":31,"losses":7,"wins":64},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":37,"wins":71},"meta/muse-glimmer-30b":{"draws":47,"losses":16,"wins":57},"meta/muse-spark-1.2":{"draws":38,"losses":55,"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":23,"losses":8,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":37,"losses":50,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":112,"wins":12},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":11,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":18,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":24,"losses":18,"wins":22},"o3":{"draws":33,"losses":67,"wins":86},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":66},"poolside/laguna-s-2.1":{"draws":46,"losses":17,"wins":67},"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":45,"losses":60,"wins":33},"qwen/qwen3.8-27b":{"draws":33,"losses":31,"wins":34},"qwen/qwen3.8-flash":{"draws":27,"losses":31,"wins":34},"qwen/qwen3.8-max":{"draws":52,"losses":45,"wins":41},"qwen/qwen3.8-max-0902":{"draws":47,"losses":57,"wins":34},"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":128,"losses":200,"wins":128},"stealth/space-bunny-alpha":{"draws":35,"losses":32,"wins":41},"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":42,"losses":53,"wins":37},"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":67,"wins":31},"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":6,"wins":23},"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":109,"losses":68,"wins":99},"z-ai/glm-5.3":{"draws":33,"losses":78,"wins":21},"z-ai/glm-5.3-flash":{"draws":30,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":39}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":118},"claude-fable-5":{"draws":10,"losses":23,"wins":111},"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":15,"losses":15,"wins":204},"claude-opus-4-8":{"draws":8,"losses":10,"wins":114},"claude-opus-5":{"draws":22,"losses":56,"wins":168},"claude-opus-5-5":{"draws":16,"losses":70,"wins":70},"claude-sonnet-5":{"draws":6,"losses":8,"wins":130},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":103},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":201},"deepseek/deepseek-v4-pro":{"draws":11,"losses":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":5,"wins":129},"gemini-3.1-pro-preview":{"draws":7,"losses":4,"wins":133},"gemini-4-argon":{"draws":17,"losses":40,"wins":87},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":94},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":164},"google/gemini-3.5-flash-lite":{"draws":15,"losses":0,"wins":237},"google/gemini-3.6-flash":{"draws":21,"losses":17,"wins":238},"google/gemini-3.8-flash":{"draws":14,"losses":11,"wins":119},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":80},"gpt-4.1":{"draws":3,"losses":0,"wins":45},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":1,"wins":116},"gpt-5.4":{"draws":6,"losses":18,"wins":114},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":90},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":139},"gpt-5.5":{"draws":5,"losses":10,"wins":117},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":128},"gpt-5.6-sol":{"draws":14,"losses":13,"wins":117},"gpt-5.6-terra":{"draws":12,"losses":4,"wins":122},"gpt-6-astra":{"draws":12,"losses":42,"wins":42},"gpt-6-luna":{"draws":13,"losses":10,"wins":121},"gpt-6-sol":{"draws":16,"losses":26,"wins":102},"gpt-6.1-sol":{"draws":17,"losses":52,"wins":75},"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":10,"losses":10,"wins":118},"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":0,"wins":78},"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":3,"wins":128},"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":10,"losses":5,"wins":123},"thinkingmachines/inkling":{"draws":11,"losses":2,"wins":179},"thinkingmachines/inkling-small":{"draws":9,"losses":0,"wins":135},"unbiased/pareto-26.10":{"draws":8,"losses":18,"wins":22},"unbiased/pareto-26.10-preview":{"draws":6,"losses":20,"wins":22},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":120},"x-ai/grok-4.6":{"draws":11,"losses":13,"wins":120},"x-ai/grok-4.7":{"draws":11,"losses":22,"wins":93},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":44},"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":20,"losses":10,"wins":258},"z-ai/glm-5.3":{"draws":18,"losses":11,"wins":109},"z-ai/glm-5.3-flash":{"draws":12,"losses":8,"wins":124},"z-ai/glm-5.3-flashx":{"draws":14,"losses":8,"wins":122}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":39,"wins":53},"claude-fable-5":{"draws":29,"losses":88,"wins":27},"claude-fable-5-1":{"draws":13,"losses":143,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":63,"wins":39},"claude-opus-4-5":{"draws":77,"losses":80,"wins":77},"claude-opus-4-8":{"draws":32,"losses":62,"wins":38},"claude-opus-5":{"draws":43,"losses":177,"wins":26},"claude-opus-5-5":{"draws":13,"losses":139,"wins":4},"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":64,"losses":46,"wins":106},"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":34,"losses":63,"wins":47},"gemini-4-argon":{"draws":10,"losses":126,"wins":8},"google/gemini-3.1-flash-lite":{"draws":27,"losses":10,"wins":59},"google/gemini-3.5-flash":{"draws":49,"losses":70,"wins":61},"google/gemini-3.5-flash-lite":{"draws":76,"losses":60,"wins":116},"google/gemini-3.6-flash":{"draws":79,"losses":124,"wins":73},"google/gemini-3.8-flash":{"draws":40,"losses":70,"wins":34},"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":42,"losses":14,"wins":40},"gpt-5.4-nano":{"draws":29,"losses":44,"wins":71},"gpt-5.5":{"draws":48,"losses":54,"wins":30},"gpt-5.6-luna":{"draws":48,"losses":39,"wins":57},"gpt-5.6-sol":{"draws":27,"losses":92,"wins":25},"gpt-5.6-terra":{"draws":40,"losses":42,"wins":56},"gpt-6-astra":{"draws":13,"losses":121,"wins":10},"gpt-6-luna":{"draws":24,"losses":36,"wins":36},"gpt-6-sol":{"draws":22,"losses":103,"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":8,"wins":53},"inception/mercury-3":{"draws":26,"losses":31,"wins":39},"inclusionai/ling-3.0-flash":{"draws":33,"losses":15,"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":22,"losses":15,"wins":41},"minimax/minimax-m3.1-flash":{"draws":26,"losses":44,"wins":56},"mistralai/mistral-large-4-0":{"draws":27,"losses":31,"wins":32},"mistralai/mistral-medium-3-5":{"draws":30,"losses":7,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":10,"wins":13},"moonshotai/kimi-k3":{"draws":43,"losses":52,"wins":43},"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":26,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":33,"losses":65,"wins":100},"openai/gpt-oss-120b":{"draws":41,"losses":26,"wins":59},"poolside/laguna-s-2.1":{"draws":41,"losses":39,"wins":58},"qwen/qwen3.7-max":{"draws":21,"losses":27,"wins":36},"qwen/qwen3.7-plus":{"draws":25,"losses":12,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":59,"wins":48},"qwen/qwen3.8-27b":{"draws":24,"losses":37,"wins":41},"qwen/qwen3.8-flash":{"draws":28,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":37,"losses":58,"wins":49},"qwen/qwen3.8-max-0902":{"draws":39,"losses":57,"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":110,"losses":209,"wins":155},"stealth/space-bunny-alpha":{"draws":37,"losses":26,"wins":51},"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":61,"wins":37},"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":33,"losses":65,"wins":46},"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":28,"wins":115},"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":72,"wins":114},"z-ai/glm-5.3":{"draws":25,"losses":84,"wins":29},"z-ai/glm-5.3-flash":{"draws":39,"losses":71,"wins":34},"z-ai/glm-5.3-flashx":{"draws":31,"losses":70,"wins":43}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":14,"wins":103},"claude-fable-5":{"draws":20,"losses":42,"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":119,"wins":94},"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":30,"wins":90},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":40,"wins":89},"elorian/glimpse":{"draws":10,"losses":15,"wins":53},"fireworks/ember-1":{"draws":20,"losses":23,"wins":101},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":102},"gemini-4-argon":{"draws":14,"losses":72,"wins":58},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":80},"google/gemini-3.5-flash":{"draws":26,"losses":28,"wins":126},"google/gemini-3.5-flash-lite":{"draws":38,"losses":23,"wins":191},"google/gemini-3.6-flash":{"draws":34,"losses":59,"wins":183},"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":24,"losses":16,"wins":98},"gpt-6-astra":{"draws":16,"losses":102,"wins":26},"gpt-6-luna":{"draws":22,"losses":19,"wins":103},"gpt-6-sol":{"draws":12,"losses":42,"wins":42},"gpt-6.1-sol":{"draws":15,"losses":91,"wins":38},"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":60,"losses":73,"wins":341},"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":42,"losses":34,"wins":212},"z-ai/glm-5.3":{"draws":20,"losses":45,"wins":73},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":17,"losses":41,"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":9,"losses":77,"wins":76},"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":75,"wins":138},"claude-opus-5-5":{"draws":19,"losses":75,"wins":62},"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":7,"losses":3,"wins":122},"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":10,"losses":18,"wins":116},"gemini-3.1-pro-preview":{"draws":3,"losses":12,"wins":129},"gemini-4-argon":{"draws":19,"losses":46,"wins":79},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":93},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":150},"google/gemini-3.5-flash-lite":{"draws":16,"losses":2,"wins":234},"google/gemini-3.6-flash":{"draws":17,"losses":25,"wins":234},"google/gemini-3.8-flash":{"draws":18,"losses":17,"wins":109},"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":3,"losses":5,"wins":88},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":134},"gpt-5.5":{"draws":7,"losses":22,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":109},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":122},"gpt-6-astra":{"draws":17,"losses":75,"wins":52},"gpt-6-luna":{"draws":13,"losses":6,"wins":125},"gpt-6-sol":{"draws":15,"losses":38,"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":6,"losses":2,"wins":76},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":20,"wins":114},"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":7,"wins":127},"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":41,"losses":33,"wins":400},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":100},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":99},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":68},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":119},"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":17,"losses":13,"wins":114},"x-ai/grok-4.7":{"draws":6,"losses":41,"wins":79},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":48},"xiaomi/mimo-v2.5":{"draws":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":22,"losses":24,"wins":92},"z-ai/glm-5.3-flash":{"draws":12,"losses":16,"wins":116},"z-ai/glm-5.3-flashx":{"draws":16,"losses":19,"wins":109}},"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":33,"wins":23},"claude-fable-5":{"draws":26,"losses":71,"wins":5},"claude-fable-5-1":{"draws":8,"losses":106,"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":33,"losses":56,"wins":9},"claude-opus-5":{"draws":31,"losses":128,"wins":7},"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":35,"losses":46,"wins":9},"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":40,"losses":55,"wins":7},"gemini-3.1-pro-preview":{"draws":38,"losses":41,"wins":23},"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":75,"losses":66,"wins":39},"google/gemini-3.6-flash":{"draws":67,"losses":115,"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":53,"wins":8},"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":20,"wins":17},"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":52,"wins":7},"qwen/qwen3.8-max-0902":{"draws":43,"losses":50,"wins":9},"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":31,"losses":37,"wins":14},"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":36,"losses":42,"wins":16},"claude-fable-5":{"draws":17,"losses":81,"wins":4},"claude-fable-5-1":{"draws":6,"losses":108,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":61,"wins":5},"claude-opus-4-5":{"draws":59,"losses":89,"wins":18},"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":34,"losses":60,"wins":8},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":7},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":13},"deepseek/deepseek-v4-flash":{"draws":59,"losses":56,"wins":43},"deepseek/deepseek-v4-pro":{"draws":32,"losses":42,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":44,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":50,"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":31,"losses":53,"wins":18},"gemini-4-argon":{"draws":7,"losses":91,"wins":4},"google/gemini-3.1-flash-lite":{"draws":22,"losses":20,"wins":24},"google/gemini-3.5-flash":{"draws":35,"losses":77,"wins":16},"google/gemini-3.5-flash-lite":{"draws":57,"losses":80,"wins":39},"google/gemini-3.6-flash":{"draws":62,"losses":110,"wins":22},"google/gemini-3.8-flash":{"draws":26,"losses":74,"wins":2},"google/gemma-4-31b-it":{"draws":32,"losses":13,"wins":13},"gpt-4.1":{"draws":13,"losses":20,"wins":1},"gpt-4.1-nano":{"draws":6,"losses":6,"wins":2},"gpt-5":{"draws":29,"losses":39,"wins":20},"gpt-5.4":{"draws":23,"losses":58,"wins":17},"gpt-5.4-mini":{"draws":26,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":24,"losses":50,"wins":30},"gpt-5.5":{"draws":38,"losses":45,"wins":9},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":85,"wins":5},"gpt-5.6-terra":{"draws":31,"losses":64,"wins":7},"gpt-6-astra":{"draws":5,"losses":96,"wins":1},"gpt-6-luna":{"draws":33,"losses":54,"wins":15},"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":17,"wins":20},"inception/mercury-3":{"draws":20,"losses":38,"wins":16},"inclusionai/ling-3.0-flash":{"draws":18,"losses":17,"wins":17},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":39,"wins":24},"meta/muse-glimmer-30b":{"draws":46,"losses":22,"wins":18},"meta/muse-spark-1.2":{"draws":27,"losses":59,"wins":10},"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":22,"wins":15},"minimax/minimax-m3.1-flash":{"draws":23,"losses":45,"wins":18},"mistralai/mistral-large-4-0":{"draws":28,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":21,"losses":18,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":27,"losses":56,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":84,"wins":1},"nex-agi/nex-n2-pro":{"draws":14,"losses":18,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":4,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":31,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":22,"wins":10},"o3":{"draws":25,"losses":92,"wins":23},"openai/gpt-oss-120b":{"draws":38,"losses":40,"wins":8},"poolside/laguna-s-2.1":{"draws":29,"losses":36,"wins":29},"qwen/qwen3.7-max":{"draws":21,"losses":28,"wins":11},"qwen/qwen3.7-plus":{"draws":16,"losses":18,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":61,"wins":4},"qwen/qwen3.8-27b":{"draws":15,"losses":46,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":38,"wins":9},"qwen/qwen3.8-max":{"draws":37,"losses":50,"wins":15},"qwen/qwen3.8-max-0902":{"draws":37,"losses":56,"wins":9},"recursive/flint-v1.0":{"draws":8,"losses":14,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":45,"wins":16},"stealth/ox-alpha":{"draws":83,"losses":212,"wins":33},"stealth/space-bunny-alpha":{"draws":30,"losses":33,"wins":13},"stepfun/step-3.7-flash":{"draws":26,"losses":30,"wins":20},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":24,"wins":8},"tencent/hy4-preview":{"draws":30,"losses":57,"wins":11},"thinkingmachines/inkling":{"draws":47,"losses":52,"wins":31},"thinkingmachines/inkling-small":{"draws":42,"losses":32,"wins":28},"unbiased/pareto-26.10":{"draws":2,"losses":32,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":10,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":24,"losses":72,"wins":6},"x-ai/grok-4.6":{"draws":33,"losses":64,"wins":5},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":19,"wins":5},"xiaomi/mimo-v2.5":{"draws":68,"losses":54,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":26,"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":85,"losses":78,"wins":41},"z-ai/glm-5.3":{"draws":21,"losses":72,"wins":3},"z-ai/glm-5.3-flash":{"draws":28,"losses":59,"wins":15},"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":38,"losses":64,"wins":42},"claude-fable-5":{"draws":15,"losses":121,"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":64,"losses":154,"wins":36},"claude-opus-4-8":{"draws":32,"losses":91,"wins":21},"claude-opus-5":{"draws":24,"losses":210,"wins":22},"claude-opus-5-5":{"draws":11,"losses":155,"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":63,"losses":94,"wins":77},"deepseek/deepseek-v4-pro":{"draws":27,"losses":86,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":71,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":89,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":108,"wins":22},"elorian/glimpse":{"draws":17,"losses":47,"wins":20},"fireworks/ember-1":{"draws":38,"losses":88,"wins":30},"gemini-3.1-pro-preview":{"draws":38,"losses":71,"wins":47},"gemini-4-argon":{"draws":8,"losses":138,"wins":10},"google/gemini-3.1-flash-lite":{"draws":20,"losses":29,"wins":63},"google/gemini-3.5-flash":{"draws":37,"losses":123,"wins":38},"google/gemini-3.5-flash-lite":{"draws":78,"losses":117,"wins":83},"google/gemini-3.6-flash":{"draws":64,"losses":190,"wins":46},"google/gemini-3.8-flash":{"draws":25,"losses":112,"wins":19},"google/gemma-4-31b-it":{"draws":33,"losses":26,"wins":35},"gpt-4.1":{"draws":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":46,"losses":62,"wins":48},"gpt-5.6-sol":{"draws":20,"losses":122,"wins":14},"gpt-5.6-terra":{"draws":40,"losses":71,"wins":37},"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":27,"losses":94,"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":32,"wins":37},"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":33,"losses":23,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":24,"wins":7},"moonshotai/kimi-k3":{"draws":39,"losses":83,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":132,"wins":7},"nex-agi/nex-n2-pro":{"draws":15,"losses":29,"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":27,"losses":46,"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":44,"losses":83,"wins":29},"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":103,"losses":326,"wins":81},"stealth/space-bunny-alpha":{"draws":32,"losses":63,"wins":31},"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":34,"wins":24},"tencent/hy4-preview":{"draws":39,"losses":89,"wins":24},"thinkingmachines/inkling":{"draws":54,"losses":77,"wins":75},"thinkingmachines/inkling-small":{"draws":48,"losses":48,"wins":60},"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":23,"losses":55,"wins":20},"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":24,"losses":99,"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":41,"losses":42,"wins":33},"claude-fable-5":{"draws":21,"losses":98,"wins":7},"claude-fable-5-1":{"draws":7,"losses":136,"wins":0},"claude-haiku-5-5":{"draws":37,"losses":68,"wins":15},"claude-opus-4-5":{"draws":74,"losses":102,"wins":28},"claude-opus-4-8":{"draws":31,"losses":67,"wins":16},"claude-opus-5":{"draws":15,"losses":193,"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":78,"losses":61,"wins":47},"deepseek/deepseek-v4-pro":{"draws":35,"losses":56,"wins":29},"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":38,"losses":69,"wins":19},"gemini-3.1-pro-preview":{"draws":48,"losses":60,"wins":18},"gemini-4-argon":{"draws":13,"losses":109,"wins":4},"google/gemini-3.1-flash-lite":{"draws":32,"losses":19,"wins":31},"google/gemini-3.5-flash":{"draws":47,"losses":87,"wins":24},"google/gemini-3.5-flash-lite":{"draws":89,"losses":78,"wins":53},"google/gemini-3.6-flash":{"draws":77,"losses":130,"wins":35},"google/gemini-3.8-flash":{"draws":29,"losses":82,"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":36,"losses":54,"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":29,"losses":53,"wins":40},"gpt-5.5":{"draws":46,"losses":58,"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":46,"losses":18,"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":33,"losses":11,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":17,"wins":10},"moonshotai/kimi-k3":{"draws":32,"losses":73,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":20,"losses":100,"wins":0},"nex-agi/nex-n2-pro":{"draws":23,"losses":16,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":29,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":11},"o3":{"draws":32,"losses":104,"wins":36},"openai/gpt-oss-120b":{"draws":47,"losses":38,"wins":27},"poolside/laguna-s-2.1":{"draws":48,"losses":44,"wins":32},"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":43,"losses":68,"wins":15},"qwen/qwen3.8-27b":{"draws":23,"losses":49,"wins":14},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":21},"qwen/qwen3.8-max":{"draws":37,"losses":65,"wins":24},"qwen/qwen3.8-max-0902":{"draws":44,"losses":70,"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":96,"losses":272,"wins":58},"stealth/space-bunny-alpha":{"draws":35,"losses":40,"wins":27},"stepfun/step-3.7-flash":{"draws":20,"losses":27,"wins":41},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":30,"wins":14},"tencent/hy4-preview":{"draws":42,"losses":70,"wins":10},"thinkingmachines/inkling":{"draws":60,"losses":56,"wins":58},"thinkingmachines/inkling-small":{"draws":54,"losses":25,"wins":47},"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":108,"losses":97,"wins":47},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":12},"z-ai/glm-5.3-flash":{"draws":26,"losses":82,"wins":18},"z-ai/glm-5.3-flashx":{"draws":36,"losses":71,"wins":19}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":31,"wins":64},"claude-fable-5":{"draws":20,"losses":86,"wins":32},"claude-fable-5-1":{"draws":7,"losses":140,"wins":9},"claude-haiku-5-5":{"draws":26,"losses":65,"wins":41},"claude-opus-4-5":{"draws":62,"losses":60,"wins":102},"claude-opus-4-8":{"draws":29,"losses":53,"wins":44},"claude-opus-5":{"draws":31,"losses":177,"wins":36},"claude-opus-5-5":{"draws":12,"losses":129,"wins":9},"claude-sonnet-5":{"draws":37,"losses":37,"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":51,"losses":34,"wins":121},"deepseek/deepseek-v4-pro":{"draws":23,"losses":46,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":40,"wins":62},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":52,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":68,"wins":44},"elorian/glimpse":{"draws":16,"losses":25,"wins":35},"fireworks/ember-1":{"draws":38,"losses":54,"wins":46},"gemini-3.1-pro-preview":{"draws":33,"losses":47,"wins":58},"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":37,"losses":55,"wins":80},"google/gemini-3.5-flash-lite":{"draws":61,"losses":45,"wins":134},"google/gemini-3.6-flash":{"draws":54,"losses":105,"wins":105},"google/gemini-3.8-flash":{"draws":24,"losses":59,"wins":55},"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":25,"losses":58,"wins":45},"gpt-5.6-luna":{"draws":37,"losses":36,"wins":65},"gpt-5.6-sol":{"draws":18,"losses":87,"wins":33},"gpt-5.6-terra":{"draws":38,"losses":39,"wins":55},"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":10,"wins":59},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":27,"losses":27,"wins":94},"meta/muse-glimmer-30b":{"draws":33,"losses":19,"wins":72},"meta/muse-spark-1.2":{"draws":22,"losses":33,"wins":33},"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":22,"losses":12,"wins":46},"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":31,"losses":14,"wins":77},"poolside/laguna-s-2.1":{"draws":28,"losses":20,"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":35,"losses":54,"wins":49},"qwen/qwen3.8-27b":{"draws":21,"losses":41,"wins":34},"qwen/qwen3.8-flash":{"draws":22,"losses":27,"wins":43},"qwen/qwen3.8-max":{"draws":36,"losses":52,"wins":50},"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":105,"losses":199,"wins":154},"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":20,"losses":14,"wins":42},"tencent/hy4-preview":{"draws":22,"losses":59,"wins":51},"thinkingmachines/inkling":{"draws":53,"losses":33,"wins":100},"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":11,"losses":19,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":29,"wins":47},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":54,"wins":27},"z-ai/glm-5.2":{"draws":66,"losses":73,"wins":137},"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":29,"losses":59,"wins":50}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":22,"wins":81},"claude-fable-5":{"draws":22,"losses":79,"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":23,"losses":35,"wins":74},"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":34,"losses":43,"wins":67},"gemini-3.1-pro-preview":{"draws":24,"losses":40,"wins":80},"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":35,"losses":46,"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":23,"losses":29,"wins":92},"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":10,"losses":6,"wins":56},"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":33,"losses":40,"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":164,"wins":219},"stealth/space-bunny-alpha":{"draws":20,"losses":23,"wins":71},"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":27,"losses":51,"wins":60},"thinkingmachines/inkling":{"draws":33,"losses":19,"wins":140},"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":24,"losses":74,"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":38,"wins":14},"claude-fable-5":{"draws":18,"losses":54,"wins":6},"claude-fable-5-1":{"draws":2,"losses":83,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":53,"wins":15},"claude-opus-4-5":{"draws":38,"losses":78,"wins":12},"claude-opus-4-8":{"draws":17,"losses":47,"wins":10},"claude-opus-5":{"draws":17,"losses":114,"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":32,"losses":43,"wins":45},"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":39,"wins":22},"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":35,"losses":53,"wins":46},"google/gemini-3.6-flash":{"draws":29,"losses":94,"wins":25},"google/gemini-3.8-flash":{"draws":14,"losses":57,"wins":7},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":16},"gpt-4.1":{"draws":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":22,"losses":41,"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":15,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":15,"losses":37,"wins":32},"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":14,"wins":18},"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":19,"losses":45,"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":150,"wins":42},"stealth/space-bunny-alpha":{"draws":13,"losses":34,"wins":15},"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":32,"losses":28,"wins":18},"claude-fable-5":{"draws":17,"losses":61,"wins":6},"claude-fable-5-1":{"draws":4,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":54,"wins":4},"claude-opus-4-5":{"draws":43,"losses":82,"wins":11},"claude-opus-4-8":{"draws":24,"losses":46,"wins":6},"claude-opus-5":{"draws":21,"losses":111,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":31,"losses":43,"wins":10},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":8},"cohere/north-mini-code":{"draws":9,"losses":12,"wins":11},"deepseek/deepseek-v4-flash":{"draws":51,"losses":44,"wins":29},"deepseek/deepseek-v4-pro":{"draws":19,"losses":46,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":43,"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":23,"losses":52,"wins":9},"gemini-3.1-pro-preview":{"draws":27,"losses":44,"wins":13},"gemini-4-argon":{"draws":3,"losses":79,"wins":2},"google/gemini-3.1-flash-lite":{"draws":16,"losses":15,"wins":23},"google/gemini-3.5-flash":{"draws":27,"losses":62,"wins":15},"google/gemini-3.5-flash-lite":{"draws":47,"losses":65,"wins":36},"google/gemini-3.6-flash":{"draws":51,"losses":93,"wins":16},"google/gemini-3.8-flash":{"draws":17,"losses":61,"wins":6},"google/gemma-4-31b-it":{"draws":22,"losses":21,"wins":7},"gpt-4.1":{"draws":12,"losses":11,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":21,"losses":36,"wins":15},"gpt-5.4":{"draws":22,"losses":45,"wins":13},"gpt-5.4-mini":{"draws":22,"losses":24,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":49,"wins":17},"gpt-5.5":{"draws":24,"losses":43,"wins":9},"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":23,"losses":49,"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":21,"losses":19,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":36,"wins":23},"meta/muse-glimmer-30b":{"draws":33,"losses":28,"wins":11},"meta/muse-spark-1.2":{"draws":22,"losses":46,"wins":12},"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":18,"wins":14},"minimax/minimax-m3.1-flash":{"draws":19,"losses":40,"wins":13},"mistralai/mistral-large-4-0":{"draws":22,"losses":23,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":23,"losses":48,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":77,"wins":0},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":29,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":20,"wins":5},"o3":{"draws":23,"losses":72,"wins":15},"openai/gpt-oss-120b":{"draws":34,"losses":26,"wins":14},"poolside/laguna-s-2.1":{"draws":27,"losses":37,"wins":18},"qwen/qwen3.7-max":{"draws":22,"losses":22,"wins":4},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":58,"wins":3},"qwen/qwen3.8-27b":{"draws":19,"losses":35,"wins":4},"qwen/qwen3.8-flash":{"draws":18,"losses":31,"wins":7},"qwen/qwen3.8-max":{"draws":24,"losses":51,"wins":9},"qwen/qwen3.8-max-0902":{"draws":25,"losses":52,"wins":7},"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":69,"losses":171,"wins":42},"stealth/space-bunny-alpha":{"draws":18,"losses":36,"wins":12},"stepfun/step-3.7-flash":{"draws":19,"losses":24,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":15,"wins":13},"tencent/hy4-preview":{"draws":21,"losses":49,"wins":10},"thinkingmachines/inkling":{"draws":37,"losses":49,"wins":24},"thinkingmachines/inkling-small":{"draws":35,"losses":31,"wins":18},"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":20,"losses":57,"wins":7},"x-ai/grok-4.6":{"draws":25,"losses":53,"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":55,"losses":45,"wins":28},"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":65,"losses":78,"wins":25},"z-ai/glm-5.3":{"draws":14,"losses":64,"wins":4},"z-ai/glm-5.3-flash":{"draws":22,"losses":51,"wins":11},"z-ai/glm-5.3-flashx":{"draws":19,"losses":57,"wins":8}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":15},"claude-fable-5":{"draws":5,"losses":26,"wins":5},"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":8,"losses":21,"wins":7},"claude-opus-5":{"draws":6,"losses":59,"wins":3},"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":7,"losses":18,"wins":11},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"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":14,"wins":17},"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":11,"losses":12,"wins":11},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":25,"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":16,"wins":8},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":7},"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":9,"losses":17,"wins":10},"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":23,"losses":51,"wins":28},"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":9,"losses":21,"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":34,"losses":32,"wins":60},"claude-fable-5":{"draws":25,"losses":86,"wins":27},"claude-fable-5-1":{"draws":5,"losses":139,"wins":12},"claude-haiku-5-5":{"draws":34,"losses":58,"wins":40},"claude-opus-4-5":{"draws":75,"losses":67,"wins":82},"claude-opus-4-8":{"draws":34,"losses":49,"wins":43},"claude-opus-5":{"draws":36,"losses":167,"wins":41},"claude-opus-5-5":{"draws":5,"losses":134,"wins":11},"claude-sonnet-5":{"draws":39,"losses":41,"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":58,"losses":42,"wins":106},"deepseek/deepseek-v4-pro":{"draws":26,"losses":43,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":51,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":58,"wins":45},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":81,"wins":39},"elorian/glimpse":{"draws":19,"losses":31,"wins":26},"fireworks/ember-1":{"draws":43,"losses":57,"wins":38},"gemini-3.1-pro-preview":{"draws":33,"losses":41,"wins":64},"gemini-4-argon":{"draws":6,"losses":117,"wins":15},"google/gemini-3.1-flash-lite":{"draws":24,"losses":10,"wins":56},"google/gemini-3.5-flash":{"draws":46,"losses":61,"wins":65},"google/gemini-3.5-flash-lite":{"draws":74,"losses":47,"wins":119},"google/gemini-3.6-flash":{"draws":68,"losses":106,"wins":90},"google/gemini-3.8-flash":{"draws":31,"losses":72,"wins":35},"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":29,"losses":43,"wins":50},"gpt-5.4":{"draws":25,"losses":69,"wins":38},"gpt-5.4-mini":{"draws":29,"losses":21,"wins":42},"gpt-5.4-nano":{"draws":32,"losses":34,"wins":70},"gpt-5.5":{"draws":35,"losses":47,"wins":46},"gpt-5.6-luna":{"draws":47,"losses":29,"wins":62},"gpt-5.6-sol":{"draws":23,"losses":84,"wins":31},"gpt-5.6-terra":{"draws":37,"losses":45,"wins":50},"gpt-6-astra":{"draws":10,"losses":118,"wins":10},"gpt-6-luna":{"draws":43,"losses":43,"wins":52},"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":27,"losses":13,"wins":56},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":39,"losses":26,"wins":83},"meta/muse-glimmer-30b":{"draws":32,"losses":19,"wins":73},"meta/muse-spark-1.2":{"draws":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":23,"losses":9,"wins":48},"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":15,"losses":10,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":29,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":16,"wins":29},"o3":{"draws":27,"losses":73,"wins":86},"openai/gpt-oss-120b":{"draws":34,"losses":19,"wins":69},"poolside/laguna-s-2.1":{"draws":40,"losses":23,"wins":71},"qwen/qwen3.7-max":{"draws":19,"losses":18,"wins":43},"qwen/qwen3.7-plus":{"draws":24,"losses":14,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":52,"wins":51},"qwen/qwen3.8-27b":{"draws":27,"losses":28,"wins":41},"qwen/qwen3.8-flash":{"draws":26,"losses":31,"wins":35},"qwen/qwen3.8-max":{"draws":36,"losses":55,"wins":47},"qwen/qwen3.8-max-0902":{"draws":31,"losses":73,"wins":34},"recursive/flint-v1.0":{"draws":10,"losses":3,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":41,"wins":52},"stealth/ox-alpha":{"draws":103,"losses":185,"wins":170},"stealth/space-bunny-alpha":{"draws":35,"losses":22,"wins":53},"stepfun/step-3.7-flash":{"draws":21,"losses":16,"wins":59},"stepfun/step-5-preview":{"draws":2,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":28},"tencent/hy4-preview":{"draws":30,"losses":56,"wins":46},"thinkingmachines/inkling":{"draws":53,"losses":39,"wins":94},"thinkingmachines/inkling-small":{"draws":44,"losses":21,"wins":73},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":27,"losses":66,"wins":45},"x-ai/grok-4.6":{"draws":31,"losses":73,"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":73,"losses":32,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":22,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":36,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":49,"wins":25},"z-ai/glm-5.2":{"draws":87,"losses":76,"wins":113},"z-ai/glm-5.3":{"draws":28,"losses":65,"wins":39},"z-ai/glm-5.3-flash":{"draws":27,"losses":67,"wins":44},"z-ai/glm-5.3-flashx":{"draws":34,"losses":66,"wins":38}},"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":16,"losses":37,"wins":13},"claude-fable-5":{"draws":12,"losses":58,"wins":2},"claude-fable-5-1":{"draws":4,"losses":77,"wins":1},"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":15,"losses":46,"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":24,"losses":52,"wins":32},"deepseek/deepseek-v4-pro":{"draws":15,"losses":37,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":40,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":48,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":53,"wins":7},"elorian/glimpse":{"draws":8,"losses":20,"wins":10},"fireworks/ember-1":{"draws":19,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":19,"losses":42,"wins":11},"gemini-4-argon":{"draws":8,"losses":59,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":13,"wins":27},"google/gemini-3.5-flash":{"draws":20,"losses":51,"wins":19},"google/gemini-3.5-flash-lite":{"draws":29,"losses":61,"wins":38},"google/gemini-3.6-flash":{"draws":25,"losses":94,"wins":19},"google/gemini-3.8-flash":{"draws":12,"losses":54,"wins":6},"google/gemma-4-31b-it":{"draws":17,"losses":16,"wins":11},"gpt-4.1":{"draws":5,"losses":14,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":12,"losses":32,"wins":20},"gpt-5.4":{"draws":16,"losses":38,"wins":16},"gpt-5.4-mini":{"draws":19,"losses":16,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":35,"wins":25},"gpt-5.5":{"draws":17,"losses":43,"wins":6},"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":40,"wins":9},"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":14,"losses":16,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":42,"wins":29},"meta/muse-glimmer-30b":{"draws":23,"losses":23,"wins":16},"meta/muse-spark-1.2":{"draws":11,"losses":46,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":56,"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":11,"losses":23,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":43,"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":20,"losses":26,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":10},"o3":{"draws":8,"losses":76,"wins":22},"openai/gpt-oss-120b":{"draws":19,"losses":23,"wins":24},"poolside/laguna-s-2.1":{"draws":21,"losses":32,"wins":19},"qwen/qwen3.7-max":{"draws":13,"losses":24,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":18,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":48,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":29,"wins":9},"qwen/qwen3.8-flash":{"draws":14,"losses":28,"wins":6},"qwen/qwen3.8-max":{"draws":19,"losses":45,"wins":8},"qwen/qwen3.8-max-0902":{"draws":19,"losses":43,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":8,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":42,"wins":12},"stealth/ox-alpha":{"draws":56,"losses":162,"wins":32},"stealth/space-bunny-alpha":{"draws":16,"losses":30,"wins":12},"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":13,"losses":10,"wins":13},"tencent/hy4-preview":{"draws":18,"losses":45,"wins":7},"thinkingmachines/inkling":{"draws":25,"losses":42,"wins":27},"thinkingmachines/inkling-small":{"draws":21,"losses":32,"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":50,"losses":73,"wins":21},"z-ai/glm-5.3":{"draws":14,"losses":56,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":50,"wins":10},"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":42,"losses":40,"wins":34},"claude-fable-5":{"draws":20,"losses":93,"wins":13},"claude-fable-5-1":{"draws":7,"losses":128,"wins":1},"claude-haiku-5-5":{"draws":32,"losses":66,"wins":26},"claude-opus-4-5":{"draws":76,"losses":103,"wins":29},"claude-opus-4-8":{"draws":28,"losses":76,"wins":18},"claude-opus-5":{"draws":26,"losses":182,"wins":6},"claude-opus-5-5":{"draws":4,"losses":136,"wins":2},"claude-sonnet-5":{"draws":44,"losses":53,"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":62,"losses":73,"wins":59},"deepseek/deepseek-v4-pro":{"draws":36,"losses":55,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":57,"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":42,"losses":61,"wins":23},"gemini-3.1-pro-preview":{"draws":45,"losses":51,"wins":30},"gemini-4-argon":{"draws":9,"losses":114,"wins":3},"google/gemini-3.1-flash-lite":{"draws":25,"losses":23,"wins":42},"google/gemini-3.5-flash":{"draws":42,"losses":83,"wins":35},"google/gemini-3.5-flash-lite":{"draws":80,"losses":71,"wins":69},"google/gemini-3.6-flash":{"draws":72,"losses":130,"wins":36},"google/gemini-3.8-flash":{"draws":33,"losses":84,"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":35,"losses":56,"wins":19},"gpt-5.4":{"draws":36,"losses":72,"wins":12},"gpt-5.4-mini":{"draws":35,"losses":24,"wins":25},"gpt-5.4-nano":{"draws":30,"losses":64,"wins":46},"gpt-5.5":{"draws":46,"losses":58,"wins":10},"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":45,"losses":57,"wins":18},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":42,"losses":58,"wins":26},"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":35,"losses":26,"wins":31},"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":51,"losses":28,"wins":29},"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":33,"losses":12,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":20,"wins":5},"moonshotai/kimi-k3":{"draws":34,"losses":57,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":107,"wins":4},"nex-agi/nex-n2-pro":{"draws":20,"losses":16,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":11,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":25,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":33,"wins":12},"o3":{"draws":33,"losses":107,"wins":44},"openai/gpt-oss-120b":{"draws":46,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":48,"losses":40,"wins":36},"qwen/qwen3.7-max":{"draws":33,"losses":26,"wins":19},"qwen/qwen3.7-plus":{"draws":21,"losses":24,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":66,"wins":15},"qwen/qwen3.8-27b":{"draws":27,"losses":42,"wins":19},"qwen/qwen3.8-flash":{"draws":31,"losses":38,"wins":15},"qwen/qwen3.8-max":{"draws":41,"losses":63,"wins":22},"qwen/qwen3.8-max-0902":{"draws":46,"losses":67,"wins":13},"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":89,"losses":223,"wins":62},"stealth/space-bunny-alpha":{"draws":35,"losses":40,"wins":23},"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":40,"losses":65,"wins":15},"thinkingmachines/inkling":{"draws":50,"losses":51,"wins":61},"thinkingmachines/inkling-small":{"draws":49,"losses":35,"wins":42},"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":30,"losses":84,"wins":12},"x-ai/grok-4.6":{"draws":44,"losses":70,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":99,"wins":9},"x-ai/grok-build-0.1":{"draws":19,"losses":13,"wins":10},"xiaomi/mimo-v2.5":{"draws":83,"losses":58,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":33,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":45,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":56,"wins":10},"z-ai/glm-5.2":{"draws":89,"losses":98,"wins":65},"z-ai/glm-5.3":{"draws":23,"losses":85,"wins":12},"z-ai/glm-5.3-flash":{"draws":22,"losses":64,"wins":40},"z-ai/glm-5.3-flashx":{"draws":28,"losses":76,"wins":22}},"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":38,"losses":56,"wins":90},"claude-fable-5":{"draws":16,"losses":153,"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":43,"losses":188,"wins":95},"claude-opus-4-8":{"draws":27,"losses":107,"wins":56},"claude-opus-5":{"draws":26,"losses":264,"wins":22},"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":20,"losses":92,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":100,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":95,"wins":65},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":124,"wins":56},"elorian/glimpse":{"draws":14,"losses":56,"wins":36},"fireworks/ember-1":{"draws":37,"losses":111,"wins":50},"gemini-3.1-pro-preview":{"draws":29,"losses":77,"wins":92},"gemini-4-argon":{"draws":2,"losses":187,"wins":9},"google/gemini-3.1-flash-lite":{"draws":22,"losses":12,"wins":124},"google/gemini-3.5-flash":{"draws":31,"losses":136,"wins":91},"google/gemini-3.5-flash-lite":{"draws":57,"losses":98,"wins":201},"google/gemini-3.6-flash":{"draws":50,"losses":207,"wins":127},"google/gemini-3.8-flash":{"draws":20,"losses":133,"wins":45},"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":23,"losses":89,"wins":68},"gpt-5.4":{"draws":19,"losses":128,"wins":49},"gpt-5.4-mini":{"draws":23,"losses":35,"wins":74},"gpt-5.4-nano":{"draws":17,"losses":103,"wins":106},"gpt-5.5":{"draws":35,"losses":105,"wins":44},"gpt-5.6-luna":{"draws":40,"losses":68,"wins":90},"gpt-5.6-sol":{"draws":12,"losses":155,"wins":31},"gpt-5.6-terra":{"draws":33,"losses":86,"wins":67},"gpt-6-astra":{"draws":7,"losses":189,"wins":2},"gpt-6-luna":{"draws":33,"losses":100,"wins":65},"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":25,"losses":23,"wins":92},"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":32,"losses":36,"wins":104},"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":23,"losses":15,"wins":72},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":24,"wins":21},"moonshotai/kimi-k3":{"draws":27,"losses":86,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":173,"wins":15},"nex-agi/nex-n2-pro":{"draws":8,"losses":22,"wins":76},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":15,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":44,"wins":107},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":49,"wins":33},"o3":{"draws":24,"losses":122,"wins":122},"openai/gpt-oss-120b":{"draws":24,"losses":29,"wins":119},"poolside/laguna-s-2.1":{"draws":30,"losses":63,"wins":99},"qwen/qwen3.7-max":{"draws":21,"losses":44,"wins":59},"qwen/qwen3.7-plus":{"draws":11,"losses":29,"wins":70},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":112,"wins":59},"qwen/qwen3.8-27b":{"draws":12,"losses":74,"wins":58},"qwen/qwen3.8-flash":{"draws":20,"losses":63,"wins":49},"qwen/qwen3.8-max":{"draws":34,"losses":100,"wins":64},"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":80,"losses":319,"wins":205},"stealth/space-bunny-alpha":{"draws":24,"losses":57,"wins":79},"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":39,"wins":43},"tencent/hy4-preview":{"draws":25,"losses":106,"wins":65},"thinkingmachines/inkling":{"draws":41,"losses":57,"wins":168},"thinkingmachines/inkling-small":{"draws":36,"losses":44,"wins":118},"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":34,"losses":120,"wins":44},"x-ai/grok-4.7":{"draws":12,"losses":130,"wins":36},"x-ai/grok-build-0.1":{"draws":13,"losses":16,"wins":37},"xiaomi/mimo-v2.5":{"draws":56,"losses":63,"wins":197},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":44,"wins":62},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":75,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":95,"wins":26},"z-ai/glm-5.2":{"draws":66,"losses":152,"wins":178},"z-ai/glm-5.3":{"draws":15,"losses":138,"wins":35},"z-ai/glm-5.3-flash":{"draws":21,"losses":101,"wins":76},"z-ai/glm-5.3-flashx":{"draws":21,"losses":119,"wins":58}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":44,"wins":32},"claude-fable-5":{"draws":26,"losses":89,"wins":11},"claude-fable-5-1":{"draws":9,"losses":133,"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":29,"losses":180,"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":33,"losses":55,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":51,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":62,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":84,"wins":17},"elorian/glimpse":{"draws":14,"losses":36,"wins":18},"fireworks/ember-1":{"draws":43,"losses":65,"wins":18},"gemini-3.1-pro-preview":{"draws":37,"losses":57,"wins":32},"gemini-4-argon":{"draws":3,"losses":121,"wins":2},"google/gemini-3.1-flash-lite":{"draws":26,"losses":19,"wins":37},"google/gemini-3.5-flash":{"draws":43,"losses":77,"wins":36},"google/gemini-3.5-flash-lite":{"draws":69,"losses":75,"wins":74},"google/gemini-3.6-flash":{"draws":72,"losses":135,"wins":33},"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":31,"losses":77,"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":34,"losses":69,"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":37,"losses":73,"wins":16},"recursive/flint-v1.0":{"draws":8,"losses":9,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":65,"wins":17},"stealth/ox-alpha":{"draws":106,"losses":257,"wins":61},"stealth/space-bunny-alpha":{"draws":28,"losses":48,"wins":24},"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":40,"losses":61,"wins":19},"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":107,"wins":50},"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":42,"losses":46,"wins":40},"claude-fable-5":{"draws":19,"losses":98,"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":75,"losses":111,"wins":36},"claude-opus-4-8":{"draws":37,"losses":68,"wins":17},"claude-opus-5":{"draws":26,"losses":209,"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":69,"losses":69,"wins":72},"deepseek/deepseek-v4-pro":{"draws":30,"losses":51,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":59,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":60,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":93,"wins":18},"elorian/glimpse":{"draws":18,"losses":40,"wins":16},"fireworks/ember-1":{"draws":46,"losses":66,"wins":26},"gemini-3.1-pro-preview":{"draws":44,"losses":61,"wins":33},"gemini-4-argon":{"draws":8,"losses":127,"wins":3},"google/gemini-3.1-flash-lite":{"draws":26,"losses":18,"wins":42},"google/gemini-3.5-flash":{"draws":32,"losses":105,"wins":33},"google/gemini-3.5-flash-lite":{"draws":71,"losses":66,"wins":101},"google/gemini-3.6-flash":{"draws":70,"losses":138,"wins":54},"google/gemini-3.8-flash":{"draws":22,"losses":99,"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":32,"losses":55,"wins":39},"gpt-5.4":{"draws":31,"losses":80,"wins":21},"gpt-5.4-mini":{"draws":34,"losses":32,"wins":26},"gpt-5.4-nano":{"draws":31,"losses":59,"wins":54},"gpt-5.5":{"draws":44,"losses":60,"wins":24},"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":46,"losses":67,"wins":17},"gpt-6-astra":{"draws":7,"losses":131,"wins":0},"gpt-6-luna":{"draws":41,"losses":58,"wins":39},"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":29,"losses":29,"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":48,"losses":32,"wins":44},"meta/muse-spark-1.2":{"draws":28,"losses":86,"wins":20},"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":27,"losses":18,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":40,"losses":71,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":108,"wins":4},"nex-agi/nex-n2-pro":{"draws":21,"losses":19,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":36,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":31,"wins":15},"o3":{"draws":30,"losses":99,"wins":63},"openai/gpt-oss-120b":{"draws":49,"losses":36,"wins":41},"poolside/laguna-s-2.1":{"draws":32,"losses":36,"wins":36},"qwen/qwen3.7-max":{"draws":30,"losses":31,"wins":21},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":86,"wins":15},"qwen/qwen3.8-27b":{"draws":23,"losses":49,"wins":22},"qwen/qwen3.8-flash":{"draws":27,"losses":42,"wins":23},"qwen/qwen3.8-max":{"draws":38,"losses":68,"wins":32},"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":112,"losses":276,"wins":90},"stealth/space-bunny-alpha":{"draws":30,"losses":46,"wins":30},"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":26,"wins":23},"tencent/hy4-preview":{"draws":34,"losses":70,"wins":28},"thinkingmachines/inkling":{"draws":56,"losses":55,"wins":77},"thinkingmachines/inkling-small":{"draws":47,"losses":23,"wins":68},"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":35,"losses":86,"wins":17},"x-ai/grok-4.7":{"draws":12,"losses":99,"wins":13},"x-ai/grok-build-0.1":{"draws":19,"losses":15,"wins":12},"xiaomi/mimo-v2.5":{"draws":62,"losses":57,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":25,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":54,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":64,"wins":18},"z-ai/glm-5.2":{"draws":97,"losses":100,"wins":79},"z-ai/glm-5.3":{"draws":25,"losses":92,"wins":15},"z-ai/glm-5.3-flash":{"draws":28,"losses":76,"wins":34},"z-ai/glm-5.3-flashx":{"draws":40,"losses":75,"wins":23}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":25,"wins":27},"claude-fable-5":{"draws":12,"losses":59,"wins":13},"claude-fable-5-1":{"draws":2,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":35,"wins":20},"claude-opus-4-5":{"draws":42,"losses":62,"wins":34},"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":50,"losses":30,"wins":50},"deepseek/deepseek-v4-pro":{"draws":23,"losses":35,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":32,"wins":17},"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":22,"losses":42,"wins":20},"gemini-3.1-pro-preview":{"draws":24,"losses":31,"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":30,"losses":40,"wins":36},"google/gemini-3.5-flash-lite":{"draws":43,"losses":39,"wins":64},"google/gemini-3.6-flash":{"draws":45,"losses":77,"wins":38},"google/gemini-3.8-flash":{"draws":24,"losses":40,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":13,"wins":20},"gpt-4.1":{"draws":11,"losses":5,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":27,"losses":29,"wins":18},"gpt-5.4":{"draws":17,"losses":45,"wins":18},"gpt-5.4-mini":{"draws":19,"losses":15,"wins":22},"gpt-5.4-nano":{"draws":24,"losses":30,"wins":38},"gpt-5.5":{"draws":26,"losses":36,"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":78,"wins":0},"gpt-6-luna":{"draws":21,"losses":36,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":76,"wins":2},"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":21,"losses":11,"wins":28},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":27,"losses":19,"wins":46},"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":22,"losses":4,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":19,"losses":43,"wins":18},"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":33,"losses":19,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":16},"o3":{"draws":21,"losses":59,"wins":44},"openai/gpt-oss-120b":{"draws":29,"losses":14,"wins":31},"poolside/laguna-s-2.1":{"draws":30,"losses":21,"wins":31},"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":28,"losses":37,"wins":19},"qwen/qwen3.8-27b":{"draws":16,"losses":25,"wins":19},"qwen/qwen3.8-flash":{"draws":18,"losses":22,"wins":16},"qwen/qwen3.8-max":{"draws":27,"losses":34,"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":60,"losses":138,"wins":60},"stealth/space-bunny-alpha":{"draws":15,"losses":22,"wins":29},"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":11,"wins":16},"tencent/hy4-preview":{"draws":19,"losses":43,"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":50,"wins":16},"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":52,"losses":62,"wins":54},"z-ai/glm-5.3":{"draws":18,"losses":49,"wins":13},"z-ai/glm-5.3-flash":{"draws":23,"losses":42,"wins":19},"z-ai/glm-5.3-flashx":{"draws":22,"losses":42,"wins":20}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":24,"wins":20},"claude-fable-5":{"draws":10,"losses":54,"wins":8},"claude-fable-5-1":{"draws":4,"losses":73,"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":18,"losses":43,"wins":11},"claude-opus-5":{"draws":16,"losses":92,"wins":8},"claude-opus-5-5":{"draws":6,"losses":70,"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":31,"losses":43,"wins":38},"deepseek/deepseek-v4-pro":{"draws":14,"losses":35,"wins":15},"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":20,"losses":39,"wins":13},"gemini-3.1-pro-preview":{"draws":24,"losses":34,"wins":14},"gemini-4-argon":{"draws":3,"losses":68,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":12,"wins":31},"google/gemini-3.5-flash":{"draws":18,"losses":53,"wins":21},"google/gemini-3.5-flash-lite":{"draws":36,"losses":50,"wins":40},"google/gemini-3.6-flash":{"draws":38,"losses":78,"wins":22},"google/gemini-3.8-flash":{"draws":15,"losses":50,"wins":7},"google/gemma-4-31b-it":{"draws":16,"losses":13,"wins":15},"gpt-4.1":{"draws":8,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":14,"losses":38,"wins":10},"gpt-5.4":{"draws":10,"losses":50,"wins":8},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":18},"gpt-5.4-nano":{"draws":17,"losses":33,"wins":32},"gpt-5.5":{"draws":24,"losses":34,"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":16,"losses":16,"wins":18},"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":15,"losses":12,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":24,"losses":30,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":60,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":9,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":8,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":23,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":16,"wins":9},"o3":{"draws":11,"losses":70,"wins":29},"openai/gpt-oss-120b":{"draws":21,"losses":20,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":33,"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":26,"losses":37,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":28,"wins":16},"qwen/qwen3.8-flash":{"draws":14,"losses":18,"wins":16},"qwen/qwen3.8-max":{"draws":25,"losses":31,"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":41,"losses":134,"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":36,"wins":44},"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":41,"losses":70,"wins":33},"z-ai/glm-5.3":{"draws":14,"losses":46,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":43,"wins":14},"z-ai/glm-5.3-flashx":{"draws":17,"losses":45,"wins":10}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":30,"wins":63},"claude-fable-5":{"draws":31,"losses":77,"wins":36},"claude-fable-5-1":{"draws":8,"losses":147,"wins":7},"claude-haiku-5-5":{"draws":36,"losses":55,"wins":47},"claude-opus-4-5":{"draws":81,"losses":62,"wins":91},"claude-opus-4-8":{"draws":41,"losses":43,"wins":48},"claude-opus-5":{"draws":31,"losses":173,"wins":42},"claude-opus-5-5":{"draws":10,"losses":129,"wins":17},"claude-sonnet-5":{"draws":45,"losses":37,"wins":62},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":45},"deepseek/deepseek-v4-flash":{"draws":65,"losses":32,"wins":119},"deepseek/deepseek-v4-pro":{"draws":34,"losses":37,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":43,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":60,"wins":48},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":73,"wins":43},"elorian/glimpse":{"draws":20,"losses":29,"wins":29},"fireworks/ember-1":{"draws":48,"losses":49,"wins":47},"gemini-3.1-pro-preview":{"draws":35,"losses":44,"wins":65},"gemini-4-argon":{"draws":9,"losses":112,"wins":23},"google/gemini-3.1-flash-lite":{"draws":23,"losses":7,"wins":66},"google/gemini-3.5-flash":{"draws":47,"losses":54,"wins":79},"google/gemini-3.5-flash-lite":{"draws":77,"losses":43,"wins":132},"google/gemini-3.6-flash":{"draws":66,"losses":115,"wins":95},"google/gemini-3.8-flash":{"draws":30,"losses":69,"wins":45},"google/gemma-4-31b-it":{"draws":29,"losses":10,"wins":45},"gpt-4.1":{"draws":16,"losses":8,"wins":24},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":36,"losses":35,"wins":55},"gpt-5.4":{"draws":27,"losses":58,"wins":53},"gpt-5.4-mini":{"draws":31,"losses":13,"wins":52},"gpt-5.4-nano":{"draws":34,"losses":26,"wins":84},"gpt-5.5":{"draws":39,"losses":47,"wins":46},"gpt-5.6-luna":{"draws":51,"losses":27,"wins":66},"gpt-5.6-sol":{"draws":21,"losses":86,"wins":37},"gpt-5.6-terra":{"draws":45,"losses":33,"wins":60},"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":10,"losses":114,"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":37,"losses":4,"wins":61},"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":43,"losses":15,"wins":68},"meta/muse-spark-1.2":{"draws":35,"losses":49,"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":23,"losses":3,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":8,"wins":16},"moonshotai/kimi-k3":{"draws":35,"losses":51,"wins":52},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":108,"wins":13},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":48},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":15,"wins":66},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":27,"losses":59,"wins":112},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":72},"poolside/laguna-s-2.1":{"draws":37,"losses":15,"wins":86},"qwen/qwen3.7-max":{"draws":28,"losses":19,"wins":37},"qwen/qwen3.7-plus":{"draws":26,"losses":9,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":35},"qwen/qwen3.8-27b":{"draws":38,"losses":28,"wins":36},"qwen/qwen3.8-flash":{"draws":24,"losses":31,"wins":41},"qwen/qwen3.8-max":{"draws":43,"losses":53,"wins":48},"qwen/qwen3.8-max-0902":{"draws":44,"losses":55,"wins":45},"recursive/flint-v1.0":{"draws":12,"losses":2,"wins":28},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":36,"wins":65},"stealth/ox-alpha":{"draws":118,"losses":177,"wins":179},"stealth/space-bunny-alpha":{"draws":40,"losses":29,"wins":45},"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":38,"losses":52,"wins":48},"thinkingmachines/inkling":{"draws":58,"losses":25,"wins":109},"thinkingmachines/inkling-small":{"draws":44,"losses":17,"wins":83},"unbiased/pareto-26.10":{"draws":5,"losses":42,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":34,"losses":62,"wins":48},"x-ai/grok-4.6":{"draws":33,"losses":61,"wins":50},"x-ai/grok-4.7":{"draws":9,"losses":86,"wins":31},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":86,"losses":25,"wins":111},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":36,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":42,"wins":30},"z-ai/glm-5.2":{"draws":96,"losses":71,"wins":121},"z-ai/glm-5.3":{"draws":26,"losses":82,"wins":30},"z-ai/glm-5.3-flash":{"draws":29,"losses":67,"wins":48},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":45}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":24,"wins":48},"claude-fable-5":{"draws":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":48,"losses":49,"wins":69},"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":23,"losses":30,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":50,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":61,"wins":26},"elorian/glimpse":{"draws":11,"losses":22,"wins":21},"fireworks/ember-1":{"draws":28,"losses":35,"wins":39},"gemini-3.1-pro-preview":{"draws":22,"losses":32,"wins":48},"gemini-4-argon":{"draws":7,"losses":88,"wins":7},"google/gemini-3.1-flash-lite":{"draws":15,"losses":9,"wins":46},"google/gemini-3.5-flash":{"draws":19,"losses":58,"wins":51},"google/gemini-3.5-flash-lite":{"draws":34,"losses":43,"wins":103},"google/gemini-3.6-flash":{"draws":40,"losses":92,"wins":66},"google/gemini-3.8-flash":{"draws":15,"losses":64,"wins":23},"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":17,"wins":34},"gpt-5.4-nano":{"draws":19,"losses":34,"wins":51},"gpt-5.5":{"draws":26,"losses":38,"wins":28},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":45},"gpt-5.6-sol":{"draws":15,"losses":70,"wins":17},"gpt-5.6-terra":{"draws":33,"losses":34,"wins":31},"gpt-6-astra":{"draws":4,"losses":97,"wins":1},"gpt-6-luna":{"draws":24,"losses":41,"wins":37},"gpt-6-sol":{"draws":16,"losses":72,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":91,"wins":4},"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":23,"losses":14,"wins":49},"meta/muse-spark-1.2":{"draws":21,"losses":34,"wins":41},"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":19,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":11},"moonshotai/kimi-k3":{"draws":27,"losses":41,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":82,"wins":4},"nex-agi/nex-n2-pro":{"draws":10,"losses":9,"wins":29},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":19,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":13,"wins":21},"o3":{"draws":12,"losses":58,"wins":74},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":46},"poolside/laguna-s-2.1":{"draws":23,"losses":22,"wins":49},"qwen/qwen3.7-max":{"draws":16,"losses":19,"wins":25},"qwen/qwen3.7-plus":{"draws":10,"losses":16,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":36,"wins":28},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":15,"losses":30,"wins":23},"qwen/qwen3.8-max":{"draws":30,"losses":33,"wins":39},"qwen/qwen3.8-max-0902":{"draws":24,"losses":51,"wins":27},"recursive/flint-v1.0":{"draws":5,"losses":7,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":34,"wins":34},"stealth/ox-alpha":{"draws":72,"losses":153,"wins":107},"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":25,"losses":45,"wins":28},"thinkingmachines/inkling":{"draws":37,"losses":30,"wins":71},"thinkingmachines/inkling-small":{"draws":28,"losses":16,"wins":58},"unbiased/pareto-26.10":{"draws":2,"losses":32,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":34,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":24,"losses":53,"wins":25},"x-ai/grok-4.6":{"draws":26,"losses":53,"wins":23},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":12,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":42,"losses":29,"wins":89},"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":64,"losses":70,"wins":70},"z-ai/glm-5.3":{"draws":24,"losses":60,"wins":12},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":32},"z-ai/glm-5.3-flashx":{"draws":22,"losses":54,"wins":26}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":20,"wins":39},"claude-fable-5":{"draws":21,"losses":55,"wins":20},"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":52,"wins":49},"claude-opus-4-8":{"draws":29,"losses":42,"wins":17},"claude-opus-5":{"draws":24,"losses":126,"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":42,"losses":32,"wins":70},"deepseek/deepseek-v4-pro":{"draws":18,"losses":30,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":32,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":40,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":51,"wins":24},"elorian/glimpse":{"draws":13,"losses":22,"wins":17},"fireworks/ember-1":{"draws":30,"losses":34,"wins":32},"gemini-3.1-pro-preview":{"draws":35,"losses":31,"wins":30},"gemini-4-argon":{"draws":12,"losses":73,"wins":11},"google/gemini-3.1-flash-lite":{"draws":22,"losses":9,"wins":33},"google/gemini-3.5-flash":{"draws":30,"losses":49,"wins":41},"google/gemini-3.5-flash-lite":{"draws":56,"losses":31,"wins":81},"google/gemini-3.6-flash":{"draws":55,"losses":82,"wins":47},"google/gemini-3.8-flash":{"draws":18,"losses":50,"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":16,"losses":32,"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":20,"losses":26,"wins":50},"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":21,"losses":9,"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":43,"wins":27},"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":18,"losses":7,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":26,"losses":35,"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":31,"losses":15,"wins":38},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":12,"wins":18},"o3":{"draws":20,"losses":49,"wins":63},"openai/gpt-oss-120b":{"draws":27,"losses":23,"wins":34},"poolside/laguna-s-2.1":{"draws":27,"losses":23,"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":24,"losses":41,"wins":31},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":30},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":29,"losses":39,"wins":28},"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":82,"losses":131,"wins":103},"stealth/space-bunny-alpha":{"draws":26,"losses":20,"wins":30},"stepfun/step-3.7-flash":{"draws":14,"losses":14,"wins":40},"stepfun/step-5-preview":{"draws":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":61,"losses":58,"wins":73},"z-ai/glm-5.3":{"draws":23,"losses":55,"wins":14},"z-ai/glm-5.3-flash":{"draws":18,"losses":43,"wins":35},"z-ai/glm-5.3-flashx":{"draws":29,"losses":42,"wins":25}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":36,"wins":53},"claude-fable-5":{"draws":25,"losses":82,"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":73,"losses":69,"wins":92},"claude-opus-4-8":{"draws":26,"losses":61,"wins":45},"claude-opus-5":{"draws":36,"losses":178,"wins":32},"claude-opus-5-5":{"draws":13,"losses":130,"wins":13},"claude-sonnet-5":{"draws":47,"losses":43,"wins":54},"claude-sonnet-5-5":{"draws":22,"losses":81,"wins":41},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":42},"deepseek/deepseek-v4-flash":{"draws":65,"losses":35,"wins":116},"deepseek/deepseek-v4-pro":{"draws":37,"losses":36,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":40,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":54,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":82,"wins":33},"elorian/glimpse":{"draws":17,"losses":30,"wins":31},"fireworks/ember-1":{"draws":41,"losses":60,"wins":43},"gemini-3.1-pro-preview":{"draws":38,"losses":47,"wins":59},"gemini-4-argon":{"draws":9,"losses":123,"wins":12},"google/gemini-3.1-flash-lite":{"draws":27,"losses":1,"wins":68},"google/gemini-3.5-flash":{"draws":54,"losses":60,"wins":66},"google/gemini-3.5-flash-lite":{"draws":79,"losses":47,"wins":126},"google/gemini-3.6-flash":{"draws":64,"losses":118,"wins":94},"google/gemini-3.8-flash":{"draws":33,"losses":62,"wins":49},"google/gemma-4-31b-it":{"draws":33,"losses":8,"wins":43},"gpt-4.1":{"draws":18,"losses":14,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":35,"losses":29,"wins":62},"gpt-5.4":{"draws":33,"losses":53,"wins":52},"gpt-5.4-mini":{"draws":36,"losses":20,"wins":40},"gpt-5.4-nano":{"draws":32,"losses":37,"wins":75},"gpt-5.5":{"draws":43,"losses":49,"wins":40},"gpt-5.6-luna":{"draws":47,"losses":29,"wins":68},"gpt-5.6-sol":{"draws":25,"losses":88,"wins":31},"gpt-5.6-terra":{"draws":52,"losses":41,"wins":45},"gpt-6-astra":{"draws":13,"losses":128,"wins":3},"gpt-6-luna":{"draws":37,"losses":49,"wins":58},"gpt-6-sol":{"draws":17,"losses":99,"wins":28},"gpt-6.1-sol":{"draws":10,"losses":127,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":43,"losses":7,"wins":52},"inception/mercury-3":{"draws":30,"losses":26,"wins":40},"inclusionai/ling-3.0-flash":{"draws":37,"losses":15,"wins":50},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":44,"losses":29,"wins":83},"meta/muse-glimmer-30b":{"draws":37,"losses":24,"wins":65},"meta/muse-spark-1.2":{"draws":36,"losses":50,"wins":52},"meta/muse-spark-1.3":{"draws":33,"losses":71,"wins":40},"meta/muse-spark-open":{"draws":28,"losses":66,"wins":44},"meta/muse-wonder":{"draws":31,"losses":81,"wins":32},"minimax/minimax-m3":{"draws":19,"losses":14,"wins":45},"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":24,"losses":9,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":36,"losses":47,"wins":55},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":113,"wins":19},"nex-agi/nex-n2-pro":{"draws":19,"losses":8,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":7,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":22,"wins":63},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":18,"wins":31},"o3":{"draws":34,"losses":64,"wins":100},"openai/gpt-oss-120b":{"draws":41,"losses":10,"wins":75},"poolside/laguna-s-2.1":{"draws":38,"losses":32,"wins":68},"qwen/qwen3.7-max":{"draws":27,"losses":23,"wins":34},"qwen/qwen3.7-plus":{"draws":25,"losses":16,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":48,"wins":53},"qwen/qwen3.8-27b":{"draws":30,"losses":39,"wins":33},"qwen/qwen3.8-flash":{"draws":29,"losses":28,"wins":39},"qwen/qwen3.8-max":{"draws":28,"losses":34,"wins":34},"qwen/qwen3.8-max-0902":{"draws":35,"losses":62,"wins":47},"recursive/flint-v1.0":{"draws":10,"losses":6,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":39,"wins":65},"stealth/ox-alpha":{"draws":122,"losses":193,"wins":159},"stealth/space-bunny-alpha":{"draws":34,"losses":30,"wins":50},"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":28,"losses":13,"wins":37},"tencent/hy4-preview":{"draws":34,"losses":60,"wins":44},"thinkingmachines/inkling":{"draws":59,"losses":32,"wins":101},"thinkingmachines/inkling-small":{"draws":40,"losses":39,"wins":65},"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":66,"wins":46},"x-ai/grok-4.6":{"draws":39,"losses":64,"wins":41},"x-ai/grok-4.7":{"draws":11,"losses":89,"wins":26},"x-ai/grok-build-0.1":{"draws":17,"losses":7,"wins":24},"xiaomi/mimo-v2.5":{"draws":73,"losses":41,"wins":108},"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":87,"losses":79,"wins":122},"z-ai/glm-5.3":{"draws":28,"losses":80,"wins":30},"z-ai/glm-5.3-flash":{"draws":28,"losses":57,"wins":59},"z-ai/glm-5.3-flashx":{"draws":38,"losses":57,"wins":49}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":23,"wins":76},"claude-fable-5":{"draws":28,"losses":81,"wins":35},"claude-fable-5-1":{"draws":7,"losses":140,"wins":15},"claude-haiku-5-5":{"draws":40,"losses":50,"wins":48},"claude-opus-4-5":{"draws":66,"losses":77,"wins":91},"claude-opus-4-8":{"draws":31,"losses":51,"wins":50},"claude-opus-5":{"draws":34,"losses":169,"wins":43},"claude-opus-5-5":{"draws":13,"losses":131,"wins":12},"claude-sonnet-5":{"draws":40,"losses":36,"wins":68},"claude-sonnet-5-5":{"draws":26,"losses":67,"wins":51},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":41},"deepseek/deepseek-v4-flash":{"draws":61,"losses":32,"wins":123},"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":46,"losses":49,"wins":49},"deepseek/deepseek-v4.1-flash-1017":{"draws":32,"losses":72,"wins":40},"elorian/glimpse":{"draws":20,"losses":28,"wins":30},"fireworks/ember-1":{"draws":37,"losses":44,"wins":63},"gemini-3.1-pro-preview":{"draws":34,"losses":40,"wins":70},"gemini-4-argon":{"draws":12,"losses":118,"wins":14},"google/gemini-3.1-flash-lite":{"draws":26,"losses":2,"wins":68},"google/gemini-3.5-flash":{"draws":45,"losses":48,"wins":87},"google/gemini-3.5-flash-lite":{"draws":67,"losses":38,"wins":147},"google/gemini-3.6-flash":{"draws":73,"losses":97,"wins":106},"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":36,"losses":35,"wins":73},"gpt-5.5":{"draws":46,"losses":44,"wins":42},"gpt-5.6-luna":{"draws":47,"losses":34,"wins":63},"gpt-5.6-sol":{"draws":21,"losses":89,"wins":34},"gpt-5.6-terra":{"draws":47,"losses":34,"wins":57},"gpt-6-astra":{"draws":9,"losses":129,"wins":6},"gpt-6-luna":{"draws":39,"losses":48,"wins":57},"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":43,"losses":9,"wins":50},"inception/mercury-3":{"draws":27,"losses":30,"wins":39},"inclusionai/ling-3.0-flash":{"draws":37,"losses":9,"wins":56},"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":44,"losses":12,"wins":70},"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":25,"losses":7,"wins":52},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":10,"wins":17},"moonshotai/kimi-k3":{"draws":31,"losses":34,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":111,"wins":15},"nex-agi/nex-n2-pro":{"draws":19,"losses":10,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":13,"wins":67},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":16,"wins":32},"o3":{"draws":35,"losses":64,"wins":99},"openai/gpt-oss-120b":{"draws":37,"losses":16,"wins":73},"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":44,"losses":45,"wins":55},"qwen/qwen3.8-27b":{"draws":24,"losses":27,"wins":51},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":33},"qwen/qwen3.8-max":{"draws":35,"losses":47,"wins":62},"qwen/qwen3.8-max-0902":{"draws":24,"losses":36,"wins":36},"recursive/flint-v1.0":{"draws":9,"losses":6,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":38,"wins":63},"stealth/ox-alpha":{"draws":105,"losses":183,"wins":186},"stealth/space-bunny-alpha":{"draws":30,"losses":22,"wins":62},"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":43,"losses":16,"wins":85},"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":43,"losses":67,"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":79,"losses":28,"wins":115},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":20,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":37,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":52,"wins":29},"z-ai/glm-5.2":{"draws":93,"losses":58,"wins":137},"z-ai/glm-5.3":{"draws":31,"losses":76,"wins":31},"z-ai/glm-5.3-flash":{"draws":38,"losses":53,"wins":53},"z-ai/glm-5.3-flashx":{"draws":31,"losses":59,"wins":54}},"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":95,"losses":90,"wins":255},"claude-fable-5":{"draws":74,"losses":278,"wins":122},"claude-fable-5-1":{"draws":30,"losses":492,"wins":28},"claude-haiku-5-5":{"draws":96,"losses":173,"wins":165},"claude-opus-4-5":{"draws":195,"losses":218,"wins":337},"claude-opus-4-8":{"draws":80,"losses":156,"wins":158},"claude-opus-5":{"draws":130,"losses":580,"wins":122},"claude-opus-5-5":{"draws":45,"losses":434,"wins":27},"claude-sonnet-5":{"draws":106,"losses":135,"wins":233},"claude-sonnet-5-5":{"draws":82,"losses":227,"wins":165},"cohere/north-mini-code":{"draws":24,"losses":23,"wins":131},"deepseek/deepseek-v4-flash":{"draws":161,"losses":132,"wins":403},"deepseek/deepseek-v4-pro":{"draws":102,"losses":131,"wins":209},"deepseek/deepseek-v4-pro-0813":{"draws":102,"losses":148,"wins":190},"deepseek/deepseek-v4.1-flash":{"draws":108,"losses":181,"wins":184},"deepseek/deepseek-v4.1-flash-1017":{"draws":79,"losses":230,"wins":163},"elorian/glimpse":{"draws":65,"losses":94,"wins":107},"fireworks/ember-1":{"draws":113,"losses":176,"wins":185},"gemini-3.1-pro-preview":{"draws":97,"losses":146,"wins":231},"gemini-4-argon":{"draws":45,"losses":380,"wins":49},"google/gemini-3.1-flash-lite":{"draws":55,"losses":28,"wins":189},"google/gemini-3.5-flash":{"draws":98,"losses":205,"wins":273},"google/gemini-3.5-flash-lite":{"draws":177,"losses":168,"wins":481},"google/gemini-3.6-flash":{"draws":184,"losses":368,"wins":364},"google/gemini-3.8-flash":{"draws":93,"losses":226,"wins":155},"google/gemma-4-31b-it":{"draws":60,"losses":40,"wins":160},"gpt-4.1":{"draws":41,"losses":38,"wins":79},"gpt-4.1-nano":{"draws":33,"losses":5,"wins":34},"gpt-5":{"draws":90,"losses":133,"wins":201},"gpt-5.4":{"draws":114,"losses":183,"wins":161},"gpt-5.4-mini":{"draws":88,"losses":60,"wins":168},"gpt-5.4-nano":{"draws":73,"losses":122,"wins":229},"gpt-5.5":{"draws":117,"losses":160,"wins":165},"gpt-5.6-luna":{"draws":145,"losses":101,"wins":228},"gpt-5.6-sol":{"draws":68,"losses":293,"wins":113},"gpt-5.6-terra":{"draws":128,"losses":128,"wins":200},"gpt-6-astra":{"draws":35,"losses":418,"wins":21},"gpt-6-luna":{"draws":110,"losses":155,"wins":209},"gpt-6-sol":{"draws":60,"losses":341,"wins":73},"gpt-6.1-sol":{"draws":41,"losses":400,"wins":33},"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":83,"losses":33,"wins":212},"inclusionai/ling-3.1-flash":{"draws":6,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":103,"losses":81,"wins":326},"meta/muse-glimmer-30b":{"draws":96,"losses":58,"wins":272},"meta/muse-spark-1.2":{"draws":105,"losses":154,"wins":199},"meta/muse-spark-1.3":{"draws":91,"losses":219,"wins":164},"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":42,"wins":150},"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":69,"losses":42,"wins":171},"moonshotai/kimi-k2.7-code":{"draws":23,"losses":28,"wins":51},"moonshotai/kimi-k3":{"draws":103,"losses":170,"wins":185},"moonshotai/kimi-k3.1-pro":{"draws":54,"losses":348,"wins":32},"nex-agi/nex-n2-pro":{"draws":56,"losses":32,"wins":162},"nex-agi/nex-n2.5-pro":{"draws":26,"losses":20,"wins":62},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":89,"losses":62,"wins":223},"nvidia/nemotron-3.5-super-vl":{"draws":55,"losses":54,"wins":101},"o3":{"draws":80,"losses":205,"wins":319},"openai/gpt-oss-120b":{"draws":106,"losses":61,"wins":257},"poolside/laguna-s-2.1":{"draws":112,"losses":90,"wins":276},"qwen/qwen3.7-max":{"draws":60,"losses":60,"wins":138},"qwen/qwen3.7-plus":{"draws":41,"losses":27,"wins":134},"qwen/qwen3.8-2.4t-a95b":{"draws":118,"losses":179,"wins":177},"qwen/qwen3.8-27b":{"draws":72,"losses":107,"wins":153},"qwen/qwen3.8-flash":{"draws":82,"losses":103,"wins":131},"qwen/qwen3.8-max":{"draws":122,"losses":159,"wins":193},"qwen/qwen3.8-max-0902":{"draws":105,"losses":186,"wins":183},"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":280,"losses":680,"wins":680},"stealth/space-bunny-alpha":{"draws":92,"losses":85,"wins":193},"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":101,"losses":193,"wins":164},"thinkingmachines/inkling":{"draws":164,"losses":120,"wins":374},"thinkingmachines/inkling-small":{"draws":125,"losses":74,"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":98,"losses":208,"wins":168},"x-ai/grok-4.6":{"draws":132,"losses":197,"wins":145},"x-ai/grok-4.7":{"draws":43,"losses":282,"wins":75},"x-ai/grok-build-0.1":{"draws":36,"losses":19,"wins":103},"xiaomi/mimo-v2.5":{"draws":169,"losses":97,"wins":380},"xiaomi/mimo-v2.5-pro":{"draws":44,"losses":59,"wins":139},"xiaomi/mimo-v2.6-flash":{"draws":53,"losses":111,"wins":134},"xiaomi/mimo-v2.6-pro":{"draws":58,"losses":154,"wins":104},"z-ai/glm-5.2":{"draws":242,"losses":230,"wins":476},"z-ai/glm-5.3":{"draws":81,"losses":259,"wins":118},"z-ai/glm-5.3-flash":{"draws":74,"losses":212,"wins":188},"z-ai/glm-5.3-flashx":{"draws":82,"losses":224,"wins":168}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":30,"wins":40},"claude-fable-5":{"draws":30,"losses":69,"wins":15},"claude-fable-5-1":{"draws":4,"losses":124,"wins":2},"claude-haiku-5-5":{"draws":33,"losses":54,"wins":23},"claude-opus-4-5":{"draws":54,"losses":84,"wins":48},"claude-opus-4-8":{"draws":25,"losses":54,"wins":27},"claude-opus-5":{"draws":30,"losses":152,"wins":14},"claude-opus-5-5":{"draws":6,"losses":115,"wins":1},"claude-sonnet-5":{"draws":24,"losses":50,"wins":40},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":24},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-flash":{"draws":48,"losses":48,"wins":72},"deepseek/deepseek-v4-pro":{"draws":29,"losses":47,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":46,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":62,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":76,"wins":18},"elorian/glimpse":{"draws":13,"losses":31,"wins":18},"fireworks/ember-1":{"draws":30,"losses":55,"wins":29},"gemini-3.1-pro-preview":{"draws":25,"losses":48,"wins":41},"gemini-4-argon":{"draws":7,"losses":103,"wins":4},"google/gemini-3.1-flash-lite":{"draws":16,"losses":14,"wins":50},"google/gemini-3.5-flash":{"draws":39,"losses":67,"wins":38},"google/gemini-3.5-flash-lite":{"draws":53,"losses":60,"wins":89},"google/gemini-3.6-flash":{"draws":55,"losses":114,"wins":51},"google/gemini-3.8-flash":{"draws":23,"losses":72,"wins":19},"google/gemma-4-31b-it":{"draws":26,"losses":16,"wins":26},"gpt-4.1":{"draws":11,"losses":14,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":20,"losses":41,"wins":39},"gpt-5.4":{"draws":30,"losses":61,"wins":19},"gpt-5.4-mini":{"draws":23,"losses":17,"wins":36},"gpt-5.4-nano":{"draws":23,"losses":39,"wins":50},"gpt-5.5":{"draws":38,"losses":47,"wins":21},"gpt-5.6-luna":{"draws":33,"losses":36,"wins":45},"gpt-5.6-sol":{"draws":19,"losses":81,"wins":14},"gpt-5.6-terra":{"draws":35,"losses":41,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":37,"losses":51,"wins":26},"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":31,"losses":14,"wins":37},"inception/mercury-3":{"draws":19,"losses":33,"wins":20},"inclusionai/ling-3.0-flash":{"draws":30,"losses":13,"wins":33},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":31,"wins":63},"meta/muse-glimmer-30b":{"draws":35,"losses":27,"wins":40},"meta/muse-spark-1.2":{"draws":30,"losses":54,"wins":26},"meta/muse-spark-1.3":{"draws":20,"losses":71,"wins":23},"meta/muse-spark-open":{"draws":24,"losses":62,"wins":24},"meta/muse-wonder":{"draws":28,"losses":68,"wins":18},"minimax/minimax-m3":{"draws":13,"losses":15,"wins":34},"minimax/minimax-m3.1-flash":{"draws":24,"losses":37,"wins":41},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":14},"mistralai/mistral-medium-3-5":{"draws":18,"losses":12,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":35,"losses":53,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":97,"wins":6},"nex-agi/nex-n2-pro":{"draws":16,"losses":12,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":23,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":21,"wins":16},"o3":{"draws":24,"losses":79,"wins":57},"openai/gpt-oss-120b":{"draws":28,"losses":24,"wins":48},"poolside/laguna-s-2.1":{"draws":30,"losses":30,"wins":46},"qwen/qwen3.7-max":{"draws":15,"losses":29,"wins":22},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":45,"wins":29},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":26,"losses":30,"wins":20},"qwen/qwen3.8-max":{"draws":34,"losses":50,"wins":30},"qwen/qwen3.8-max-0902":{"draws":30,"losses":62,"wins":22},"recursive/flint-v1.0":{"draws":9,"losses":10,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":32,"losses":52,"wins":22},"stealth/ox-alpha":{"draws":92,"losses":193,"wins":85},"stealth/space-bunny-alpha":{"draws":16,"losses":20,"wins":20},"stepfun/step-3.7-flash":{"draws":19,"losses":23,"wins":38},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":23,"losses":17,"wins":22},"tencent/hy4-preview":{"draws":30,"losses":53,"wins":27},"thinkingmachines/inkling":{"draws":48,"losses":45,"wins":61},"thinkingmachines/inkling-small":{"draws":34,"losses":27,"wins":53},"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":64,"wins":19},"x-ai/grok-4.6":{"draws":30,"losses":63,"wins":21},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":19},"xiaomi/mimo-v2.5":{"draws":60,"losses":44,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":17,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":43,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":38,"wins":19},"z-ai/glm-5.2":{"draws":76,"losses":77,"wins":75},"z-ai/glm-5.3":{"draws":22,"losses":80,"wins":8},"z-ai/glm-5.3-flash":{"draws":28,"losses":67,"wins":19},"z-ai/glm-5.3-flashx":{"draws":24,"losses":66,"wins":24}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":38,"wins":33},"claude-fable-5":{"draws":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":27,"wins":22},"claude-fable-5":{"draws":21,"losses":45,"wins":12},"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":53,"wins":29},"claude-opus-4-8":{"draws":19,"losses":39,"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":29,"losses":35,"wins":14},"gemini-3.1-pro-preview":{"draws":21,"losses":34,"wins":23},"gemini-4-argon":{"draws":4,"losses":71,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":13,"wins":21},"google/gemini-3.5-flash":{"draws":28,"losses":41,"wins":29},"google/gemini-3.5-flash-lite":{"draws":50,"losses":28,"wins":58},"google/gemini-3.6-flash":{"draws":45,"losses":73,"wins":30},"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":56,"wins":8},"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":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":24,"wins":34},"meta/muse-glimmer-30b":{"draws":26,"losses":14,"wins":30},"meta/muse-spark-1.2":{"draws":20,"losses":42,"wins":14},"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":13,"wins":15},"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":13,"losses":13,"wins":10},"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":43,"wins":39},"openai/gpt-oss-120b":{"draws":22,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":27,"losses":23,"wins":26},"qwen/qwen3.7-max":{"draws":19,"losses":16,"wins":11},"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":28,"losses":37,"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":23,"losses":22,"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":32,"losses":26,"wins":46},"thinkingmachines/inkling-small":{"draws":31,"losses":17,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":2},"upstage/solar-mini4":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":24,"losses":47,"wins":7},"x-ai/grok-4.6":{"draws":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":34,"wins":46},"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":52,"losses":56,"wins":48},"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":40,"losses":17,"wins":71},"claude-fable-5":{"draws":19,"losses":89,"wins":30},"claude-fable-5-1":{"draws":8,"losses":135,"wins":13},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":54},"claude-opus-4-5":{"draws":62,"losses":58,"wins":104},"claude-opus-4-8":{"draws":31,"losses":45,"wins":50},"claude-opus-5":{"draws":24,"losses":175,"wins":35},"claude-opus-5-5":{"draws":12,"losses":126,"wins":12},"claude-sonnet-5":{"draws":39,"losses":35,"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":51,"losses":38,"wins":117},"deepseek/deepseek-v4-pro":{"draws":27,"losses":38,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":43,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":41,"wins":57},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":71,"wins":43},"elorian/glimpse":{"draws":13,"losses":33,"wins":30},"fireworks/ember-1":{"draws":37,"losses":48,"wins":53},"gemini-3.1-pro-preview":{"draws":32,"losses":42,"wins":64},"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":35,"losses":52,"wins":87},"google/gemini-3.5-flash-lite":{"draws":64,"losses":48,"wins":132},"google/gemini-3.6-flash":{"draws":61,"losses":105,"wins":100},"google/gemini-3.8-flash":{"draws":29,"losses":55,"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":32,"losses":40,"wins":50},"gpt-5.4":{"draws":28,"losses":58,"wins":48},"gpt-5.4-mini":{"draws":34,"losses":11,"wins":47},"gpt-5.4-nano":{"draws":21,"losses":28,"wins":89},"gpt-5.5":{"draws":41,"losses":42,"wins":45},"gpt-5.6-luna":{"draws":44,"losses":25,"wins":69},"gpt-5.6-sol":{"draws":19,"losses":72,"wins":47},"gpt-5.6-terra":{"draws":42,"losses":37,"wins":53},"gpt-6-astra":{"draws":10,"losses":123,"wins":5},"gpt-6-luna":{"draws":40,"losses":37,"wins":61},"gpt-6-sol":{"draws":19,"losses":92,"wins":27},"gpt-6.1-sol":{"draws":6,"losses":119,"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":30,"losses":11,"wins":57},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":39,"losses":24,"wins":89},"meta/muse-glimmer-30b":{"draws":42,"losses":10,"wins":70},"meta/muse-spark-1.2":{"draws":22,"losses":51,"wins":59},"meta/muse-spark-1.3":{"draws":27,"losses":60,"wins":51},"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":21,"losses":10,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":30,"losses":46,"wins":56},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":16},"nex-agi/nex-n2-pro":{"draws":18,"losses":7,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":15,"wins":65},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":16,"wins":33},"o3":{"draws":25,"losses":65,"wins":106},"openai/gpt-oss-120b":{"draws":40,"losses":19,"wins":61},"poolside/laguna-s-2.1":{"draws":34,"losses":28,"wins":70},"qwen/qwen3.7-max":{"draws":19,"losses":18,"wins":43},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":48,"wins":52},"qwen/qwen3.8-27b":{"draws":25,"losses":28,"wins":45},"qwen/qwen3.8-flash":{"draws":24,"losses":28,"wins":40},"qwen/qwen3.8-max":{"draws":34,"losses":44,"wins":60},"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":101,"losses":164,"wins":193},"stealth/space-bunny-alpha":{"draws":30,"losses":27,"wins":53},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":63},"stepfun/step-5-preview":{"draws":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":49,"losses":29,"wins":108},"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":29,"losses":55,"wins":54},"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":16,"losses":5,"wins":25},"xiaomi/mimo-v2.5":{"draws":69,"losses":20,"wins":123},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":15,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":35,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":43,"wins":33},"z-ai/glm-5.2":{"draws":65,"losses":61,"wins":150},"z-ai/glm-5.3":{"draws":21,"losses":85,"wins":26},"z-ai/glm-5.3-flash":{"draws":21,"losses":63,"wins":54},"z-ai/glm-5.3-flashx":{"draws":31,"losses":51,"wins":56}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":59,"losses":72,"wins":47},"claude-fable-5":{"draws":36,"losses":144,"wins":12},"claude-fable-5-1":{"draws":10,"losses":208,"wins":0},"claude-haiku-5-5":{"draws":49,"losses":110,"wins":23},"claude-opus-4-5":{"draws":102,"losses":162,"wins":46},"claude-opus-4-8":{"draws":44,"losses":107,"wins":21},"claude-opus-5":{"draws":49,"losses":259,"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":93,"losses":93,"wins":98},"deepseek/deepseek-v4-pro":{"draws":58,"losses":93,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":75,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":62,"losses":100,"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":56,"losses":107,"wins":29},"gemini-3.1-pro-preview":{"draws":58,"losses":85,"wins":49},"gemini-4-argon":{"draws":17,"losses":164,"wins":11},"google/gemini-3.1-flash-lite":{"draws":36,"losses":32,"wins":58},"google/gemini-3.5-flash":{"draws":54,"losses":139,"wins":47},"google/gemini-3.5-flash-lite":{"draws":93,"losses":129,"wins":116},"google/gemini-3.6-flash":{"draws":103,"losses":215,"wins":54},"google/gemini-3.8-flash":{"draws":48,"losses":125,"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":38,"losses":95,"wins":39},"gpt-5.4":{"draws":49,"losses":108,"wins":29},"gpt-5.4-mini":{"draws":47,"losses":44,"wins":37},"gpt-5.4-nano":{"draws":41,"losses":77,"wins":70},"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":179,"wins":2},"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":47,"losses":31,"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":53,"losses":100,"wins":33},"meta/muse-spark-1.3":{"draws":33,"losses":140,"wins":19},"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":37,"losses":24,"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":25,"losses":27,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":17,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":61,"wins":51},"nvidia/nemotron-3.5-super-vl":{"draws":25,"losses":42,"wins":19},"o3":{"draws":41,"losses":168,"wins":57},"openai/gpt-oss-120b":{"draws":47,"losses":56,"wins":65},"poolside/laguna-s-2.1":{"draws":56,"losses":77,"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":58,"losses":109,"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":59,"losses":101,"wins":32},"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":48,"losses":61,"wins":45},"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":32,"losses":46,"wins":26},"tencent/hy4-preview":{"draws":49,"losses":108,"wins":29},"thinkingmachines/inkling":{"draws":68,"losses":68,"wins":68},"thinkingmachines/inkling-small":{"draws":71,"losses":46,"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":63,"losses":108,"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":57,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":29,"losses":69,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":90,"wins":13},"z-ai/glm-5.2":{"draws":116,"losses":174,"wins":94},"z-ai/glm-5.3":{"draws":35,"losses":126,"wins":21},"z-ai/glm-5.3-flash":{"draws":40,"losses":122,"wins":30},"z-ai/glm-5.3-flashx":{"draws":44,"losses":123,"wins":25}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":46,"losses":57,"wins":29},"claude-fable-5":{"draws":22,"losses":108,"wins":14},"claude-fable-5-1":{"draws":10,"losses":152,"wins":0},"claude-haiku-5-5":{"draws":33,"losses":92,"wins":13},"claude-opus-4-5":{"draws":77,"losses":125,"wins":32},"claude-opus-4-8":{"draws":39,"losses":80,"wins":13},"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":85,"losses":83,"wins":48},"deepseek/deepseek-v4-pro":{"draws":44,"losses":69,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":67,"wins":26},"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":43,"losses":81,"wins":20},"gemini-3.1-pro-preview":{"draws":44,"losses":72,"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":46,"losses":100,"wins":34},"google/gemini-3.5-flash-lite":{"draws":81,"losses":98,"wins":73},"google/gemini-3.6-flash":{"draws":83,"losses":147,"wins":46},"google/gemini-3.8-flash":{"draws":35,"losses":90,"wins":19},"google/gemma-4-31b-it":{"draws":35,"losses":24,"wins":25},"gpt-4.1":{"draws":15,"losses":18,"wins":15},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":42,"losses":62,"wins":22},"gpt-5.4":{"draws":38,"losses":83,"wins":17},"gpt-5.4-mini":{"draws":41,"losses":30,"wins":25},"gpt-5.4-nano":{"draws":44,"losses":60,"wins":40},"gpt-5.5":{"draws":45,"losses":67,"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":42,"losses":28,"wins":32},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":48,"losses":60,"wins":48},"meta/muse-glimmer-30b":{"draws":54,"losses":47,"wins":25},"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":35,"losses":18,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":44,"losses":73,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":122,"wins":5},"nex-agi/nex-n2-pro":{"draws":21,"losses":19,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":10,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":42,"wins":35},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":38,"wins":9},"o3":{"draws":36,"losses":118,"wins":44},"openai/gpt-oss-120b":{"draws":48,"losses":47,"wins":31},"poolside/laguna-s-2.1":{"draws":47,"losses":68,"wins":23},"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":44,"losses":83,"wins":17},"qwen/qwen3.8-27b":{"draws":28,"losses":58,"wins":16},"qwen/qwen3.8-flash":{"draws":36,"losses":40,"wins":20},"qwen/qwen3.8-max":{"draws":40,"losses":65,"wins":39},"qwen/qwen3.8-max-0902":{"draws":43,"losses":85,"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":125,"losses":275,"wins":74},"stealth/space-bunny-alpha":{"draws":34,"losses":53,"wins":27},"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":30,"wins":17},"tencent/hy4-preview":{"draws":42,"losses":81,"wins":15},"thinkingmachines/inkling":{"draws":71,"losses":75,"wins":46},"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":110,"wins":1},"x-ai/grok-build-0.1":{"draws":20,"losses":14,"wins":14},"xiaomi/mimo-v2.5":{"draws":85,"losses":76,"wins":61},"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":100,"losses":129,"wins":59},"z-ai/glm-5.3":{"draws":23,"losses":105,"wins":10},"z-ai/glm-5.3-flash":{"draws":30,"losses":92,"wins":22},"z-ai/glm-5.3-flashx":{"draws":32,"losses":90,"wins":22}},"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":17,"wins":85},"claude-fable-5":{"draws":23,"losses":76,"wins":45},"claude-fable-5-1":{"draws":9,"losses":142,"wins":11},"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":161,"wins":47},"claude-opus-5-5":{"draws":18,"losses":120,"wins":18},"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":33,"losses":38,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":44,"wins":59},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":48,"wins":64},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":61,"wins":56},"elorian/glimpse":{"draws":14,"losses":28,"wins":36},"fireworks/ember-1":{"draws":32,"losses":40,"wins":72},"gemini-3.1-pro-preview":{"draws":30,"losses":43,"wins":71},"gemini-4-argon":{"draws":10,"losses":108,"wins":26},"google/gemini-3.1-flash-lite":{"draws":17,"losses":3,"wins":76},"google/gemini-3.5-flash":{"draws":32,"losses":61,"wins":87},"google/gemini-3.5-flash-lite":{"draws":62,"losses":46,"wins":144},"google/gemini-3.6-flash":{"draws":58,"losses":104,"wins":114},"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":43,"wins":54},"gpt-5.6-luna":{"draws":37,"losses":35,"wins":72},"gpt-5.6-sol":{"draws":19,"losses":84,"wins":41},"gpt-5.6-terra":{"draws":40,"losses":31,"wins":67},"gpt-6-astra":{"draws":9,"losses":120,"wins":15},"gpt-6-luna":{"draws":33,"losses":46,"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":20,"losses":7,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":4,"wins":23},"moonshotai/kimi-k3":{"draws":27,"losses":45,"wins":66},"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":30,"losses":12,"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":46,"wins":66},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":61},"recursive/flint-v1.0":{"draws":12,"losses":0,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":38,"losses":31,"wins":63},"stealth/ox-alpha":{"draws":98,"losses":168,"wins":208},"stealth/space-bunny-alpha":{"draws":31,"losses":19,"wins":64},"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":29,"losses":54,"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":43,"wins":36},"z-ai/glm-5.2":{"draws":71,"losses":59,"wins":158},"z-ai/glm-5.3":{"draws":26,"losses":78,"wins":34},"z-ai/glm-5.3-flash":{"draws":19,"losses":65,"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":33,"losses":16,"wins":83},"claude-fable-5":{"draws":31,"losses":64,"wins":49},"claude-fable-5-1":{"draws":9,"losses":129,"wins":24},"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":160,"wins":48},"claude-opus-5-5":{"draws":16,"losses":125,"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":52,"losses":22,"wins":142},"deepseek/deepseek-v4-pro":{"draws":32,"losses":27,"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":37,"losses":43,"wins":64},"gemini-3.1-pro-preview":{"draws":38,"losses":27,"wins":79},"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":46,"losses":38,"wins":96},"google/gemini-3.5-flash-lite":{"draws":62,"losses":32,"wins":158},"google/gemini-3.6-flash":{"draws":70,"losses":82,"wins":124},"google/gemini-3.8-flash":{"draws":40,"losses":53,"wins":51},"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":34,"losses":19,"wins":73},"gpt-5.4":{"draws":36,"losses":47,"wins":55},"gpt-5.4-mini":{"draws":31,"losses":14,"wins":51},"gpt-5.4-nano":{"draws":23,"losses":25,"wins":96},"gpt-5.5":{"draws":39,"losses":38,"wins":55},"gpt-5.6-luna":{"draws":37,"losses":21,"wins":86},"gpt-5.6-sol":{"draws":28,"losses":58,"wins":58},"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":17,"losses":114,"wins":13},"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":33,"losses":5,"wins":64},"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":25,"losses":6,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":8,"wins":18},"moonshotai/kimi-k3":{"draws":31,"losses":34,"wins":73},"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":44,"losses":12,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":10,"wins":42},"o3":{"draws":34,"losses":44,"wins":120},"openai/gpt-oss-120b":{"draws":37,"losses":10,"wins":79},"poolside/laguna-s-2.1":{"draws":35,"losses":17,"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":33,"losses":50,"wins":61},"qwen/qwen3.8-27b":{"draws":26,"losses":23,"wins":53},"qwen/qwen3.8-flash":{"draws":35,"losses":16,"wins":45},"qwen/qwen3.8-max":{"draws":39,"losses":41,"wins":64},"qwen/qwen3.8-max-0902":{"draws":43,"losses":34,"wins":67},"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":132,"losses":145,"wins":197},"stealth/space-bunny-alpha":{"draws":30,"losses":21,"wins":63},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":67},"stepfun/step-5-preview":{"draws":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":63,"losses":21,"wins":108},"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":74,"losses":50,"wins":164},"z-ai/glm-5.3":{"draws":27,"losses":67,"wins":44},"z-ai/glm-5.3-flash":{"draws":33,"losses":50,"wins":61},"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":15,"wins":93},"claude-fable-5":{"draws":7,"losses":42,"wins":77},"claude-fable-5-1":{"draws":6,"losses":97,"wins":37},"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":101,"wins":99},"claude-opus-5-5":{"draws":11,"losses":98,"wins":29},"claude-sonnet-5":{"draws":12,"losses":25,"wins":89},"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":18,"losses":15,"wins":159},"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":12,"losses":24,"wins":90},"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":24,"wins":120},"google/gemini-3.5-flash-lite":{"draws":20,"losses":28,"wins":170},"google/gemini-3.6-flash":{"draws":15,"losses":57,"wins":168},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":89},"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":15,"losses":11,"wins":106},"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":11,"losses":93,"wins":22},"gpt-6-luna":{"draws":10,"losses":20,"wins":96},"gpt-6-sol":{"draws":13,"losses":53,"wins":60},"gpt-6.1-sol":{"draws":6,"losses":79,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":72},"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":16,"wins":50},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":31,"wins":86},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":58},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":63},"qwen/qwen3.8-max":{"draws":11,"losses":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":43,"losses":75,"wins":282},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":73},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":75},"stepfun/step-5-preview":{"draws":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":1,"wins":110},"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":14,"losses":20,"wins":10},"claude-fable-5":{"draws":8,"losses":34,"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":38,"wins":13},"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":25,"losses":28,"wins":19},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":26,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":7},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":13},"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":16,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":33,"losses":26,"wins":25},"google/gemini-3.6-flash":{"draws":31,"losses":55,"wins":6},"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":13,"losses":20,"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":9,"losses":26,"wins":13},"gpt-5.5":{"draws":21,"losses":16,"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":23,"wins":6},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"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":10,"losses":5,"wins":19},"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":19,"losses":10,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":13,"losses":37,"wins":16},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":15},"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":12,"losses":21,"wins":1},"qwen/qwen3.8-flash":{"draws":15,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":17,"losses":24,"wins":7},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":36,"losses":103,"wins":19},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"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":16,"losses":25,"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":35,"wins":19},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":30,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":72,"losses":80,"wins":52},"claude-fable-5":{"draws":38,"losses":178,"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":184,"wins":54},"claude-opus-4-8":{"draws":62,"losses":132,"wins":24},"claude-opus-5":{"draws":57,"losses":298,"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":115,"losses":111,"wins":108},"deepseek/deepseek-v4-pro":{"draws":71,"losses":99,"wins":32},"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":70,"losses":115,"wins":37},"gemini-3.1-pro-preview":{"draws":72,"losses":95,"wins":55},"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":81,"losses":153,"wins":50},"google/gemini-3.5-flash-lite":{"draws":126,"losses":136,"wins":130},"google/gemini-3.6-flash":{"draws":129,"losses":244,"wins":51},"google/gemini-3.8-flash":{"draws":58,"losses":144,"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":56,"losses":95,"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":54,"losses":108,"wins":74},"gpt-5.5":{"draws":83,"losses":99,"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":115,"wins":28},"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":68,"losses":38,"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":55,"losses":28,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":30,"wins":11},"moonshotai/kimi-k3":{"draws":73,"losses":107,"wins":32},"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":83,"losses":67,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":47,"wins":24},"o3":{"draws":56,"losses":197,"wins":63},"openai/gpt-oss-120b":{"draws":66,"losses":68,"wins":54},"poolside/laguna-s-2.1":{"draws":62,"losses":83,"wins":57},"qwen/qwen3.7-max":{"draws":53,"losses":54,"wins":27},"qwen/qwen3.7-plus":{"draws":42,"losses":44,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":86,"losses":111,"wins":25},"qwen/qwen3.8-27b":{"draws":42,"losses":89,"wins":29},"qwen/qwen3.8-flash":{"draws":57,"losses":60,"wins":31},"qwen/qwen3.8-max":{"draws":73,"losses":108,"wins":41},"qwen/qwen3.8-max-0902":{"draws":79,"losses":115,"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":169,"losses":380,"wins":97},"stealth/space-bunny-alpha":{"draws":60,"losses":74,"wins":44},"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":46,"wins":34},"tencent/hy4-preview":{"draws":69,"losses":123,"wins":20},"thinkingmachines/inkling":{"draws":96,"losses":82,"wins":112},"thinkingmachines/inkling-small":{"draws":85,"losses":61,"wins":76},"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":162,"losses":192,"wins":90},"z-ai/glm-5.3":{"draws":47,"losses":159,"wins":4},"z-ai/glm-5.3-flash":{"draws":49,"losses":134,"wins":39},"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":7,"losses":66,"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":15,"losses":44,"wins":15},"claude-opus-5":{"draws":13,"losses":110,"wins":5},"claude-opus-5-5":{"draws":3,"losses":82,"wins":1},"claude-sonnet-5":{"draws":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":32,"losses":42,"wins":46},"deepseek/deepseek-v4-pro":{"draws":13,"losses":38,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":38,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":38,"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":14,"losses":36,"wins":28},"gemini-4-argon":{"draws":2,"losses":72,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":2,"wins":44},"google/gemini-3.5-flash":{"draws":19,"losses":51,"wins":30},"google/gemini-3.5-flash-lite":{"draws":41,"losses":48,"wins":49},"google/gemini-3.6-flash":{"draws":31,"losses":88,"wins":31},"google/gemini-3.8-flash":{"draws":14,"losses":51,"wins":13},"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":11,"losses":23,"wins":18},"gpt-5.4-nano":{"draws":14,"losses":35,"wins":37},"gpt-5.5":{"draws":20,"losses":37,"wins":15},"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":19,"losses":11,"wins":26},"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":11,"losses":44,"wins":19},"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":17,"losses":35,"wins":22},"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":14,"losses":44,"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":20,"losses":25,"wins":17},"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":15,"losses":46,"wins":15},"thinkingmachines/inkling":{"draws":22,"losses":25,"wins":57},"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":13,"losses":20,"wins":49},"claude-fable-5":{"draws":15,"losses":53,"wins":22},"claude-fable-5-1":{"draws":4,"losses":87,"wins":9},"claude-haiku-5-5":{"draws":21,"losses":38,"wins":27},"claude-opus-4-5":{"draws":33,"losses":44,"wins":69},"claude-opus-4-8":{"draws":16,"losses":28,"wins":38},"claude-opus-5":{"draws":16,"losses":119,"wins":17},"claude-opus-5-5":{"draws":8,"losses":88,"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":27,"losses":28,"wins":83},"deepseek/deepseek-v4-pro":{"draws":18,"losses":26,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":36,"wins":36},"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":11,"losses":37,"wins":42},"gemini-3.1-pro-preview":{"draws":15,"losses":30,"wins":45},"gemini-4-argon":{"draws":3,"losses":79,"wins":8},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":44},"google/gemini-3.5-flash":{"draws":18,"losses":43,"wins":51},"google/gemini-3.5-flash-lite":{"draws":29,"losses":20,"wins":107},"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":12,"losses":27,"wins":41},"gpt-5.4":{"draws":21,"losses":38,"wins":27},"gpt-5.4-mini":{"draws":13,"losses":15,"wins":32},"gpt-5.4-nano":{"draws":22,"losses":20,"wins":52},"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":61,"wins":20},"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":23,"losses":20,"wins":55},"meta/muse-glimmer-30b":{"draws":19,"losses":16,"wins":43},"meta/muse-spark-1.2":{"draws":10,"losses":47,"wins":29},"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":19,"losses":31,"wins":36},"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":20,"losses":15,"wins":45},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":18},"o3":{"draws":16,"losses":37,"wins":75},"openai/gpt-oss-120b":{"draws":20,"losses":7,"wins":53},"poolside/laguna-s-2.1":{"draws":22,"losses":14,"wins":54},"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":20,"losses":34,"wins":36},"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":14,"losses":39,"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":53,"losses":134,"wins":111},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":43},"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":15,"losses":36,"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":36,"losses":49,"wins":95},"z-ai/glm-5.3":{"draws":14,"losses":54,"wins":18},"z-ai/glm-5.3-flash":{"draws":12,"losses":44,"wins":34},"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":14,"losses":83,"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":9,"losses":81,"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":12,"losses":27,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":31,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":42,"wins":44},"elorian/glimpse":{"draws":8,"losses":22,"wins":22},"fireworks/ember-1":{"draws":21,"losses":29,"wins":46},"gemini-3.1-pro-preview":{"draws":15,"losses":24,"wins":57},"gemini-4-argon":{"draws":9,"losses":64,"wins":23},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":50},"google/gemini-3.5-flash":{"draws":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":30,"wins":46},"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":30,"wins":42},"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":58,"losses":104,"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":13,"wins":90},"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":36,"wins":43},"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":94,"losses":74,"wins":96},"claude-fable-5":{"draws":56,"losses":190,"wins":42},"claude-fable-5-1":{"draws":19,"losses":298,"wins":7},"claude-haiku-5-5":{"draws":64,"losses":148,"wins":64},"claude-opus-4-5":{"draws":144,"losses":191,"wins":133},"claude-opus-4-8":{"draws":74,"losses":131,"wins":59},"claude-opus-5":{"draws":73,"losses":385,"wins":34},"claude-opus-5-5":{"draws":18,"losses":282,"wins":12},"claude-sonnet-5":{"draws":79,"losses":120,"wins":89},"claude-sonnet-5-5":{"draws":54,"losses":168,"wins":66},"cohere/north-mini-code":{"draws":30,"losses":18,"wins":60},"deepseek/deepseek-v4-flash":{"draws":144,"losses":105,"wins":183},"deepseek/deepseek-v4-pro":{"draws":81,"losses":99,"wins":84},"deepseek/deepseek-v4-pro-0813":{"draws":84,"losses":101,"wins":79},"deepseek/deepseek-v4.1-flash":{"draws":101,"losses":123,"wins":64},"deepseek/deepseek-v4.1-flash-1017":{"draws":62,"losses":173,"wins":53},"elorian/glimpse":{"draws":35,"losses":72,"wins":49},"fireworks/ember-1":{"draws":83,"losses":131,"wins":74},"gemini-3.1-pro-preview":{"draws":82,"losses":112,"wins":94},"gemini-4-argon":{"draws":27,"losses":247,"wins":14},"google/gemini-3.1-flash-lite":{"draws":43,"losses":23,"wins":126},"google/gemini-3.5-flash":{"draws":90,"losses":158,"wins":112},"google/gemini-3.5-flash-lite":{"draws":160,"losses":143,"wins":201},"google/gemini-3.6-flash":{"draws":146,"losses":255,"wins":151},"google/gemini-3.8-flash":{"draws":68,"losses":160,"wins":60},"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":74,"losses":103,"wins":75},"gpt-5.4":{"draws":76,"losses":140,"wins":60},"gpt-5.4-mini":{"draws":81,"losses":37,"wins":74},"gpt-5.4-nano":{"draws":63,"losses":98,"wins":127},"gpt-5.5":{"draws":97,"losses":118,"wins":49},"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":109,"losses":99,"wins":68},"gpt-6-astra":{"draws":20,"losses":258,"wins":10},"gpt-6-luna":{"draws":102,"losses":114,"wins":72},"gpt-6-sol":{"draws":42,"losses":212,"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":85,"losses":41,"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":108,"losses":47,"wins":97},"meta/muse-spark-1.2":{"draws":66,"losses":137,"wins":73},"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":65,"losses":25,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":31,"wins":24},"moonshotai/kimi-k3":{"draws":87,"losses":113,"wins":76},"moonshotai/kimi-k3.1-pro":{"draws":32,"losses":229,"wins":15},"nex-agi/nex-n2-pro":{"draws":50,"losses":21,"wins":73},"nex-agi/nex-n2.5-pro":{"draws":16,"losses":21,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":89,"losses":65,"wins":98},"nvidia/nemotron-3.5-super-vl":{"draws":42,"losses":46,"wins":44},"o3":{"draws":66,"losses":178,"wins":152},"openai/gpt-oss-120b":{"draws":95,"losses":50,"wins":107},"poolside/laguna-s-2.1":{"draws":97,"losses":79,"wins":100},"qwen/qwen3.7-max":{"draws":52,"losses":54,"wins":62},"qwen/qwen3.7-plus":{"draws":41,"losses":33,"wins":70},"qwen/qwen3.8-2.4t-a95b":{"draws":96,"losses":121,"wins":71},"qwen/qwen3.8-27b":{"draws":64,"losses":70,"wins":70},"qwen/qwen3.8-flash":{"draws":61,"losses":73,"wins":58},"qwen/qwen3.8-max":{"draws":87,"losses":122,"wins":79},"qwen/qwen3.8-max-0902":{"draws":93,"losses":137,"wins":58},"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":242,"losses":476,"wins":230},"stealth/space-bunny-alpha":{"draws":76,"losses":75,"wins":77},"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":52,"losses":48,"wins":56},"tencent/hy4-preview":{"draws":65,"losses":150,"wins":61},"thinkingmachines/inkling":{"draws":116,"losses":94,"wins":174},"thinkingmachines/inkling-small":{"draws":100,"losses":59,"wins":129},"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":74,"losses":164,"wins":50},"x-ai/grok-4.7":{"draws":29,"losses":186,"wins":37},"x-ai/grok-build-0.1":{"draws":42,"losses":19,"wins":35},"xiaomi/mimo-v2.5":{"draws":162,"losses":90,"wins":192},"xiaomi/mimo-v2.5-pro":{"draws":46,"losses":49,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":36,"losses":95,"wins":49},"xiaomi/mimo-v2.6-pro":{"draws":49,"losses":106,"wins":37},"z-ai/glm-5.2":{"draws":162,"losses":159,"wins":159},"z-ai/glm-5.3":{"draws":63,"losses":175,"wins":38},"z-ai/glm-5.3-flash":{"draws":62,"losses":161,"wins":65},"z-ai/glm-5.3-flashx":{"draws":81,"losses":142,"wins":65}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":17,"wins":86},"claude-fable-5":{"draws":20,"losses":54,"wins":64},"claude-fable-5-1":{"draws":12,"losses":123,"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":20,"losses":31,"wins":75},"claude-opus-5":{"draws":31,"losses":138,"wins":65},"claude-opus-5-5":{"draws":10,"losses":114,"wins":26},"claude-sonnet-5":{"draws":28,"losses":19,"wins":91},"claude-sonnet-5-5":{"draws":22,"losses":53,"wins":63},"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":21,"losses":27,"wins":78},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":25,"wins":79},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":27,"wins":86},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":41,"wins":73},"elorian/glimpse":{"draws":13,"losses":15,"wins":46},"fireworks/ember-1":{"draws":23,"losses":26,"wins":89},"gemini-3.1-pro-preview":{"draws":26,"losses":28,"wins":84},"gemini-4-argon":{"draws":15,"losses":83,"wins":40},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":79},"google/gemini-3.5-flash":{"draws":31,"losses":35,"wins":106},"google/gemini-3.5-flash-lite":{"draws":40,"losses":17,"wins":185},"google/gemini-3.6-flash":{"draws":51,"losses":61,"wins":152},"google/gemini-3.8-flash":{"draws":28,"losses":39,"wins":71},"google/gemma-4-31b-it":{"draws":22,"losses":7,"wins":53},"gpt-4.1":{"draws":6,"losses":8,"wins":32},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":16,"losses":22,"wins":82},"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":28,"losses":23,"wins":75},"gpt-5.6-luna":{"draws":28,"losses":15,"wins":95},"gpt-5.6-sol":{"draws":22,"losses":62,"wins":54},"gpt-5.6-terra":{"draws":33,"losses":21,"wins":78},"gpt-6-astra":{"draws":18,"losses":109,"wins":11},"gpt-6-luna":{"draws":25,"losses":29,"wins":84},"gpt-6-sol":{"draws":20,"losses":73,"wins":45},"gpt-6.1-sol":{"draws":22,"losses":92,"wins":24},"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":21,"losses":3,"wins":72},"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":24,"losses":40,"wins":74},"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":14,"losses":4,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":21},"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":2,"wins":56},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":12,"wins":85},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":51},"o3":{"draws":15,"losses":35,"wins":138},"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":14,"losses":7,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":30,"wins":82},"qwen/qwen3.8-27b":{"draws":24,"losses":12,"wins":60},"qwen/qwen3.8-flash":{"draws":23,"losses":14,"wins":55},"qwen/qwen3.8-max":{"draws":28,"losses":30,"wins":80},"qwen/qwen3.8-max-0902":{"draws":31,"losses":31,"wins":76},"recursive/flint-v1.0":{"draws":7,"losses":2,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":22,"wins":88},"stealth/ox-alpha":{"draws":81,"losses":118,"wins":259},"stealth/space-bunny-alpha":{"draws":22,"losses":8,"wins":80},"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":21,"losses":26,"wins":85},"thinkingmachines/inkling":{"draws":35,"losses":21,"wins":126},"thinkingmachines/inkling-small":{"draws":23,"losses":10,"wins":105},"unbiased/pareto-26.10":{"draws":5,"losses":37,"wins":4},"unbiased/pareto-26.10-preview":{"draws":4,"losses":37,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":32},"x-ai/grok-4.5":{"draws":26,"losses":34,"wins":78},"x-ai/grok-4.6":{"draws":27,"losses":44,"wins":67},"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":63,"losses":38,"wins":175},"z-ai/glm-5.3":{"draws":20,"losses":34,"wins":34},"z-ai/glm-5.3-flash":{"draws":31,"losses":32,"wins":75},"z-ai/glm-5.3-flashx":{"draws":25,"losses":33,"wins":80}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":30,"wins":74},"claude-fable-5":{"draws":21,"losses":77,"wins":46},"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":54,"losses":56,"wins":124},"claude-opus-4-8":{"draws":19,"losses":52,"wins":61},"claude-opus-5":{"draws":37,"losses":163,"wins":46},"claude-opus-5-5":{"draws":12,"losses":134,"wins":10},"claude-sonnet-5":{"draws":24,"losses":41,"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":51,"losses":45,"wins":120},"deepseek/deepseek-v4-pro":{"draws":21,"losses":38,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":36,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":58,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":73,"wins":45},"elorian/glimpse":{"draws":12,"losses":31,"wins":35},"fireworks/ember-1":{"draws":25,"losses":46,"wins":73},"gemini-3.1-pro-preview":{"draws":34,"losses":43,"wins":67},"gemini-4-argon":{"draws":15,"losses":110,"wins":19},"google/gemini-3.1-flash-lite":{"draws":19,"losses":13,"wins":64},"google/gemini-3.5-flash":{"draws":22,"losses":61,"wins":97},"google/gemini-3.5-flash-lite":{"draws":46,"losses":48,"wins":158},"google/gemini-3.6-flash":{"draws":41,"losses":92,"wins":143},"google/gemini-3.8-flash":{"draws":18,"losses":71,"wins":55},"google/gemma-4-31b-it":{"draws":25,"losses":14,"wins":45},"gpt-4.1":{"draws":5,"losses":15,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":18,"losses":35,"wins":73},"gpt-5.4":{"draws":16,"losses":63,"wins":59},"gpt-5.4-mini":{"draws":21,"losses":21,"wins":54},"gpt-5.4-nano":{"draws":20,"losses":40,"wins":84},"gpt-5.5":{"draws":24,"losses":50,"wins":58},"gpt-5.6-luna":{"draws":38,"losses":28,"wins":78},"gpt-5.6-sol":{"draws":24,"losses":73,"wins":47},"gpt-5.6-terra":{"draws":30,"losses":42,"wins":66},"gpt-6-astra":{"draws":12,"losses":124,"wins":8},"gpt-6-luna":{"draws":39,"losses":34,"wins":71},"gpt-6-sol":{"draws":19,"losses":90,"wins":35},"gpt-6.1-sol":{"draws":12,"losses":116,"wins":16},"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":28,"losses":15,"wins":59},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":33,"wins":99},"meta/muse-glimmer-30b":{"draws":26,"losses":18,"wins":82},"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":22,"losses":11,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":17},"moonshotai/kimi-k3":{"draws":27,"losses":44,"wins":67},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":103,"wins":19},"nex-agi/nex-n2-pro":{"draws":12,"losses":10,"wins":50},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":40,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":21,"wins":35},"o3":{"draws":21,"losses":76,"wins":101},"openai/gpt-oss-120b":{"draws":26,"losses":20,"wins":80},"poolside/laguna-s-2.1":{"draws":28,"losses":34,"wins":76},"qwen/qwen3.7-max":{"draws":23,"losses":19,"wins":42},"qwen/qwen3.7-plus":{"draws":15,"losses":14,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":48,"wins":67},"qwen/qwen3.8-27b":{"draws":19,"losses":32,"wins":51},"qwen/qwen3.8-flash":{"draws":18,"losses":35,"wins":43},"qwen/qwen3.8-max":{"draws":28,"losses":59,"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":74,"losses":188,"wins":212},"stealth/space-bunny-alpha":{"draws":28,"losses":19,"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":21,"losses":54,"wins":63},"thinkingmachines/inkling":{"draws":40,"losses":30,"wins":122},"thinkingmachines/inkling-small":{"draws":30,"losses":22,"wins":92},"unbiased/pareto-26.10":{"draws":3,"losses":39,"wins":6},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":6},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":19,"losses":60,"wins":65},"x-ai/grok-4.6":{"draws":33,"losses":61,"wins":50},"x-ai/grok-4.7":{"draws":16,"losses":76,"wins":34},"x-ai/grok-build-0.1":{"draws":10,"losses":8,"wins":30},"xiaomi/mimo-v2.5":{"draws":49,"losses":39,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":14,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":34,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":50,"wins":30},"z-ai/glm-5.2":{"draws":62,"losses":65,"wins":161},"z-ai/glm-5.3":{"draws":31,"losses":75,"wins":32},"z-ai/glm-5.3-flash":{"draws":12,"losses":42,"wins":42},"z-ai/glm-5.3-flashx":{"draws":31,"losses":56,"wins":57}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":25,"wins":83},"claude-fable-5":{"draws":22,"losses":78,"wins":44},"claude-fable-5-1":{"draws":11,"losses":139,"wins":12},"claude-haiku-5-5":{"draws":27,"losses":60,"wins":51},"claude-opus-4-5":{"draws":52,"losses":56,"wins":126},"claude-opus-4-8":{"draws":25,"losses":58,"wins":49},"claude-opus-5":{"draws":36,"losses":167,"wins":43},"claude-opus-5-5":{"draws":14,"losses":130,"wins":12},"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":57,"losses":34,"wins":125},"deepseek/deepseek-v4-pro":{"draws":30,"losses":42,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":39,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":44,"wins":60},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":72,"wins":48},"elorian/glimpse":{"draws":17,"losses":29,"wins":32},"fireworks/ember-1":{"draws":28,"losses":49,"wins":67},"gemini-3.1-pro-preview":{"draws":32,"losses":40,"wins":72},"gemini-4-argon":{"draws":12,"losses":110,"wins":22},"google/gemini-3.1-flash-lite":{"draws":24,"losses":8,"wins":64},"google/gemini-3.5-flash":{"draws":36,"losses":50,"wins":94},"google/gemini-3.5-flash-lite":{"draws":63,"losses":47,"wins":142},"google/gemini-3.6-flash":{"draws":68,"losses":96,"wins":112},"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":32,"losses":32,"wins":62},"gpt-5.4":{"draws":29,"losses":54,"wins":55},"gpt-5.4-mini":{"draws":26,"losses":13,"wins":57},"gpt-5.4-nano":{"draws":28,"losses":35,"wins":81},"gpt-5.5":{"draws":40,"losses":44,"wins":48},"gpt-5.6-luna":{"draws":42,"losses":29,"wins":73},"gpt-5.6-sol":{"draws":24,"losses":79,"wins":41},"gpt-5.6-terra":{"draws":38,"losses":39,"wins":61},"gpt-6-astra":{"draws":14,"losses":122,"wins":8},"gpt-6-luna":{"draws":31,"losses":43,"wins":70},"gpt-6-sol":{"draws":17,"losses":86,"wins":41},"gpt-6.1-sol":{"draws":16,"losses":109,"wins":19},"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":29,"losses":50,"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":19,"losses":8,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":13,"wins":12},"moonshotai/kimi-k3":{"draws":34,"losses":38,"wins":66},"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":28,"losses":22,"wins":76},"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":22,"losses":26,"wins":54},"qwen/qwen3.8-flash":{"draws":29,"losses":25,"wins":42},"qwen/qwen3.8-max":{"draws":38,"losses":49,"wins":57},"qwen/qwen3.8-max-0902":{"draws":31,"losses":54,"wins":59},"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":82,"losses":168,"wins":224},"stealth/space-bunny-alpha":{"draws":24,"losses":24,"wins":66},"stepfun/step-3.7-flash":{"draws":13,"losses":14,"wins":75},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":14,"wins":48},"tencent/hy4-preview":{"draws":31,"losses":56,"wins":51},"thinkingmachines/inkling":{"draws":44,"losses":25,"wins":123},"thinkingmachines/inkling-small":{"draws":32,"losses":22,"wins":90},"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":81,"losses":65,"wins":142},"z-ai/glm-5.3":{"draws":25,"losses":80,"wins":33},"z-ai/glm-5.3-flash":{"draws":31,"losses":57,"wins":56},"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":9,"wins":9},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":29,"losses":32,"wins":17},"claude-opus-4-8":{"draws":14,"losses":24,"wins":6},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":15,"losses":23,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":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":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":34,"losses":17,"wins":33},"google/gemini-3.6-flash":{"draws":24,"losses":44,"wins":24},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":15,"wins":12},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":19},"gpt-5.5":{"draws":18,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":12},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":6,"wins":13},"inception/mercury-3":{"draws":15,"losses":7,"wins":10},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":11,"wins":28},"meta/muse-glimmer-30b":{"draws":15,"losses":9,"wins":18},"meta/muse-spark-1.2":{"draws":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":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":10,"losses":16,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":22,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":35,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":5,"wins":7},"o3":{"draws":14,"losses":29,"wins":23},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":17,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":18},"qwen/qwen3.8-max-0902":{"draws":15,"losses":23,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":36,"losses":87,"wins":35},"stealth/space-bunny-alpha":{"draws":18,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":23,"wins":8},"thinkingmachines/inkling":{"draws":25,"losses":11,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":28,"wins":6},"x-ai/grok-4.6":{"draws":9,"losses":34,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":35,"losses":30,"wins":31},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":36},"claude-fable-5":{"draws":1,"losses":12,"wins":19},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":1,"losses":12,"wins":65},"claude-opus-4-8":{"draws":1,"losses":12,"wins":31},"claude-opus-5":{"draws":10,"losses":40,"wins":32},"claude-opus-5-5":{"draws":6,"losses":38,"wins":8},"claude-sonnet-5":{"draws":3,"losses":5,"wins":40},"claude-sonnet-5-5":{"draws":1,"losses":19,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":9,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":7,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":27},"elorian/glimpse":{"draws":0,"losses":6,"wins":20},"fireworks/ember-1":{"draws":6,"losses":5,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":34},"gemini-4-argon":{"draws":7,"losses":28,"wins":13},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":30},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":54},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":78},"google/gemini-3.6-flash":{"draws":4,"losses":19,"wins":69},"google/gemini-3.8-flash":{"draws":4,"losses":19,"wins":25},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":9,"wins":32},"gpt-5.4":{"draws":7,"losses":16,"wins":23},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":6,"wins":41},"gpt-5.5":{"draws":3,"losses":18,"wins":23},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":41},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":26},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":35},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":6,"losses":10,"wins":32},"gpt-6-sol":{"draws":4,"losses":27,"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":2,"losses":1,"wins":31},"inception/mercury-3":{"draws":3,"losses":3,"wins":26},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":46},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":38},"meta/muse-spark-1.2":{"draws":2,"losses":8,"wins":36},"meta/muse-spark-1.3":{"draws":3,"losses":8,"wins":37},"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":1,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":8,"wins":35},"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":1,"losses":5,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":21},"o3":{"draws":3,"losses":11,"wins":52},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":11,"wins":35},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":29},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":23},"qwen/qwen3.8-max":{"draws":4,"losses":9,"wins":35},"qwen/qwen3.8-max-0902":{"draws":4,"losses":11,"wins":33},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":8,"wins":33},"stealth/ox-alpha":{"draws":11,"losses":23,"wins":124},"stealth/space-bunny-alpha":{"draws":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":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":38},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":44},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"unbiased/pareto-26.10-preview":{"draws":3,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":35},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":20},"z-ai/glm-5.2":{"draws":8,"losses":10,"wins":78},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":7,"losses":7,"wins":34},"z-ai/glm-5.3-flashx":{"draws":3,"losses":11,"wins":34}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":56},"claude-fable-5":{"draws":0,"losses":4,"wins":62},"claude-fable-5-1":{"draws":7,"losses":8,"wins":41},"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":18,"wins":90},"claude-opus-5-5":{"draws":7,"losses":32,"wins":31},"claude-sonnet-5":{"draws":0,"losses":1,"wins":65},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":53},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":25},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":95},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":5,"wins":60},"elorian/glimpse":{"draws":1,"losses":2,"wins":35},"fireworks/ember-1":{"draws":1,"losses":1,"wins":64},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":63},"gemini-4-argon":{"draws":3,"losses":13,"wins":50},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":41},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":80},"google/gemini-3.5-flash-lite":{"draws":1,"losses":2,"wins":113},"google/gemini-3.6-flash":{"draws":1,"losses":4,"wins":123},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":60},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":37},"gpt-4.1":{"draws":0,"losses":0,"wins":22},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":58},"gpt-5.4":{"draws":1,"losses":3,"wins":60},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":44},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":58},"gpt-5.5":{"draws":0,"losses":3,"wins":59},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":65},"gpt-5.6-sol":{"draws":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":2,"wins":63},"gpt-6-sol":{"draws":2,"losses":11,"wins":53},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":42},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":45},"inception/mercury-3":{"draws":0,"losses":0,"wins":42},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":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":7,"losses":5,"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":2,"wins":63},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":57},"x-ai/grok-4.7":{"draws":2,"losses":4,"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":2,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":3,"wins":36},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":129},"z-ai/glm-5.3":{"draws":3,"losses":2,"wins":59},"z-ai/glm-5.3-flash":{"draws":2,"losses":3,"wins":61},"z-ai/glm-5.3-flashx":{"draws":3,"losses":2,"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":10,"losses":7,"wins":27},"claude-fable-5":{"draws":6,"losses":33,"wins":9},"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":15,"losses":16,"wins":13},"claude-opus-5":{"draws":9,"losses":65,"wins":8},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":20,"losses":10,"wins":18},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":40},"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":13,"losses":16,"wins":19},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"wins":24},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":23},"google/gemini-3.5-flash-lite":{"draws":29,"losses":19,"wins":36},"google/gemini-3.6-flash":{"draws":24,"losses":43,"wins":25},"google/gemini-3.8-flash":{"draws":13,"losses":27,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":13,"wins":18},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":4,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":22},"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":9,"losses":9,"wins":34},"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":7,"losses":2,"wins":19},"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":15,"losses":3,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":7},"o3":{"draws":7,"losses":18,"wins":41},"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":16,"losses":19,"wins":13},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":8,"losses":14,"wins":10},"qwen/qwen3.8-max":{"draws":13,"losses":22,"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":35,"losses":64,"wins":59},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"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":9,"wins":37},"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":27,"losses":23,"wins":46},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":20,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":5,"wins":29},"claude-fable-5":{"draws":5,"losses":16,"wins":21},"claude-fable-5-1":{"draws":2,"losses":34,"wins":10},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":26},"claude-opus-4-5":{"draws":15,"losses":11,"wins":44},"claude-opus-4-8":{"draws":4,"losses":4,"wins":20},"claude-opus-5":{"draws":11,"losses":39,"wins":20},"claude-opus-5-5":{"draws":8,"losses":29,"wins":9},"claude-sonnet-5":{"draws":9,"losses":5,"wins":28},"claude-sonnet-5-5":{"draws":11,"losses":11,"wins":20},"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":5,"losses":6,"wins":27},"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":6,"losses":6,"wins":30},"gemini-4-argon":{"draws":4,"losses":22,"wins":16},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":38},"google/gemini-3.5-flash-lite":{"draws":10,"losses":4,"wins":60},"google/gemini-3.6-flash":{"draws":14,"losses":22,"wins":44},"google/gemini-3.8-flash":{"draws":9,"losses":12,"wins":21},"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":3,"losses":14,"wins":23},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":37},"gpt-5.5":{"draws":7,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":25},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":31},"gpt-6-astra":{"draws":5,"losses":33,"wins":4},"gpt-6-luna":{"draws":6,"losses":6,"wins":30},"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":6,"losses":1,"wins":25},"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":4,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":4,"wins":25},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":8,"losses":11,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":12},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":4,"wins":33},"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":3,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":11,"wins":21},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":19},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":32},"qwen/qwen3.8-max-0902":{"draws":9,"losses":13,"wins":20},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":5,"wins":30},"stealth/ox-alpha":{"draws":20,"losses":21,"wins":77},"stealth/space-bunny-alpha":{"draws":5,"losses":5,"wins":24},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":9,"wins":25},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":45},"thinkingmachines/inkling-small":{"draws":4,"losses":4,"wins":34},"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":1,"losses":2,"wins":21},"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":5,"losses":15,"wins":20},"z-ai/glm-5.3-flash":{"draws":3,"losses":13,"wins":26},"z-ai/glm-5.3-flashx":{"draws":8,"losses":5,"wins":29}},"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":42,"wins":38},"claude-haiku-5-5":{"draws":1,"losses":11,"wins":62},"claude-opus-4-5":{"draws":9,"losses":10,"wins":107},"claude-opus-4-8":{"draws":2,"losses":12,"wins":56},"claude-opus-5":{"draws":15,"losses":35,"wins":76},"claude-opus-5-5":{"draws":5,"losses":40,"wins":41},"claude-sonnet-5":{"draws":4,"losses":7,"wins":67},"claude-sonnet-5-5":{"draws":3,"losses":17,"wins":58},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":1,"losses":8,"wins":105},"deepseek/deepseek-v4-pro":{"draws":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":13,"wins":63},"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":3,"losses":2,"wins":41},"google/gemini-3.5-flash":{"draws":8,"losses":4,"wins":84},"google/gemini-3.5-flash-lite":{"draws":2,"losses":5,"wins":127},"google/gemini-3.6-flash":{"draws":6,"losses":20,"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":7,"wins":63},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":72},"gpt-5.6-sol":{"draws":5,"losses":14,"wins":59},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":65},"gpt-6-astra":{"draws":7,"losses":49,"wins":22},"gpt-6-luna":{"draws":8,"losses":6,"wins":64},"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":2,"wins":47},"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":2,"losses":6,"wins":70},"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":1,"losses":3,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":20},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":63},"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":2,"losses":4,"wins":62},"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":7,"wins":68},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":45},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":48},"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":20,"losses":24,"wins":222},"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":10,"wins":136},"z-ai/glm-5.3":{"draws":6,"losses":8,"wins":60},"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":5,"losses":6,"wins":43},"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":11,"wins":66},"claude-opus-5-5":{"draws":2,"losses":9,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":3,"losses":4,"wins":41},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":45},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":44},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":0,"losses":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":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":5,"losses":13,"wins":30},"gpt-6-luna":{"draws":0,"losses":0,"wins":48},"gpt-6-sol":{"draws":3,"losses":1,"wins":44},"gpt-6.1-sol":{"draws":8,"losses":7,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"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":3,"losses":3,"wins":42},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":28},"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":25,"wins":15},"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":13,"losses":58,"wins":11},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":8,"losses":5,"wins":19},"claude-sonnet-5-5":{"draws":6,"losses":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":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":18,"losses":11,"wins":55},"google/gemini-3.6-flash":{"draws":14,"losses":34,"wins":44},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":29},"gpt-5.5":{"draws":11,"losses":17,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":22},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":23},"gpt-6-astra":{"draws":2,"losses":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":9,"losses":11,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":35},"qwen/qwen3.7-max":{"draws":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":3,"losses":18,"wins":33},"claude-haiku-5-5":{"draws":5,"losses":2,"wins":39},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":5,"losses":1,"wins":38},"claude-opus-5":{"draws":6,"losses":16,"wins":60},"claude-opus-5-5":{"draws":8,"losses":18,"wins":26},"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":1,"losses":3,"wins":44},"gemini-4-argon":{"draws":7,"losses":7,"wins":34},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":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":16,"wins":27},"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":4,"losses":44,"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":15,"losses":15,"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":15,"losses":12,"wins":15},"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":26,"wins":17},"google/gemini-3.6-flash":{"draws":26,"losses":43,"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":12,"losses":21,"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":17,"losses":15,"wins":10},"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":13,"losses":8,"wins":11},"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":16,"wins":19},"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":41,"wins":29},"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":13,"wins":20},"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":3,"losses":45,"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":9,"losses":18,"wins":21},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":16},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":21},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":18,"wins":18},"stealth/ox-alpha":{"draws":29,"losses":55,"wins":74},"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":9,"wins":26},"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":28,"wins":46},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":19}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":12,"losses":17,"wins":19},"claude-fable-5-1":{"draws":5,"losses":42,"wins":7},"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":8,"losses":10,"wins":30},"gemini-3.1-pro-preview":{"draws":8,"losses":12,"wins":28},"gemini-4-argon":{"draws":4,"losses":32,"wins":12},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"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":11,"wins":29},"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":9,"losses":9,"wins":26},"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":4,"losses":1,"wins":29},"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":4,"wins":29},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":7,"wins":29},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":24},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":27},"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":29,"losses":42,"wins":87},"stealth/space-bunny-alpha":{"draws":3,"losses":5,"wins":30},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":8,"losses":14,"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":7,"losses":12,"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":7,"losses":27,"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":46,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":18,"losses":15,"wins":45},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":8,"losses":48,"wins":26},"claude-opus-5-5":{"draws":3,"losses":41,"wins":8},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":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":6,"losses":6,"wins":20},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"gemini-4-argon":{"draws":4,"losses":32,"wins":12},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":13,"wins":36},"google/gemini-3.5-flash-lite":{"draws":21,"losses":11,"wins":52},"google/gemini-3.6-flash":{"draws":16,"losses":28,"wins":48},"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":10,"losses":1,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":29},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":18},"gpt-5.6-terra":{"draws":10,"losses":9,"wins":27},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":10},"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":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":7,"losses":19,"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":9,"losses":4,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":12},"o3":{"draws":7,"losses":5,"wins":54},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":10,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":17},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":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":14,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":23},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":5,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":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":7,"losses":7,"wins":30},"claude-fable-5":{"draws":4,"losses":24,"wins":20},"claude-fable-5-1":{"draws":5,"losses":46,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":26},"claude-opus-4-5":{"draws":12,"losses":18,"wins":48},"claude-opus-4-8":{"draws":5,"losses":15,"wins":24},"claude-opus-5":{"draws":6,"losses":50,"wins":26},"claude-opus-5-5":{"draws":3,"losses":40,"wins":9},"claude-sonnet-5":{"draws":8,"losses":12,"wins":28},"claude-sonnet-5-5":{"draws":6,"losses":19,"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":6,"losses":7,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":13,"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":4,"losses":6,"wins":22},"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":7,"losses":15,"wins":38},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"wins":57},"google/gemini-3.6-flash":{"draws":12,"losses":24,"wins":56},"google/gemini-3.8-flash":{"draws":6,"losses":14,"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":6,"losses":5,"wins":31},"gpt-5.4":{"draws":5,"losses":16,"wins":25},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"gpt-5.5":{"draws":5,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":30},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":23},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":28},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":5,"losses":8,"wins":35},"gpt-6-sol":{"draws":3,"losses":26,"wins":19},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":24},"inception/mercury-3":{"draws":9,"losses":7,"wins":16},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":7,"losses":3,"wins":32},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":26},"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":1,"wins":21},"minimax/minimax-m3.1-flash":{"draws":6,"losses":8,"wins":28},"mistralai/mistral-large-4-0":{"draws":5,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"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":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":36},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":28},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":14,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":31},"stealth/ox-alpha":{"draws":20,"losses":48,"wins":90},"stealth/space-bunny-alpha":{"draws":5,"losses":7,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":14,"wins":29},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":41},"thinkingmachines/inkling-small":{"draws":8,"losses":4,"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":5,"losses":15,"wins":28},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":12,"losses":8,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":16,"losses":16,"wins":64},"z-ai/glm-5.3":{"draws":7,"losses":18,"wins":21},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":7,"losses":13,"wins":28}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":4,"losses":5,"wins":39},"claude-fable-5-1":{"draws":4,"losses":19,"wins":31},"claude-haiku-5-5":{"draws":2,"losses":8,"wins":36},"claude-opus-4-5":{"draws":1,"losses":2,"wins":75},"claude-opus-4-8":{"draws":0,"losses":5,"wins":39},"claude-opus-5":{"draws":8,"losses":19,"wins":55},"claude-opus-5-5":{"draws":5,"losses":24,"wins":23},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":70},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":3,"wins":40},"elorian/glimpse":{"draws":0,"losses":4,"wins":22},"fireworks/ember-1":{"draws":1,"losses":6,"wins":41},"gemini-3.1-pro-preview":{"draws":1,"losses":4,"wins":43},"gemini-4-argon":{"draws":3,"losses":5,"wins":24},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":56},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":1,"losses":6,"wins":85},"google/gemini-3.8-flash":{"draws":4,"losses":3,"wins":41},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":0,"wins":42},"gpt-5.4":{"draws":1,"losses":4,"wins":41},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":27},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":2,"losses":5,"wins":37},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":43},"gpt-6-astra":{"draws":3,"losses":22,"wins":23},"gpt-6-luna":{"draws":0,"losses":1,"wins":47},"gpt-6-sol":{"draws":4,"losses":8,"wins":36},"gpt-6.1-sol":{"draws":9,"losses":13,"wins":26},"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":2,"losses":27,"wins":1},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":4},"claude-opus-4-5":{"draws":11,"losses":35,"wins":4},"claude-opus-4-8":{"draws":6,"losses":22,"wins":2},"claude-opus-5":{"draws":8,"losses":37,"wins":1},"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":9,"losses":16,"wins":3},"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":6,"losses":18,"wins":6},"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":22,"losses":25,"wins":9},"google/gemini-3.6-flash":{"draws":14,"losses":39,"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":12,"losses":14,"wins":2},"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":0,"losses":30,"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":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":0},"nex-agi/nex-n2-pro":{"draws":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":6,"losses":19,"wins":5},"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":7,"losses":21,"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":6,"losses":14,"wins":6},"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":7,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":1},"thinkingmachines/inkling":{"draws":11,"losses":15,"wins":12},"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":6,"losses":11,"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":17,"losses":37,"wins":6},"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":9,"wins":30},"claude-fable-5":{"draws":7,"losses":25,"wins":16},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":12,"losses":14,"wins":20},"claude-opus-4-5":{"draws":25,"losses":9,"wins":44},"claude-opus-4-8":{"draws":7,"losses":17,"wins":20},"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":9,"wins":27},"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":7,"losses":13,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":13,"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":8,"losses":14,"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":9,"losses":4,"wins":31},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":57},"google/gemini-3.6-flash":{"draws":13,"losses":23,"wins":56},"google/gemini-3.8-flash":{"draws":4,"losses":21,"wins":23},"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":10,"losses":8,"wins":24},"gpt-5.4":{"draws":8,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":36},"gpt-5.5":{"draws":7,"losses":14,"wins":23},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":31},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":18},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":20},"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":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":42},"meta/muse-glimmer-30b":{"draws":11,"losses":3,"wins":28},"meta/muse-spark-1.2":{"draws":8,"losses":14,"wins":24},"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":5,"losses":15,"wins":26},"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":15,"wins":24},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-max":{"draws":14,"losses":13,"wins":21},"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":26,"losses":50,"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":20,"wins":20},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":46},"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":7,"losses":15,"wins":26},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"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":3,"losses":8,"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":4,"losses":19,"wins":25},"z-ai/glm-5.3-flashx":{"draws":9,"losses":20,"wins":19}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":26,"wins":25},"claude-fable-5":{"draws":10,"losses":57,"wins":11},"claude-fable-5-1":{"draws":4,"losses":86,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":48,"wins":11},"claude-opus-4-5":{"draws":36,"losses":58,"wins":32},"claude-opus-4-8":{"draws":16,"losses":44,"wins":10},"claude-opus-5":{"draws":8,"losses":107,"wins":13},"claude-opus-5-5":{"draws":8,"losses":74,"wins":0},"claude-sonnet-5":{"draws":17,"losses":39,"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":34,"losses":31,"wins":49},"deepseek/deepseek-v4-pro":{"draws":18,"losses":36,"wins":18},"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":26,"losses":37,"wins":15},"gemini-3.1-pro-preview":{"draws":19,"losses":35,"wins":24},"gemini-4-argon":{"draws":5,"losses":68,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":12,"wins":31},"google/gemini-3.5-flash":{"draws":25,"losses":49,"wins":24},"google/gemini-3.5-flash-lite":{"draws":27,"losses":43,"wins":44},"google/gemini-3.6-flash":{"draws":35,"losses":86,"wins":31},"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":16,"losses":33,"wins":19},"gpt-5.4":{"draws":13,"losses":46,"wins":17},"gpt-5.4-mini":{"draws":19,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":12,"losses":29,"wins":33},"gpt-5.5":{"draws":21,"losses":35,"wins":16},"gpt-5.6-luna":{"draws":26,"losses":27,"wins":25},"gpt-5.6-sol":{"draws":13,"losses":58,"wins":7},"gpt-5.6-terra":{"draws":20,"losses":37,"wins":17},"gpt-6-astra":{"draws":5,"losses":73,"wins":0},"gpt-6-luna":{"draws":20,"losses":40,"wins":18},"gpt-6-sol":{"draws":11,"losses":62,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":74,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":22,"losses":10,"wins":24},"inception/mercury-3":{"draws":10,"losses":26,"wins":12},"inclusionai/ling-3.0-flash":{"draws":13,"losses":12,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":23,"wins":40},"meta/muse-glimmer-30b":{"draws":23,"losses":19,"wins":26},"meta/muse-spark-1.2":{"draws":19,"losses":41,"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":11,"losses":14,"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":10,"losses":13,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":39,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":65,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":21,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":13,"wins":11},"o3":{"draws":17,"losses":61,"wins":32},"openai/gpt-oss-120b":{"draws":21,"losses":20,"wins":27},"poolside/laguna-s-2.1":{"draws":21,"losses":31,"wins":20},"qwen/qwen3.7-max":{"draws":11,"losses":20,"wins":13},"qwen/qwen3.7-plus":{"draws":11,"losses":11,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":39,"wins":17},"qwen/qwen3.8-27b":{"draws":7,"losses":36,"wins":13},"qwen/qwen3.8-flash":{"draws":17,"losses":26,"wins":9},"qwen/qwen3.8-max":{"draws":24,"losses":40,"wins":14},"qwen/qwen3.8-max-0902":{"draws":19,"losses":45,"wins":14},"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":46,"losses":159,"wins":63},"stealth/space-bunny-alpha":{"draws":13,"losses":31,"wins":20},"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":46,"wins":16},"thinkingmachines/inkling":{"draws":27,"losses":35,"wins":44},"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":18,"losses":41,"wins":19},"x-ai/grok-4.6":{"draws":19,"losses":49,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":11},"xiaomi/mimo-v2.5":{"draws":41,"losses":37,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":34,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":9},"z-ai/glm-5.2":{"draws":36,"losses":68,"wins":52},"z-ai/glm-5.3":{"draws":9,"losses":60,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":53,"wins":12},"z-ai/glm-5.3-flashx":{"draws":16,"losses":45,"wins":17}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":60},"claude-fable-5":{"draws":10,"losses":42,"wins":44},"claude-fable-5-1":{"draws":4,"losses":97,"wins":7},"claude-haiku-5-5":{"draws":22,"losses":24,"wins":46},"claude-opus-4-5":{"draws":37,"losses":24,"wins":95},"claude-opus-4-8":{"draws":16,"losses":28,"wins":44},"claude-opus-5":{"draws":23,"losses":105,"wins":36},"claude-opus-5-5":{"draws":13,"losses":81,"wins":10},"claude-sonnet-5":{"draws":15,"losses":20,"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":25,"losses":8,"wins":111},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":53},"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":25,"wins":49},"gemini-3.1-pro-preview":{"draws":20,"losses":25,"wins":51},"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":35,"losses":18,"wins":115},"google/gemini-3.6-flash":{"draws":26,"losses":42,"wins":84},"google/gemini-3.8-flash":{"draws":21,"losses":39,"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":17,"losses":35,"wins":40},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":43},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":70},"gpt-5.5":{"draws":17,"losses":30,"wins":41},"gpt-5.6-luna":{"draws":20,"losses":18,"wins":58},"gpt-5.6-sol":{"draws":14,"losses":43,"wins":39},"gpt-5.6-terra":{"draws":18,"losses":16,"wins":58},"gpt-6-astra":{"draws":7,"losses":78,"wins":11},"gpt-6-luna":{"draws":23,"losses":20,"wins":53},"gpt-6-sol":{"draws":13,"losses":56,"wins":27},"gpt-6.1-sol":{"draws":8,"losses":76,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":49},"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":17,"losses":26,"wins":49},"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":18,"losses":7,"wins":31},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":25,"wins":53},"qwen/qwen3.8-27b":{"draws":14,"losses":13,"wins":41},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":40},"qwen/qwen3.8-max":{"draws":20,"losses":18,"wins":58},"qwen/qwen3.8-max-0902":{"draws":25,"losses":35,"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":51,"losses":101,"wins":164},"stealth/space-bunny-alpha":{"draws":16,"losses":10,"wins":50},"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":12,"losses":8,"wins":32},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":55},"thinkingmachines/inkling":{"draws":32,"losses":15,"wins":81},"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":17,"losses":32,"wins":47},"x-ai/grok-4.6":{"draws":20,"losses":32,"wins":44},"x-ai/grok-4.7":{"draws":8,"losses":52,"wins":24},"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":25,"wins":125},"z-ai/glm-5.3":{"draws":19,"losses":40,"wins":33},"z-ai/glm-5.3-flash":{"draws":15,"losses":41,"wins":40},"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":20,"wins":21},"claude-fable-5-1":{"draws":5,"losses":42,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":11,"losses":20,"wins":47},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":2,"losses":59,"wins":21},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":4,"losses":12,"wins":32},"claude-sonnet-5-5":{"draws":4,"losses":21,"wins":23},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":16,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":21,"wins":20},"elorian/glimpse":{"draws":1,"losses":7,"wins":18},"fireworks/ember-1":{"draws":5,"losses":17,"wins":26},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":35},"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":7,"wins":47},"google/gemini-3.5-flash-lite":{"draws":6,"losses":8,"wins":70},"google/gemini-3.6-flash":{"draws":10,"losses":27,"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":7,"losses":17,"wins":22},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"gpt-6-luna":{"draws":11,"losses":7,"wins":30},"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":6,"losses":11,"wins":29},"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":3,"losses":14,"wins":31},"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":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":11,"losses":19,"wins":66},"z-ai/glm-5.3":{"draws":9,"losses":23,"wins":14},"z-ai/glm-5.3-flash":{"draws":6,"losses":15,"wins":27},"z-ai/glm-5.3-flashx":{"draws":6,"losses":15,"wins":27}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":9,"wins":17},"claude-fable-5":{"draws":8,"losses":30,"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":4,"losses":44,"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":14,"losses":21,"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":9,"losses":12,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":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":6,"losses":31,"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":3,"losses":37,"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":5,"losses":10,"wins":23},"claude-opus-5":{"draws":9,"losses":44,"wins":17},"claude-opus-5-5":{"draws":3,"losses":35,"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":5,"losses":6,"wins":43},"google/gemini-3.5-flash-lite":{"draws":11,"losses":6,"wins":59},"google/gemini-3.6-flash":{"draws":14,"losses":14,"wins":54},"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":3,"losses":2,"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":4,"wins":17},"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":8,"wins":29},"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":9,"losses":5,"wins":26},"claude-fable-5":{"draws":7,"losses":18,"wins":17},"claude-fable-5-1":{"draws":0,"losses":37,"wins":11},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":22},"claude-opus-4-5":{"draws":15,"losses":9,"wins":44},"claude-opus-4-8":{"draws":7,"losses":6,"wins":25},"claude-opus-5":{"draws":3,"losses":37,"wins":30},"claude-opus-5-5":{"draws":1,"losses":36,"wins":9},"claude-sonnet-5":{"draws":7,"losses":8,"wins":27},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":51},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":10,"wins":22},"elorian/glimpse":{"draws":6,"losses":5,"wins":13},"fireworks/ember-1":{"draws":8,"losses":8,"wins":26},"gemini-3.1-pro-preview":{"draws":7,"losses":5,"wins":30},"gemini-4-argon":{"draws":3,"losses":21,"wins":18},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":7,"losses":10,"wins":37},"google/gemini-3.5-flash-lite":{"draws":16,"losses":6,"wins":54},"google/gemini-3.6-flash":{"draws":17,"losses":13,"wins":52},"google/gemini-3.8-flash":{"draws":9,"losses":9,"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":8,"losses":5,"wins":25},"gpt-5.4":{"draws":12,"losses":12,"wins":18},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":19},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":36},"gpt-5.5":{"draws":8,"losses":6,"wins":12},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":15,"wins":21},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":27},"gpt-6-astra":{"draws":1,"losses":36,"wins":5},"gpt-6-luna":{"draws":11,"losses":5,"wins":26},"gpt-6-sol":{"draws":3,"losses":23,"wins":16},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inception/mercury-3":{"draws":4,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":35},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":4,"losses":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":3,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"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":8,"losses":1,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":15},"o3":{"draws":6,"losses":6,"wins":52},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":31},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":19},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":10,"wins":22},"qwen/qwen3.8-max-0902":{"draws":8,"losses":10,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":7,"wins":25},"stealth/ox-alpha":{"draws":29,"losses":31,"wins":82},"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":8,"losses":11,"wins":23},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":44},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":7,"wins":23},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":17,"wins":16},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":20,"losses":1,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":21,"losses":7,"wins":56},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":10},"z-ai/glm-5.3-flash":{"draws":2,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":24}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":9,"wins":19},"claude-fable-5":{"draws":8,"losses":28,"wins":12},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":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":14,"losses":9,"wins":25},"gemini-3.1-pro-preview":{"draws":13,"losses":12,"wins":23},"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":20,"losses":9,"wins":31},"google/gemini-3.5-flash-lite":{"draws":29,"losses":13,"wins":42},"google/gemini-3.6-flash":{"draws":25,"losses":31,"wins":36},"google/gemini-3.8-flash":{"draws":13,"losses":17,"wins":18},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":14},"gpt-4.1":{"draws":8,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":18,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":17,"losses":14,"wins":13},"gpt-5.6-luna":{"draws":13,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":23,"wins":15},"gpt-5.6-terra":{"draws":17,"losses":7,"wins":22},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"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":13,"losses":7,"wins":32},"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":15,"wins":34},"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":17,"losses":16,"wins":15},"qwen/qwen3.8-max-0902":{"draws":16,"losses":11,"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":12,"losses":8,"wins":18},"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":13,"losses":21,"wins":14},"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":36,"wins":12},"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":6,"losses":40,"wins":36},"claude-opus-5-5":{"draws":5,"losses":31,"wins":16},"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":6,"wins":37},"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":3,"losses":7,"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":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":39},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":26},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":38},"gpt-6-astra":{"draws":5,"losses":35,"wins":8},"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":5,"wins":23},"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":4,"losses":12,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":27},"claude-fable-5":{"draws":12,"losses":25,"wins":11},"claude-fable-5-1":{"draws":1,"losses":50,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":26,"losses":25,"wins":27},"claude-opus-4-8":{"draws":6,"losses":19,"wins":19},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":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":18,"losses":9,"wins":45},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"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":13,"losses":15,"wins":20},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"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":18,"losses":12,"wins":30},"google/gemini-3.5-flash-lite":{"draws":22,"losses":11,"wins":51},"google/gemini-3.6-flash":{"draws":28,"losses":36,"wins":28},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":11,"wins":21},"gpt-5.4":{"draws":12,"losses":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":11,"losses":20,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":21},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":10},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":11,"losses":29,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":18},"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":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":16,"losses":11,"wins":19},"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":5,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":3,"wins":10},"o3":{"draws":9,"losses":19,"wins":38},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":11,"losses":7,"wins":28},"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":12,"losses":21,"wins":15},"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":16,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":16},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":15,"wins":21},"stealth/ox-alpha":{"draws":39,"losses":62,"wins":57},"stealth/space-bunny-alpha":{"draws":11,"losses":7,"wins":20},"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":11,"losses":17,"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":35,"losses":21,"wins":40},"z-ai/glm-5.3":{"draws":11,"losses":24,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":16}},"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":5,"losses":15,"wins":34},"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":2,"losses":1,"wins":41},"claude-opus-5":{"draws":2,"losses":9,"wins":71},"claude-opus-5-5":{"draws":4,"losses":17,"wins":31},"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":0,"wins":48},"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":2,"losses":0,"wins":82},"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":0,"losses":1,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":2,"losses":6,"wins":24},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":7,"losses":4,"wins":37},"gpt-6.1-sol":{"draws":5,"losses":9,"wins":34},"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":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":43},"stealth/ox-alpha":{"draws":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":1,"wins":63},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":4,"losses":1,"wins":11},"unbiased/pareto-26.10-preview":{"draws":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":1,"wins":15},"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":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":6,"losses":43,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":20,"wins":21},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":6,"losses":16,"wins":22},"claude-opus-5":{"draws":8,"losses":59,"wins":15},"claude-opus-5-5":{"draws":7,"losses":41,"wins":4},"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":9,"losses":13,"wins":50},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":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":9,"losses":21,"wins":30},"google/gemini-3.5-flash-lite":{"draws":9,"losses":20,"wins":55},"google/gemini-3.6-flash":{"draws":13,"losses":35,"wins":44},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":20},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":19},"gpt-4.1":{"draws":1,"losses":6,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":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":4,"losses":13,"wins":31},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":26,"wins":14},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":6,"losses":33,"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":1,"losses":8,"wins":19},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":16,"wins":24},"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":28,"losses":58,"wins":72},"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":17,"wins":22},"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":7,"losses":20,"wins":21},"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":12,"wins":49},"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":26,"wins":50},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":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":11,"wins":34},"claude-fable-5-1":{"draws":4,"losses":24,"wins":26},"claude-haiku-5-5":{"draws":5,"losses":8,"wins":33},"claude-opus-4-5":{"draws":3,"losses":11,"wins":64},"claude-opus-4-8":{"draws":3,"losses":10,"wins":31},"claude-opus-5":{"draws":12,"losses":25,"wins":45},"claude-opus-5-5":{"draws":6,"losses":26,"wins":20},"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":4,"losses":8,"wins":36},"gemini-4-argon":{"draws":3,"losses":20,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":44},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":4,"losses":18,"wins":70},"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":3,"losses":6,"wins":37},"gpt-6-astra":{"draws":4,"losses":32,"wins":12},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":3,"losses":9,"wins":20},"gpt-6.1-sol":{"draws":4,"losses":23,"wins":21},"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":5,"losses":17,"wins":32},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":0,"losses":2,"wins":76},"claude-opus-4-8":{"draws":1,"losses":1,"wins":42},"claude-opus-5":{"draws":7,"losses":14,"wins":61},"claude-opus-5-5":{"draws":4,"losses":22,"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":3,"wins":45},"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":0,"losses":6,"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":12,"wins":6},"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":11,"losses":23,"wins":2},"claude-opus-5":{"draws":12,"losses":44,"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":14,"losses":15,"wins":7},"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":25,"losses":41,"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":18,"wins":1},"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":11,"wins":6},"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":12,"losses":12,"wins":4},"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":14,"losses":9,"wins":15},"claude-fable-5":{"draws":7,"losses":33,"wins":2},"claude-fable-5-1":{"draws":3,"losses":44,"wins":0},"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":9,"losses":65,"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":13,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":10},"gemini-4-argon":{"draws":5,"losses":36,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":18,"losses":23,"wins":11},"google/gemini-3.5-flash-lite":{"draws":28,"losses":21,"wins":23},"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":13,"losses":21,"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":8,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":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":11,"losses":9,"wins":14},"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":15,"losses":19,"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":12,"losses":26,"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":12,"losses":24,"wins":2},"claude-opus-5":{"draws":11,"losses":53,"wins":6},"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":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":11,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":10},"gemini-4-argon":{"draws":1,"losses":39,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":8,"wins":12},"google/gemini-3.5-flash":{"draws":15,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":30,"losses":26,"wins":18},"google/gemini-3.6-flash":{"draws":26,"losses":46,"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":6,"losses":5,"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":13,"losses":22,"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":19,"losses":17,"wins":12},"meta/muse-glimmer-30b":{"draws":18,"losses":13,"wins":5},"meta/muse-spark-1.2":{"draws":13,"losses":19,"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":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":11,"losses":18,"wins":7},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-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":11,"wins":7},"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":16,"wins":8},"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":12,"losses":25,"wins":5},"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":8,"losses":19,"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":11,"losses":27,"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":30,"losses":17,"wins":15},"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":36,"losses":34,"wins":14},"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":23,"losses":14,"wins":13},"claude-fable-5":{"draws":10,"losses":40,"wins":4},"claude-fable-5-1":{"draws":4,"losses":51,"wins":1},"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":16,"losses":31,"wins":7},"claude-opus-5":{"draws":13,"losses":83,"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":37,"losses":25,"wins":20},"deepseek/deepseek-v4-pro":{"draws":17,"losses":23,"wins":8},"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":22,"losses":26,"wins":6},"gemini-3.1-pro-preview":{"draws":23,"losses":18,"wins":13},"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":23,"losses":29,"wins":16},"google/gemini-3.5-flash-lite":{"draws":41,"losses":27,"wins":26},"google/gemini-3.6-flash":{"draws":42,"losses":50,"wins":8},"google/gemini-3.8-flash":{"draws":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":20,"losses":26,"wins":16},"gpt-5.5":{"draws":24,"losses":23,"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":21,"losses":6,"wins":9},"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":17,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":24,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":47,"wins":0},"nex-agi/nex-n2-pro":{"draws":11,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":16,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":4},"o3":{"draws":17,"losses":44,"wins":13},"openai/gpt-oss-120b":{"draws":25,"losses":10,"wins":13},"poolside/laguna-s-2.1":{"draws":26,"losses":18,"wins":12},"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":15,"losses":16,"wins":5},"qwen/qwen3.8-flash":{"draws":17,"losses":16,"wins":3},"qwen/qwen3.8-max":{"draws":24,"losses":26,"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":49,"losses":87,"wins":14},"stealth/space-bunny-alpha":{"draws":16,"losses":19,"wins":7},"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":15,"losses":37,"wins":2},"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":50,"losses":42,"wins":16},"z-ai/glm-5.3":{"draws":13,"losses":36,"wins":3},"z-ai/glm-5.3-flash":{"draws":15,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":36,"wins":59},"claude-fable-5":{"draws":2,"losses":94,"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":9,"losses":123,"wins":56},"claude-opus-4-8":{"draws":7,"losses":66,"wins":37},"claude-opus-5":{"draws":6,"losses":154,"wins":12},"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":1,"losses":55,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":64,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":57,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":73,"wins":37},"elorian/glimpse":{"draws":4,"losses":33,"wins":23},"fireworks/ember-1":{"draws":7,"losses":71,"wins":36},"gemini-3.1-pro-preview":{"draws":9,"losses":46,"wins":59},"gemini-4-argon":{"draws":0,"losses":108,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":9,"wins":82},"google/gemini-3.5-flash":{"draws":4,"losses":88,"wins":58},"google/gemini-3.5-flash-lite":{"draws":13,"losses":65,"wins":128},"google/gemini-3.6-flash":{"draws":9,"losses":133,"wins":80},"google/gemini-3.8-flash":{"draws":2,"losses":80,"wins":32},"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":1,"losses":63,"wins":42},"gpt-5.4":{"draws":1,"losses":84,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":18,"wins":52},"gpt-5.4-nano":{"draws":2,"losses":67,"wins":69},"gpt-5.5":{"draws":12,"losses":66,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":43,"wins":57},"gpt-5.6-sol":{"draws":3,"losses":90,"wins":21},"gpt-5.6-terra":{"draws":8,"losses":54,"wins":44},"gpt-6-astra":{"draws":4,"losses":109,"wins":1},"gpt-6-luna":{"draws":14,"losses":62,"wins":38},"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":6,"losses":18,"wins":56},"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":8,"losses":21,"wins":69},"meta/muse-spark-1.2":{"draws":3,"losses":49,"wins":54},"meta/muse-spark-1.3":{"draws":2,"losses":73,"wins":39},"meta/muse-spark-open":{"draws":3,"losses":82,"wins":29},"meta/muse-wonder":{"draws":4,"losses":86,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":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":4,"losses":9,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":13,"wins":15},"moonshotai/kimi-k3":{"draws":5,"losses":53,"wins":48},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":96,"wins":14},"nex-agi/nex-n2-pro":{"draws":1,"losses":17,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":9,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":28,"wins":76},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":30,"wins":21},"o3":{"draws":8,"losses":78,"wins":84},"openai/gpt-oss-120b":{"draws":6,"losses":21,"wins":73},"poolside/laguna-s-2.1":{"draws":7,"losses":44,"wins":63},"qwen/qwen3.7-max":{"draws":5,"losses":31,"wins":38},"qwen/qwen3.7-plus":{"draws":0,"losses":17,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":68,"wins":39},"qwen/qwen3.8-27b":{"draws":2,"losses":44,"wins":38},"qwen/qwen3.8-flash":{"draws":4,"losses":38,"wins":34},"qwen/qwen3.8-max":{"draws":10,"losses":63,"wins":41},"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":21,"losses":176,"wins":147},"stealth/space-bunny-alpha":{"draws":5,"losses":37,"wins":50},"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":22,"wins":29},"tencent/hy4-preview":{"draws":6,"losses":66,"wins":42},"thinkingmachines/inkling":{"draws":11,"losses":34,"wins":109},"thinkingmachines/inkling-small":{"draws":10,"losses":30,"wins":74},"unbiased/pareto-26.10":{"draws":0,"losses":38,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":35,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":9,"wins":25},"x-ai/grok-4.5":{"draws":5,"losses":72,"wins":37},"x-ai/grok-4.6":{"draws":12,"losses":71,"wins":31},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":3,"losses":13,"wins":22},"xiaomi/mimo-v2.5":{"draws":14,"losses":34,"wins":132},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":25,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":45,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":51,"wins":21},"z-ai/glm-5.2":{"draws":14,"losses":98,"wins":116},"z-ai/glm-5.3":{"draws":2,"losses":82,"wins":24},"z-ai/glm-5.3-flash":{"draws":0,"losses":59,"wins":55},"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":4,"losses":44,"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":11,"losses":14,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":26,"wins":7},"elorian/glimpse":{"draws":7,"losses":9,"wins":6},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":15},"gemini-4-argon":{"draws":2,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":13},"google/gemini-3.5-flash":{"draws":15,"losses":19,"wins":18},"google/gemini-3.5-flash-lite":{"draws":22,"losses":20,"wins":32},"google/gemini-3.6-flash":{"draws":22,"losses":45,"wins":13},"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":11,"losses":20,"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":73,"wins":35},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":9},"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":35,"wins":21},"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":3,"wins":30},"claude-fable-5":{"draws":11,"losses":13,"wins":24},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":25},"claude-opus-4-5":{"draws":23,"losses":7,"wins":48},"claude-opus-4-8":{"draws":10,"losses":5,"wins":29},"claude-opus-5":{"draws":11,"losses":52,"wins":19},"claude-opus-5-5":{"draws":3,"losses":39,"wins":10},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":9,"losses":17,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":15,"losses":5,"wins":52},"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":15,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":20,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":11,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":9,"losses":9,"wins":30},"gemini-4-argon":{"draws":4,"losses":31,"wins":13},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":12,"losses":10,"wins":38},"google/gemini-3.5-flash-lite":{"draws":18,"losses":5,"wins":61},"google/gemini-3.6-flash":{"draws":21,"losses":22,"wins":49},"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":12,"wins":21},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":8,"losses":18,"wins":22},"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":1,"losses":34,"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":12,"losses":8,"wins":26},"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":6,"wins":21},"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":10,"wins":24},"qwen/qwen3.8-max-0902":{"draws":13,"losses":10,"wins":25},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":5,"wins":32},"stealth/ox-alpha":{"draws":32,"losses":37,"wins":89},"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":11,"wins":14},"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":3,"losses":7,"wins":24},"claude-fable-5":{"draws":3,"losses":22,"wins":11},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":14,"wins":18},"claude-opus-4-5":{"draws":5,"losses":16,"wins":39},"claude-opus-4-8":{"draws":4,"losses":14,"wins":18},"claude-opus-5":{"draws":8,"losses":44,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":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":2,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":23,"wins":11},"elorian/glimpse":{"draws":2,"losses":7,"wins":11},"fireworks/ember-1":{"draws":2,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":3,"losses":9,"wins":24},"gemini-4-argon":{"draws":3,"losses":29,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":2,"losses":13,"wins":33},"google/gemini-3.5-flash-lite":{"draws":4,"losses":8,"wins":54},"google/gemini-3.6-flash":{"draws":4,"losses":27,"wins":39},"google/gemini-3.8-flash":{"draws":2,"losses":17,"wins":17},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":16},"gpt-4.1":{"draws":1,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":8,"wins":23},"gpt-5.4":{"draws":3,"losses":22,"wins":11},"gpt-5.4-mini":{"draws":1,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":0,"losses":13,"wins":27},"gpt-5.5":{"draws":1,"losses":16,"wins":17},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":3,"losses":23,"wins":10},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":18},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":2,"losses":13,"wins":21},"gpt-6-sol":{"draws":4,"losses":24,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":4},"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":3,"losses":0,"wins":29},"meta/muse-spark-1.2":{"draws":1,"losses":10,"wins":23},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":20},"meta/muse-spark-open":{"draws":2,"losses":17,"wins":17},"meta/muse-wonder":{"draws":3,"losses":28,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":18},"minimax/minimax-m3.1-flash":{"draws":3,"losses":12,"wins":17},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":3,"losses":16,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":5,"wins":13},"o3":{"draws":1,"losses":19,"wins":40},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":1,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":0,"losses":7,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":13,"wins":17},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":1,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":5,"losses":12,"wins":19},"qwen/qwen3.8-max-0902":{"draws":4,"losses":15,"wins":17},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":9,"wins":22},"stealth/ox-alpha":{"draws":14,"losses":38,"wins":50},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":0,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":18},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":34},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":0,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":5,"losses":17,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":1,"losses":6,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":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":10,"losses":21,"wins":41},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":11,"wins":21},"z-ai/glm-5.3-flashx":{"draws":3,"losses":15,"wins":18}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":19},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":23,"losses":20,"wins":35},"claude-opus-4-8":{"draws":5,"losses":22,"wins":17},"claude-opus-5":{"draws":7,"losses":63,"wins":12},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":13,"losses":14,"wins":21},"claude-sonnet-5-5":{"draws":6,"losses":25,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":11,"losses":15,"wins":46},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":12,"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":12,"losses":18,"wins":18},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":24},"gemini-4-argon":{"draws":6,"losses":38,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":56},"google/gemini-3.6-flash":{"draws":13,"losses":39,"wins":40},"google/gemini-3.8-flash":{"draws":11,"losses":22,"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":9,"losses":14,"wins":19},"gpt-5.4":{"draws":8,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":28},"gpt-5.5":{"draws":12,"losses":14,"wins":18},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":30},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":18},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":22},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":43,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":22},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":20},"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":9,"losses":8,"wins":25},"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":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":38,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":7,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":6,"losses":24,"wins":36},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":6,"losses":9,"wins":31},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-27b":{"draws":7,"losses":10,"wins":17},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max-0902":{"draws":8,"losses":23,"wins":17},"recursive/flint-v1.0":{"draws":1,"losses":2,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":15,"wins":22},"stealth/ox-alpha":{"draws":36,"losses":63,"wins":59},"stealth/space-bunny-alpha":{"draws":8,"losses":9,"wins":21},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":11,"losses":10,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":20,"wins":19},"x-ai/grok-4.6":{"draws":12,"losses":17,"wins":19},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":8,"wins":43},"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":22,"losses":30,"wins":44},"z-ai/glm-5.3":{"draws":5,"losses":30,"wins":11},"z-ai/glm-5.3-flash":{"draws":11,"losses":12,"wins":25},"z-ai/glm-5.3-flashx":{"draws":15,"losses":16,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":33},"claude-fable-5":{"draws":10,"losses":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":13,"losses":19,"wins":108},"claude-fable-5":{"draws":15,"losses":75,"wins":60},"claude-fable-5-1":{"draws":18,"losses":136,"wins":18},"claude-haiku-5-5":{"draws":17,"losses":43,"wins":80},"claude-opus-4-5":{"draws":25,"losses":51,"wins":164},"claude-opus-4-8":{"draws":16,"losses":36,"wins":78},"claude-opus-5":{"draws":34,"losses":168,"wins":56},"claude-opus-5-5":{"draws":8,"losses":132,"wins":22},"claude-sonnet-5":{"draws":13,"losses":32,"wins":105},"claude-sonnet-5-5":{"draws":10,"losses":65,"wins":75},"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":34,"wins":93},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":33,"wins":92},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":42,"wins":92},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":57,"wins":77},"elorian/glimpse":{"draws":10,"losses":23,"wins":51},"fireworks/ember-1":{"draws":20,"losses":35,"wins":95},"gemini-3.1-pro-preview":{"draws":17,"losses":35,"wins":98},"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":17,"losses":41,"wins":128},"google/gemini-3.5-flash-lite":{"draws":21,"losses":33,"wins":210},"google/gemini-3.6-flash":{"draws":27,"losses":81,"wins":182},"google/gemini-3.8-flash":{"draws":14,"losses":57,"wins":79},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":69},"gpt-4.1":{"draws":8,"losses":10,"wins":32},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":14},"gpt-5":{"draws":10,"losses":30,"wins":94},"gpt-5.4":{"draws":19,"losses":47,"wins":80},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":76},"gpt-5.4-nano":{"draws":7,"losses":35,"wins":100},"gpt-5.5":{"draws":17,"losses":43,"wins":80},"gpt-5.6-luna":{"draws":23,"losses":22,"wins":105},"gpt-5.6-sol":{"draws":15,"losses":74,"wins":61},"gpt-5.6-terra":{"draws":19,"losses":38,"wins":87},"gpt-6-astra":{"draws":15,"losses":121,"wins":14},"gpt-6-luna":{"draws":18,"losses":30,"wins":102},"gpt-6-sol":{"draws":17,"losses":92,"wins":41},"gpt-6.1-sol":{"draws":16,"losses":116,"wins":18},"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":7,"losses":6,"wins":93},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":11,"losses":19,"wins":134},"meta/muse-glimmer-30b":{"draws":9,"losses":9,"wins":116},"meta/muse-spark-1.2":{"draws":18,"losses":29,"wins":97},"meta/muse-spark-1.3":{"draws":18,"losses":48,"wins":84},"meta/muse-spark-open":{"draws":12,"losses":50,"wins":84},"meta/muse-wonder":{"draws":12,"losses":76,"wins":62},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":64},"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":6,"wins":24},"moonshotai/kimi-k3":{"draws":15,"losses":39,"wins":90},"moonshotai/kimi-k3.1-pro":{"draws":21,"losses":99,"wins":20},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":64},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":18,"wins":93},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":11,"wins":48},"o3":{"draws":7,"losses":41,"wins":156},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":111},"poolside/laguna-s-2.1":{"draws":13,"losses":18,"wins":117},"qwen/qwen3.7-max":{"draws":5,"losses":11,"wins":68},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":43,"wins":88},"qwen/qwen3.8-27b":{"draws":7,"losses":22,"wins":77},"qwen/qwen3.8-flash":{"draws":8,"losses":23,"wins":69},"qwen/qwen3.8-max":{"draws":19,"losses":35,"wins":96},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":90},"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":49,"losses":131,"wins":308},"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":18,"losses":50,"wins":78},"thinkingmachines/inkling":{"draws":21,"losses":23,"wins":162},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":127},"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":27,"losses":58,"wins":65},"x-ai/grok-4.7":{"draws":8,"losses":78,"wins":42},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":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":16,"losses":39,"wins":45},"z-ai/glm-5.2":{"draws":29,"losses":49,"wins":222},"z-ai/glm-5.3":{"draws":16,"losses":64,"wins":64},"z-ai/glm-5.3-flash":{"draws":15,"losses":43,"wins":92},"z-ai/glm-5.3-flashx":{"draws":16,"losses":52,"wins":82}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":17},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":0,"losses":38,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":11},"claude-opus-4-5":{"draws":17,"losses":29,"wins":14},"claude-opus-4-8":{"draws":6,"losses":15,"wins":15},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":3,"losses":13,"wins":20},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":11,"losses":14,"wins":29},"deepseek/deepseek-v4-pro":{"draws":8,"losses":12,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":6},"elorian/glimpse":{"draws":2,"losses":11,"wins":7},"fireworks/ember-1":{"draws":5,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":3,"losses":11,"wins":22},"gemini-4-argon":{"draws":1,"losses":31,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":14,"losses":15,"wins":37},"google/gemini-3.6-flash":{"draws":14,"losses":31,"wins":25},"google/gemini-3.8-flash":{"draws":5,"losses":21,"wins":10},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":13,"wins":17},"gpt-5.4":{"draws":3,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":10,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":5,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":12},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":14},"gpt-6-sol":{"draws":1,"losses":27,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":14},"inception/mercury-3":{"draws":3,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":21},"meta/muse-glimmer-30b":{"draws":7,"losses":2,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":5,"losses":14,"wins":17},"meta/muse-spark-open":{"draws":5,"losses":22,"wins":9},"meta/muse-wonder":{"draws":5,"losses":24,"wins":7},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":15},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":29,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":12,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":9},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":2,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":14},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":7,"losses":19,"wins":10},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":15,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":47,"wins":36},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":18},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":24},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":26},"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":22,"wins":6},"x-ai/grok-4.6":{"draws":4,"losses":20,"wins":12},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":13,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":15,"losses":23,"wins":34},"z-ai/glm-5.3":{"draws":4,"losses":23,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":21,"wins":11}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":17,"wins":9},"claude-fable-5":{"draws":0,"losses":28,"wins":2},"claude-fable-5-1":{"draws":0,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":22,"wins":5},"claude-opus-4-5":{"draws":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":13,"wins":13},"claude-fable-5":{"draws":10,"losses":26,"wins":6},"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":30,"wins":17},"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":14,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"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":28,"wins":6},"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":7,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":22},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":18},"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":7,"wins":9},"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":7,"losses":6,"wins":7},"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":25,"wins":27},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":11,"losses":11,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":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":9,"losses":12,"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":10,"wins":29},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":18},"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":22,"wins":29},"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":21,"losses":33,"wins":30},"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":9,"losses":21,"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":20,"losses":7,"wins":45},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"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":10,"losses":11,"wins":27},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"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":15,"losses":7,"wins":38},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":51},"google/gemini-3.6-flash":{"draws":22,"losses":27,"wins":43},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":25},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":15,"losses":8,"wins":19},"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":14,"losses":4,"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":7,"losses":3,"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":12,"losses":15,"wins":39},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"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":12,"losses":10,"wins":26},"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":34,"losses":27,"wins":97},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":10,"losses":4,"wins":20},"stepfun/step-5-preview":{"draws":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":20,"losses":12,"wins":64},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":18,"wins":20},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":34,"wins":20},"claude-fable-5":{"draws":11,"losses":68,"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":73,"wins":19},"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":42,"losses":31,"wins":55},"deepseek/deepseek-v4-pro":{"draws":24,"losses":40,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":33,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":44,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":50,"wins":13},"elorian/glimpse":{"draws":9,"losses":25,"wins":12},"fireworks/ember-1":{"draws":25,"losses":46,"wins":13},"gemini-3.1-pro-preview":{"draws":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":26,"losses":52,"wins":26},"google/gemini-3.5-flash-lite":{"draws":46,"losses":45,"wins":53},"google/gemini-3.6-flash":{"draws":43,"losses":85,"wins":32},"google/gemini-3.8-flash":{"draws":26,"losses":49,"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":17,"losses":38,"wins":21},"gpt-5.4":{"draws":21,"losses":44,"wins":15},"gpt-5.4-mini":{"draws":22,"losses":17,"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":77,"wins":1},"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":21,"losses":14,"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":15,"losses":9,"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":12,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":23,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":10},"o3":{"draws":24,"losses":60,"wins":32},"openai/gpt-oss-120b":{"draws":23,"losses":19,"wins":34},"poolside/laguna-s-2.1":{"draws":27,"losses":33,"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":28,"losses":48,"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":25,"losses":42,"wins":17},"qwen/qwen3.8-max-0902":{"draws":26,"losses":44,"wins":14},"recursive/flint-v1.0":{"draws":8,"losses":5,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":36,"wins":18},"stealth/ox-alpha":{"draws":70,"losses":157,"wins":55},"stealth/space-bunny-alpha":{"draws":19,"losses":25,"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":19,"wins":12},"tencent/hy4-preview":{"draws":18,"losses":46,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":32},"thinkingmachines/inkling-small":{"draws":34,"losses":12,"wins":38},"unbiased/pareto-26.10":{"draws":0,"losses":28,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":8},"x-ai/grok-4.5":{"draws":27,"losses":47,"wins":10},"x-ai/grok-4.6":{"draws":25,"losses":52,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":58,"wins":5},"x-ai/grok-build-0.1":{"draws":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":43,"losses":76,"wins":49},"z-ai/glm-5.3":{"draws":18,"losses":53,"wins":9},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":14},"z-ai/glm-5.3-flashx":{"draws":22,"losses":50,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":18,"wins":10},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":30,"wins":5},"claude-opus-4-5":{"draws":30,"losses":30,"wins":18},"claude-opus-4-8":{"draws":13,"losses":24,"wins":7},"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":18,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":21,"wins":7},"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":14,"losses":24,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"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":29,"wins":13},"google/gemini-3.5-flash-lite":{"draws":27,"losses":22,"wins":35},"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":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":18,"wins":8},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":10},"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":6,"wins":13},"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":20,"losses":13,"wins":9},"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":32,"wins":19},"openai/gpt-oss-120b":{"draws":18,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":9},"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":22,"losses":18,"wins":8},"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":14,"losses":28,"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":9,"losses":19,"wins":10},"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":22,"losses":16,"wins":26},"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":36,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":18,"wins":22},"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":27,"wins":9}},"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":6,"losses":18,"wins":24},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":18,"losses":21,"wins":39},"claude-opus-4-8":{"draws":11,"losses":15,"wins":18},"claude-opus-5":{"draws":10,"losses":54,"wins":18},"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":13,"losses":8,"wins":23},"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":13,"wins":27},"gemini-4-argon":{"draws":1,"losses":37,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":26},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":37},"google/gemini-3.5-flash-lite":{"draws":14,"losses":17,"wins":53},"google/gemini-3.6-flash":{"draws":14,"losses":32,"wins":46},"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":24,"wins":19},"gpt-5.6-terra":{"draws":10,"losses":7,"wins":29},"gpt-6-astra":{"draws":0,"losses":42,"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":6,"losses":1,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":29},"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":9,"losses":2,"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":29,"losses":51,"wins":78},"stealth/space-bunny-alpha":{"draws":8,"losses":7,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":17,"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":5,"losses":21,"wins":22},"z-ai/glm-5.3-flashx":{"draws":4,"losses":20,"wins":24}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":6,"wins":30},"claude-fable-5":{"draws":11,"losses":17,"wins":20},"claude-fable-5-1":{"draws":3,"losses":36,"wins":15},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":18},"claude-opus-4-5":{"draws":17,"losses":18,"wins":43},"claude-opus-4-8":{"draws":9,"losses":13,"wins":22},"claude-opus-5":{"draws":10,"losses":49,"wins":22},"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":16,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"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":6,"wins":33},"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":13,"losses":11,"wins":36},"google/gemini-3.5-flash-lite":{"draws":19,"losses":8,"wins":57},"google/gemini-3.6-flash":{"draws":18,"losses":26,"wins":48},"google/gemini-3.8-flash":{"draws":12,"losses":13,"wins":23},"google/gemma-4-31b-it":{"draws":9,"losses":0,"wins":19},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":3,"wins":29},"gpt-5.4":{"draws":11,"losses":12,"wins":23},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":18},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":11,"losses":7,"wins":26},"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":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inception/mercury-3":{"draws":9,"losses":3,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":23},"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":3,"losses":1,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":28},"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":16,"losses":3,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":13,"losses":16,"wins":37},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":10,"losses":5,"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":5,"losses":20,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":12,"losses":2,"wins":18},"qwen/qwen3.8-max":{"draws":6,"losses":16,"wins":26},"qwen/qwen3.8-max-0902":{"draws":11,"losses":13,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":42,"losses":45,"wins":71},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":24},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":17,"losses":8,"wins":21},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":39},"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":18,"losses":15,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":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":9,"wins":30},"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":2,"wins":48},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":71},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":65},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":3,"wins":32},"gpt-5.4":{"draws":2,"losses":8,"wins":30},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":43},"gpt-5.5":{"draws":3,"losses":9,"wins":26},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":37},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":30,"wins":8},"gpt-6-luna":{"draws":0,"losses":6,"wins":36},"gpt-6-sol":{"draws":1,"losses":13,"wins":28},"gpt-6.1-sol":{"draws":1,"losses":23,"wins":18},"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":5,"wins":20},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":7,"wins":35},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.8-max":{"draws":1,"losses":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":5,"losses":16,"wins":119},"stealth/space-bunny-alpha":{"draws":0,"losses":5,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":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":9,"losses":21,"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":21,"losses":15,"wins":10},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":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":14,"losses":12,"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":17,"losses":17,"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":10,"losses":18,"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":10,"losses":12,"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":11,"losses":17,"wins":4},"gpt-5.5":{"draws":14,"losses":8,"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":13,"losses":7,"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":11,"losses":4,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":10,"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":20,"losses":6,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":1},"o3":{"draws":11,"losses":19,"wins":8},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":13,"losses":11,"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":16,"losses":11,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":3},"qwen/qwen3.8-flash":{"draws":14,"losses":6,"wins":0},"qwen/qwen3.8-max":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.8-max-0902":{"draws":16,"losses":10,"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":33,"losses":38,"wins":11},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":3},"stepfun/step-5-preview":{"draws":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":30,"losses":23,"wins":7},"z-ai/glm-5.3":{"draws":11,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":5},"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":29,"wins":8},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":19,"losses":35,"wins":24},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":19,"losses":60,"wins":3},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":8,"losses":22,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":26,"losses":19,"wins":27},"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":9,"losses":19,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"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":31,"losses":18,"wins":35},"google/gemini-3.6-flash":{"draws":24,"losses":46,"wins":22},"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":17,"losses":19,"wins":10},"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":18,"losses":20,"wins":10},"qwen/qwen3.8-max-0902":{"draws":15,"losses":27,"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":47,"losses":76,"wins":35},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"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":26,"wins":25},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":16,"losses":24,"wins":8}},"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":4,"losses":23,"wins":21},"claude-fable-5-1":{"draws":2,"losses":46,"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":12,"losses":52,"wins":18},"claude-opus-5-5":{"draws":4,"losses":44,"wins":4},"claude-sonnet-5":{"draws":3,"losses":14,"wins":31},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":5,"losses":21,"wins":46},"deepseek/deepseek-v4-pro":{"draws":2,"losses":15,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":10,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":22,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":18},"elorian/glimpse":{"draws":3,"losses":9,"wins":14},"fireworks/ember-1":{"draws":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":4,"losses":21,"wins":35},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":55},"google/gemini-3.6-flash":{"draws":6,"losses":33,"wins":53},"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":6,"losses":14,"wins":26},"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":5,"losses":18,"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":6,"losses":38,"wins":8},"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":8,"wins":36},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":29},"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":5,"losses":10,"wins":45},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":58},"google/gemini-3.6-flash":{"draws":21,"losses":22,"wins":49},"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":9,"losses":5,"wins":28},"gpt-5.4":{"draws":5,"losses":11,"wins":30},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":35},"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":40,"wins":5},"gpt-6-luna":{"draws":8,"losses":10,"wins":30},"gpt-6-sol":{"draws":5,"losses":24,"wins":19},"gpt-6.1-sol":{"draws":8,"losses":33,"wins":7},"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":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":32},"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":9,"losses":3,"wins":30},"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":3,"losses":7,"wins":24},"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":7,"losses":12,"wins":29},"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":18,"losses":33,"wins":107},"stealth/space-bunny-alpha":{"draws":3,"losses":6,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":27},"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":18,"losses":14,"wins":64},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":9,"losses":13,"wins":26},"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":6,"wins":13},"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":10,"losses":52,"wins":12},"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":10,"losses":17,"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":20,"wins":34},"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":12,"losses":14,"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":15,"wins":13},"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":71,"wins":36},"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":24,"losses":29,"wins":31},"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":15,"losses":12,"wins":51},"claude-opus-4-8":{"draws":11,"losses":8,"wins":25},"claude-opus-5":{"draws":12,"losses":46,"wins":24},"claude-opus-5-5":{"draws":5,"losses":38,"wins":9},"claude-sonnet-5":{"draws":8,"losses":10,"wins":30},"claude-sonnet-5-5":{"draws":11,"losses":16,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":4,"wins":53},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":29},"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":13,"losses":14,"wins":33},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":56},"google/gemini-3.6-flash":{"draws":15,"losses":33,"wins":44},"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":10,"losses":11,"wins":25},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":38},"gpt-5.5":{"draws":11,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":23},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":1,"losses":38,"wins":9},"gpt-6-luna":{"draws":11,"losses":8,"wins":29},"gpt-6-sol":{"draws":8,"losses":24,"wins":16},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":3,"wins":22},"inception/mercury-3":{"draws":8,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":26},"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":7,"losses":5,"wins":30},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":28},"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":6,"losses":3,"wins":19},"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":4,"losses":1,"wins":19},"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":5,"losses":10,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":11,"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":11,"losses":12,"wins":25},"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":28,"losses":47,"wins":83},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":10,"losses":7,"wins":29},"thinkingmachines/inkling":{"draws":15,"losses":4,"wins":45},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":16},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":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":20,"losses":14,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":7,"losses":16,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":15,"wins":23}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":1,"wins":41},"claude-fable-5":{"draws":4,"losses":9,"wins":35},"claude-fable-5-1":{"draws":3,"losses":25,"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":3,"losses":4,"wins":37},"claude-opus-5":{"draws":4,"losses":38,"wins":40},"claude-opus-5-5":{"draws":5,"losses":34,"wins":13},"claude-sonnet-5":{"draws":3,"losses":3,"wins":42},"claude-sonnet-5-5":{"draws":1,"losses":11,"wins":36},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":66},"deepseek/deepseek-v4-pro":{"draws":5,"losses":3,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"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":2,"losses":2,"wins":44},"gemini-4-argon":{"draws":4,"losses":21,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":52},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":78},"google/gemini-3.6-flash":{"draws":10,"losses":10,"wins":72},"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":3,"losses":5,"wins":38},"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":9,"wins":32},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":41},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":36},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":37},"gpt-6-astra":{"draws":5,"losses":33,"wins":10},"gpt-6-luna":{"draws":7,"losses":3,"wins":38},"gpt-6-sol":{"draws":6,"losses":13,"wins":29},"gpt-6.1-sol":{"draws":4,"losses":29,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"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":6,"losses":0,"wins":36},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":38},"meta/muse-spark-1.3":{"draws":3,"losses":7,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":8,"wins":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":2,"losses":1,"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":2,"losses":0,"wins":40},"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":3,"losses":3,"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":2,"losses":6,"wins":38},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":58},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":8},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":39},"x-ai/grok-4.6":{"draws":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":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":2,"wins":25},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":84},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":33},"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":13,"losses":16,"wins":15},"claude-opus-5":{"draws":14,"losses":60,"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":40,"wins":28},"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":6,"losses":39,"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":12,"losses":28,"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":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"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":13,"losses":19,"wins":16},"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":9,"losses":14,"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":13,"losses":5,"wins":58},"claude-fable-5":{"draws":12,"losses":23,"wins":49},"claude-fable-5-1":{"draws":8,"losses":67,"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":13,"losses":11,"wins":52},"claude-opus-5":{"draws":19,"losses":60,"wins":53},"claude-opus-5-5":{"draws":8,"losses":60,"wins":24},"claude-sonnet-5":{"draws":13,"losses":9,"wins":62},"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":19,"losses":1,"wins":104},"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":10,"losses":11,"wins":63},"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":14,"losses":6,"wins":84},"google/gemini-3.5-flash-lite":{"draws":22,"losses":11,"wins":111},"google/gemini-3.6-flash":{"draws":19,"losses":25,"wins":116},"google/gemini-3.8-flash":{"draws":7,"losses":19,"wins":58},"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":11,"losses":15,"wins":54},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":39},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":67},"gpt-5.5":{"draws":11,"losses":21,"wins":48},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":64},"gpt-5.6-sol":{"draws":17,"losses":22,"wins":45},"gpt-5.6-terra":{"draws":11,"losses":8,"wins":61},"gpt-6-astra":{"draws":5,"losses":60,"wins":19},"gpt-6-luna":{"draws":15,"losses":9,"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":16,"losses":1,"wins":39},"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":11,"losses":8,"wins":69},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":66},"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":5,"losses":5,"wins":38},"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":7,"losses":2,"wins":67},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":75},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":37},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":11,"wins":56},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":39},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":44},"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":43,"losses":29,"wins":212},"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":4,"losses":13,"wins":63},"thinkingmachines/inkling":{"draws":19,"losses":4,"wins":93},"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":13,"losses":14,"wins":57},"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":29,"losses":6,"wins":93},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":16,"wins":31},"z-ai/glm-5.2":{"draws":22,"losses":11,"wins":135},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":46},"z-ai/glm-5.3-flash":{"draws":10,"losses":19,"wins":55},"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":4,"losses":2,"wins":48},"claude-fable-5-1":{"draws":5,"losses":18,"wins":37},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":50},"claude-opus-4-5":{"draws":4,"losses":1,"wins":83},"claude-opus-4-8":{"draws":1,"losses":1,"wins":48},"claude-opus-5":{"draws":3,"losses":19,"wins":72},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":0,"wins":54},"claude-sonnet-5-5":{"draws":4,"losses":10,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":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":0,"wins":68},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":94},"google/gemini-3.6-flash":{"draws":2,"losses":10,"wins":90},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":49},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":32},"gpt-4.1":{"draws":0,"losses":0,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":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":0,"losses":1,"wins":51},"gpt-6-astra":{"draws":3,"losses":23,"wins":28},"gpt-6-luna":{"draws":0,"losses":1,"wins":53},"gpt-6-sol":{"draws":4,"losses":14,"wins":36},"gpt-6.1-sol":{"draws":4,"losses":19,"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":2,"losses":1,"wins":57},"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":1,"losses":0,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":54},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":33},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":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":3,"wins":48},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":68},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":52},"unbiased/pareto-26.10":{"draws":1,"losses":6,"wins":11},"unbiased/pareto-26.10-preview":{"draws":0,"losses":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":0,"losses":0,"wins":34},"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":3,"losses":5,"wins":44},"z-ai/glm-5.3-flash":{"draws":4,"losses":3,"wins":47},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":51}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":7,"wins":23},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":26,"losses":29,"wins":23},"claude-opus-4-8":{"draws":14,"losses":20,"wins":10},"claude-opus-5":{"draws":9,"losses":60,"wins":13},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"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":18,"losses":17,"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":11,"losses":21,"wins":16},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"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":25,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":22,"wins":33},"google/gemini-3.6-flash":{"draws":27,"losses":50,"wins":15},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":11,"wins":19},"gpt-5.4":{"draws":11,"losses":27,"wins":8},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":21},"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":14,"losses":3,"wins":17},"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":13,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":11},"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":35,"losses":93,"wins":30},"stealth/space-bunny-alpha":{"draws":8,"losses":15,"wins":15},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":23,"wins":7},"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":30,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":28,"wins":9},"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":2,"losses":49,"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":59,"wins":14},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"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":13,"losses":15,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":9,"losses":8,"wins":9},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":20},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":13,"losses":19,"wins":28},"google/gemini-3.5-flash-lite":{"draws":24,"losses":16,"wins":44},"google/gemini-3.6-flash":{"draws":22,"losses":39,"wins":31},"google/gemini-3.8-flash":{"draws":6,"losses":25,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":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":5,"losses":33,"wins":10},"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":21,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":9,"losses":17,"wins":22},"qwen/qwen3.8-max-0902":{"draws":10,"losses":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":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":13,"wins":12},"claude-fable-5":{"draws":6,"losses":28,"wins":2},"claude-fable-5-1":{"draws":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":6,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":1},"elorian/glimpse":{"draws":3,"losses":12,"wins":5},"fireworks/ember-1":{"draws":7,"losses":22,"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":48,"wins":8},"google/gemini-3.8-flash":{"draws":4,"losses":26,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":5},"gpt-4.1":{"draws":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":28,"wins":3},"qwen/qwen3.8-max-0902":{"draws":4,"losses":27,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":21,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":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":33,"losses":50,"wins":37},"claude-fable-5":{"draws":20,"losses":104,"wins":8},"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":62,"losses":116,"wins":38},"claude-opus-4-8":{"draws":31,"losses":78,"wins":15},"claude-opus-5":{"draws":22,"losses":190,"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":36,"losses":79,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":93,"wins":15},"elorian/glimpse":{"draws":15,"losses":39,"wins":16},"fireworks/ember-1":{"draws":37,"losses":74,"wins":21},"gemini-3.1-pro-preview":{"draws":34,"losses":67,"wins":31},"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":97,"wins":35},"google/gemini-3.5-flash-lite":{"draws":65,"losses":83,"wins":82},"google/gemini-3.6-flash":{"draws":57,"losses":155,"wins":40},"google/gemini-3.8-flash":{"draws":24,"losses":96,"wins":12},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":27},"gpt-4.1":{"draws":14,"losses":23,"wins":7},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":34,"losses":56,"wins":26},"gpt-5.4":{"draws":30,"losses":78,"wins":18},"gpt-5.4-mini":{"draws":30,"losses":33,"wins":25},"gpt-5.4-nano":{"draws":24,"losses":63,"wins":53},"gpt-5.5":{"draws":39,"losses":70,"wins":11},"gpt-5.6-luna":{"draws":51,"losses":55,"wins":26},"gpt-5.6-sol":{"draws":17,"losses":109,"wins":6},"gpt-5.6-terra":{"draws":37,"losses":74,"wins":15},"gpt-6-astra":{"draws":3,"losses":125,"wins":4},"gpt-6-luna":{"draws":34,"losses":72,"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":32,"losses":26,"wins":36},"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":39,"losses":30,"wins":45},"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":17,"losses":27,"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":28,"losses":20,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":16,"wins":8},"moonshotai/kimi-k3":{"draws":38,"losses":68,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":118,"wins":2},"nex-agi/nex-n2-pro":{"draws":15,"losses":24,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":40,"wins":47},"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":34,"losses":46,"wins":48},"qwen/qwen3.7-max":{"draws":24,"losses":31,"wins":25},"qwen/qwen3.7-plus":{"draws":17,"losses":27,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":79,"wins":16},"qwen/qwen3.8-27b":{"draws":22,"losses":52,"wins":20},"qwen/qwen3.8-flash":{"draws":23,"losses":42,"wins":23},"qwen/qwen3.8-max":{"draws":39,"losses":72,"wins":21},"qwen/qwen3.8-max-0902":{"draws":37,"losses":78,"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":95,"losses":253,"wins":68},"stealth/space-bunny-alpha":{"draws":31,"losses":52,"wins":21},"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":29,"losses":76,"wins":21},"thinkingmachines/inkling":{"draws":49,"losses":67,"wins":58},"thinkingmachines/inkling-small":{"draws":46,"losses":33,"wins":53},"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":30,"losses":93,"wins":9},"x-ai/grok-4.7":{"draws":11,"losses":99,"wins":8},"x-ai/grok-build-0.1":{"draws":14,"losses":12,"wins":18},"xiaomi/mimo-v2.5":{"draws":62,"losses":72,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":33,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":56,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":63,"wins":13},"z-ai/glm-5.2":{"draws":80,"losses":118,"wins":66},"z-ai/glm-5.3":{"draws":27,"losses":91,"wins":8},"z-ai/glm-5.3-flash":{"draws":24,"losses":78,"wins":30},"z-ai/glm-5.3-flashx":{"draws":34,"losses":77,"wins":21}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":28},"claude-fable-5":{"draws":7,"losses":28,"wins":13},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":22,"losses":18,"wins":38},"claude-opus-4-8":{"draws":9,"losses":19,"wins":16},"claude-opus-5":{"draws":8,"losses":58,"wins":16},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":15,"losses":17,"wins":40},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":20,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":28,"wins":10},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":11,"losses":20,"wins":17},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":23},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":23},"google/gemini-3.5-flash-lite":{"draws":14,"losses":22,"wins":48},"google/gemini-3.6-flash":{"draws":21,"losses":31,"wins":40},"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":13,"wins":23},"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":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":13},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":20},"gpt-6-astra":{"draws":4,"losses":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":10,"losses":4,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":39},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":26},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":22},"meta/muse-spark-1.3":{"draws":9,"losses":22,"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":3,"wins":19},"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":8,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":7,"losses":10,"wins":29},"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":38,"losses":64,"wins":56},"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":8,"losses":22,"wins":16},"thinkingmachines/inkling":{"draws":20,"losses":5,"wins":39},"thinkingmachines/inkling-small":{"draws":15,"losses":6,"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":9,"losses":25,"wins":14},"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":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":28,"losses":23,"wins":45},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":15},"z-ai/glm-5.3-flash":{"draws":9,"losses":22,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":21,"wins":18}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":18},"claude-fable-5":{"draws":5,"losses":33,"wins":10},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":10,"losses":24,"wins":12},"claude-opus-4-5":{"draws":24,"losses":29,"wins":25},"claude-opus-4-8":{"draws":11,"losses":17,"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":18,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":12},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":11,"losses":26,"wins":11},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":19},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":23},"google/gemini-3.5-flash":{"draws":15,"losses":27,"wins":18},"google/gemini-3.5-flash-lite":{"draws":27,"losses":17,"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":14,"wins":17},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":34,"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":7,"losses":27,"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":6,"losses":5,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":18,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":8,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":10,"losses":23,"wins":33},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":12,"losses":14,"wins":20},"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":15,"losses":18,"wins":15},"qwen/qwen3.8-27b":{"draws":10,"losses":16,"wins":8},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":11},"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":39,"losses":69,"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":33,"losses":31,"wins":32},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":5,"losses":30,"wins":13},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":7,"wins":22},"claude-fable-5":{"draws":12,"losses":24,"wins":12},"claude-fable-5-1":{"draws":4,"losses":45,"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":26,"losses":7,"wins":39},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":12,"wins":13},"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":14,"losses":12,"wins":22},"gemini-4-argon":{"draws":8,"losses":35,"wins":5},"google/gemini-3.1-flash-lite":{"draws":12,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":18,"losses":17,"wins":25},"google/gemini-3.5-flash-lite":{"draws":33,"losses":7,"wins":44},"google/gemini-3.6-flash":{"draws":29,"losses":35,"wins":28},"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":13,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":30,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"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":35,"losses":62,"wins":61},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"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":7,"losses":18,"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":13,"losses":5,"wins":26},"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":16,"losses":16,"wins":12},"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":17,"wins":17},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":22,"losses":12,"wins":38},"deepseek/deepseek-v4-pro":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":27,"wins":7},"elorian/glimpse":{"draws":7,"losses":7,"wins":12},"fireworks/ember-1":{"draws":8,"losses":8,"wins":16},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":25},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":18,"wins":25},"google/gemini-3.5-flash-lite":{"draws":32,"losses":8,"wins":44},"google/gemini-3.6-flash":{"draws":27,"losses":29,"wins":36},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":20},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":9,"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":17,"losses":14,"wins":13},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":14,"losses":11,"wins":23},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":38,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":20},"inception/mercury-3":{"draws":12,"losses":9,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":32},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":19,"losses":17,"wins":12},"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":6,"losses":2,"wins":20},"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":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"o3":{"draws":12,"losses":16,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":15,"losses":21,"wins":12},"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":45,"losses":52,"wins":61},"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":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":20,"wins":15},"thinkingmachines/inkling":{"draws":22,"losses":4,"wins":38},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":15,"losses":20,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":25,"losses":10,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":13,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":18,"wins":6},"z-ai/glm-5.2":{"draws":29,"losses":21,"wins":46},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":17}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":18},"claude-fable-5":{"draws":13,"losses":26,"wins":9},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":23,"losses":37,"wins":18},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":9,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":16,"losses":18,"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":23,"losses":22,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":13,"losses":25,"wins":10},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":11},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":20},"google/gemini-3.5-flash":{"draws":13,"losses":33,"wins":14},"google/gemini-3.5-flash-lite":{"draws":34,"losses":24,"wins":26},"google/gemini-3.6-flash":{"draws":21,"losses":47,"wins":24},"google/gemini-3.8-flash":{"draws":10,"losses":32,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":5,"wins":9},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":12,"wins":15},"gpt-5.4":{"draws":12,"losses":22,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":21},"gpt-5.5":{"draws":11,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":13,"losses":19,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":16,"losses":17,"wins":15},"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":17,"losses":7,"wins":10},"inception/mercury-3":{"draws":11,"losses":16,"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":13,"losses":17,"wins":22},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":25,"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":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":26,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":11,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":7},"o3":{"draws":15,"losses":29,"wins":22},"openai/gpt-oss-120b":{"draws":13,"losses":10,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":23,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":24,"wins":13},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":43,"losses":75,"wins":40},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"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":9,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":10},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"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":10,"losses":24,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":30,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":32,"losses":19,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":40,"wins":31},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":12,"losses":28,"wins":8}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":38},"claude-fable-5":{"draws":3,"losses":15,"wins":30},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":30},"claude-opus-4-5":{"draws":5,"losses":7,"wins":66},"claude-opus-4-8":{"draws":5,"losses":8,"wins":31},"claude-opus-5":{"draws":12,"losses":43,"wins":27},"claude-opus-5-5":{"draws":1,"losses":38,"wins":13},"claude-sonnet-5":{"draws":7,"losses":4,"wins":37},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":2,"wins":63},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":2,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":7,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":10,"wins":29},"elorian/glimpse":{"draws":6,"losses":3,"wins":17},"fireworks/ember-1":{"draws":7,"losses":4,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":38},"gemini-4-argon":{"draws":7,"losses":16,"wins":9},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":51},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":73},"google/gemini-3.6-flash":{"draws":11,"losses":13,"wins":68},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":35},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":2,"wins":38},"gpt-5.4":{"draws":8,"losses":13,"wins":25},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":25},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":44},"gpt-5.5":{"draws":5,"losses":8,"wins":31},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":29},"gpt-5.6-terra":{"draws":7,"losses":3,"wins":36},"gpt-6-astra":{"draws":4,"losses":35,"wins":9},"gpt-6-luna":{"draws":6,"losses":5,"wins":37},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":5,"losses":34,"wins":9},"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":11,"losses":15,"wins":8},"claude-fable-5":{"draws":4,"losses":31,"wins":1},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":4},"claude-opus-4-5":{"draws":14,"losses":45,"wins":1},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":7,"losses":48,"wins":3},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":14,"losses":21,"wins":1},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":18,"losses":27,"wins":9},"deepseek/deepseek-v4-pro":{"draws":9,"losses":22,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":28,"wins":1},"elorian/glimpse":{"draws":7,"losses":11,"wins":2},"fireworks/ember-1":{"draws":4,"losses":26,"wins":6},"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":11,"losses":27,"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":11,"losses":25,"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":8,"losses":20,"wins":4},"gpt-5.4":{"draws":6,"losses":27,"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":21,"wins":2},"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":9,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":21,"wins":14},"meta/muse-glimmer-30b":{"draws":12,"losses":13,"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":4,"losses":7,"wins":9},"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":7,"losses":13,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":12,"wins":2},"o3":{"draws":10,"losses":45,"wins":5},"openai/gpt-oss-120b":{"draws":10,"losses":15,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":10},"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":26,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":3},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":25,"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":21,"losses":68,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":18,"wins":6},"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":13,"losses":23,"wins":12},"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":7,"losses":28,"wins":1},"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":4,"losses":17,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":0},"z-ai/glm-5.2":{"draws":14,"losses":46,"wins":12},"z-ai/glm-5.3":{"draws":4,"losses":30,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":25,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":22,"wins":4}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":27},"claude-fable-5":{"draws":10,"losses":26,"wins":12},"claude-fable-5-1":{"draws":7,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":19},"claude-opus-4-5":{"draws":21,"losses":16,"wins":41},"claude-opus-4-8":{"draws":8,"losses":13,"wins":23},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"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":22,"losses":10,"wins":40},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":20,"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":16,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":13,"wins":28},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":23},"google/gemini-3.5-flash-lite":{"draws":16,"losses":7,"wins":61},"google/gemini-3.6-flash":{"draws":19,"losses":34,"wins":39},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":6,"losses":12,"wins":24},"gpt-5.4":{"draws":7,"losses":23,"wins":16},"gpt-5.4-mini":{"draws":7,"losses":10,"wins":15},"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":9,"wins":21},"gpt-5.6-sol":{"draws":5,"losses":29,"wins":14},"gpt-5.6-terra":{"draws":12,"losses":12,"wins":22},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":13,"losses":13,"wins":22},"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":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":34},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":12,"losses":17,"wins":17},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":14},"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":14,"losses":14,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"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":18,"wins":42},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":35},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"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":25,"losses":54,"wins":79},"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":20,"wins":19},"thinkingmachines/inkling":{"draws":17,"losses":5,"wins":42},"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":23,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"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":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":21,"wins":54},"z-ai/glm-5.3":{"draws":11,"losses":19,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":20,"wins":21},"z-ai/glm-5.3-flashx":{"draws":13,"losses":16,"wins":19}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":34,"wins":18},"claude-fable-5":{"draws":14,"losses":65,"wins":5},"claude-fable-5-1":{"draws":6,"losses":87,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":48,"wins":12},"claude-opus-4-5":{"draws":49,"losses":73,"wins":14},"claude-opus-4-8":{"draws":25,"losses":50,"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":45,"wins":13},"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":44,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":60,"wins":9},"elorian/glimpse":{"draws":12,"losses":28,"wins":6},"fireworks/ember-1":{"draws":31,"losses":43,"wins":10},"gemini-3.1-pro-preview":{"draws":31,"losses":38,"wins":15},"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":25,"losses":60,"wins":21},"google/gemini-3.5-flash-lite":{"draws":40,"losses":48,"wins":34},"google/gemini-3.6-flash":{"draws":46,"losses":95,"wins":21},"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":38,"wins":26},"meta/muse-glimmer-30b":{"draws":31,"losses":20,"wins":23},"meta/muse-spark-1.2":{"draws":19,"losses":51,"wins":10},"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":13,"wins":17},"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":42,"wins":14},"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":23,"losses":55,"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":17,"losses":38,"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":26,"losses":43,"wins":13},"thinkingmachines/inkling":{"draws":30,"losses":50,"wins":34},"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":20,"wins":11},"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":60,"losses":76,"wins":32},"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":17,"losses":13,"wins":48},"claude-fable-5":{"draws":13,"losses":42,"wins":29},"claude-fable-5-1":{"draws":9,"losses":79,"wins":8},"claude-haiku-5-5":{"draws":15,"losses":29,"wins":36},"claude-opus-4-5":{"draws":38,"losses":29,"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":22,"wins":42},"claude-sonnet-5-5":{"draws":13,"losses":33,"wins":38},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":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":22,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":35,"wins":36},"elorian/glimpse":{"draws":9,"losses":14,"wins":23},"fireworks/ember-1":{"draws":17,"losses":34,"wins":33},"gemini-3.1-pro-preview":{"draws":15,"losses":25,"wins":44},"gemini-4-argon":{"draws":5,"losses":61,"wins":18},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":46},"google/gemini-3.5-flash":{"draws":21,"losses":31,"wins":54},"google/gemini-3.5-flash-lite":{"draws":37,"losses":28,"wins":85},"google/gemini-3.6-flash":{"draws":26,"losses":47,"wins":63},"google/gemini-3.8-flash":{"draws":15,"losses":39,"wins":30},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":28},"gpt-4.1":{"draws":7,"losses":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":31,"wins":35},"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":24,"losses":13,"wins":47},"gpt-5.6-sol":{"draws":11,"losses":47,"wins":26},"gpt-5.6-terra":{"draws":23,"losses":15,"wins":42},"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":16,"losses":2,"wins":40},"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":28,"wins":37},"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":20,"losses":24,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":60,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":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":7,"wins":44},"poolside/laguna-s-2.1":{"draws":17,"losses":14,"wins":47},"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":24,"wins":40},"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":19,"losses":28,"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":51,"losses":103,"wins":130},"stealth/space-bunny-alpha":{"draws":18,"losses":10,"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":8,"wins":23},"tencent/hy4-preview":{"draws":20,"losses":26,"wins":36},"thinkingmachines/inkling":{"draws":28,"losses":15,"wins":73},"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":29,"wins":37},"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":1,"wins":19},"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":37,"losses":47,"wins":84},"z-ai/glm-5.3":{"draws":13,"losses":45,"wins":22},"z-ai/glm-5.3-flash":{"draws":8,"losses":44,"wins":32},"z-ai/glm-5.3-flashx":{"draws":15,"losses":30,"wins":39}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":27},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":28,"losses":12,"wins":38},"claude-opus-4-8":{"draws":13,"losses":11,"wins":20},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":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":11,"losses":12,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":12,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":23,"wins":14},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":12,"losses":9,"wins":27},"gemini-4-argon":{"draws":12,"losses":33,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":14,"wins":36},"google/gemini-3.5-flash-lite":{"draws":21,"losses":3,"wins":60},"google/gemini-3.6-flash":{"draws":23,"losses":25,"wins":44},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":14},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":13,"wins":20},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":19},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":31},"gpt-5.5":{"draws":21,"losses":14,"wins":9},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":14},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":22},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":14,"losses":14,"wins":20},"gpt-6-sol":{"draws":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":8,"losses":0,"wins":26},"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":13,"losses":3,"wins":26},"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":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":8,"wins":27},"mistralai/mistral-large-4-0":{"draws":11,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":11,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":32,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":0,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":7,"wins":13},"o3":{"draws":8,"losses":19,"wins":39},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":14,"wins":21},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-max-0902":{"draws":18,"losses":11,"wins":19},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":22},"stealth/ox-alpha":{"draws":34,"losses":44,"wins":80},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":10,"losses":15,"wins":21},"thinkingmachines/inkling":{"draws":21,"losses":4,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":31},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":10,"losses":22,"wins":16},"x-ai/grok-4.6":{"draws":21,"losses":16,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":3,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":25,"losses":16,"wins":55},"z-ai/glm-5.3":{"draws":8,"losses":22,"wins":16},"z-ai/glm-5.3-flash":{"draws":5,"losses":17,"wins":26},"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":8,"losses":16,"wins":16},"claude-fable-5":{"draws":5,"losses":29,"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":14,"losses":32,"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":15,"wins":14},"claude-sonnet-5-5":{"draws":6,"losses":27,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":13,"losses":18,"wins":31},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":24,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":8,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":12},"gemini-4-argon":{"draws":3,"losses":33,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":15,"losses":26,"wins":35},"google/gemini-3.6-flash":{"draws":8,"losses":42,"wins":32},"google/gemini-3.8-flash":{"draws":5,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":11},"gpt-4.1":{"draws":3,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":6},"gpt-5.4":{"draws":7,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":10,"wins":12},"gpt-5.4-nano":{"draws":2,"losses":21,"wins":19},"gpt-5.5":{"draws":9,"losses":18,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":3,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":18,"wins":13},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":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":9,"losses":8,"wins":13},"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":9,"losses":12,"wins":17},"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":3,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":9,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":11,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":8,"losses":23,"wins":33},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":4,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":3,"losses":31,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"recursive/flint-v1.0":{"draws":1,"losses":5,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":29,"losses":63,"wins":50},"stealth/space-bunny-alpha":{"draws":5,"losses":16,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":11,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":19,"wins":14},"x-ai/grok-4.6":{"draws":9,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":18,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":21,"losses":27,"wins":36},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":8},"z-ai/glm-5.3-flash":{"draws":4,"losses":26,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":27,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":25},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":4,"losses":44,"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":7,"losses":62,"wins":13},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":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":15,"losses":13,"wins":20},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"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":9,"losses":13,"wins":24},"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":13,"losses":11,"wins":20},"claude-fable-5":{"draws":10,"losses":28,"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":22,"losses":30,"wins":26},"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":11,"wins":37},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":32,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":14,"losses":23,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":19},"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":17,"losses":17,"wins":26},"google/gemini-3.5-flash-lite":{"draws":28,"losses":15,"wins":41},"google/gemini-3.6-flash":{"draws":21,"losses":45,"wins":26},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":11},"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":8,"losses":10,"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":21,"losses":15,"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":1,"losses":42,"wins":5},"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":9,"losses":3,"wins":22},"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":13,"losses":15,"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":13,"losses":9,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":6},"o3":{"draws":9,"losses":29,"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":13,"losses":24,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":14},"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":77,"wins":47},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":16},"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":22,"losses":11,"wins":31},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"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":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":24,"wins":11},"x-ai/grok-4.6":{"draws":12,"losses":24,"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":5,"losses":7,"wins":14},"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":35,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":28,"wins":26},"claude-fable-5":{"draws":6,"losses":56,"wins":10},"claude-fable-5-1":{"draws":2,"losses":76,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":38,"wins":24},"claude-opus-4-5":{"draws":30,"losses":49,"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":21,"losses":38,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":36,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":31,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":36,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":46,"wins":16},"elorian/glimpse":{"draws":5,"losses":18,"wins":15},"fireworks/ember-1":{"draws":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":11,"losses":48,"wins":35},"google/gemini-3.5-flash-lite":{"draws":17,"losses":54,"wins":57},"google/gemini-3.6-flash":{"draws":22,"losses":82,"wins":34},"google/gemini-3.8-flash":{"draws":9,"losses":48,"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":7,"losses":30,"wins":27},"gpt-5.4":{"draws":7,"losses":44,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":12,"wins":27},"gpt-5.4-nano":{"draws":4,"losses":26,"wins":30},"gpt-5.5":{"draws":12,"losses":35,"wins":19},"gpt-5.6-luna":{"draws":13,"losses":30,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":56,"wins":10},"gpt-5.6-terra":{"draws":8,"losses":36,"wins":24},"gpt-6-astra":{"draws":0,"losses":70,"wins":2},"gpt-6-luna":{"draws":12,"losses":30,"wins":30},"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":11,"losses":18,"wins":23},"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":11,"losses":21,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":32,"wins":25},"meta/muse-spark-1.3":{"draws":11,"losses":40,"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":7,"losses":6,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":8},"moonshotai/kimi-k3":{"draws":15,"losses":32,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":63,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":11,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":24,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":14,"wins":15},"o3":{"draws":7,"losses":46,"wins":65},"openai/gpt-oss-120b":{"draws":11,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":6,"losses":24,"wins":38},"qwen/qwen3.7-max":{"draws":6,"losses":19,"wins":21},"qwen/qwen3.7-plus":{"draws":7,"losses":16,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":40,"wins":15},"qwen/qwen3.8-27b":{"draws":6,"losses":25,"wins":21},"qwen/qwen3.8-flash":{"draws":8,"losses":24,"wins":16},"qwen/qwen3.8-max":{"draws":17,"losses":38,"wins":17},"qwen/qwen3.8-max-0902":{"draws":14,"losses":38,"wins":20},"recursive/flint-v1.0":{"draws":3,"losses":10,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":30,"wins":24},"stealth/ox-alpha":{"draws":28,"losses":103,"wins":71},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":7,"losses":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":8,"losses":42,"wins":20},"thinkingmachines/inkling":{"draws":17,"losses":29,"wins":48},"thinkingmachines/inkling-small":{"draws":20,"losses":17,"wins":35},"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":8,"losses":52,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":51,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":15},"xiaomi/mimo-v2.5":{"draws":24,"losses":35,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":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":24,"losses":58,"wins":62},"z-ai/glm-5.3":{"draws":7,"losses":47,"wins":14},"z-ai/glm-5.3-flash":{"draws":9,"losses":38,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":42,"wins":20}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":10,"wins":16},"claude-fable-5":{"draws":11,"losses":23,"wins":14},"claude-fable-5-1":{"draws":2,"losses":48,"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":12,"losses":13,"wins":19},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"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":23,"losses":11,"wins":38},"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":12,"losses":14,"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":17,"losses":18,"wins":25},"google/gemini-3.5-flash-lite":{"draws":32,"losses":16,"wins":36},"google/gemini-3.6-flash":{"draws":25,"losses":33,"wins":34},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":10,"wins":20},"gpt-5.4":{"draws":12,"losses":18,"wins":16},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":18,"wins":18},"gpt-5.5":{"draws":9,"losses":9,"wins":10},"gpt-5.6-luna":{"draws":19,"losses":7,"wins":22},"gpt-5.6-sol":{"draws":10,"losses":22,"wins":16},"gpt-5.6-terra":{"draws":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":13,"losses":5,"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":12,"losses":16,"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":7,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":20},"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":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":9},"o3":{"draws":13,"losses":20,"wins":33},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":17,"losses":11,"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":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":11},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":8,"wins":24},"stealth/ox-alpha":{"draws":44,"losses":65,"wins":49},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":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":22,"wins":18},"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":39,"losses":19,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":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":16,"losses":15,"wins":17},"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":31,"wins":5},"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":17,"losses":21,"wins":10},"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":8,"losses":16,"wins":14},"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":6,"wins":32},"claude-fable-5":{"draws":8,"losses":20,"wins":20},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":17,"losses":11,"wins":50},"claude-opus-4-8":{"draws":4,"losses":15,"wins":25},"claude-opus-5":{"draws":13,"losses":50,"wins":19},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":25},"elorian/glimpse":{"draws":2,"losses":7,"wins":17},"fireworks/ember-1":{"draws":6,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":17,"wins":27},"gemini-4-argon":{"draws":6,"losses":30,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":29},"google/gemini-3.5-flash":{"draws":5,"losses":15,"wins":40},"google/gemini-3.5-flash-lite":{"draws":10,"losses":10,"wins":64},"google/gemini-3.6-flash":{"draws":8,"losses":27,"wins":57},"google/gemini-3.8-flash":{"draws":5,"losses":17,"wins":26},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":9,"losses":14,"wins":23},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":38},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":35},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":8,"losses":10,"wins":30},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":5,"losses":7,"wins":20},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":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":5,"losses":16,"wins":25},"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":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":24},"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":5,"losses":10,"wins":51},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":37},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":31},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":24},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":21},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":6,"losses":11,"wins":31},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":6,"wins":35},"stealth/ox-alpha":{"draws":21,"losses":35,"wins":102},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":26},"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":14,"wins":27},"x-ai/grok-4.6":{"draws":9,"losses":22,"wins":17},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":7,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":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":9,"losses":14,"wins":23},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":8,"losses":15,"wins":25}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":11,"wins":21},"claude-fable-5":{"draws":10,"losses":30,"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":13,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"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":22,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":19},"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":19,"wins":29},"google/gemini-3.5-flash-lite":{"draws":23,"losses":15,"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":8,"losses":3,"wins":5},"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":13,"wins":28},"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":6,"losses":4,"wins":18},"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":17,"losses":15,"wins":16},"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":42,"losses":67,"wins":49},"stealth/space-bunny-alpha":{"draws":9,"losses":11,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":13,"losses":20,"wins":13},"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":22,"wins":13},"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":4,"wins":6},"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":34,"losses":23,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":30,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":18}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":41},"claude-fable-5":{"draws":4,"losses":6,"wins":38},"claude-fable-5-1":{"draws":7,"losses":19,"wins":28},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":41},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":10,"losses":23,"wins":49},"claude-opus-5-5":{"draws":4,"losses":25,"wins":23},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":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":3,"losses":2,"wins":43},"gemini-4-argon":{"draws":3,"losses":14,"wins":31},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":54},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":80},"google/gemini-3.6-flash":{"draws":6,"losses":7,"wins":79},"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":1,"losses":1,"wins":46},"gpt-5.5":{"draws":1,"losses":3,"wins":40},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":42},"gpt-5.6-sol":{"draws":4,"losses":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":5,"losses":3,"wins":38},"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":4,"losses":6,"wins":38},"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":17,"losses":14,"wins":13},"claude-fable-5":{"draws":8,"losses":30,"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":29,"losses":33,"wins":16},"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":31,"losses":14,"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":13,"losses":20,"wins":15},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":17},"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":29,"losses":49,"wins":14},"google/gemini-3.8-flash":{"draws":19,"losses":23,"wins":6},"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":16,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":16,"wins":20},"gpt-5.5":{"draws":21,"losses":17,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":14,"wins":12},"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":4,"wins":12},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":18},"inclusionai/ling-3.1-flash":{"draws":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":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":9,"losses":17,"wins":16},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":18,"losses":17,"wins":11},"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":12,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":8},"o3":{"draws":14,"losses":21,"wins":31},"openai/gpt-oss-120b":{"draws":14,"losses":11,"wins":17},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":9,"losses":17,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"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":11,"losses":13,"wins":14},"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":12,"losses":26,"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":6,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":11,"wins":33},"elorian/glimpse":{"draws":5,"losses":4,"wins":17},"fireworks/ember-1":{"draws":7,"losses":6,"wins":35},"gemini-3.1-pro-preview":{"draws":2,"losses":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":13,"losses":15,"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":13,"wins":26},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":11,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":38},"claude-fable-5":{"draws":3,"losses":9,"wins":36},"claude-fable-5-1":{"draws":1,"losses":24,"wins":29},"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":27,"wins":21},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":1,"losses":10,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":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":1,"losses":4,"wins":43},"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":6,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":5,"losses":6,"wins":81},"google/gemini-3.8-flash":{"draws":3,"losses":6,"wins":39},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":2,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":29},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":46},"gpt-5.5":{"draws":1,"losses":6,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":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":16,"wins":15},"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":2,"losses":1,"wins":25},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":39},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":29},"qwen/qwen3.8-max":{"draws":4,"losses":3,"wins":41},"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":1,"losses":14,"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":4,"losses":5,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"wins":39}},"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":8,"losses":28,"wins":0},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":25,"wins":1},"claude-opus-4-5":{"draws":21,"losses":38,"wins":1},"claude-opus-4-8":{"draws":11,"losses":24,"wins":1},"claude-opus-5":{"draws":7,"losses":48,"wins":3},"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":11,"losses":20,"wins":1},"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":14,"losses":22,"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":28,"losses":28,"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":21,"wins":1},"qwen/qwen3.8-max-0902":{"draws":14,"losses":18,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":21,"wins":2},"stealth/ox-alpha":{"draws":33,"losses":65,"wins":4},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"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":25,"wins":11},"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":23,"losses":40,"wins":7},"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":4,"wins":12},"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":5,"wins":7},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"wins":6},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":5},"moonshotai/kimi-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":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":9,"wins":12},"stealth/ox-alpha":{"draws":21,"losses":65,"wins":16},"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":6,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":9},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":24,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":20,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":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":28,"wins":20},"claude-fable-5":{"draws":7,"losses":54,"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":6,"losses":70,"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":32,"losses":41,"wins":33},"deepseek/deepseek-v4-pro":{"draws":13,"losses":40,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":34,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":43,"wins":13},"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":39,"wins":19},"gemini-3.1-pro-preview":{"draws":13,"losses":33,"wins":26},"gemini-4-argon":{"draws":5,"losses":61,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":15,"wins":31},"google/gemini-3.5-flash":{"draws":18,"losses":56,"wins":18},"google/gemini-3.5-flash-lite":{"draws":32,"losses":49,"wins":49},"google/gemini-3.6-flash":{"draws":30,"losses":87,"wins":21},"google/gemini-3.8-flash":{"draws":14,"losses":46,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":15,"wins":18},"gpt-4.1":{"draws":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":21,"losses":29,"wins":22},"gpt-5.6-sol":{"draws":11,"losses":53,"wins":8},"gpt-5.6-terra":{"draws":18,"losses":32,"wins":18},"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":13,"wins":17},"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":14,"wins":21},"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":15,"losses":24,"wins":21},"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":12,"wins":11},"tencent/hy4-preview":{"draws":20,"losses":39,"wins":11},"thinkingmachines/inkling":{"draws":25,"losses":34,"wins":33},"thinkingmachines/inkling-small":{"draws":20,"losses":21,"wins":31},"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":10,"losses":25,"wins":9},"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":15,"losses":17,"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":14,"losses":28,"wins":4},"claude-opus-4-5":{"draws":28,"losses":40,"wins":10},"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":31,"losses":29,"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":13,"losses":29,"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":34,"wins":7},"google/gemini-3.5-flash-lite":{"draws":40,"losses":30,"wins":14},"google/gemini-3.6-flash":{"draws":28,"losses":58,"wins":6},"google/gemini-3.8-flash":{"draws":10,"losses":34,"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":12,"losses":21,"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":10,"losses":23,"wins":15},"gpt-5.5":{"draws":11,"losses":24,"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":11,"losses":29,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":39,"wins":0},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":15,"wins":8},"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":19,"losses":15,"wins":12},"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":12,"losses":34,"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":13,"losses":27,"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":37,"losses":106,"wins":15},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":31,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":18},"thinkingmachines/inkling-small":{"draws":19,"losses":13,"wins":16},"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":39,"losses":41,"wins":16},"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":8,"losses":9,"wins":21},"claude-fable-5":{"draws":7,"losses":23,"wins":12},"claude-fable-5-1":{"draws":2,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":8,"losses":16,"wins":16},"claude-opus-4-5":{"draws":21,"losses":10,"wins":37},"claude-opus-4-8":{"draws":9,"losses":13,"wins":16},"claude-opus-5":{"draws":10,"losses":53,"wins":17},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":11,"losses":11,"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":17,"losses":4,"wins":41},"deepseek/deepseek-v4-pro":{"draws":6,"losses":15,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":11,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":19,"wins":16},"elorian/glimpse":{"draws":5,"losses":7,"wins":12},"fireworks/ember-1":{"draws":12,"losses":14,"wins":16},"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":12,"losses":10,"wins":30},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":46},"google/gemini-3.6-flash":{"draws":14,"losses":24,"wins":42},"google/gemini-3.8-flash":{"draws":6,"losses":13,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":4,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":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":7,"losses":15,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":22},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":14},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":18},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":12,"losses":7,"wins":23},"gpt-6-sol":{"draws":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":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":27},"meta/muse-spark-1.2":{"draws":8,"losses":8,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":21},"meta/muse-spark-open":{"draws":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":6,"losses":5,"wins":13},"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":9,"losses":2,"wins":27},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"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":10,"losses":14,"wins":18},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":13,"losses":14,"wins":15},"qwen/qwen3.8-max-0902":{"draws":13,"losses":13,"wins":16},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":11,"wins":20},"stealth/ox-alpha":{"draws":38,"losses":57,"wins":47},"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":4,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":15,"wins":16},"thinkingmachines/inkling":{"draws":16,"losses":6,"wins":36},"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":3,"losses":3,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":16,"losses":17,"wins":51},"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":10,"losses":16,"wins":16}},"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":9,"losses":8,"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":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":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":18,"wins":6},"claude-fable-5":{"draws":9,"losses":32,"wins":1},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":31,"wins":5},"claude-opus-4-5":{"draws":20,"losses":47,"wins":3},"claude-opus-4-8":{"draws":13,"losses":27,"wins":2},"claude-opus-5":{"draws":9,"losses":58,"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":24,"wins":7},"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":20,"losses":37,"wins":17},"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":13,"losses":23,"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":12,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":26,"wins":14},"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":9,"wins":7},"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":11,"losses":24,"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":85,"wins":12},"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":9,"losses":8,"wins":15},"claude-fable-5":{"draws":5,"losses":26,"wins":5},"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":8,"losses":21,"wins":7},"claude-opus-5":{"draws":6,"losses":59,"wins":3},"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":7,"losses":18,"wins":11},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"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":14,"wins":17},"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":11,"losses":12,"wins":11},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":25,"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":16,"wins":8},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":7},"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":9,"losses":17,"wins":10},"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":23,"losses":51,"wins":28},"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":9,"losses":21,"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":11,"losses":12,"wins":21},"claude-fable-5":{"draws":14,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":11},"claude-opus-4-5":{"draws":28,"losses":27,"wins":23},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":13,"losses":61,"wins":8},"claude-opus-5-5":{"draws":2,"losses":46,"wins":4},"claude-sonnet-5":{"draws":15,"losses":15,"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":17,"losses":13,"wins":42},"deepseek/deepseek-v4-pro":{"draws":8,"losses":15,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":9},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":17,"losses":20,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":23,"wins":22},"google/gemini-3.5-flash-lite":{"draws":24,"losses":16,"wins":44},"google/gemini-3.6-flash":{"draws":24,"losses":41,"wins":27},"google/gemini-3.8-flash":{"draws":12,"losses":29,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":16,"wins":16},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":26},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":18,"losses":10,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":16,"losses":15,"wins":15},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":16,"losses":16,"wins":16},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":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":5,"losses":4,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":31},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":11,"losses":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":11,"losses":2,"wins":15},"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":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":8,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":9,"losses":26,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":7,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":23,"wins":11},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":19,"wins":13},"stealth/ox-alpha":{"draws":33,"losses":69,"wins":56},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":27,"wins":12},"x-ai/grok-4.6":{"draws":17,"losses":23,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":25,"losses":9,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":26,"losses":33,"wins":37},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":11}},"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":21,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":24,"wins":4},"elorian/glimpse":{"draws":0,"losses":11,"wins":5},"fireworks/ember-1":{"draws":2,"losses":26,"wins":2},"gemini-3.1-pro-preview":{"draws":3,"losses":22,"wins":5},"gemini-4-argon":{"draws":0,"losses":29,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":31,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":39,"wins":11},"google/gemini-3.6-flash":{"draws":2,"losses":52,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":30,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":4},"gpt-4.1":{"draws":0,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":21,"wins":6},"gpt-5.4":{"draws":4,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":1,"losses":19,"wins":12},"gpt-5.5":{"draws":0,"losses":26,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":21,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":25,"wins":2},"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":1,"losses":10,"wins":9},"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":3,"losses":18,"wins":5},"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":1,"losses":13,"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":17,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":9,"wins":3},"o3":{"draws":1,"losses":45,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":21,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":24,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":14,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":17,"wins":1},"qwen/qwen3.8-max":{"draws":4,"losses":22,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":24,"wins":2},"recursive/flint-v1.0":{"draws":0,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":22,"wins":3},"stealth/ox-alpha":{"draws":13,"losses":86,"wins":9},"stealth/space-bunny-alpha":{"draws":2,"losses":19,"wins":3},"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":24,"wins":4},"thinkingmachines/inkling":{"draws":6,"losses":24,"wins":10},"thinkingmachines/inkling-small":{"draws":3,"losses":20,"wins":7},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":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":12,"losses":43,"wins":5},"z-ai/glm-5.3":{"draws":3,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":27,"wins":1},"z-ai/glm-5.3-flashx":{"draws":2,"losses":27,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":8},"claude-fable-5":{"draws":4,"losses":23,"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":19,"losses":23,"wins":8},"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":14,"losses":17,"wins":19},"deepseek/deepseek-v4-pro":{"draws":4,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":15,"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":10,"losses":14,"wins":6},"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":4,"losses":5,"wins":13},"google/gemini-3.5-flash":{"draws":7,"losses":25,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":20,"wins":18},"google/gemini-3.6-flash":{"draws":10,"losses":33,"wins":13},"google/gemini-3.8-flash":{"draws":6,"losses":22,"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":6,"losses":14,"wins":6},"gpt-5.4":{"draws":5,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":16,"wins":14},"gpt-5.5":{"draws":5,"losses":15,"wins":6},"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":6,"losses":15,"wins":9},"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":5,"losses":10,"wins":11},"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":8,"losses":7,"wins":9},"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":6,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":25,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":2},"o3":{"draws":6,"losses":29,"wins":11},"openai/gpt-oss-120b":{"draws":9,"losses":13,"wins":4},"poolside/laguna-s-2.1":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":16,"wins":5},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":7,"losses":13,"wins":10},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":3},"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":15,"losses":44,"wins":23},"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":9,"losses":13,"wins":6},"thinkingmachines/inkling":{"draws":8,"losses":13,"wins":15},"thinkingmachines/inkling-small":{"draws":9,"losses":7,"wins":14},"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":6,"losses":20,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":14,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":4},"z-ai/glm-5.2":{"draws":18,"losses":24,"wins":18},"z-ai/glm-5.3":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":13,"wins":13},"z-ai/glm-5.3-flashx":{"draws":5,"losses":16,"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":10,"losses":37,"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":13,"losses":23,"wins":8},"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":17,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":23,"wins":12},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":8,"wins":13},"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":14,"losses":32,"wins":2},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":26,"wins":5},"stealth/ox-alpha":{"draws":42,"losses":102,"wins":14},"stealth/space-bunny-alpha":{"draws":11,"losses":20,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":15,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":12,"wins":6},"tencent/hy4-preview":{"draws":17,"losses":23,"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":22,"losses":25,"wins":15},"claude-fable-5":{"draws":14,"losses":45,"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":53,"wins":11},"claude-opus-4-8":{"draws":23,"losses":30,"wins":5},"claude-opus-5":{"draws":18,"losses":98,"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":40,"losses":34,"wins":24},"deepseek/deepseek-v4-pro":{"draws":19,"losses":22,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":28,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":28,"wins":10},"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":25,"losses":29,"wins":12},"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":21,"losses":47,"wins":12},"google/gemini-3.5-flash-lite":{"draws":45,"losses":32,"wins":37},"google/gemini-3.6-flash":{"draws":40,"losses":69,"wins":15},"google/gemini-3.8-flash":{"draws":12,"losses":48,"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":19,"losses":28,"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":20,"losses":27,"wins":19},"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":33,"wins":10},"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":19,"losses":13,"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":18,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":23,"losses":38,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":52,"wins":0},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":19,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":4},"o3":{"draws":15,"losses":45,"wins":22},"openai/gpt-oss-120b":{"draws":30,"losses":22,"wins":8},"poolside/laguna-s-2.1":{"draws":16,"losses":20,"wins":14},"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":21,"losses":40,"wins":5},"qwen/qwen3.8-27b":{"draws":14,"losses":24,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":7},"qwen/qwen3.8-max":{"draws":22,"losses":35,"wins":9},"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":65,"losses":138,"wins":27},"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":29,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":55,"losses":49,"wins":28},"z-ai/glm-5.3":{"draws":18,"losses":40,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":37,"wins":14},"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":2,"losses":43,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":12},"claude-opus-4-5":{"draws":21,"losses":28,"wins":21},"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":30,"losses":9,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":12,"wins":13},"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":11,"losses":18,"wins":13},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"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":17,"losses":17,"wins":20},"google/gemini-3.5-flash-lite":{"draws":27,"losses":18,"wins":29},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":10,"losses":21,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":14,"wins":8},"gpt-5.4":{"draws":8,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":21},"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":38,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":1},"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":12,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":25},"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":10,"losses":1,"wins":13},"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":13,"losses":23,"wins":26},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":16},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":16},"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":15,"losses":17,"wins":10},"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":11,"losses":14,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":19,"wins":10},"stealth/ox-alpha":{"draws":31,"losses":56,"wins":31},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":21},"stepfun/step-5-preview":{"draws":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":24,"wins":11},"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":24,"losses":33,"wins":27},"z-ai/glm-5.3":{"draws":10,"losses":21,"wins":9},"z-ai/glm-5.3-flash":{"draws":13,"losses":17,"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":8,"losses":11,"wins":13},"claude-fable-5":{"draws":3,"losses":28,"wins":5},"claude-fable-5-1":{"draws":0,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":22,"wins":7},"claude-opus-4-5":{"draws":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":14,"losses":18,"wins":26},"deepseek/deepseek-v4-pro":{"draws":4,"losses":16,"wins":12},"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":8,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":12},"gemini-4-argon":{"draws":2,"losses":33,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":7,"losses":23,"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":6,"losses":26,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":9},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":18,"wins":8},"gpt-5.4":{"draws":4,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":24},"gpt-5.5":{"draws":13,"losses":15,"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":7,"losses":4,"wins":15},"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":6,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":6,"wins":8},"o3":{"draws":5,"losses":29,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":14,"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":11,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":11},"stealth/ox-alpha":{"draws":18,"losses":62,"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":19,"losses":28,"wins":25},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":18,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":9}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":10,"losses":34,"wins":4},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":22,"wins":8},"claude-opus-4-5":{"draws":32,"losses":30,"wins":16},"claude-opus-4-8":{"draws":16,"losses":20,"wins":8},"claude-opus-5":{"draws":11,"losses":59,"wins":12},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":18,"losses":21,"wins":9},"claude-sonnet-5-5":{"draws":14,"losses":24,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":28,"losses":15,"wins":29},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":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":25,"losses":21,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":16},"google/gemini-3.5-flash":{"draws":17,"losses":26,"wins":17},"google/gemini-3.5-flash-lite":{"draws":31,"losses":22,"wins":31},"google/gemini-3.6-flash":{"draws":24,"losses":48,"wins":20},"google/gemini-3.8-flash":{"draws":8,"losses":31,"wins":9},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":16,"losses":16,"wins":10},"gpt-5.4":{"draws":10,"losses":27,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":19},"gpt-5.5":{"draws":16,"losses":19,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":13},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":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":16,"losses":2,"wins":16},"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":21,"losses":2,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":24,"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":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":23,"wins":9},"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":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":9,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":8,"wins":6},"o3":{"draws":12,"losses":29,"wins":25},"openai/gpt-oss-120b":{"draws":20,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":13,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":26,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":18,"wins":14},"stealth/ox-alpha":{"draws":50,"losses":73,"wins":35},"stealth/space-bunny-alpha":{"draws":17,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":20,"losses":11,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":29,"wins":8},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":16,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":16,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":40,"losses":31,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":35,"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":13,"losses":17,"wins":18},"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":18,"losses":11,"wins":15},"claude-opus-5":{"draws":12,"losses":60,"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":18,"losses":11,"wins":19},"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":10,"wins":33},"google/gemini-3.5-flash-lite":{"draws":27,"losses":3,"wins":54},"google/gemini-3.6-flash":{"draws":22,"losses":29,"wins":41},"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":12,"losses":14,"wins":22},"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":41,"wins":77},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":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":15,"losses":10,"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":17,"wins":36},"claude-opus-4-8":{"draws":11,"losses":20,"wins":13},"claude-opus-5":{"draws":15,"losses":59,"wins":8},"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":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":22,"losses":10,"wins":40},"deepseek/deepseek-v4-pro":{"draws":14,"losses":13,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":29,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"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":22,"wins":22},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":38},"google/gemini-3.6-flash":{"draws":28,"losses":42,"wins":22},"google/gemini-3.8-flash":{"draws":12,"losses":20,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":8,"wins":22},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":27},"gpt-5.5":{"draws":16,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":19,"losses":16,"wins":11},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"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":2,"wins":16},"inception/mercury-3":{"draws":13,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":15,"wins":25},"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":14,"losses":15,"wins":17},"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":13,"losses":6,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":12,"losses":20,"wins":34},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":20},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":13,"wins":19},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"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":37,"losses":63,"wins":58},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"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":21,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"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":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":25,"losses":15,"wins":34},"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":30,"losses":25,"wins":41},"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":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":3,"losses":51,"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":57,"wins":10},"claude-opus-5-5":{"draws":4,"losses":47,"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":10,"losses":23,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":19,"wins":18},"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":24,"wins":34},"google/gemini-3.6-flash":{"draws":18,"losses":51,"wins":23},"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":13,"losses":19,"wins":16},"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":11,"losses":5,"wins":18},"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":8,"losses":1,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":20},"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":15,"losses":9,"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":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":5},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":18,"wins":13},"stealth/ox-alpha":{"draws":35,"losses":79,"wins":44},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"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":31,"losses":33,"wins":80},"claude-fable-5":{"draws":28,"losses":91,"wins":37},"claude-fable-5-1":{"draws":7,"losses":167,"wins":8},"claude-haiku-5-5":{"draws":31,"losses":59,"wins":52},"claude-opus-4-5":{"draws":73,"losses":74,"wins":99},"claude-opus-4-8":{"draws":30,"losses":50,"wins":48},"claude-opus-5":{"draws":50,"losses":188,"wins":42},"claude-opus-5-5":{"draws":19,"losses":145,"wins":4},"claude-sonnet-5":{"draws":40,"losses":43,"wins":73},"claude-sonnet-5-5":{"draws":35,"losses":72,"wins":49},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":47},"deepseek/deepseek-v4-flash":{"draws":54,"losses":47,"wins":127},"deepseek/deepseek-v4-pro":{"draws":32,"losses":45,"wins":69},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":49,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":62,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":81,"wins":47},"elorian/glimpse":{"draws":20,"losses":30,"wins":38},"fireworks/ember-1":{"draws":35,"losses":64,"wins":57},"gemini-3.1-pro-preview":{"draws":34,"losses":49,"wins":73},"gemini-4-argon":{"draws":16,"losses":125,"wins":15},"google/gemini-3.1-flash-lite":{"draws":20,"losses":14,"wins":52},"google/gemini-3.5-flash":{"draws":39,"losses":64,"wins":85},"google/gemini-3.5-flash-lite":{"draws":60,"losses":58,"wins":152},"google/gemini-3.6-flash":{"draws":75,"losses":126,"wins":99},"google/gemini-3.8-flash":{"draws":36,"losses":72,"wins":48},"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":29,"losses":45,"wins":66},"gpt-5.4":{"draws":38,"losses":59,"wins":53},"gpt-5.4-mini":{"draws":28,"losses":17,"wins":59},"gpt-5.4-nano":{"draws":26,"losses":35,"wins":75},"gpt-5.5":{"draws":40,"losses":56,"wins":50},"gpt-5.6-luna":{"draws":51,"losses":31,"wins":74},"gpt-5.6-sol":{"draws":23,"losses":104,"wins":29},"gpt-5.6-terra":{"draws":40,"losses":39,"wins":71},"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":132,"wins":9},"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":25,"losses":9,"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":29,"losses":21,"wins":92},"meta/muse-spark-1.2":{"draws":35,"losses":58,"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":18,"losses":20,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":10,"wins":17},"moonshotai/kimi-k3":{"draws":39,"losses":63,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":116,"wins":7},"nex-agi/nex-n2-pro":{"draws":17,"losses":14,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":9,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":18,"wins":73},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":19,"wins":32},"o3":{"draws":27,"losses":71,"wins":94},"openai/gpt-oss-120b":{"draws":29,"losses":25,"wins":88},"poolside/laguna-s-2.1":{"draws":33,"losses":31,"wins":96},"qwen/qwen3.7-max":{"draws":22,"losses":22,"wins":40},"qwen/qwen3.7-plus":{"draws":15,"losses":10,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":64,"wins":50},"qwen/qwen3.8-27b":{"draws":22,"losses":40,"wins":44},"qwen/qwen3.8-flash":{"draws":28,"losses":36,"wins":40},"qwen/qwen3.8-max":{"draws":49,"losses":49,"wins":58},"qwen/qwen3.8-max-0902":{"draws":32,"losses":71,"wins":53},"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":97,"losses":246,"wins":207},"stealth/space-bunny-alpha":{"draws":31,"losses":30,"wins":61},"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":31,"losses":67,"wins":52},"thinkingmachines/inkling":{"draws":55,"losses":45,"wins":116},"thinkingmachines/inkling-small":{"draws":40,"losses":37,"wins":79},"unbiased/pareto-26.10":{"draws":5,"losses":45,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":50,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":36,"losses":71,"wins":49},"x-ai/grok-4.6":{"draws":41,"losses":65,"wins":50},"x-ai/grok-4.7":{"draws":16,"losses":98,"wins":18},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":34},"xiaomi/mimo-v2.5":{"draws":59,"losses":32,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":35,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":51,"wins":37},"z-ai/glm-5.2":{"draws":79,"losses":83,"wins":150},"z-ai/glm-5.3":{"draws":31,"losses":88,"wins":33},"z-ai/glm-5.3-flash":{"draws":28,"losses":76,"wins":52},"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":10,"losses":26,"wins":6},"claude-fable-5-1":{"draws":1,"losses":47,"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":10,"losses":23,"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":12,"losses":19,"wins":11},"gemini-4-argon":{"draws":5,"losses":37,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":18,"losses":27,"wins":29},"google/gemini-3.6-flash":{"draws":23,"losses":43,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":15},"gpt-5.4":{"draws":12,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":6,"losses":18,"wins":16},"gpt-5.5":{"draws":10,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":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":15,"losses":15,"wins":12},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":6},"stealth/ox-alpha":{"draws":31,"losses":76,"wins":35},"stealth/space-bunny-alpha":{"draws":7,"losses":11,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":16},"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":29,"wins":10},"claude-fable-5-1":{"draws":1,"losses":43,"wins":4},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":22},"claude-opus-4-5":{"draws":13,"losses":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":36,"wins":6},"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":16,"wins":18},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":25},"gemini-4-argon":{"draws":9,"losses":23,"wins":10},"google/gemini-3.1-flash-lite":{"draws":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":9,"losses":14,"wins":17},"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":0,"losses":38,"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":14,"losses":18,"wins":12},"claude-fable-5":{"draws":9,"losses":35,"wins":4},"claude-fable-5-1":{"draws":5,"losses":49,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":3},"claude-opus-4-5":{"draws":23,"losses":48,"wins":7},"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":29,"losses":29,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":29,"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":14,"losses":28,"wins":6},"gemini-3.1-pro-preview":{"draws":15,"losses":27,"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":13,"losses":34,"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":11,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":5},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":23,"wins":8},"gpt-5.4":{"draws":14,"losses":27,"wins":5},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":27,"wins":9},"gpt-5.5":{"draws":13,"losses":21,"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":13,"losses":10,"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":10,"losses":9,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":42,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":19,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":10,"losses":45,"wins":11},"openai/gpt-oss-120b":{"draws":14,"losses":20,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":26,"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":11,"losses":32,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":22,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":28,"wins":8},"qwen/qwen3.8-max-0902":{"draws":14,"losses":28,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":22,"wins":8},"stealth/ox-alpha":{"draws":45,"losses":90,"wins":23},"stealth/space-bunny-alpha":{"draws":12,"losses":17,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":13,"wins":3},"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":31,"losses":47,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":34,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":34,"wins":6},"z-ai/glm-5.3-flashx":{"draws":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":26,"wins":14},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":21},"claude-opus-4-5":{"draws":19,"losses":18,"wins":41},"claude-opus-4-8":{"draws":7,"losses":15,"wins":22},"claude-opus-5":{"draws":13,"losses":53,"wins":16},"claude-opus-5-5":{"draws":5,"losses":40,"wins":7},"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":11,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":14,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":20,"wins":17},"elorian/glimpse":{"draws":5,"losses":9,"wins":12},"fireworks/ember-1":{"draws":11,"losses":15,"wins":22},"gemini-3.1-pro-preview":{"draws":9,"losses":13,"wins":26},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":18,"losses":14,"wins":52},"google/gemini-3.6-flash":{"draws":22,"losses":29,"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":9,"wins":22},"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":5,"losses":38,"wins":5},"gpt-6-luna":{"draws":10,"losses":15,"wins":23},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"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":11,"losses":13,"wins":22},"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":16,"wins":22},"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":30,"losses":46,"wins":82},"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":11,"wins":15},"z-ai/glm-5.2":{"draws":25,"losses":15,"wins":56},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":12},"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":3,"wins":36},"claude-fable-5":{"draws":7,"losses":17,"wins":24},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-5":{"draws":15,"losses":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":20,"wins":54},"google/gemini-3.8-flash":{"draws":11,"losses":16,"wins":21},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":24},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":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":14,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":13,"wins":25},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":2,"losses":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":10,"wins":28},"qwen/qwen3.8-27b":{"draws":7,"losses":3,"wins":24},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":19},"qwen/qwen3.8-max":{"draws":12,"losses":7,"wins":29},"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":21,"wins":17},"z-ai/glm-5.3-flash":{"draws":12,"losses":11,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":36},"claude-fable-5":{"draws":1,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":30,"wins":16},"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":25,"wins":46},"claude-opus-5-5":{"draws":6,"losses":28,"wins":12},"claude-sonnet-5":{"draws":3,"losses":5,"wins":34},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":56},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":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":3,"losses":5,"wins":34},"gemini-4-argon":{"draws":3,"losses":22,"wins":17},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":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":4,"losses":1,"wins":35},"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":6,"losses":27,"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":0,"wins":40},"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":14,"losses":20,"wins":10},"claude-fable-5":{"draws":8,"losses":34,"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":38,"wins":13},"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":25,"losses":28,"wins":19},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":26,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":7},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":13},"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":16,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":33,"losses":26,"wins":25},"google/gemini-3.6-flash":{"draws":31,"losses":55,"wins":6},"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":13,"losses":20,"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":9,"losses":26,"wins":13},"gpt-5.5":{"draws":21,"losses":16,"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":23,"wins":6},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"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":10,"losses":5,"wins":19},"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":19,"losses":10,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":13,"losses":37,"wins":16},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":15},"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":12,"losses":21,"wins":1},"qwen/qwen3.8-flash":{"draws":15,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":17,"losses":24,"wins":7},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":36,"losses":103,"wins":19},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"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":16,"losses":25,"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":35,"wins":19},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":30,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":35,"wins":13},"claude-fable-5":{"draws":17,"losses":69,"wins":4},"claude-fable-5-1":{"draws":6,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":28,"losses":52,"wins":10},"claude-opus-4-5":{"draws":57,"losses":73,"wins":20},"claude-opus-4-8":{"draws":33,"losses":51,"wins":6},"claude-opus-5":{"draws":23,"losses":124,"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":48,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":61,"wins":5},"elorian/glimpse":{"draws":16,"losses":22,"wins":10},"fireworks/ember-1":{"draws":32,"losses":49,"wins":9},"gemini-3.1-pro-preview":{"draws":36,"losses":35,"wins":19},"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":56,"losses":46,"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":26,"losses":9,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":78,"wins":1},"nex-agi/nex-n2-pro":{"draws":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":35,"losses":45,"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":30,"losses":31,"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":26,"losses":53,"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":2,"losses":32,"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":6,"losses":21,"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":13,"losses":14,"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":4,"losses":15,"wins":17},"gemini-4-argon":{"draws":0,"losses":33,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":16},"google/gemini-3.5-flash-lite":{"draws":21,"losses":15,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":37,"wins":17},"google/gemini-3.8-flash":{"draws":5,"losses":24,"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":3,"losses":18,"wins":13},"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":4,"losses":20,"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":9,"losses":8,"wins":13},"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":4,"losses":26,"wins":18},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":9,"losses":20,"wins":17},"claude-opus-4-5":{"draws":11,"losses":17,"wins":50},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":8,"losses":63,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"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":9,"losses":11,"wins":52},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":21,"wins":20},"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":2,"losses":19,"wins":27},"gemini-3.1-pro-preview":{"draws":7,"losses":13,"wins":28},"gemini-4-argon":{"draws":1,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":8,"losses":19,"wins":33},"google/gemini-3.5-flash-lite":{"draws":14,"losses":9,"wins":61},"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":3,"losses":10,"wins":29},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":22},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":31},"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":9,"losses":11,"wins":32},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":5,"losses":22,"wins":19},"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":7,"losses":14,"wins":25},"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":7,"losses":7,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":6,"wins":13},"o3":{"draws":7,"losses":15,"wins":44},"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":6,"losses":17,"wins":25},"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":5,"losses":18,"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":21,"losses":62,"wins":75},"stealth/space-bunny-alpha":{"draws":4,"losses":6,"wins":28},"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":5,"losses":18,"wins":25},"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":27,"losses":17,"wins":44},"claude-fable-5":{"draws":22,"losses":59,"wins":15},"claude-fable-5-1":{"draws":9,"losses":96,"wins":3},"claude-haiku-5-5":{"draws":23,"losses":40,"wins":29},"claude-opus-4-5":{"draws":53,"losses":47,"wins":56},"claude-opus-4-8":{"draws":25,"losses":39,"wins":24},"claude-opus-5":{"draws":23,"losses":132,"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":18,"losses":53,"wins":25},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":50,"losses":33,"wins":61},"deepseek/deepseek-v4-pro":{"draws":29,"losses":29,"wins":30},"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":29,"losses":41,"wins":26},"gemini-3.1-pro-preview":{"draws":29,"losses":32,"wins":35},"gemini-4-argon":{"draws":9,"losses":83,"wins":4},"google/gemini-3.1-flash-lite":{"draws":18,"losses":5,"wins":41},"google/gemini-3.5-flash":{"draws":32,"losses":40,"wins":48},"google/gemini-3.5-flash-lite":{"draws":59,"losses":36,"wins":73},"google/gemini-3.6-flash":{"draws":42,"losses":79,"wins":63},"google/gemini-3.8-flash":{"draws":21,"losses":50,"wins":25},"google/gemma-4-31b-it":{"draws":25,"losses":8,"wins":23},"gpt-4.1":{"draws":13,"losses":5,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":27,"losses":29,"wins":28},"gpt-5.4":{"draws":27,"losses":39,"wins":26},"gpt-5.4-mini":{"draws":29,"losses":9,"wins":26},"gpt-5.4-nano":{"draws":23,"losses":26,"wins":47},"gpt-5.5":{"draws":36,"losses":38,"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":37,"losses":29,"wins":26},"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":29,"losses":13,"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":36,"losses":16,"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":21,"losses":8,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":12},"moonshotai/kimi-k3":{"draws":32,"losses":30,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":73,"wins":8},"nex-agi/nex-n2-pro":{"draws":16,"losses":4,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":22,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":13,"wins":16},"o3":{"draws":21,"losses":53,"wins":58},"openai/gpt-oss-120b":{"draws":39,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":36,"losses":22,"wins":34},"qwen/qwen3.7-max":{"draws":20,"losses":12,"wins":24},"qwen/qwen3.7-plus":{"draws":14,"losses":11,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":42,"wins":26},"qwen/qwen3.8-27b":{"draws":21,"losses":20,"wins":27},"qwen/qwen3.8-flash":{"draws":15,"losses":28,"wins":21},"qwen/qwen3.8-max":{"draws":25,"losses":41,"wins":30},"qwen/qwen3.8-max-0902":{"draws":30,"losses":44,"wins":22},"recursive/flint-v1.0":{"draws":5,"losses":6,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":35,"wins":24},"stealth/ox-alpha":{"draws":80,"losses":144,"wins":92},"stealth/space-bunny-alpha":{"draws":28,"losses":23,"wins":25},"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":20,"losses":49,"wins":23},"thinkingmachines/inkling":{"draws":40,"losses":28,"wins":60},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":50},"unbiased/pareto-26.10":{"draws":1,"losses":30,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":29,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":28,"losses":41,"wins":27},"x-ai/grok-4.6":{"draws":25,"losses":52,"wins":19},"x-ai/grok-4.7":{"draws":9,"losses":60,"wins":15},"x-ai/grok-build-0.1":{"draws":16,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":55,"losses":18,"wins":75},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":10,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":24,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":31,"wins":15},"z-ai/glm-5.2":{"draws":59,"losses":43,"wins":58},"z-ai/glm-5.3":{"draws":20,"losses":55,"wins":17},"z-ai/glm-5.3-flash":{"draws":22,"losses":43,"wins":31},"z-ai/glm-5.3-flashx":{"draws":31,"losses":40,"wins":25}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":8,"losses":18,"wins":22},"claude-fable-5-1":{"draws":6,"losses":40,"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":5,"losses":11,"wins":28},"claude-opus-5":{"draws":13,"losses":51,"wins":18},"claude-opus-5-5":{"draws":4,"losses":35,"wins":13},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":5,"losses":15,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":56},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":5,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":14,"wins":29},"elorian/glimpse":{"draws":4,"losses":5,"wins":17},"fireworks/ember-1":{"draws":5,"losses":11,"wins":32},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"gemini-4-argon":{"draws":5,"losses":32,"wins":11},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":43},"google/gemini-3.5-flash-lite":{"draws":11,"losses":3,"wins":70},"google/gemini-3.6-flash":{"draws":18,"losses":19,"wins":55},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":8,"wins":31},"gpt-5.4":{"draws":5,"losses":12,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":10,"losses":10,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":8,"losses":24,"wins":16},"gpt-5.6-terra":{"draws":11,"losses":4,"wins":31},"gpt-6-astra":{"draws":7,"losses":39,"wins":2},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":12,"losses":29,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":7,"losses":7,"wins":18},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":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":8,"losses":13,"wins":27},"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":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"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":0,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"o3":{"draws":5,"losses":8,"wins":53},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":32},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":12,"wins":29},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-max":{"draws":9,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":7,"losses":7,"wins":34},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":4,"wins":34},"stealth/ox-alpha":{"draws":20,"losses":38,"wins":100},"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":3,"losses":12,"wins":31},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":28},"x-ai/grok-4.6":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.7":{"draws":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":16,"losses":14,"wins":66},"z-ai/glm-5.3":{"draws":9,"losses":8,"wins":13},"z-ai/glm-5.3-flash":{"draws":11,"losses":9,"wins":28},"z-ai/glm-5.3-flashx":{"draws":6,"losses":10,"wins":32}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":27},"claude-fable-5":{"draws":8,"losses":23,"wins":17},"claude-fable-5-1":{"draws":4,"losses":46,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":19,"losses":13,"wins":46},"claude-opus-4-8":{"draws":8,"losses":12,"wins":24},"claude-opus-5":{"draws":10,"losses":54,"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":16,"losses":8,"wins":48},"deepseek/deepseek-v4-pro":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":11,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":19},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":7,"losses":13,"wins":28},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":27},"gemini-4-argon":{"draws":6,"losses":35,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":8,"losses":15,"wins":37},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":64},"google/gemini-3.6-flash":{"draws":12,"losses":25,"wins":55},"google/gemini-3.8-flash":{"draws":8,"losses":23,"wins":17},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":11,"wins":25},"gpt-5.4":{"draws":8,"losses":20,"wins":18},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":24},"gpt-5.4-nano":{"draws":6,"losses":10,"wins":32},"gpt-5.5":{"draws":9,"losses":14,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":11,"wins":24},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"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":8,"losses":3,"wins":23},"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":8,"losses":4,"wins":30},"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":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":31,"wins":11},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":11},"o3":{"draws":8,"losses":18,"wins":40},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":29},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":15},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":18},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":23,"losses":53,"wins":82},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":3,"losses":18,"wins":25},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":9,"losses":4,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":19,"wins":23},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":22,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":17,"losses":15,"wins":64},"z-ai/glm-5.3":{"draws":9,"losses":22,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":9,"losses":29,"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":9,"losses":20,"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":13,"losses":22,"wins":25},"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":9,"losses":17,"wins":16},"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":10,"losses":19,"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":13,"losses":20,"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":13,"losses":15,"wins":18},"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":10,"losses":20,"wins":18},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":16},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":17,"wins":19},"stealth/ox-alpha":{"draws":31,"losses":65,"wins":62},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":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":8,"losses":28,"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":3,"losses":36,"wins":3},"claude-fable-5-1":{"draws":1,"losses":45,"wins":2},"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":9,"losses":29,"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":19,"losses":27,"wins":16},"deepseek/deepseek-v4-pro":{"draws":10,"losses":26,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":23,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":33,"wins":5},"elorian/glimpse":{"draws":4,"losses":14,"wins":6},"fireworks/ember-1":{"draws":9,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":24,"wins":8},"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":32,"wins":12},"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":7,"losses":31,"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":13,"losses":7,"wins":10},"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":9,"losses":26,"wins":5},"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":10,"losses":28,"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":8,"losses":21,"wins":5},"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":4,"wins":32},"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":15,"losses":54,"wins":13},"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":14,"wins":23},"gemini-4-argon":{"draws":1,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":30},"google/gemini-3.5-flash-lite":{"draws":21,"losses":12,"wins":51},"google/gemini-3.6-flash":{"draws":21,"losses":32,"wins":39},"google/gemini-3.8-flash":{"draws":10,"losses":22,"wins":16},"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":9,"losses":3,"wins":20},"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":52,"wins":71},"stealth/space-bunny-alpha":{"draws":12,"losses":7,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":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":27,"wins":9},"claude-haiku-5-5":{"draws":2,"losses":6,"wins":38},"claude-opus-4-5":{"draws":6,"losses":2,"wins":70},"claude-opus-4-8":{"draws":3,"losses":4,"wins":37},"claude-opus-5":{"draws":15,"losses":23,"wins":44},"claude-opus-5-5":{"draws":3,"losses":29,"wins":20},"claude-sonnet-5":{"draws":5,"losses":2,"wins":41},"claude-sonnet-5-5":{"draws":4,"losses":13,"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":5,"losses":1,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":2,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":7,"wins":38},"elorian/glimpse":{"draws":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":3,"losses":1,"wins":44},"gemini-3.1-pro-preview":{"draws":4,"losses":1,"wins":43},"gemini-4-argon":{"draws":7,"losses":19,"wins":22},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":50},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":77},"google/gemini-3.6-flash":{"draws":8,"losses":3,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":4,"wins":40},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":1,"wins":39},"gpt-5.4":{"draws":4,"losses":8,"wins":34},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":1,"losses":6,"wins":37},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":41},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":37},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":4,"losses":32,"wins":12},"gpt-6-luna":{"draws":5,"losses":1,"wins":42},"gpt-6-sol":{"draws":7,"losses":14,"wins":27},"gpt-6.1-sol":{"draws":3,"losses":25,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":29},"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":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":3,"losses":1,"wins":42},"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":2,"losses":0,"wins":24},"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":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":19,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":18},"o3":{"draws":2,"losses":3,"wins":61},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":44},"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":4,"losses":2,"wins":42},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":29},"qwen/qwen3.8-flash":{"draws":3,"losses":1,"wins":28},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":43},"qwen/qwen3.8-max-0902":{"draws":3,"losses":5,"wins":40},"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":13,"losses":9,"wins":136},"stealth/space-bunny-alpha":{"draws":2,"losses":0,"wins":36},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":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":4,"losses":0,"wins":44},"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":8,"wins":38},"x-ai/grok-4.7":{"draws":2,"losses":18,"wins":22},"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":2,"losses":3,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":22},"z-ai/glm-5.2":{"draws":9,"losses":2,"wins":85},"z-ai/glm-5.3":{"draws":4,"losses":11,"wins":31},"z-ai/glm-5.3-flash":{"draws":6,"losses":2,"wins":40},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":39}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":18,"wins":7},"claude-opus-4-5":{"draws":30,"losses":32,"wins":16},"claude-opus-4-8":{"draws":15,"losses":27,"wins":2},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":22,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":30,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"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":13,"losses":17,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"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":60,"wins":6},"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":14,"losses":20,"wins":10},"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":16,"losses":25,"wins":19},"google/gemini-3.5-flash-lite":{"draws":28,"losses":18,"wins":38},"google/gemini-3.6-flash":{"draws":27,"losses":41,"wins":24},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":14,"wins":14},"gpt-5.4":{"draws":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":33,"wins":6},"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":12,"losses":18,"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":18,"losses":15,"wins":13},"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":9,"losses":17,"wins":40},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":14},"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":44,"losses":77,"wins":37},"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":4,"wins":14},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":24,"losses":10,"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":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":20,"wins":15},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"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":2,"losses":44,"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":7,"losses":15,"wins":6},"claude-opus-5":{"draws":12,"losses":50,"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":13,"losses":10,"wins":19},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":23,"wins":21},"google/gemini-3.5-flash-lite":{"draws":22,"losses":11,"wins":41},"google/gemini-3.6-flash":{"draws":19,"losses":40,"wins":21},"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":32,"wins":5},"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":12,"losses":16,"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":27,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":22,"wins":14}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":56},"claude-fable-5":{"draws":19,"losses":27,"wins":38},"claude-fable-5-1":{"draws":9,"losses":65,"wins":20},"claude-haiku-5-5":{"draws":19,"losses":14,"wins":47},"claude-opus-4-5":{"draws":34,"losses":19,"wins":83},"claude-opus-4-8":{"draws":17,"losses":11,"wins":48},"claude-opus-5":{"draws":22,"losses":69,"wins":35},"claude-opus-5-5":{"draws":12,"losses":65,"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":13,"losses":16,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":13,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":21,"wins":45},"elorian/glimpse":{"draws":8,"losses":11,"wins":27},"fireworks/ember-1":{"draws":15,"losses":16,"wins":53},"gemini-3.1-pro-preview":{"draws":11,"losses":20,"wins":53},"gemini-4-argon":{"draws":13,"losses":45,"wins":26},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":45},"google/gemini-3.5-flash":{"draws":14,"losses":20,"wins":70},"google/gemini-3.5-flash-lite":{"draws":25,"losses":17,"wins":104},"google/gemini-3.6-flash":{"draws":32,"losses":44,"wins":84},"google/gemini-3.8-flash":{"draws":15,"losses":23,"wins":46},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":34},"gpt-4.1":{"draws":7,"losses":2,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":15,"losses":9,"wins":50},"gpt-5.4":{"draws":17,"losses":13,"wins":50},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":34},"gpt-5.4-nano":{"draws":12,"losses":6,"wins":64},"gpt-5.5":{"draws":14,"losses":18,"wins":46},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":60},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":50},"gpt-5.6-terra":{"draws":11,"losses":10,"wins":59},"gpt-6-astra":{"draws":10,"losses":59,"wins":15},"gpt-6-luna":{"draws":20,"losses":11,"wins":53},"gpt-6-sol":{"draws":14,"losses":38,"wins":32},"gpt-6.1-sol":{"draws":13,"losses":52,"wins":19},"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":17,"wins":49},"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":18,"losses":23,"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":7,"wins":86},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":52},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":62},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":24,"wins":49},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":34},"qwen/qwen3.8-max":{"draws":21,"losses":21,"wins":42},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":47},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":50},"stealth/ox-alpha":{"draws":67,"losses":69,"wins":146},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":44},"stepfun/step-5-preview":{"draws":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":15,"losses":21,"wins":48},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":46},"x-ai/grok-4.7":{"draws":8,"losses":39,"wins":27},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":19},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":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":14,"losses":34,"wins":32},"z-ai/glm-5.3-flash":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3-flashx":{"draws":17,"losses":23,"wins":44}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":8,"losses":17,"wins":29},"claude-fable-5-1":{"draws":5,"losses":40,"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":2,"losses":31,"wins":11},"claude-sonnet-5":{"draws":10,"losses":9,"wins":35},"claude-sonnet-5-5":{"draws":7,"losses":17,"wins":30},"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":10,"wins":36},"gemini-3.1-pro-preview":{"draws":9,"losses":5,"wins":40},"gemini-4-argon":{"draws":6,"losses":26,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":52},"google/gemini-3.5-flash-lite":{"draws":17,"losses":1,"wins":76},"google/gemini-3.6-flash":{"draws":18,"losses":11,"wins":73},"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":3,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":4,"wins":36},"gpt-5.4":{"draws":8,"losses":4,"wins":40},"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":9,"losses":13,"wins":32},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":41},"gpt-6-astra":{"draws":8,"losses":34,"wins":12},"gpt-6-luna":{"draws":13,"losses":3,"wins":38},"gpt-6-sol":{"draws":7,"losses":25,"wins":22},"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":7,"wins":40},"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":12,"wins":32},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":32},"qwen/qwen3.8-max-0902":{"draws":9,"losses":5,"wins":40},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":3,"wins":36},"stealth/ox-alpha":{"draws":38,"losses":24,"wins":112},"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":13,"wins":29},"x-ai/grok-4.6":{"draws":12,"losses":13,"wins":29},"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":18,"wins":28},"z-ai/glm-5.3-flash":{"draws":7,"losses":6,"wins":41},"z-ai/glm-5.3-flashx":{"draws":10,"losses":8,"wins":36}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":16},"claude-fable-5":{"draws":8,"losses":34,"wins":6},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":28,"losses":31,"wins":19},"claude-opus-4-8":{"draws":13,"losses":23,"wins":8},"claude-opus-5":{"draws":12,"losses":60,"wins":10},"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":16,"losses":23,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":20,"wins":14},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":30,"wins":14},"google/gemini-3.5-flash-lite":{"draws":23,"losses":23,"wins":38},"google/gemini-3.6-flash":{"draws":26,"losses":41,"wins":25},"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":12,"losses":24,"wins":10},"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":12,"losses":26,"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":9,"losses":16,"wins":13},"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":15,"losses":22,"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":32,"wins":6},"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":1,"losses":53,"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":13,"losses":23,"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":12,"losses":25,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":33,"wins":7},"elorian/glimpse":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":11,"losses":22,"wins":15},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":11,"wins":14},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":21},"google/gemini-3.5-flash-lite":{"draws":20,"losses":22,"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":9,"losses":4,"wins":15},"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":11,"losses":24,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":28,"wins":10},"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":39,"losses":91,"wins":28},"stealth/space-bunny-alpha":{"draws":8,"losses":15,"wins":15},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":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":20,"losses":42,"wins":34},"z-ai/glm-5.3":{"draws":7,"losses":33,"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":36,"wins":10},"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":17,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":25,"wins":3},"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":12,"losses":18,"wins":12},"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":11,"losses":21,"wins":10},"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":10,"losses":17,"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":12,"losses":25,"wins":5},"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":24,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":22,"wins":10},"stealth/ox-alpha":{"draws":29,"losses":80,"wins":31},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":16},"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":7,"losses":29,"wins":6}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":15,"wins":9},"claude-fable-5":{"draws":7,"losses":25,"wins":4},"claude-fable-5-1":{"draws":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":16,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":5,"losses":14,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":27,"wins":5},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":21,"wins":9},"gemini-4-argon":{"draws":3,"losses":32,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":26,"wins":12},"google/gemini-3.5-flash-lite":{"draws":20,"losses":23,"wins":21},"google/gemini-3.6-flash":{"draws":21,"losses":37,"wins":12},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":7,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":1,"losses":22,"wins":11},"gpt-5.5":{"draws":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":14,"losses":13,"wins":7},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":8},"gpt-6-sol":{"draws":3,"losses":29,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":6,"wins":8},"inception/mercury-3":{"draws":5,"losses":11,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":21,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":7},"meta/muse-wonder":{"draws":2,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":10,"losses":12,"wins":10},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":27,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":5},"o3":{"draws":6,"losses":26,"wins":20},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":11},"poolside/laguna-s-2.1":{"draws":10,"losses":20,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":7,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":29,"losses":66,"wins":31},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":7},"thinkingmachines/inkling":{"draws":19,"losses":14,"wins":19},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":17,"wins":7},"x-ai/grok-4.6":{"draws":14,"losses":20,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":21,"losses":13,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":22,"losses":32,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":26,"wins":7},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":5}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":9},"claude-fable-5":{"draws":6,"losses":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":17,"wins":18},"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":26,"wins":8},"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":23,"wins":21},"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":7,"wins":3},"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":7,"losses":22,"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":66,"wins":24},"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":18,"wins":7},"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":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":29,"losses":20,"wins":23},"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":19,"wins":9},"claude-fable-5":{"draws":10,"losses":33,"wins":5},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":30,"losses":34,"wins":14},"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":19,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":29,"losses":18,"wins":25},"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":14,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":31,"wins":5},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":15,"losses":28,"wins":5},"gemini-3.1-pro-preview":{"draws":13,"losses":25,"wins":10},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":15,"losses":7,"wins":10},"google/gemini-3.5-flash":{"draws":17,"losses":32,"wins":11},"google/gemini-3.5-flash-lite":{"draws":30,"losses":38,"wins":16},"google/gemini-3.6-flash":{"draws":27,"losses":54,"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":13,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":12,"losses":22,"wins":14},"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":20,"losses":17,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":17,"losses":24,"wins":7},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"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":20,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":18,"wins":22},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":27,"wins":8},"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":14,"losses":23,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":1},"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":20,"losses":10,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":11,"wins":4},"o3":{"draws":15,"losses":36,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":18,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":15,"wins":10},"qwen/qwen3.7-max":{"draws":11,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":24,"wins":10},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"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":44,"losses":80,"wins":33},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"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":10,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":14,"wins":27},"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":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":20,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":12,"wins":5},"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":38,"losses":37,"wins":21},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":30,"wins":7},"z-ai/glm-5.3-flashx":{"draws":14,"losses":29,"wins":5}},"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":30,"losses":31,"wins":17},"claude-opus-4-8":{"draws":16,"losses":26,"wins":2},"claude-opus-5":{"draws":9,"losses":69,"wins":4},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":15,"losses":21,"wins":12},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":25,"losses":25,"wins":22},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":9},"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":8,"losses":6,"wins":18},"google/gemini-3.5-flash":{"draws":18,"losses":32,"wins":10},"google/gemini-3.5-flash-lite":{"draws":31,"losses":32,"wins":21},"google/gemini-3.6-flash":{"draws":31,"losses":42,"wins":19},"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":14,"losses":23,"wins":11},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"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":18,"losses":3,"wins":13},"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":15,"losses":24,"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":29,"wins":19},"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":17,"wins":13},"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":11,"losses":7,"wins":8},"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":36,"losses":37,"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":15,"losses":18,"wins":11},"claude-fable-5":{"draws":11,"losses":37,"wins":0},"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":13,"losses":28,"wins":3},"claude-opus-5":{"draws":9,"losses":69,"wins":4},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":16,"losses":25,"wins":7},"claude-sonnet-5-5":{"draws":8,"losses":33,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":10,"wins":4},"deepseek/deepseek-v4-flash":{"draws":27,"losses":26,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":24,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":23,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":25,"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":15,"losses":29,"wins":4},"gemini-3.1-pro-preview":{"draws":8,"losses":19,"wins":5},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":10,"wins":12},"google/gemini-3.5-flash":{"draws":15,"losses":36,"wins":9},"google/gemini-3.5-flash-lite":{"draws":33,"losses":30,"wins":21},"google/gemini-3.6-flash":{"draws":34,"losses":52,"wins":6},"google/gemini-3.8-flash":{"draws":10,"losses":38,"wins":0},"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":15,"losses":29,"wins":2},"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":19,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":39,"wins":2},"gpt-5.6-terra":{"draws":21,"losses":22,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"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":12,"wins":7},"inception/mercury-3":{"draws":12,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":10,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":22,"wins":12},"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":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":24,"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":16,"losses":18,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":29,"wins":2},"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":13,"losses":32,"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":34,"losses":108,"wins":16},"stealth/space-bunny-alpha":{"draws":9,"losses":20,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":12,"wins":6},"tencent/hy4-preview":{"draws":17,"losses":26,"wins":3},"thinkingmachines/inkling":{"draws":24,"losses":25,"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":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":5},"z-ai/glm-5.2":{"draws":41,"losses":38,"wins":17},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":30,"wins":5},"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":10,"losses":18,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":0},"elorian/glimpse":{"draws":2,"losses":10,"wins":2},"fireworks/ember-1":{"draws":8,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":20,"wins":3},"gemini-4-argon":{"draws":1,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":31,"wins":1},"google/gemini-3.5-flash-lite":{"draws":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":20,"wins":3},"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":7,"losses":22,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":32,"wins":25},"claude-fable-5":{"draws":12,"losses":66,"wins":6},"claude-fable-5-1":{"draws":4,"losses":90,"wins":0},"claude-haiku-5-5":{"draws":18,"losses":45,"wins":19},"claude-opus-4-5":{"draws":35,"losses":75,"wins":28},"claude-opus-4-8":{"draws":21,"losses":51,"wins":8},"claude-opus-5":{"draws":14,"losses":118,"wins":8},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":29,"losses":33,"wins":22},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":33,"losses":44,"wins":49},"deepseek/deepseek-v4-pro":{"draws":20,"losses":34,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":37,"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":22,"losses":39,"wins":23},"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":12,"losses":52,"wins":16},"google/gemini-3.5-flash-lite":{"draws":41,"losses":65,"wins":44},"google/gemini-3.6-flash":{"draws":42,"losses":85,"wins":35},"google/gemini-3.8-flash":{"draws":18,"losses":61,"wins":5},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":20},"gpt-4.1":{"draws":10,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":20,"losses":35,"wins":19},"gpt-5.4":{"draws":11,"losses":56,"wins":15},"gpt-5.4-mini":{"draws":19,"losses":18,"wins":19},"gpt-5.4-nano":{"draws":14,"losses":35,"wins":39},"gpt-5.5":{"draws":25,"losses":41,"wins":12},"gpt-5.6-luna":{"draws":24,"losses":33,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":70,"wins":7},"gpt-5.6-terra":{"draws":26,"losses":41,"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":20,"losses":13,"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":26,"losses":19,"wins":29},"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":14,"losses":12,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":27,"losses":36,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":74,"wins":4},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":24,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":21,"wins":12},"o3":{"draws":19,"losses":61,"wins":46},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":23},"poolside/laguna-s-2.1":{"draws":21,"losses":26,"wins":31},"qwen/qwen3.7-max":{"draws":13,"losses":26,"wins":11},"qwen/qwen3.7-plus":{"draws":10,"losses":14,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":50,"wins":7},"qwen/qwen3.8-27b":{"draws":9,"losses":36,"wins":15},"qwen/qwen3.8-flash":{"draws":17,"losses":24,"wins":15},"qwen/qwen3.8-max":{"draws":26,"losses":38,"wins":20},"qwen/qwen3.8-max-0902":{"draws":23,"losses":48,"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":47,"losses":169,"wins":44},"stealth/space-bunny-alpha":{"draws":20,"losses":30,"wins":18},"stepfun/step-3.7-flash":{"draws":13,"losses":17,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":22,"losses":47,"wins":13},"thinkingmachines/inkling":{"draws":24,"losses":37,"wins":51},"thinkingmachines/inkling-small":{"draws":26,"losses":23,"wins":35},"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":22,"losses":55,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":46,"losses":37,"wins":53},"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":51,"losses":71,"wins":46},"z-ai/glm-5.3":{"draws":13,"losses":62,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":58,"wins":15},"z-ai/glm-5.3-flashx":{"draws":14,"losses":58,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":26,"wins":29},"claude-fable-5":{"draws":15,"losses":63,"wins":12},"claude-fable-5-1":{"draws":4,"losses":95,"wins":1},"claude-haiku-5-5":{"draws":18,"losses":53,"wins":17},"claude-opus-4-5":{"draws":48,"losses":56,"wins":44},"claude-opus-4-8":{"draws":23,"losses":51,"wins":12},"claude-opus-5":{"draws":19,"losses":122,"wins":11},"claude-opus-5-5":{"draws":4,"losses":93,"wins":1},"claude-sonnet-5":{"draws":27,"losses":42,"wins":21},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":15},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":41,"losses":40,"wins":55},"deepseek/deepseek-v4-pro":{"draws":20,"losses":33,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":37,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":46,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":62,"wins":15},"elorian/glimpse":{"draws":15,"losses":21,"wins":12},"fireworks/ember-1":{"draws":27,"losses":37,"wins":26},"gemini-3.1-pro-preview":{"draws":34,"losses":31,"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":25,"losses":53,"wins":36},"google/gemini-3.5-flash-lite":{"draws":43,"losses":36,"wins":49},"google/gemini-3.6-flash":{"draws":50,"losses":76,"wins":46},"google/gemini-3.8-flash":{"draws":16,"losses":66,"wins":8},"google/gemma-4-31b-it":{"draws":20,"losses":9,"wins":25},"gpt-4.1":{"draws":9,"losses":5,"wins":16},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":21,"losses":34,"wins":23},"gpt-5.4":{"draws":22,"losses":49,"wins":15},"gpt-5.4-mini":{"draws":19,"losses":18,"wins":23},"gpt-5.4-nano":{"draws":18,"losses":36,"wins":40},"gpt-5.5":{"draws":32,"losses":37,"wins":13},"gpt-5.6-luna":{"draws":27,"losses":28,"wins":35},"gpt-5.6-sol":{"draws":10,"losses":68,"wins":12},"gpt-5.6-terra":{"draws":26,"losses":35,"wins":25},"gpt-6-astra":{"draws":5,"losses":85,"wins":0},"gpt-6-luna":{"draws":30,"losses":36,"wins":24},"gpt-6-sol":{"draws":13,"losses":68,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":1},"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":23,"losses":42,"wins":21},"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":17,"losses":10,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":11,"wins":7},"moonshotai/kimi-k3":{"draws":26,"losses":39,"wins":21},"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":33,"losses":19,"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":24,"losses":28,"wins":32},"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":27,"losses":43,"wins":20},"qwen/qwen3.8-27b":{"draws":13,"losses":31,"wins":20},"qwen/qwen3.8-flash":{"draws":17,"losses":25,"wins":18},"qwen/qwen3.8-max":{"draws":27,"losses":40,"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":65,"losses":144,"wins":67},"stealth/space-bunny-alpha":{"draws":23,"losses":20,"wins":29},"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":22,"losses":19,"wins":9},"tencent/hy4-preview":{"draws":24,"losses":43,"wins":19},"thinkingmachines/inkling":{"draws":36,"losses":31,"wins":51},"thinkingmachines/inkling-small":{"draws":30,"losses":19,"wins":41},"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":48,"wins":19},"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":64,"losses":57,"wins":59},"z-ai/glm-5.3":{"draws":13,"losses":66,"wins":7},"z-ai/glm-5.3-flash":{"draws":14,"losses":54,"wins":22},"z-ai/glm-5.3-flashx":{"draws":26,"losses":44,"wins":20}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":32,"wins":29},"claude-fable-5":{"draws":17,"losses":68,"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":53,"losses":64,"wins":39},"claude-opus-4-8":{"draws":26,"losses":40,"wins":22},"claude-opus-5":{"draws":20,"losses":127,"wins":17},"claude-opus-5-5":{"draws":3,"losses":99,"wins":2},"claude-sonnet-5":{"draws":32,"losses":42,"wins":22},"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":47,"losses":36,"wins":61},"deepseek/deepseek-v4-pro":{"draws":28,"losses":39,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":40,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":41,"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":32,"losses":36,"wins":28},"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":31,"losses":65,"wins":24},"google/gemini-3.5-flash-lite":{"draws":59,"losses":52,"wins":57},"google/gemini-3.6-flash":{"draws":40,"losses":85,"wins":27},"google/gemini-3.8-flash":{"draws":21,"losses":60,"wins":15},"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":25,"losses":44,"wins":15},"gpt-5.4":{"draws":22,"losses":48,"wins":22},"gpt-5.4-mini":{"draws":23,"losses":17,"wins":24},"gpt-5.4-nano":{"draws":23,"losses":37,"wins":36},"gpt-5.5":{"draws":34,"losses":39,"wins":15},"gpt-5.6-luna":{"draws":38,"losses":27,"wins":31},"gpt-5.6-sol":{"draws":13,"losses":74,"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":35,"losses":30,"wins":31},"gpt-6-sol":{"draws":13,"losses":76,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":91,"wins":0},"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":29,"losses":15,"wins":24},"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":40,"losses":15,"wins":29},"meta/muse-spark-1.2":{"draws":22,"losses":51,"wins":19},"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":24,"losses":10,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":6},"moonshotai/kimi-k3":{"draws":26,"losses":45,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":77,"wins":1},"nex-agi/nex-n2-pro":{"draws":16,"losses":7,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":19,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":22,"wins":10},"o3":{"draws":21,"losses":79,"wins":32},"openai/gpt-oss-120b":{"draws":36,"losses":18,"wins":30},"poolside/laguna-s-2.1":{"draws":33,"losses":27,"wins":32},"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":28,"losses":46,"wins":22},"qwen/qwen3.8-27b":{"draws":16,"losses":35,"wins":17},"qwen/qwen3.8-flash":{"draws":27,"losses":22,"wins":15},"qwen/qwen3.8-max":{"draws":25,"losses":48,"wins":23},"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":82,"losses":160,"wins":74},"stealth/space-bunny-alpha":{"draws":21,"losses":31,"wins":24},"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":25,"losses":53,"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":67,"losses":79,"wins":46},"z-ai/glm-5.3":{"draws":19,"losses":67,"wins":6},"z-ai/glm-5.3-flash":{"draws":18,"losses":58,"wins":20},"z-ai/glm-5.3-flashx":{"draws":27,"losses":47,"wins":22}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":9,"wins":22},"claude-fable-5":{"draws":8,"losses":30,"wins":10},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":17},"claude-opus-4-5":{"draws":29,"losses":15,"wins":34},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":12,"losses":58,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":13,"losses":13,"wins":22},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":27,"wins":13},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":12,"losses":18,"wins":18},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"gemini-4-argon":{"draws":1,"losses":44,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":22,"wins":25},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":57},"google/gemini-3.6-flash":{"draws":24,"losses":29,"wins":39},"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":14,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":18},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"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":9,"losses":8,"wins":35},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-spark-open":{"draws":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":3,"wins":7},"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":8,"losses":16,"wins":42},"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":14,"losses":17,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":16},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max":{"draws":14,"losses":15,"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":68,"wins":53},"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":14,"losses":18,"wins":14},"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":19,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":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":23,"wins":17}},"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":7,"losses":29,"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":28,"losses":33,"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":3,"losses":47,"wins":2},"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":11,"losses":21,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"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":30,"wins":16},"google/gemini-3.5-flash-lite":{"draws":28,"losses":28,"wins":28},"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":18,"losses":13,"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":12,"losses":5,"wins":11},"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":11,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":24,"wins":8},"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":18,"losses":16,"wins":14},"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":79,"wins":38},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":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":15,"wins":18},"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":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":5,"losses":28,"wins":15},"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":13,"losses":13,"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":32,"wins":22},"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":1,"losses":51,"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":13,"losses":17,"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":20,"losses":44,"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":19,"losses":20,"wins":5},"claude-fable-5":{"draws":10,"losses":37,"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":30,"losses":29,"wins":13},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":8},"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":23,"losses":22,"wins":3},"gemini-3.1-pro-preview":{"draws":19,"losses":22,"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":18,"losses":37,"wins":5},"google/gemini-3.5-flash-lite":{"draws":31,"losses":36,"wins":17},"google/gemini-3.6-flash":{"draws":34,"losses":53,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":34,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":23,"wins":4},"gpt-5.4":{"draws":16,"losses":30,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":16,"losses":26,"wins":6},"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":21,"losses":23,"wins":4},"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":17,"losses":13,"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":12,"losses":9,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":27,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":0},"nex-agi/nex-n2-pro":{"draws":9,"losses":10,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":16,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":0},"o3":{"draws":14,"losses":45,"wins":7},"openai/gpt-oss-120b":{"draws":21,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":21,"losses":20,"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":18,"losses":28,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":24,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":24,"losses":23,"wins":1},"recursive/flint-v1.0":{"draws":4,"losses":8,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":23,"wins":3},"stealth/ox-alpha":{"draws":54,"losses":91,"wins":13},"stealth/space-bunny-alpha":{"draws":12,"losses":25,"wins":1},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":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":23,"losses":18,"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":46,"losses":45,"wins":5},"z-ai/glm-5.3":{"draws":15,"losses":30,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":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":10,"losses":58,"wins":4},"claude-fable-5-1":{"draws":0,"losses":76,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":38,"wins":15},"claude-opus-4-5":{"draws":33,"losses":62,"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":28,"losses":45,"wins":41},"deepseek/deepseek-v4-pro":{"draws":9,"losses":31,"wins":24},"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":19,"losses":37,"wins":16},"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":16,"losses":58,"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":16,"losses":47,"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":9,"losses":38,"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":12,"losses":26,"wins":22},"gpt-5.5":{"draws":17,"losses":34,"wins":13},"gpt-5.6-luna":{"draws":21,"losses":31,"wins":20},"gpt-5.6-sol":{"draws":4,"losses":61,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":37,"wins":14},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"gpt-6-luna":{"draws":17,"losses":41,"wins":14},"gpt-6-sol":{"draws":8,"losses":56,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":67,"wins":2},"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":13,"losses":12,"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":9,"losses":11,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":38,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":64,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":14,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":22,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":15,"wins":9},"o3":{"draws":10,"losses":60,"wins":38},"openai/gpt-oss-120b":{"draws":24,"losses":24,"wins":16},"poolside/laguna-s-2.1":{"draws":25,"losses":30,"wins":21},"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":17,"losses":44,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":26,"wins":13},"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":45,"losses":126,"wins":51},"stealth/space-bunny-alpha":{"draws":10,"losses":30,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":21,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":47,"wins":8},"thinkingmachines/inkling":{"draws":24,"losses":41,"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":9,"losses":55,"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":14,"losses":27,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":39,"losses":69,"wins":36},"z-ai/glm-5.3":{"draws":12,"losses":49,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":46,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":39,"wins":15}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":12},"claude-fable-5":{"draws":12,"losses":23,"wins":7},"claude-fable-5-1":{"draws":2,"losses":43,"wins":3},"claude-haiku-5-5":{"draws":17,"losses":17,"wins":6},"claude-opus-4-5":{"draws":36,"losses":21,"wins":11},"claude-opus-4-8":{"draws":18,"losses":16,"wins":4},"claude-opus-5":{"draws":15,"losses":64,"wins":1},"claude-opus-5-5":{"draws":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":32,"losses":8,"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":13,"losses":20,"wins":9},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":12},"gemini-4-argon":{"draws":4,"losses":38,"wins":0},"google/gemini-3.1-flash-lite":{"draws":14,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":18,"losses":21,"wins":13},"google/gemini-3.5-flash-lite":{"draws":36,"losses":14,"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":19,"losses":2,"wins":7},"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":8,"losses":3,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":4,"wins":9},"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":10,"losses":14,"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":44,"losses":69,"wins":29},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":10},"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":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":1,"losses":53,"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":28,"losses":31,"wins":13},"deepseek/deepseek-v4-pro":{"draws":13,"losses":26,"wins":5},"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":11,"losses":29,"wins":8},"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":12,"losses":42,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":43,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":63,"wins":4},"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":24,"wins":8},"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":16,"losses":30,"wins":6},"meta/muse-glimmer-30b":{"draws":17,"losses":22,"wins":3},"meta/muse-spark-1.2":{"draws":15,"losses":24,"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":16,"losses":26,"wins":4},"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":30,"wins":6},"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":13,"losses":21,"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":13,"losses":30,"wins":3},"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":15,"wins":18},"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":11,"losses":17,"wins":32},"google/gemini-3.5-flash-lite":{"draws":21,"losses":10,"wins":53},"google/gemini-3.6-flash":{"draws":20,"losses":31,"wins":41},"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":10,"losses":19,"wins":17},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":41},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":22,"wins":18},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":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":11,"losses":10,"wins":17},"claude-fable-5":{"draws":10,"losses":31,"wins":1},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":5},"claude-opus-4-5":{"draws":30,"losses":28,"wins":10},"claude-opus-4-8":{"draws":17,"losses":18,"wins":3},"claude-opus-5":{"draws":7,"losses":53,"wins":10},"claude-opus-5-5":{"draws":3,"losses":41,"wins":2},"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":12,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":8},"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":13,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":19,"losses":24,"wins":9},"google/gemini-3.5-flash-lite":{"draws":27,"losses":22,"wins":23},"google/gemini-3.6-flash":{"draws":27,"losses":42,"wins":11},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":15,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":19,"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":9,"losses":15,"wins":16},"gpt-5.5":{"draws":21,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":28,"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":10,"losses":6,"wins":18},"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":15,"losses":16,"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":9,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":2},"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":18,"losses":6,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":6,"wins":4},"o3":{"draws":12,"losses":24,"wins":18},"openai/gpt-oss-120b":{"draws":18,"losses":1,"wins":17},"poolside/laguna-s-2.1":{"draws":21,"losses":6,"wins":11},"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":17,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":3},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":10},"qwen/qwen3.8-max-0902":{"draws":18,"losses":19,"wins":5},"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":47,"losses":71,"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":18,"losses":16,"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":40,"losses":24,"wins":20},"z-ai/glm-5.3":{"draws":12,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":5},"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":4,"losses":27,"wins":23},"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":4,"losses":7,"wins":33},"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":10,"wins":33},"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":4,"losses":1,"wins":43},"gemini-4-argon":{"draws":8,"losses":17,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":7,"losses":1,"wins":52},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":75},"google/gemini-3.6-flash":{"draws":13,"losses":5,"wins":74},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":34},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":0,"wins":37},"gpt-5.4":{"draws":5,"losses":7,"wins":34},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":28},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":45},"gpt-5.5":{"draws":4,"losses":3,"wins":37},"gpt-5.6-luna":{"draws":7,"losses":2,"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":6,"losses":15,"wins":11},"gpt-6-luna":{"draws":7,"losses":4,"wins":37},"gpt-6-sol":{"draws":3,"losses":15,"wins":30},"gpt-6.1-sol":{"draws":5,"losses":24,"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":0,"wins":24},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":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":8,"losses":1,"wins":37},"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":4,"losses":8,"wins":36},"x-ai/grok-4.6":{"draws":7,"losses":6,"wins":35},"x-ai/grok-4.7":{"draws":6,"losses":9,"wins":27},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":14,"losses":6,"wins":76},"z-ai/glm-5.3":{"draws":10,"losses":4,"wins":32},"z-ai/glm-5.3-flash":{"draws":8,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":10,"losses":2,"wins":36}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":16},"claude-fable-5":{"draws":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":5,"wins":33},"claude-fable-5":{"draws":9,"losses":20,"wins":19},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":14,"wins":23},"claude-opus-4-5":{"draws":15,"losses":10,"wins":53},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":11,"losses":58,"wins":13},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"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":10,"losses":11,"wins":27},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"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":10,"losses":15,"wins":35},"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":4,"losses":37,"wins":7},"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":24,"losses":33,"wins":101},"stealth/space-bunny-alpha":{"draws":9,"losses":4,"wins":25},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":27},"stepfun/step-5-preview":{"draws":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":21,"losses":15,"wins":60},"z-ai/glm-5.3":{"draws":8,"losses":20,"wins":18},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":6,"losses":23,"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":3,"losses":36,"wins":15},"claude-haiku-5-5":{"draws":8,"losses":4,"wins":34},"claude-opus-4-5":{"draws":18,"losses":9,"wins":51},"claude-opus-4-8":{"draws":4,"losses":8,"wins":32},"claude-opus-5":{"draws":13,"losses":35,"wins":34},"claude-opus-5-5":{"draws":11,"losses":26,"wins":15},"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":10,"losses":7,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":6,"wins":40},"gemini-4-argon":{"draws":10,"losses":19,"wins":19},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":44},"google/gemini-3.5-flash-lite":{"draws":10,"losses":1,"wins":73},"google/gemini-3.6-flash":{"draws":9,"losses":12,"wins":71},"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":2,"losses":2,"wins":28},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":30},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":37},"gpt-6-astra":{"draws":4,"losses":34,"wins":10},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":5,"losses":24,"wins":19},"gpt-6.1-sol":{"draws":1,"losses":24,"wins":7},"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":3,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":2,"wins":37},"stealth/ox-alpha":{"draws":26,"losses":19,"wins":113},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":34},"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":12,"losses":4,"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":8,"losses":14,"wins":24},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":34},"z-ai/glm-5.3-flashx":{"draws":11,"losses":9,"wins":28}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":10},"claude-fable-5":{"draws":9,"losses":16,"wins":5},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":3},"claude-opus-4-5":{"draws":23,"losses":20,"wins":5},"claude-opus-4-8":{"draws":11,"losses":9,"wins":6},"claude-opus-5":{"draws":12,"losses":36,"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":9,"wins":12},"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":24,"losses":30,"wins":10},"claude-fable-5":{"draws":13,"losses":50,"wins":3},"claude-fable-5-1":{"draws":4,"losses":68,"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":22,"losses":40,"wins":4},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":3},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":41,"losses":36,"wins":25},"deepseek/deepseek-v4-pro":{"draws":22,"losses":22,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":29,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":29,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":51,"wins":2},"elorian/glimpse":{"draws":9,"losses":23,"wins":6},"fireworks/ember-1":{"draws":29,"losses":36,"wins":1},"gemini-3.1-pro-preview":{"draws":21,"losses":32,"wins":13},"gemini-4-argon":{"draws":6,"losses":58,"wins":2},"google/gemini-3.1-flash-lite":{"draws":16,"losses":13,"wins":9},"google/gemini-3.5-flash":{"draws":24,"losses":49,"wins":9},"google/gemini-3.5-flash-lite":{"draws":40,"losses":48,"wins":26},"google/gemini-3.6-flash":{"draws":39,"losses":70,"wins":15},"google/gemini-3.8-flash":{"draws":17,"losses":48,"wins":1},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":5},"gpt-4.1":{"draws":9,"losses":13,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":19,"losses":23,"wins":16},"gpt-5.4":{"draws":16,"losses":37,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":18,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":36,"wins":16},"gpt-5.5":{"draws":28,"losses":27,"wins":5},"gpt-5.6-luna":{"draws":37,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":8,"losses":56,"wins":2},"gpt-5.6-terra":{"draws":22,"losses":41,"wins":3},"gpt-6-astra":{"draws":3,"losses":62,"wins":1},"gpt-6-luna":{"draws":24,"losses":33,"wins":9},"gpt-6-sol":{"draws":10,"losses":50,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":63,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":13,"wins":8},"inception/mercury-3":{"draws":10,"losses":29,"wins":11},"inclusionai/ling-3.0-flash":{"draws":14,"losses":10,"wins":12},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":25,"wins":12},"meta/muse-glimmer-30b":{"draws":32,"losses":12,"wins":12},"meta/muse-spark-1.2":{"draws":16,"losses":42,"wins":4},"meta/muse-spark-1.3":{"draws":15,"losses":47,"wins":4},"meta/muse-spark-open":{"draws":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":12,"losses":14,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":19,"losses":36,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":53,"wins":0},"nex-agi/nex-n2-pro":{"draws":10,"losses":14,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":22,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":15,"wins":5},"o3":{"draws":21,"losses":55,"wins":12},"openai/gpt-oss-120b":{"draws":29,"losses":25,"wins":2},"poolside/laguna-s-2.1":{"draws":22,"losses":21,"wins":25},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":43,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":9},"qwen/qwen3.8-flash":{"draws":14,"losses":25,"wins":5},"qwen/qwen3.8-max":{"draws":24,"losses":35,"wins":7},"qwen/qwen3.8-max-0902":{"draws":27,"losses":36,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":10,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":36,"wins":4},"stealth/ox-alpha":{"draws":62,"losses":147,"wins":17},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":8},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":4},"tencent/hy4-preview":{"draws":22,"losses":34,"wins":8},"thinkingmachines/inkling":{"draws":27,"losses":36,"wins":21},"thinkingmachines/inkling-small":{"draws":29,"losses":18,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":21,"wins":0},"unbiased/pareto-26.10-preview":{"draws":2,"losses":20,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":48,"wins":3},"x-ai/grok-4.6":{"draws":22,"losses":41,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":48,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":42,"losses":34,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":14,"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":63,"losses":43,"wins":26},"z-ai/glm-5.3":{"draws":16,"losses":43,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":12},"z-ai/glm-5.3-flashx":{"draws":25,"losses":35,"wins":6}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":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":20,"losses":36,"wins":22},"claude-fable-5":{"draws":8,"losses":67,"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":35,"losses":83,"wins":18},"claude-opus-4-8":{"draws":16,"losses":50,"wins":10},"claude-opus-5":{"draws":13,"losses":118,"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":14,"losses":46,"wins":18},"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":24,"losses":49,"wins":11},"gemini-3.1-pro-preview":{"draws":25,"losses":38,"wins":21},"gemini-4-argon":{"draws":3,"losses":77,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":14,"wins":32},"google/gemini-3.5-flash":{"draws":19,"losses":67,"wins":20},"google/gemini-3.5-flash-lite":{"draws":46,"losses":68,"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":25,"losses":33,"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":14,"losses":55,"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":16,"losses":15,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":15,"wins":2},"moonshotai/kimi-k3":{"draws":22,"losses":43,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":69,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":15,"wins":21},"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":14,"losses":23,"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":23,"losses":41,"wins":20},"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":54,"losses":185,"wins":43},"stealth/space-bunny-alpha":{"draws":17,"losses":39,"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":19,"losses":50,"wins":13},"thinkingmachines/inkling":{"draws":29,"losses":43,"wins":42},"thinkingmachines/inkling-small":{"draws":28,"losses":27,"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":13,"losses":52,"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":12,"losses":16,"wins":6},"claude-fable-5":{"draws":6,"losses":27,"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":17,"losses":21,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":17,"wins":10},"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":10,"losses":30,"wins":6},"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":8,"losses":23,"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":8,"losses":19,"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":3,"losses":21,"wins":10},"gpt-5.5":{"draws":14,"losses":18,"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":7,"losses":6,"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":6,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":27,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":9,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":4},"o3":{"draws":6,"losses":32,"wins":14},"openai/gpt-oss-120b":{"draws":10,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":17,"wins":9},"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":12,"losses":20,"wins":4},"qwen/qwen3.8-27b":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"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":24,"losses":86,"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":28,"losses":28,"wins":16},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":4,"losses":28,"wins":4},"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":2,"losses":52,"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":12,"losses":26,"wins":6},"claude-opus-5":{"draws":8,"losses":64,"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":12,"losses":25,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":14,"losses":25,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":21,"wins":14},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":15,"losses":28,"wins":17},"google/gemini-3.5-flash-lite":{"draws":27,"losses":22,"wins":35},"google/gemini-3.6-flash":{"draws":24,"losses":51,"wins":17},"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":7,"losses":17,"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":20,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":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":85,"wins":36},"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":9,"losses":26,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":30,"wins":7},"x-ai/grok-4.6":{"draws":10,"losses":35,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":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":9,"losses":36,"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":13,"losses":22,"wins":9},"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":15,"losses":22,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":20,"wins":17},"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":14,"losses":14,"wins":20},"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":19,"losses":16,"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":86,"wins":33},"stealth/space-bunny-alpha":{"draws":7,"losses":15,"wins":16},"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":13,"losses":28,"wins":5},"thinkingmachines/inkling":{"draws":20,"losses":9,"wins":35},"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":8,"losses":35,"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":11,"losses":17,"wins":28},"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":28,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":2,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":7,"losses":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":5,"losses":12,"wins":11},"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":15,"losses":17,"wins":8},"claude-fable-5":{"draws":5,"losses":35,"wins":2},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":22,"losses":45,"wins":1},"claude-opus-4-8":{"draws":12,"losses":22,"wins":4},"claude-opus-5":{"draws":10,"losses":58,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":13,"losses":27,"wins":2},"claude-sonnet-5-5":{"draws":6,"losses":33,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":26,"losses":27,"wins":9},"deepseek/deepseek-v4-pro":{"draws":7,"losses":24,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":24,"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":8,"losses":7,"wins":11},"google/gemini-3.5-flash":{"draws":12,"losses":35,"wins":5},"google/gemini-3.5-flash-lite":{"draws":17,"losses":39,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":47,"wins":8},"google/gemini-3.8-flash":{"draws":6,"losses":34,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":11,"wins":2},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":9,"losses":20,"wins":7},"gpt-5.4":{"draws":8,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":29,"wins":6},"gpt-5.5":{"draws":10,"losses":23,"wins":5},"gpt-5.6-luna":{"draws":15,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":35,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":3},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":25,"wins":2},"gpt-6-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":10,"wins":5},"inception/mercury-3":{"draws":8,"losses":18,"wins":2},"inclusionai/ling-3.0-flash":{"draws":11,"losses":11,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":19,"wins":11},"meta/muse-glimmer-30b":{"draws":15,"losses":15,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":27,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":34,"wins":1},"meta/muse-spark-open":{"draws":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":8,"losses":30,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":39,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":18,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":3},"o3":{"draws":9,"losses":39,"wins":6},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":3},"poolside/laguna-s-2.1":{"draws":11,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":32,"wins":1},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-max":{"draws":9,"losses":29,"wins":4},"qwen/qwen3.8-max-0902":{"draws":13,"losses":27,"wins":2},"recursive/flint-v1.0":{"draws":4,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":27,"wins":3},"stealth/ox-alpha":{"draws":31,"losses":93,"wins":16},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":12,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":28,"wins":5},"thinkingmachines/inkling":{"draws":19,"losses":27,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":14,"wins":12},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":25,"losses":28,"wins":13},"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":29,"losses":44,"wins":11},"z-ai/glm-5.3":{"draws":6,"losses":33,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":33,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":5,"losses":30,"wins":13},"claude-fable-5-1":{"draws":2,"losses":50,"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":12,"losses":15,"wins":17},"claude-opus-5":{"draws":12,"losses":53,"wins":17},"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":9,"losses":16,"wins":23},"gemini-4-argon":{"draws":0,"losses":42,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":21},"google/gemini-3.5-flash-lite":{"draws":23,"losses":20,"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":17,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":12,"losses":18,"wins":18},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":12},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":12,"wins":20},"stealth/ox-alpha":{"draws":40,"losses":66,"wins":52},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":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":13,"losses":16,"wins":9},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"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":12,"losses":23,"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":19,"losses":27,"wins":16},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":22,"wins":5},"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":16,"losses":20,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":22,"wins":27},"google/gemini-3.6-flash":{"draws":23,"losses":42,"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":11,"losses":11,"wins":14},"gpt-5.4":{"draws":12,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":13},"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":13,"losses":6,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":17,"wins":18},"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":10,"losses":26,"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":10,"losses":10,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":19,"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":17,"losses":9,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":7},"o3":{"draws":7,"losses":31,"wins":18},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":14},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":14},"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":12,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":23,"wins":4},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":20,"wins":9},"stealth/ox-alpha":{"draws":43,"losses":76,"wins":23},"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":12,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":3},"thinkingmachines/inkling":{"draws":19,"losses":18,"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":38,"losses":30,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":23,"wins":9},"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":11,"losses":16,"wins":13},"claude-fable-5":{"draws":6,"losses":30,"wins":6},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":12},"claude-opus-4-5":{"draws":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":10,"losses":19,"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":11,"losses":31,"wins":20},"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":12,"losses":29,"wins":13},"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":12,"losses":18,"wins":8},"gpt-5.4":{"draws":13,"losses":25,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":4,"losses":22,"wins":16},"gpt-5.5":{"draws":17,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":13},"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":9,"losses":10,"wins":11},"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":6,"losses":25,"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":8,"losses":4,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":6},"o3":{"draws":10,"losses":34,"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":11,"losses":25,"wins":6},"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":10,"losses":24,"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":25,"losses":92,"wins":25},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":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":21,"losses":32,"wins":31},"z-ai/glm-5.3":{"draws":6,"losses":30,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":27,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":28,"wins":8}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":1},"claude-fable-5":{"draws":4,"losses":14,"wins":0},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":11,"wins":4},"claude-opus-4-5":{"draws":9,"losses":18,"wins":3},"claude-opus-4-8":{"draws":5,"losses":12,"wins":1},"claude-opus-5":{"draws":4,"losses":25,"wins":3},"claude-opus-5-5":{"draws":1,"losses":21,"wins":0},"claude-sonnet-5":{"draws":6,"losses":11,"wins":1},"claude-sonnet-5-5":{"draws":4,"losses":13,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":4,"losses":16,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":10,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":12,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":14,"wins":0},"elorian/glimpse":{"draws":4,"losses":5,"wins":3},"fireworks/ember-1":{"draws":4,"losses":10,"wins":4},"gemini-3.1-pro-preview":{"draws":3,"losses":12,"wins":3},"gemini-4-argon":{"draws":0,"losses":16,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":5,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":12,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":20,"wins":4},"google/gemini-3.8-flash":{"draws":2,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":4,"losses":11,"wins":1},"gpt-5.4":{"draws":6,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":11,"wins":4},"gpt-5.5":{"draws":6,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":7},"gpt-5.6-sol":{"draws":1,"losses":16,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":10,"wins":3},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":5,"losses":11,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":15,"wins":0},"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":8,"losses":16,"wins":8},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":21,"wins":5},"claude-opus-4-5":{"draws":19,"losses":34,"wins":5},"claude-opus-4-8":{"draws":9,"losses":22,"wins":1},"claude-opus-5":{"draws":5,"losses":59,"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":11,"losses":21,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":20,"wins":5},"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":21,"losses":38,"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":9,"losses":21,"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":30,"losses":82,"wins":12},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":6},"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":20,"losses":21,"wins":25},"claude-fable-5":{"draws":5,"losses":53,"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":33,"losses":58,"wins":25},"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":29,"losses":35,"wins":48},"deepseek/deepseek-v4-pro":{"draws":11,"losses":29,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":31,"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":17,"losses":38,"wins":17},"gemini-3.1-pro-preview":{"draws":19,"losses":32,"wins":21},"gemini-4-argon":{"draws":2,"losses":69,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":10,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":58,"wins":21},"google/gemini-3.5-flash-lite":{"draws":26,"losses":34,"wins":64},"google/gemini-3.6-flash":{"draws":30,"losses":69,"wins":39},"google/gemini-3.8-flash":{"draws":10,"losses":51,"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":13,"losses":27,"wins":28},"gpt-5.4":{"draws":15,"losses":43,"wins":12},"gpt-5.4-mini":{"draws":16,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":32,"wins":35},"gpt-5.5":{"draws":22,"losses":32,"wins":14},"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":20,"losses":36,"wins":12},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":18,"losses":25,"wins":29},"gpt-6-sol":{"draws":10,"losses":54,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":1},"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":10,"losses":16,"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":19,"losses":21,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":43,"wins":17},"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":9,"losses":10,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":17,"losses":33,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":56,"wins":4},"nex-agi/nex-n2-pro":{"draws":10,"losses":9,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":17,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":17,"wins":11},"o3":{"draws":15,"losses":54,"wins":41},"openai/gpt-oss-120b":{"draws":19,"losses":14,"wins":33},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":22},"qwen/qwen3.7-max":{"draws":12,"losses":20,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":46,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":25,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":21,"wins":16},"qwen/qwen3.8-max":{"draws":16,"losses":33,"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":47,"losses":138,"wins":63},"stealth/space-bunny-alpha":{"draws":11,"losses":26,"wins":19},"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":13,"wins":15},"tencent/hy4-preview":{"draws":14,"losses":38,"wins":18},"thinkingmachines/inkling":{"draws":20,"losses":29,"wins":51},"thinkingmachines/inkling-small":{"draws":20,"losses":11,"wins":41},"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":19,"losses":42,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":9,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":30,"wins":53},"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":42,"losses":51,"wins":51},"z-ai/glm-5.3":{"draws":7,"losses":52,"wins":9},"z-ai/glm-5.3-flash":{"draws":13,"losses":39,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":19,"wins":10},"claude-fable-5":{"draws":5,"losses":32,"wins":5},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":19,"wins":8},"claude-opus-4-5":{"draws":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":20,"losses":21,"wins":25},"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":11,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"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":21,"wins":35},"google/gemini-3.6-flash":{"draws":21,"losses":43,"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":13,"losses":15,"wins":10},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":17},"gpt-5.5":{"draws":13,"losses":18,"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":9,"losses":7,"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":8,"losses":24,"wins":8},"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":14,"losses":11,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":9,"wins":6},"o3":{"draws":8,"losses":36,"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":11,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":20,"wins":6},"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":29,"losses":82,"wins":29},"stealth/space-bunny-alpha":{"draws":8,"losses":13,"wins":11},"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":5,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":22,"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":28,"losses":29,"wins":27},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":7},"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":7,"losses":26,"wins":3},"claude-fable-5-1":{"draws":4,"losses":36,"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":10,"losses":23,"wins":3},"claude-opus-5":{"draws":7,"losses":44,"wins":7},"claude-opus-5-5":{"draws":4,"losses":32,"wins":0},"claude-sonnet-5":{"draws":11,"losses":21,"wins":4},"claude-sonnet-5-5":{"draws":8,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":17,"losses":25,"wins":12},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":26,"wins":3},"elorian/glimpse":{"draws":6,"losses":8,"wins":4},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":21,"wins":2},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":8,"wins":13},"google/gemini-3.5-flash":{"draws":11,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":19,"losses":35,"wins":10},"google/gemini-3.6-flash":{"draws":22,"losses":45,"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":28,"wins":10},"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":13,"wins":19},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":14},"claude-opus-4-5":{"draws":26,"losses":25,"wins":27},"claude-opus-4-8":{"draws":15,"losses":18,"wins":11},"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":22,"losses":12,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":23,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":24,"wins":12},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"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":18,"wins":24},"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":10,"losses":24,"wins":14},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":13,"wins":19},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":10,"wins":26},"gpt-5.5":{"draws":12,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":20},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"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":9,"losses":20,"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":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":26,"wins":11},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":13,"wins":19},"stealth/ox-alpha":{"draws":36,"losses":67,"wins":55},"stealth/space-bunny-alpha":{"draws":12,"losses":14,"wins":12},"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":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":22,"wins":16},"x-ai/grok-4.6":{"draws":12,"losses":21,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":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":29,"losses":27,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":8},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":25,"wins":11}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":8},"claude-fable-5":{"draws":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":39,"wins":8},"claude-opus-4-8":{"draws":11,"losses":31,"wins":2},"claude-opus-5":{"draws":12,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":18,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":21,"losses":26,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":25,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":32,"wins":8},"elorian/glimpse":{"draws":7,"losses":15,"wins":4},"fireworks/ember-1":{"draws":15,"losses":25,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":20,"wins":11},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":8,"wins":12},"google/gemini-3.5-flash":{"draws":13,"losses":39,"wins":8},"google/gemini-3.5-flash-lite":{"draws":29,"losses":28,"wins":27},"google/gemini-3.6-flash":{"draws":33,"losses":53,"wins":6},"google/gemini-3.8-flash":{"draws":8,"losses":39,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":28,"wins":9},"gpt-5.4":{"draws":8,"losses":28,"wins":10},"gpt-5.4-mini":{"draws":13,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":12,"losses":18,"wins":18},"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":10,"losses":8,"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":28,"wins":6},"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":10,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":27,"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":17,"losses":12,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":13,"losses":37,"wins":16},"openai/gpt-oss-120b":{"draws":12,"losses":17,"wins":13},"poolside/laguna-s-2.1":{"draws":16,"losses":21,"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":14,"losses":30,"wins":4},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":0},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-max-0902":{"draws":16,"losses":23,"wins":9},"recursive/flint-v1.0":{"draws":5,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":42,"losses":90,"wins":26},"stealth/space-bunny-alpha":{"draws":13,"losses":16,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":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":33,"losses":47,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":18,"losses":26,"wins":4}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":12,"wins":15},"claude-fable-5":{"draws":9,"losses":24,"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":25,"losses":32,"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":42,"wins":5},"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":10,"wins":30},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":21,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":24,"wins":15},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":12,"losses":23,"wins":13},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"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":33,"losses":19,"wins":32},"google/gemini-3.6-flash":{"draws":23,"losses":37,"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":7,"losses":31,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":13,"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":22,"losses":8,"wins":22},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":17,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":20,"wins":17},"meta/muse-spark-open":{"draws":12,"losses":24,"wins":10},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"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":12,"wins":17},"qwen/qwen3.7-max":{"draws":11,"losses":9,"wins":8},"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":12,"losses":20,"wins":16},"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":11,"losses":11,"wins":16},"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":2,"wins":8},"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":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":28,"losses":26,"wins":24},"claude-opus-4-8":{"draws":14,"losses":13,"wins":17},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":1,"losses":49,"wins":2},"claude-sonnet-5":{"draws":15,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":23,"losses":12,"wins":37},"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":18,"losses":18,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":28,"wins":11},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":15,"losses":12,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":18,"losses":16,"wins":26},"google/gemini-3.5-flash-lite":{"draws":29,"losses":9,"wins":46},"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":21,"losses":14,"wins":9},"gpt-5.6-luna":{"draws":18,"losses":14,"wins":16},"gpt-5.6-sol":{"draws":5,"losses":34,"wins":9},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":16},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":8,"losses":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":16,"losses":5,"wins":13},"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":16,"losses":3,"wins":23},"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":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":9,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":2,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":9},"o3":{"draws":16,"losses":21,"wins":29},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":17,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":16},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":13,"losses":17,"wins":18},"qwen/qwen3.8-max-0902":{"draws":7,"losses":15,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":13,"wins":20},"stealth/ox-alpha":{"draws":38,"losses":64,"wins":56},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":22},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":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":17,"losses":2,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":15,"losses":28,"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":29,"losses":9,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":17},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":15}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":11,"wins":13},"claude-fable-5":{"draws":9,"losses":22,"wins":11},"claude-fable-5-1":{"draws":1,"losses":46,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":11},"claude-opus-4-5":{"draws":30,"losses":19,"wins":19},"claude-opus-4-8":{"draws":12,"losses":15,"wins":11},"claude-opus-5":{"draws":11,"losses":58,"wins":11},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":18,"losses":13,"wins":11},"claude-sonnet-5-5":{"draws":13,"losses":19,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":31},"deepseek/deepseek-v4-pro":{"draws":12,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":11,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":15,"losses":12,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":12},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":17,"wins":26},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":7,"losses":22,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":5,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":9,"losses":14,"wins":15},"gpt-5.4":{"draws":9,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":19},"gpt-5.5":{"draws":11,"losses":22,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":13},"gpt-6-astra":{"draws":4,"losses":35,"wins":3},"gpt-6-luna":{"draws":10,"losses":18,"wins":14},"gpt-6-sol":{"draws":8,"losses":26,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":35,"wins":5},"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":51,"losses":38,"wins":67},"claude-fable-5":{"draws":31,"losses":112,"wins":25},"claude-fable-5-1":{"draws":5,"losses":189,"wins":2},"claude-haiku-5-5":{"draws":48,"losses":71,"wins":33},"claude-opus-4-5":{"draws":97,"losses":93,"wins":74},"claude-opus-4-8":{"draws":34,"losses":70,"wins":32},"claude-opus-5":{"draws":46,"losses":224,"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":92,"losses":63,"wins":91},"deepseek/deepseek-v4-pro":{"draws":57,"losses":52,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":50,"losses":66,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":53,"losses":77,"wins":38},"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":46,"losses":62,"wins":60},"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":42,"losses":100,"wins":60},"google/gemini-3.5-flash-lite":{"draws":96,"losses":77,"wins":119},"google/gemini-3.6-flash":{"draws":82,"losses":161,"wins":83},"google/gemini-3.8-flash":{"draws":43,"losses":97,"wins":28},"google/gemma-4-31b-it":{"draws":35,"losses":15,"wins":40},"gpt-4.1":{"draws":21,"losses":19,"wins":16},"gpt-4.1-nano":{"draws":16,"losses":2,"wins":10},"gpt-5":{"draws":51,"losses":58,"wins":41},"gpt-5.4":{"draws":57,"losses":77,"wins":28},"gpt-5.4-mini":{"draws":47,"losses":32,"wins":33},"gpt-5.4-nano":{"draws":40,"losses":52,"wins":54},"gpt-5.5":{"draws":60,"losses":61,"wins":35},"gpt-5.6-luna":{"draws":71,"losses":48,"wins":49},"gpt-5.6-sol":{"draws":30,"losses":115,"wins":23},"gpt-5.6-terra":{"draws":69,"losses":51,"wins":42},"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":51,"losses":18,"wins":47},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":62,"losses":36,"wins":80},"meta/muse-glimmer-30b":{"draws":58,"losses":28,"wins":64},"meta/muse-spark-1.2":{"draws":52,"losses":67,"wins":43},"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":23,"losses":20,"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":49,"losses":68,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":133,"wins":5},"nex-agi/nex-n2-pro":{"draws":32,"losses":11,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":14,"losses":10,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":26,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":27,"losses":24,"wins":21},"o3":{"draws":46,"losses":93,"wins":69},"openai/gpt-oss-120b":{"draws":64,"losses":28,"wins":58},"poolside/laguna-s-2.1":{"draws":66,"losses":41,"wins":63},"qwen/qwen3.7-max":{"draws":33,"losses":27,"wins":30},"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":75,"wins":39},"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":134,"losses":303,"wins":165},"stealth/space-bunny-alpha":{"draws":50,"losses":39,"wins":41},"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":52,"losses":76,"wins":34},"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":134,"losses":98,"wins":104},"z-ai/glm-5.3":{"draws":34,"losses":107,"wins":21},"z-ai/glm-5.3-flash":{"draws":31,"losses":93,"wins":44},"z-ai/glm-5.3-flashx":{"draws":42,"losses":94,"wins":32}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":11,"losses":21,"wins":4},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":4},"claude-opus-4-5":{"draws":16,"losses":32,"wins":10},"claude-opus-4-8":{"draws":9,"losses":16,"wins":7},"claude-opus-5":{"draws":10,"losses":55,"wins":3},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":9,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":9,"losses":21,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":17,"wins":15},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":14,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":4},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":8},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":16,"losses":19,"wins":9},"google/gemini-3.5-flash-lite":{"draws":21,"losses":18,"wins":23},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":10},"google/gemini-3.8-flash":{"draws":7,"losses":23,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":5},"gpt-4.1":{"draws":3,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":14,"wins":7},"gpt-5.4":{"draws":15,"losses":13,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":14},"gpt-5.5":{"draws":18,"losses":14,"wins":2},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":12,"losses":12,"wins":10},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":17,"wins":7},"gpt-6-sol":{"draws":6,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":8},"inception/mercury-3":{"draws":7,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":8,"wins":3},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":2},"meta/muse-spark-open":{"draws":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":8,"losses":3,"wins":11},"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":8,"losses":1,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":0,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":8,"wins":4},"o3":{"draws":10,"losses":26,"wins":8},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":14},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":1},"qwen/qwen3.8-flash":{"draws":9,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":42,"losses":70,"wins":14},"stealth/space-bunny-alpha":{"draws":5,"losses":8,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":18,"wins":1},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":16},"thinkingmachines/inkling-small":{"draws":16,"losses":10,"wins":10},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.6":{"draws":12,"losses":20,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":21,"losses":13,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":28,"losses":26,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":19,"wins":5},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":5}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":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":11,"losses":19,"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":9,"losses":17,"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":10,"losses":17,"wins":9},"gemini-4-argon":{"draws":1,"losses":33,"wins":2},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":12},"google/gemini-3.5-flash-lite":{"draws":29,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":23,"losses":31,"wins":14},"google/gemini-3.8-flash":{"draws":17,"losses":16,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":11,"losses":10,"wins":11},"gpt-5.4":{"draws":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":10,"losses":21,"wins":5},"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":17,"losses":16,"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":15,"losses":9,"wins":20},"claude-fable-5":{"draws":7,"losses":39,"wins":2},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":21,"wins":15},"claude-opus-4-5":{"draws":28,"losses":30,"wins":20},"claude-opus-4-8":{"draws":12,"losses":21,"wins":11},"claude-opus-5":{"draws":11,"losses":62,"wins":9},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":14,"losses":19,"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":20,"losses":20,"wins":32},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":5,"losses":14,"wins":7},"fireworks/ember-1":{"draws":19,"losses":21,"wins":8},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"gemini-4-argon":{"draws":1,"losses":45,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":18},"google/gemini-3.5-flash-lite":{"draws":26,"losses":26,"wins":32},"google/gemini-3.6-flash":{"draws":30,"losses":40,"wins":22},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":9},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":19,"wins":12},"gpt-5.4":{"draws":12,"losses":26,"wins":8},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":23},"gpt-5.5":{"draws":18,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":35,"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":19,"losses":19,"wins":10},"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":9,"losses":6,"wins":19},"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":12,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"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":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":8,"losses":37,"wins":21},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":10,"losses":13,"wins":23},"qwen/qwen3.7-max":{"draws":11,"losses":8,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":22,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":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":36,"losses":81,"wins":41},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":5},"thinkingmachines/inkling":{"draws":17,"losses":15,"wins":32},"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":16,"losses":24,"wins":8},"x-ai/grok-4.6":{"draws":17,"losses":25,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":31,"losses":12,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":14,"losses":23,"wins":11}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":21,"wins":20},"claude-fable-5":{"draws":16,"losses":49,"wins":7},"claude-fable-5-1":{"draws":6,"losses":76,"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":19,"losses":36,"wins":9},"claude-opus-5":{"draws":18,"losses":97,"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":38,"losses":36,"wins":30},"deepseek/deepseek-v4-pro":{"draws":21,"losses":32,"wins":15},"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":23,"losses":34,"wins":15},"gemini-3.1-pro-preview":{"draws":21,"losses":29,"wins":22},"gemini-4-argon":{"draws":5,"losses":62,"wins":5},"google/gemini-3.1-flash-lite":{"draws":12,"losses":15,"wins":19},"google/gemini-3.5-flash":{"draws":21,"losses":51,"wins":18},"google/gemini-3.5-flash-lite":{"draws":31,"losses":52,"wins":45},"google/gemini-3.6-flash":{"draws":46,"losses":76,"wins":18},"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":11,"losses":31,"wins":26},"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":22,"losses":30,"wins":18},"meta/muse-spark-1.3":{"draws":15,"losses":48,"wins":9},"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":9,"losses":7,"wins":18},"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":60,"losses":140,"wins":50},"stealth/space-bunny-alpha":{"draws":19,"losses":21,"wins":18},"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":13,"losses":17,"wins":10},"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":22,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":30,"wins":4},"z-ai/glm-5.2":{"draws":51,"losses":55,"wins":38},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":10},"z-ai/glm-5.3-flash":{"draws":19,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":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":27,"wins":5},"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":11,"wins":21},"claude-fable-5":{"draws":9,"losses":32,"wins":7},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":15,"losses":54,"wins":13},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"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":43,"wins":27},"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":21,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":33,"wins":10},"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":11,"losses":20,"wins":15},"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":17,"wins":16},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":14},"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":28,"wins":8},"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":13,"losses":30,"wins":5},"claude-fable-5-1":{"draws":2,"losses":51,"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":2,"losses":48,"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":25,"losses":14,"wins":33},"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":17,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":18,"losses":14,"wins":16},"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":16,"losses":10,"wins":20},"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":18,"losses":9,"wins":15},"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":60,"losses":73,"wins":25},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":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":13,"wins":20},"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":13,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":20},"gemini-4-argon":{"draws":8,"losses":29,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":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":14,"wins":20},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":15,"wins":16},"gpt-5.4":{"draws":8,"losses":14,"wins":18},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":10,"losses":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":12,"losses":88,"wins":2},"claude-fable-5-1":{"draws":6,"losses":104,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":64,"wins":20},"claude-opus-4-5":{"draws":45,"losses":92,"wins":31},"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":58,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":79,"wins":10},"elorian/glimpse":{"draws":13,"losses":33,"wins":8},"fireworks/ember-1":{"draws":24,"losses":54,"wins":24},"gemini-3.1-pro-preview":{"draws":21,"losses":50,"wins":31},"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":42,"losses":75,"wins":67},"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":64,"wins":13},"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":22,"wins":22},"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":32,"losses":59,"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":19,"losses":34,"wins":29},"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":23,"wins":18},"tencent/hy4-preview":{"draws":27,"losses":65,"wins":8},"thinkingmachines/inkling":{"draws":31,"losses":43,"wins":64},"thinkingmachines/inkling-small":{"draws":29,"losses":26,"wins":47},"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":5,"losses":64,"wins":1},"claude-opus-5-5":{"draws":1,"losses":44,"wins":1},"claude-sonnet-5":{"draws":8,"losses":28,"wins":6},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":19,"losses":28,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":23,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":26,"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":20,"losses":33,"wins":19},"google/gemini-3.6-flash":{"draws":15,"losses":51,"wins":14},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":17,"wins":12},"gpt-5.4":{"draws":6,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":16,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":22,"wins":15},"gpt-5.5":{"draws":12,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":29,"wins":4},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":25,"wins":7},"gpt-6-sol":{"draws":1,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":10},"inception/mercury-3":{"draws":10,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":10,"losses":9,"wins":11},"inclusionai/ling-3.1-flash":{"draws":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":26,"wins":6},"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":10,"losses":22,"wins":8},"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":8,"losses":26,"wins":6},"thinkingmachines/inkling":{"draws":14,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":8,"losses":28,"wins":6},"x-ai/grok-4.6":{"draws":11,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":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":10,"losses":11,"wins":17},"claude-fable-5":{"draws":11,"losses":27,"wins":4},"claude-fable-5-1":{"draws":2,"losses":41,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":10},"claude-opus-4-5":{"draws":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":18,"losses":17,"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":9,"losses":18,"wins":15},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":17},"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":10,"losses":24,"wins":18},"google/gemini-3.5-flash-lite":{"draws":15,"losses":11,"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":9,"losses":17,"wins":12},"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":30,"wins":5},"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":12,"losses":17,"wins":11},"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":9,"wins":20},"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":9,"losses":21,"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":32,"losses":72,"wins":36},"stealth/space-bunny-alpha":{"draws":7,"losses":10,"wins":15},"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":9,"losses":18,"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":24,"losses":29,"wins":31},"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":5,"losses":45,"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":5,"losses":42,"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":8,"losses":18,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":27,"wins":17},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":27,"losses":43,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":22,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":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":17,"wins":15},"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":44,"losses":67,"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":9,"wins":34},"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":23,"wins":14},"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":50,"losses":44,"wins":38},"claude-fable-5":{"draws":23,"losses":102,"wins":19},"claude-fable-5-1":{"draws":7,"losses":154,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":84,"wins":26},"claude-opus-4-5":{"draws":72,"losses":109,"wins":53},"claude-opus-4-8":{"draws":37,"losses":72,"wins":23},"claude-opus-5":{"draws":31,"losses":193,"wins":22},"claude-opus-5-5":{"draws":9,"losses":142,"wins":5},"claude-sonnet-5":{"draws":46,"losses":63,"wins":35},"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":68,"losses":53,"wins":95},"deepseek/deepseek-v4-pro":{"draws":41,"losses":53,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":46,"losses":48,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":48,"losses":67,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":95,"wins":20},"elorian/glimpse":{"draws":19,"losses":36,"wins":23},"fireworks/ember-1":{"draws":45,"losses":71,"wins":28},"gemini-3.1-pro-preview":{"draws":42,"losses":65,"wins":37},"gemini-4-argon":{"draws":11,"losses":123,"wins":10},"google/gemini-3.1-flash-lite":{"draws":20,"losses":16,"wins":60},"google/gemini-3.5-flash":{"draws":40,"losses":92,"wins":48},"google/gemini-3.5-flash-lite":{"draws":70,"losses":89,"wins":93},"google/gemini-3.6-flash":{"draws":80,"losses":130,"wins":66},"google/gemini-3.8-flash":{"draws":33,"losses":85,"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":31,"losses":59,"wins":36},"gpt-5.4":{"draws":35,"losses":75,"wins":28},"gpt-5.4-mini":{"draws":39,"losses":23,"wins":34},"gpt-5.4-nano":{"draws":30,"losses":55,"wins":59},"gpt-5.5":{"draws":48,"losses":59,"wins":25},"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":48,"losses":53,"wins":37},"gpt-6-astra":{"draws":8,"losses":134,"wins":2},"gpt-6-luna":{"draws":53,"losses":58,"wins":33},"gpt-6-sol":{"draws":25,"losses":106,"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":39,"losses":24,"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":55,"losses":24,"wins":47},"meta/muse-spark-1.2":{"draws":33,"losses":68,"wins":37},"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":35,"losses":12,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":38,"losses":64,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":118,"wins":6},"nex-agi/nex-n2-pro":{"draws":25,"losses":13,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":8,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":36,"wins":49},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":25,"wins":19},"o3":{"draws":30,"losses":96,"wins":72},"openai/gpt-oss-120b":{"draws":42,"losses":34,"wins":50},"poolside/laguna-s-2.1":{"draws":43,"losses":50,"wins":45},"qwen/qwen3.7-max":{"draws":23,"losses":35,"wins":26},"qwen/qwen3.7-plus":{"draws":18,"losses":17,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":53,"losses":60,"wins":31},"qwen/qwen3.8-27b":{"draws":34,"losses":40,"wins":28},"qwen/qwen3.8-flash":{"draws":35,"losses":32,"wins":29},"qwen/qwen3.8-max":{"draws":44,"losses":61,"wins":39},"qwen/qwen3.8-max-0902":{"draws":48,"losses":66,"wins":30},"recursive/flint-v1.0":{"draws":11,"losses":12,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":37,"losses":50,"wins":45},"stealth/ox-alpha":{"draws":115,"losses":256,"wins":103},"stealth/space-bunny-alpha":{"draws":34,"losses":43,"wins":37},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":46},"stepfun/step-5-preview":{"draws":4,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":27,"losses":24,"wins":27},"tencent/hy4-preview":{"draws":30,"losses":80,"wins":28},"thinkingmachines/inkling":{"draws":58,"losses":48,"wins":86},"thinkingmachines/inkling-small":{"draws":49,"losses":36,"wins":59},"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":35,"losses":87,"wins":22},"x-ai/grok-4.7":{"draws":15,"losses":94,"wins":17},"x-ai/grok-build-0.1":{"draws":20,"losses":13,"wins":15},"xiaomi/mimo-v2.5":{"draws":73,"losses":58,"wins":91},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":32,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":55,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":56,"wins":18},"z-ai/glm-5.2":{"draws":74,"losses":90,"wins":76},"z-ai/glm-5.3":{"draws":32,"losses":94,"wins":12},"z-ai/glm-5.3-flash":{"draws":28,"losses":88,"wins":28},"z-ai/glm-5.3-flashx":{"draws":34,"losses":78,"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":4,"losses":48,"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":4,"losses":47,"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":15,"losses":16,"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":15,"losses":13,"wins":20},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":22},"google/gemini-3.5-flash":{"draws":20,"losses":20,"wins":20},"google/gemini-3.5-flash-lite":{"draws":25,"losses":13,"wins":46},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":34},"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":14,"losses":9,"wins":19},"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":16,"losses":19,"wins":13},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":16},"stealth/ox-alpha":{"draws":46,"losses":68,"wins":44},"stealth/space-bunny-alpha":{"draws":13,"losses":5,"wins":20},"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":13,"wins":34},"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":12,"losses":20,"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":8,"losses":15,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":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":25,"wins":25},"google/gemini-3.5-flash-lite":{"draws":23,"losses":22,"wins":39},"google/gemini-3.6-flash":{"draws":23,"losses":34,"wins":35},"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":1,"losses":8,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":10,"losses":12,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":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":12,"losses":27,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":15,"wins":17},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"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":12,"losses":13,"wins":27},"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":8,"losses":27,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":10,"wins":20},"poolside/laguna-s-2.1":{"draws":17,"losses":12,"wins":17},"qwen/qwen3.7-max":{"draws":11,"losses":8,"wins":9},"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":14,"losses":22,"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":34,"losses":78,"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":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":19,"losses":17,"wins":28},"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":8,"losses":22,"wins":18},"x-ai/grok-4.6":{"draws":17,"losses":21,"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":27,"losses":13,"wins":34},"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":34,"losses":24,"wins":38},"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":25,"wins":10}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":8,"losses":31,"wins":9},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":22,"losses":25,"wins":31},"claude-opus-4-8":{"draws":11,"losses":20,"wins":13},"claude-opus-5":{"draws":13,"losses":59,"wins":10},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"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":21,"losses":17,"wins":34},"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":18,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":14,"losses":20,"wins":14},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":18},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":24},"google/gemini-3.5-flash-lite":{"draws":30,"losses":13,"wins":41},"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":20,"losses":13,"wins":11},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"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":16,"losses":14,"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":14,"losses":8,"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":33,"losses":70,"wins":55},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":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":6,"wins":28},"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":36,"losses":25,"wins":35},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":10}}}}}