{"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":"2026-09-10T11:16:53Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:ae6ec4a095f6b7a9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.427439999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.2723400000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.2723400000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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},"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.42744}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":24},"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":15.613270000000002},"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":81.90889466396656,"highest":90.95955634051866,"medium":79.44415234078821,"none":75.3229753105928},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-09-10T11:11:15Z","match_totals_all":{"draws":290,"losses":319,"wins":2248},"match_totals_tracks":{"highest":{"draws":35,"losses":60,"wins":857},"medium":{"draws":115,"losses":116,"wins":722},"none":{"draws":140,"losses":143,"wins":669}},"model_slug":"gpt-6-astra","overall":{"max":100.0,"mean":81.90889466396655,"min":50.47588011557324},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":89.05863634547586,"GB2-02":98.89567905132267,"GB2-03":100.0,"GB2-04":98.28111373405677,"GB2-05":100.0,"GB2-06":74.19917615120977,"GB2-07":98.77254193497626,"GB2-08":68.46930350710791},"per_game_all":{"GB2-01":76.75876231791118,"GB2-02":73.19947816507673,"GB2-03":77.03524861977232,"GB2-04":92.02234498432301,"GB2-05":94.25748839681135,"GB2-06":73.8118731130519,"GB2-07":97.44526569600828,"GB2-08":70.74069601877768},"per_game_match_totals_all":{"GB2-01":{"draws":14,"losses":62,"wins":279},"GB2-02":{"draws":87,"losses":22,"wins":203},"GB2-03":{"draws":107,"losses":23,"wins":266},"GB2-04":{"draws":40,"losses":34,"wins":268},"GB2-05":{"draws":0,"losses":16,"wins":344},"GB2-06":{"draws":42,"losses":63,"wins":249},"GB2-07":{"draws":0,"losses":15,"wins":357},"GB2-08":{"draws":0,"losses":84,"wins":282}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":5,"wins":113},"GB2-02":{"draws":5,"losses":3,"wins":96},"GB2-03":{"draws":4,"losses":1,"wins":127},"GB2-04":{"draws":10,"losses":5,"wins":99},"GB2-05":{"draws":0,"losses":0,"wins":120},"GB2-06":{"draws":16,"losses":16,"wins":86},"GB2-07":{"draws":0,"losses":2,"wins":122},"GB2-08":{"draws":0,"losses":28,"wins":94}},"medium":{"GB2-01":{"draws":9,"losses":44,"wins":66},"GB2-02":{"draws":36,"losses":8,"wins":60},"GB2-03":{"draws":46,"losses":6,"wins":80},"GB2-04":{"draws":14,"losses":8,"wins":92},"GB2-05":{"draws":0,"losses":10,"wins":110},"GB2-06":{"draws":10,"losses":21,"wins":87},"GB2-07":{"draws":0,"losses":6,"wins":118},"GB2-08":{"draws":0,"losses":13,"wins":109}},"none":{"GB2-01":{"draws":5,"losses":13,"wins":100},"GB2-02":{"draws":46,"losses":11,"wins":47},"GB2-03":{"draws":57,"losses":16,"wins":59},"GB2-04":{"draws":16,"losses":21,"wins":77},"GB2-05":{"draws":0,"losses":6,"wins":114},"GB2-06":{"draws":16,"losses":26,"wins":76},"GB2-07":{"draws":0,"losses":7,"wins":117},"GB2-08":{"draws":0,"losses":43,"wins":79}}},"per_game_raw_elo_all":{"GB2-01":1907.1271780081352,"GB2-02":1798.8459812936562,"GB2-03":1873.500240860926,"GB2-04":1869.5870384567982,"GB2-05":2078.3146995532393,"GB2-06":1812.191887449928,"GB2-07":2069.5672250648804,"GB2-08":1849.061802724986},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2056.7386464310007,"GB2-02":1941.5395346701005,"GB2-03":2094.223525062207,"GB2-04":1907.4055627869584,"GB2-05":2151.5735715815727,"GB2-06":1817.1444184138888,"GB2-07":2085.499777586485,"GB2-08":1824.43663835412},"medium":{"GB2-01":1671.1890753713847,"GB2-02":1782.338822767404,"GB2-03":1849.1528943906224,"GB2-04":1883.1951086512008,"GB2-05":1992.4645295287164,"GB2-06":1817.90041052838,"GB2-07":2051.5484644930266,"GB2-08":1965.2290624670259},"none":{"GB2-01":1993.4538122220206,"GB2-02":1672.6595864434637,"GB2-03":1677.1243031299484,"GB2-04":1818.160443932235,"GB2-05":2090.9059975494283,"GB2-06":1801.5308334075144,"GB2-07":2071.65343311513,"GB2-08":1757.519707353812}},"per_game_tracks":{"highest":{"GB2-01":89.05863634547586,"GB2-02":98.89567905132267,"GB2-03":100.0,"GB2-04":98.28111373405677,"GB2-05":100.0,"GB2-06":74.19917615120977,"GB2-07":98.77254193497626,"GB2-08":68.46930350710791},"medium":{"GB2-01":57.36356914969686,"GB2-02":70.22687532833427,"GB2-03":74.50207337964267,"GB2-04":94.27440970618706,"GB2-05":87.52798814855652,"GB2-06":74.25829704210302,"GB2-07":95.94419593771026,"GB2-08":81.45581003407503},"none":{"GB2-01":83.85408145856084,"GB2-02":50.47588011557324,"GB2-03":56.603672479674294,"GB2-04":83.51151151272518,"GB2-05":95.24447704187754,"GB2-06":72.97814614584291,"GB2-07":97.61905921533831,"GB2-08":62.29697451515008}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":90.95955634051866,"medium":79.44415234078821,"none":75.3229753105928},"reasoning_agg":{"highest":{"max":100.0,"mean":90.95955634051866,"min":68.46930350710791},"medium":{"max":95.94419593771026,"mean":79.44415234078821,"min":57.36356914969686},"none":{"max":97.61905921533831,"mean":75.3229753105928,"min":50.47588011557324}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":88.70964258020325,"reasoning_variance":15.636581029925864,"reliability_score":97.99553903717157,"uncertainty_avg":2.004460962828431,"uncertainty_penalty":6.800747916236702},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":91.11470737124438,"reliability_score":97.98756493747796,"uncertainty_avg":2.0124350625220444,"uncertainty_penalty":0.1551510307257189},"medium":{"ceiling_score":95.94419593771026,"expected_score":86.79090954002112,"reliability_score":98.01148723655879,"uncertainty_avg":1.9885127634412036,"uncertainty_penalty":7.346757199232911},"none":{"ceiling_score":97.61905921533831,"expected_score":88.22331082934429,"reliability_score":97.98756493747796,"uncertainty_avg":2.0124350625220444,"uncertainty_penalty":12.90033551875149}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:ff8eddc4d6e61a06","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"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},"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"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},"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},"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.7391179312137}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781585},"codegen_output_tokens":{"attempt_count":35,"output_max":231035,"output_mean":46647.59375,"output_min":5610,"run_count":32},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":231035,"output_mean":80471.125,"output_min":38285,"run_count":16},"medium":{"attempt_count":9,"output_max":25949,"output_mean":17238.625,"output_min":9715,"run_count":8},"none":{"attempt_count":8,"output_max":10198,"output_mean":8409.5,"output_min":5610,"run_count":8}},"display_name":"Claude Fable 5.1","economics":{"all":81.11701473119925,"highest":92.37884458659907,"medium":77.18422949193521,"none":73.78797011506347},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"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}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-09-10T11:10:23Z","match_totals_all":{"draws":251,"losses":427,"wins":2550},"match_totals_tracks":{"highest":{"draws":46,"losses":95,"wins":1181},"medium":{"draws":82,"losses":171,"wins":701},"none":{"draws":123,"losses":161,"wins":668}},"model_slug":"claude-fable-5-1","overall":{"max":100.0,"mean":81.11701473119925,"min":44.553723611281114},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.96244740112121,"GB2-02":100.0,"GB2-03":89.4371849014492,"GB2-04":88.60770691415766,"GB2-05":91.18583886791443,"GB2-06":100.0,"GB2-07":92.8375786081501,"GB2-08":100.0},"per_game_all":{"GB2-01":69.2291214790214,"GB2-02":82.97239009671479,"GB2-03":83.62227823407197,"GB2-04":61.95533286347777,"GB2-05":89.7040831113785,"GB2-06":87.74745686964202,"GB2-07":91.73921522694651,"GB2-08":81.96623996834101},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":17,"wins":100},"GB2-02":{"draws":5,"losses":5,"wins":94},"GB2-03":{"draws":4,"losses":4,"wins":124},"GB2-04":{"draws":9,"losses":16,"wins":89},"GB2-05":{"draws":0,"losses":10,"wins":110},"GB2-06":{"draws":6,"losses":1,"wins":111},"GB2-07":{"draws":0,"losses":7,"wins":117},"GB2-08":{"draws":0,"losses":3,"wins":119}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":17,"wins":100},"GB2-02":{"draws":5,"losses":5,"wins":94},"GB2-03":{"draws":4,"losses":4,"wins":124},"GB2-04":{"draws":9,"losses":16,"wins":89},"GB2-05":{"draws":0,"losses":10,"wins":110},"GB2-06":{"draws":6,"losses":1,"wins":111},"GB2-07":{"draws":0,"losses":7,"wins":117},"GB2-08":{"draws":0,"losses":3,"wins":119}}},"per_game_raw_elo_all":{"GB2-01":1815.5200389805461,"GB2-02":1853.1159310241208,"GB2-03":1936.8107808065536,"GB2-04":1687.907530090911,"GB2-05":2020.2255987992348,"GB2-06":1990.389327840918,"GB2-07":2001.0721024068134,"GB2-08":1970.7628576902343},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1909.6549229355353,"GB2-02":1947.6719384807805,"GB2-03":1992.7001425373535,"GB2-04":1848.9541347501813,"GB2-05":2039.1287831280288,"GB2-06":2147.0653496170057,"GB2-07":2014.2567973068285,"GB2-08":2166.2747750373137},"medium":{"GB2-01":1621.4320540516248,"GB2-02":1834.7977187233885,"GB2-03":1950.600091461118,"GB2-04":1632.0099106719301,"GB2-05":2007.3708129337665,"GB2-06":1991.6471169850581,"GB2-07":2100.234118121552,"GB2-08":1843.3344616499016},"none":{"GB2-01":1915.473139954479,"GB2-02":1776.8781358681929,"GB2-03":1867.1321084211895,"GB2-04":1582.7585448506213,"GB2-05":2014.1772003359092,"GB2-06":1832.4555169206908,"GB2-07":1888.7253917920593,"GB2-08":1902.679336383488}},"per_game_tracks":{"highest":{"GB2-01":76.96244740112121,"GB2-02":100.0,"GB2-03":89.4371849014492,"GB2-04":88.60770691415766,"GB2-05":91.18583886791443,"GB2-06":100.0,"GB2-07":92.8375786081501,"GB2-08":100.0},"medium":{"GB2-01":53.28397853663737,"GB2-02":79.6736533842389,"GB2-03":85.0569619016003,"GB2-04":52.70456806499455,"GB2-05":88.69644055635243,"GB2-06":87.8458198199057,"GB2-07":100.0,"GB2-08":70.21241367175236},"none":{"GB2-01":77.44093849930564,"GB2-02":69.24351690590547,"GB2-03":76.3726878991664,"GB2-04":44.553723611281114,"GB2-05":89.2299699098686,"GB2-06":75.39655078902038,"GB2-07":82.38006707268947,"GB2-08":75.68630623327066}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":92.37884458659907,"medium":77.18422949193521,"none":73.78797011506347},"reasoning_agg":{"highest":{"max":100.0,"mean":92.37884458659907,"min":76.96244740112121},"medium":{"max":100.0,"mean":77.18422949193521,"min":52.70456806499455},"none":{"max":89.2299699098686,"mean":73.78797011506347,"min":44.553723611281114}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":87.99692027660019,"reasoning_variance":18.5908744715356,"reliability_score":98.00341407901401,"uncertainty_avg":1.9965859209859982,"uncertainty_penalty":6.879905545400945},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":92.53656749876441,"reliability_score":97.98756493747796,"uncertainty_avg":2.0124350625220444,"uncertainty_penalty":0.1577229121653403},"medium":{"ceiling_score":100.0,"expected_score":84.9743692745461,"reliability_score":98.0351123620861,"uncertainty_avg":1.9648876379139057,"uncertainty_penalty":7.790139782610893},"none":{"ceiling_score":89.2299699098686,"expected_score":86.47982405649006,"reliability_score":97.98756493747796,"uncertainty_avg":2.0124350625220444,"uncertainty_penalty":12.691853941426587}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:1cfce33a4d60e796","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.07445},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.138875000000001},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570124999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.1388750000000005},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.074450000000002}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":61.26075171069582,"highest":64.24813629810149,"medium":62.639402761935784,"none":59.71965002282272},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["end_turn"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":48,"requested_max_output_token_observations":48,"requested_max_output_tokens":[128000],"total_output_tokens":1230744,"total_reasoning_output_tokens":878158,"total_visible_output_tokens":352586,"visible_token_observations":48},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-06"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_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":14,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_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":13,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":13,"first_pass_rate":0.8125,"model_code_failure_rate":0.1875,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-09-10T04:58:29Z","match_totals_all":{"draws":411,"losses":488,"wins":1898},"match_totals_tracks":{"highest":{"draws":40,"losses":115,"wins":471},"medium":{"draws":123,"losses":154,"wins":679},"none":{"draws":248,"losses":219,"wins":748}},"model_slug":"claude-opus-5","overall":{"max":85.05036844756516,"mean":59.77996525764912,"min":36.957881306791684},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.610603965911444,"GB2-02":42.027298685176675,"GB2-03":65.43559754230012,"GB2-04":65.0016466552378,"GB2-05":77.46597085447985,"GB2-07":85.05036844756516,"GB2-08":62.145467936039324},"per_game_all":{"GB2-01":57.31848592203844,"GB2-02":44.81708155066254,"GB2-03":59.41672458562629,"GB2-04":46.446661826211944,"GB2-05":78.44276454426414,"GB2-07":78.3722520000503,"GB2-08":64.01129154601706},"per_game_match_totals_all":{"GB2-01":{"draws":100,"losses":89,"wins":248},"GB2-02":{"draws":103,"losses":26,"wins":157},"GB2-03":{"draws":29,"losses":58,"wins":229},"GB2-04":{"draws":137,"losses":86,"wins":173},"GB2-05":{"draws":0,"losses":48,"wins":360},"GB2-06":{"draws":3,"losses":3,"wins":60},"GB2-07":{"draws":0,"losses":41,"wins":209},"GB2-08":{"draws":39,"losses":137,"wins":462}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":37,"wins":62},"GB2-02":{"draws":20,"losses":11,"wins":35},"GB2-03":{"draws":0,"losses":7,"wins":65},"GB2-04":{"draws":19,"losses":14,"wins":79},"GB2-05":{"draws":0,"losses":15,"wins":83},"GB2-07":{"draws":0,"losses":1,"wins":51},"GB2-08":{"draws":0,"losses":30,"wins":96}},"medium":{"GB2-01":{"draws":15,"losses":37,"wins":102},"GB2-02":{"draws":38,"losses":8,"wins":54},"GB2-03":{"draws":4,"losses":12,"wins":98},"GB2-04":{"draws":66,"losses":34,"wins":46},"GB2-05":{"draws":0,"losses":20,"wins":134},"GB2-07":{"draws":0,"losses":24,"wins":108},"GB2-08":{"draws":0,"losses":19,"wins":137}},"none":{"GB2-01":{"draws":84,"losses":15,"wins":84},"GB2-02":{"draws":45,"losses":7,"wins":68},"GB2-03":{"draws":25,"losses":39,"wins":66},"GB2-04":{"draws":52,"losses":38,"wins":48},"GB2-05":{"draws":0,"losses":13,"wins":143},"GB2-06":{"draws":3,"losses":3,"wins":60},"GB2-07":{"draws":0,"losses":16,"wins":50},"GB2-08":{"draws":39,"losses":88,"wins":229}}},"per_game_raw_elo_all":{"GB2-01":1681.9247879849172,"GB2-02":1660.8224863911817,"GB2-03":1725.331533247294,"GB2-04":1606.0033459502622,"GB2-05":1889.1825234358814,"GB2-07":1855.819973200505,"GB2-08":1782.8429491743057},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1632.891716608698,"GB2-02":1655.3294738631357,"GB2-03":1793.0866148930616,"GB2-04":1722.0204237619773,"GB2-05":1884.381955867567,"GB2-07":1939.9466836858041,"GB2-08":1769.8149510159715},"medium":{"GB2-01":1729.9610845756647,"GB2-02":1661.2356908966067,"GB2-03":1802.657390906043,"GB2-04":1548.6162307333443,"GB2-05":1864.477227519094,"GB2-07":1839.0854245052378,"GB2-08":1877.7575378139375},"none":{"GB2-01":1682.921562770389,"GB2-02":1665.9022944138023,"GB2-03":1580.2505939427776,"GB2-04":1547.3733833554654,"GB2-05":1918.6883869209828,"GB2-06":1897.0527582969269,"GB2-07":1788.427811410473,"GB2-08":1700.9563586930085}},"per_game_tracks":{"highest":{"GB2-01":52.610603965911444,"GB2-02":42.027298685176675,"GB2-03":65.43559754230012,"GB2-04":65.0016466552378,"GB2-05":77.46597085447985,"GB2-07":85.05036844756516,"GB2-08":62.145467936039324},"medium":{"GB2-01":61.43562510044728,"GB2-02":45.36178169780819,"GB2-03":67.80798395215069,"GB2-04":37.38045751660635,"GB2-05":76.79549207854782,"GB2-07":77.13223675647313,"GB2-08":72.56224223151698},"none":{"GB2-01":57.90922869975661,"GB2-02":47.062164269002736,"GB2-03":45.00659226242805,"GB2-04":36.957881306791684,"GB2-05":81.06683069976471,"GB2-06":79.49418767823046,"GB2-07":72.9341507961126,"GB2-08":57.326164470494916}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":60.99810969744108,"medium":60.58283905311381,"none":57.75894702239247},"reasoning_agg":{"highest":{"max":85.05036844756516,"mean":60.99810969744108,"min":42.027298685176675},"medium":{"max":77.13223675647313,"mean":60.58283905311381,"min":37.38045751660635},"none":{"max":81.06683069976471,"mean":57.75894702239247,"min":36.957881306791684}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":85.05036844756516,"expected_score":66.15919448915264,"reasoning_variance":3.239162675048611,"reliability_score":80.19260854361838,"uncertainty_avg":19.807391456381627,"uncertainty_penalty":6.379229231503523},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.05036844756516,"expected_score":63.049394870009635,"reliability_score":71.42996580735348,"uncertainty_avg":28.57003419264652,"uncertainty_penalty":2.051285172568555},"medium":{"ceiling_score":77.13223675647313,"expected_score":70.01195784384633,"reliability_score":82.99026422392413,"uncertainty_avg":17.00973577607588,"uncertainty_penalty":9.429118790732524},"none":{"ceiling_score":81.06683069976471,"expected_score":69.7392019094017,"reliability_score":85.72105587736125,"uncertainty_avg":14.278944122638753,"uncertainty_penalty":11.980254887009231}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:e3cbd9a07a4054c5","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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},"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.0229249999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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},"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},"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},"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.227983749999998},"codegen_output_tokens":{"attempt_count":25,"output_max":35149,"output_mean":11102.833333333334,"output_min":1851,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":35149,"output_mean":24638.75,"output_min":19522,"run_count":8},"medium":{"attempt_count":8,"output_max":6769,"output_mean":6021.5,"output_min":5176,"run_count":8},"none":{"attempt_count":8,"output_max":3391,"output_mean":2648.25,"output_min":1851,"run_count":8}},"display_name":"GPT-5.6 Sol","economics":{"all":58.73272306177361,"highest":75.3716089885212,"medium":56.18273720189021,"none":44.64382299490942},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-09-10T11:12:01Z","match_totals_all":{"draws":779,"losses":1411,"wins":2847},"match_totals_tracks":{"highest":{"draws":112,"losses":314,"wins":1168},"medium":{"draws":251,"losses":516,"wins":858},"none":{"draws":416,"losses":581,"wins":821}},"model_slug":"gpt-5-6-sol","overall":{"max":95.50333681723484,"mean":58.73272306177361,"min":13.272080636024716},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.6005678523054,"GB2-02":70.45903844353168,"GB2-03":76.6845715154764,"GB2-04":81.74661371399337,"GB2-05":65.02038273879721,"GB2-06":85.26032097966694,"GB2-07":95.50333681723484,"GB2-08":70.6980398471637},"per_game_all":{"GB2-01":63.35359692963154,"GB2-02":40.91152862425274,"GB2-03":55.54853555270193,"GB2-04":59.59918473480324,"GB2-05":62.22674554734175,"GB2-06":57.2561122696012,"GB2-07":68.34716248479846,"GB2-08":62.61891835105801},"per_game_match_totals_all":{"GB2-01":{"draws":45,"losses":218,"wins":347},"GB2-02":{"draws":295,"losses":63,"wins":180},"GB2-03":{"draws":117,"losses":195,"wins":349},"GB2-04":{"draws":217,"losses":90,"wins":289},"GB2-05":{"draws":0,"losses":198,"wins":446},"GB2-06":{"draws":36,"losses":256,"wins":397},"GB2-07":{"draws":0,"losses":207,"wins":472},"GB2-08":{"draws":69,"losses":184,"wins":367}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":7,"losses":80,"wins":116},"GB2-02":{"draws":47,"losses":12,"wins":109},"GB2-03":{"draws":5,"losses":36,"wins":170},"GB2-04":{"draws":29,"losses":18,"wins":139},"GB2-05":{"draws":0,"losses":60,"wins":146},"GB2-06":{"draws":24,"losses":25,"wins":157},"GB2-07":{"draws":0,"losses":23,"wins":185},"GB2-08":{"draws":0,"losses":60,"wins":146}},"medium":{"GB2-01":{"draws":37,"losses":77,"wins":90},"GB2-02":{"draws":94,"losses":18,"wins":56},"GB2-03":{"draws":25,"losses":75,"wins":109},"GB2-04":{"draws":43,"losses":21,"wins":122},"GB2-05":{"draws":0,"losses":58,"wins":150},"GB2-06":{"draws":5,"losses":121,"wins":106},"GB2-07":{"draws":0,"losses":71,"wins":139},"GB2-08":{"draws":47,"losses":75,"wins":86}},"none":{"GB2-01":{"draws":1,"losses":61,"wins":141},"GB2-02":{"draws":154,"losses":33,"wins":15},"GB2-03":{"draws":87,"losses":84,"wins":70},"GB2-04":{"draws":145,"losses":51,"wins":28},"GB2-05":{"draws":0,"losses":80,"wins":150},"GB2-06":{"draws":7,"losses":110,"wins":134},"GB2-07":{"draws":0,"losses":113,"wins":148},"GB2-08":{"draws":22,"losses":49,"wins":135}}},"per_game_raw_elo_all":{"GB2-01":1735.492842524375,"GB2-02":1610.3827765465003,"GB2-03":1659.2278034756637,"GB2-04":1664.7598318743778,"GB2-05":1660.5885209154967,"GB2-06":1590.2231889923644,"GB2-07":1711.137338481298,"GB2-08":1752.7007306698345},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1665.561627843407,"GB2-02":1775.3612754351213,"GB2-03":1862.9174588920664,"GB2-04":1799.4467778247522,"GB2-05":1696.766819796055,"GB2-06":1949.7197444262995,"GB2-07":2038.1479062581575,"GB2-08":1840.334484911061},"medium":{"GB2-01":1712.4066257257862,"GB2-02":1600.6853646986274,"GB2-03":1649.65448556946,"GB2-04":1740.1002470017625,"GB2-05":1841.9988908139892,"GB2-06":1302.406805806133,"GB2-07":1629.7367324775714,"GB2-08":1614.9647465144133},"none":{"GB2-01":1828.5102740039317,"GB2-02":1455.101689505752,"GB2-03":1465.111465965465,"GB2-04":1454.7324707966186,"GB2-05":1442.999852136446,"GB2-06":1518.5430167446611,"GB2-07":1465.5273767081653,"GB2-08":1802.802960584029}},"per_game_tracks":{"highest":{"GB2-01":57.6005678523054,"GB2-02":70.45903844353168,"GB2-03":76.6845715154764,"GB2-04":81.74661371399337,"GB2-05":65.02038273879721,"GB2-06":85.26032097966694,"GB2-07":95.50333681723484,"GB2-08":70.6980398471637},"medium":{"GB2-01":61.45873236257106,"GB2-02":39.00346679320183,"GB2-03":54.48243593724166,"GB2-04":71.92507204628161,"GB2-05":76.41507877251388,"GB2-06":34.76336759556245,"GB2-07":61.491210707100855,"GB2-08":49.92253340064839},"none":{"GB2-01":71.00149057401816,"GB2-02":13.272080636024716,"GB2-03":35.47859920538773,"GB2-04":25.12586844413473,"GB2-05":45.24477513071418,"GB2-06":51.74464823357423,"GB2-07":48.046939930059665,"GB2-08":67.23618180536194}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":75.3716089885212,"medium":56.18273720189021,"none":44.64382299490942},"reasoning_agg":{"highest":{"max":95.50333681723484,"mean":75.3716089885212,"min":57.6005678523054},"medium":{"max":76.41507877251388,"mean":56.18273720189021,"min":34.76336759556245},"none":{"max":71.00149057401816,"mean":44.64382299490942,"min":13.272080636024716}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":95.50333681723484,"expected_score":58.81009131019727,"reasoning_variance":30.727785993611782,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.07736824842366019},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":95.50333681723484,"expected_score":71.55719987694636,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.8144091115748466},"medium":{"ceiling_score":76.41507877251388,"expected_score":57.8621539910599,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.6794167891696858},"none":{"ceiling_score":71.00149057401816,"expected_score":47.010920062585555,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.3670970676761343}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:3abeca073b191728","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.5256212,"mean":0.38805244562499996,"median":0.41839404999999996,"min":0.063446985,"recorded_attempt_count":8,"run_count":8,"total":3.104419565},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"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},"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},"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.2555551600000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181687999999996},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.5256212,"mean":0.38805244562499996,"median":0.41839404999999996,"min":0.063446985,"recorded_attempt_count":8,"run_count":8,"total":3.1044195650000006}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"evidence_basis":"Provider-reported","max":0.5256212,"mean":0.19965798354166664,"median":0.1553977,"min":0.0217974,"recorded_attempt_count":26,"run_count":24,"total":4.791791604999999},"codegen_latency_ms":{"attempt_count":26,"max_ms":2052448,"mean_ms":650299.2083333334,"min_ms":28293,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":2052448,"mean_ms":1191674.625,"min_ms":447340,"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":26,"output_max":117143,"output_mean":43372.708333333336,"output_min":2671,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":117143,"output_mean":87116.125,"output_min":13152,"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":57.61725428837766,"highest":78.85594773673789,"medium":59.35550035157464,"none":35.13669356616318},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"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,"reconciliation_get_attempts":120,"total_output_tokens":1040945,"total_reasoning_output_tokens":925880,"total_visible_output_tokens":115065,"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":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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":7,"first_pass_admitted":7,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-04"],"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}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-09-10T11:07:59Z","match_totals_all":{"draws":625,"losses":821,"wins":1399},"match_totals_tracks":{"highest":{"draws":101,"losses":112,"wins":625},"medium":{"draws":176,"losses":321,"wins":510},"none":{"draws":348,"losses":388,"wins":264}},"model_slug":"z-ai-glm-5-3","overall":{"max":98.77394998739801,"mean":57.782713884825235,"min":10.263403044539475},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":5,"overall_ranking_status":"partial","per_game":{"GB2-01":79.47185662559322,"GB2-02":35.48069279237866,"GB2-03":79.03699890255805,"GB2-05":92.02404202093135,"GB2-06":90.60154698973984,"GB2-07":98.77394998739801,"GB2-08":76.60254683856613},"per_game_all":{"GB2-01":57.563943922733245,"GB2-02":23.503460553006732,"GB2-03":54.948246634876774,"GB2-05":66.02408177504003,"GB2-06":78.58177533533704,"GB2-07":75.8169040289568,"GB2-08":46.88236776869306},"per_game_match_totals_all":{"GB2-01":{"draws":57,"losses":157,"wins":198},"GB2-02":{"draws":231,"losses":35,"wins":48},"GB2-03":{"draws":101,"losses":96,"wins":198},"GB2-04":{"draws":84,"losses":38,"wins":106},"GB2-05":{"draws":0,"losses":152,"wins":222},"GB2-06":{"draws":33,"losses":105,"wins":244},"GB2-07":{"draws":0,"losses":122,"wins":250},"GB2-08":{"draws":119,"losses":116,"wins":133}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":16,"wins":92},"GB2-02":{"draws":61,"losses":11,"wins":32},"GB2-03":{"draws":16,"losses":23,"wins":93},"GB2-05":{"draws":0,"losses":13,"wins":107},"GB2-06":{"draws":14,"losses":11,"wins":93},"GB2-07":{"draws":0,"losses":10,"wins":114},"GB2-08":{"draws":0,"losses":28,"wins":94}},"medium":{"GB2-01":{"draws":26,"losses":81,"wins":67},"GB2-02":{"draws":71,"losses":17,"wins":16},"GB2-03":{"draws":21,"losses":39,"wins":71},"GB2-04":{"draws":14,"losses":14,"wins":86},"GB2-05":{"draws":0,"losses":61,"wins":59},"GB2-06":{"draws":11,"losses":7,"wins":100},"GB2-07":{"draws":0,"losses":52,"wins":72},"GB2-08":{"draws":33,"losses":50,"wins":39}},"none":{"GB2-01":{"draws":21,"losses":60,"wins":39},"GB2-02":{"draws":99,"losses":7,"wins":0},"GB2-03":{"draws":64,"losses":34,"wins":34},"GB2-04":{"draws":70,"losses":24,"wins":20},"GB2-05":{"draws":0,"losses":78,"wins":56},"GB2-06":{"draws":8,"losses":87,"wins":51},"GB2-07":{"draws":0,"losses":60,"wins":64},"GB2-08":{"draws":86,"losses":38,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1671.5336085078072,"GB2-02":1522.7568829984787,"GB2-03":1661.2570631389854,"GB2-05":1717.4873056374097,"GB2-06":1871.96020017359,"GB2-07":1809.9415359283933,"GB2-08":1590.3066158295921},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1940.1681080558346,"GB2-02":1589.3898232530091,"GB2-03":1892.739852440075,"GB2-05":2049.821981812471,"GB2-06":2026.885219432552,"GB2-07":2085.516679771956,"GB2-08":1912.6127034227568},"medium":{"GB2-01":1509.5022233610664,"GB2-02":1529.8916581476587,"GB2-03":1677.0077846493843,"GB2-04":1826.3218602875163,"GB2-05":1586.236607414437,"GB2-06":2093.753980134374,"GB2-07":1708.102176119845,"GB2-08":1572.2266605384239},"none":{"GB2-01":1564.9304941065209,"GB2-02":1448.9891675947683,"GB2-03":1414.0235523274969,"GB2-04":1392.7280216533547,"GB2-05":1516.4033276853204,"GB2-06":1495.241400953843,"GB2-07":1636.2057518933793,"GB2-08":1286.0804835275962}},"per_game_tracks":{"highest":{"GB2-01":79.47185662559322,"GB2-02":35.48069279237866,"GB2-03":79.03699890255805,"GB2-05":92.02404202093135,"GB2-06":90.60154698973984,"GB2-07":98.77394998739801,"GB2-08":76.60254683856613},"medium":{"GB2-01":44.58269393252839,"GB2-02":24.766285822102056,"GB2-03":56.577906094603094,"GB2-04":84.862183400186,"GB2-05":55.68517523467149,"GB2-06":95.8308881823799,"GB2-07":67.33308059374065,"GB2-08":45.20578955238555},"none":{"GB2-01":48.63728121007812,"GB2-02":10.263403044539475,"GB2-03":29.22983490746917,"GB2-04":13.104662042950768,"GB2-05":50.36302806951727,"GB2-06":49.3128908338914,"GB2-07":61.34368150573174,"GB2-08":18.83876691512749}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":78.85594773673789,"medium":59.35550035157464,"none":35.13669356616318},"reasoning_agg":{"highest":{"max":98.77394998739801,"mean":78.85594773673789,"min":35.48069279237866},"medium":{"max":95.8308881823799,"mean":59.35550035157464,"min":24.766285822102056},"none":{"max":61.34368150573174,"mean":35.13669356616318,"min":10.263403044539475}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":98.77394998739801,"expected_score":58.949437578654035,"reasoning_variance":43.71925417057471,"reliability_score":98.44773122229853,"uncertainty_avg":1.552268777701476,"uncertainty_penalty":1.1667236938288},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":98.77394998739801,"expected_score":77.7355047212894,"reliability_score":98.11082284454848,"uncertainty_avg":1.889177155451524,"uncertainty_penalty":-1.1204430154484868},"medium":{"ceiling_score":95.8308881823799,"expected_score":62.26217239637314,"reliability_score":98.24818054390428,"uncertainty_avg":1.7518194560957234,"uncertainty_penalty":2.9066720447984977},"none":{"ceiling_score":61.34368150573174,"expected_score":36.11899475833668,"reliability_score":98.6113338226455,"uncertainty_avg":1.3886661773544895,"uncertainty_penalty":0.9823011921735016}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:d7f80fef92b21cfc","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":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},"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},"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.3088499999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"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},"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.3088499999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":0.7608541666666667,"median":0.47084000000000004,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":18.260500000000004},"codegen_output_tokens":{"attempt_count":24,"output_max":40578,"output_mean":12704.708333333334,"output_min":2179,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":40578,"output_mean":26899.0,"output_min":17366,"run_count":8},"medium":{"attempt_count":8,"output_max":12403,"output_mean":7955.375,"output_min":4188,"run_count":8},"none":{"attempt_count":8,"output_max":4224,"output_mean":3259.75,"output_min":2179,"run_count":8}},"display_name":"Claude Fable 5","economics":{"all":51.46007326840031,"highest":59.95385418281583,"medium":49.646949204317174,"none":44.77941641806791},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-09-10T11:07:59Z","match_totals_all":{"draws":686,"losses":1009,"wins":1326},"match_totals_tracks":{"highest":{"draws":169,"losses":289,"wins":514},"medium":{"draws":197,"losses":344,"wins":413},"none":{"draws":320,"losses":376,"wins":399}},"model_slug":"claude-fable-5","overall":{"max":85.88512253636422,"mean":51.4600732684003,"min":6.646568053595592},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":78.22953456127536,"GB2-02":45.92580124934712,"GB2-03":58.89408767141809,"GB2-04":58.99307917629111,"GB2-05":51.51493494903386,"GB2-06":85.88512253636422,"GB2-07":62.58866323477045,"GB2-08":37.59961008402652},"per_game_all":{"GB2-01":60.54664179171646,"GB2-02":26.157809073959942,"GB2-03":31.651823760079157,"GB2-04":37.41712096635185,"GB2-05":57.637255469903955,"GB2-06":75.72573316104062,"GB2-07":61.932669648263534,"GB2-08":60.61153227588695},"per_game_match_totals_all":{"GB2-01":{"draws":30,"losses":136,"wins":192},"GB2-02":{"draws":187,"losses":42,"wins":83},"GB2-03":{"draws":168,"losses":127,"wins":101},"GB2-04":{"draws":202,"losses":111,"wins":114},"GB2-05":{"draws":0,"losses":190,"wins":170},"GB2-06":{"draws":39,"losses":96,"wins":221},"GB2-07":{"draws":0,"losses":208,"wins":218},"GB2-08":{"draws":60,"losses":99,"wins":227}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":26,"wins":92},"GB2-02":{"draws":36,"losses":16,"wins":52},"GB2-03":{"draws":47,"losses":17,"wins":68},"GB2-04":{"draws":16,"losses":23,"wins":75},"GB2-05":{"draws":0,"losses":70,"wins":50},"GB2-06":{"draws":11,"losses":21,"wins":86},"GB2-07":{"draws":0,"losses":64,"wins":60},"GB2-08":{"draws":59,"losses":52,"wins":31}},"medium":{"GB2-01":{"draws":15,"losses":54,"wins":51},"GB2-02":{"draws":61,"losses":20,"wins":23},"GB2-03":{"draws":45,"losses":75,"wins":12},"GB2-04":{"draws":58,"losses":33,"wins":23},"GB2-05":{"draws":0,"losses":59,"wins":61},"GB2-06":{"draws":18,"losses":30,"wins":70},"GB2-07":{"draws":0,"losses":57,"wins":67},"GB2-08":{"draws":0,"losses":16,"wins":106}},"none":{"GB2-01":{"draws":15,"losses":56,"wins":49},"GB2-02":{"draws":90,"losses":6,"wins":8},"GB2-03":{"draws":76,"losses":35,"wins":21},"GB2-04":{"draws":128,"losses":55,"wins":16},"GB2-05":{"draws":0,"losses":61,"wins":59},"GB2-06":{"draws":10,"losses":45,"wins":65},"GB2-07":{"draws":0,"losses":87,"wins":91},"GB2-08":{"draws":1,"losses":31,"wins":90}}},"per_game_raw_elo_all":{"GB2-01":1709.8439108702014,"GB2-02":1537.6189248472208,"GB2-03":1437.3022425687177,"GB2-04":1536.6304142210038,"GB2-05":1611.139856380016,"GB2-06":1836.5634113629997,"GB2-07":1641.3160392061566,"GB2-08":1738.3747190501601},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1925.0620812038217,"GB2-02":1647.3925469912467,"GB2-03":1699.1383870159802,"GB2-04":1670.008152813912,"GB2-05":1533.0356527584136,"GB2-06":1966.5752403122613,"GB2-07":1651.1504455479346,"GB2-08":1487.147621438758},"medium":{"GB2-01":1601.767086979764,"GB2-02":1536.1931602057512,"GB2-03":1235.3161010419403,"GB2-04":1491.3894653501343,"GB2-05":1630.175690041946,"GB2-06":1854.3315939739264,"GB2-07":1730.9511982705933,"GB2-08":1885.1060573978139},"none":{"GB2-01":1602.7025644270188,"GB2-02":1429.2710673446647,"GB2-03":1377.4522396482325,"GB2-04":1448.4936244989651,"GB2-05":1670.208226339689,"GB2-06":1688.7833998028116,"GB2-07":1541.8464737999418,"GB2-08":1842.870478313909}},"per_game_tracks":{"highest":{"GB2-01":78.22953456127536,"GB2-02":45.92580124934712,"GB2-03":58.89408767141809,"GB2-04":58.99307917629111,"GB2-05":51.51493494903386,"GB2-06":85.88512253636422,"GB2-07":62.58866323477045,"GB2-08":37.59961008402652},"medium":{"GB2-01":51.666728499497296,"GB2-02":25.901057918937127,"GB2-03":10.636544202241724,"GB2-04":29.432616968483536,"GB2-05":59.12940915250124,"GB2-06":77.10732678766597,"GB2-07":69.23653982560063,"GB2-08":74.06537027960984},"none":{"GB2-01":51.74366231437673,"GB2-02":6.646568053595592,"GB2-03":25.424839406577654,"GB2-04":23.825666754280896,"GB2-05":62.26742230817677,"GB2-06":64.18475015909165,"GB2-07":53.97280588441953,"GB2-08":70.16961646402447}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":59.95385418281583,"medium":49.646949204317174,"none":44.77941641806791},"reasoning_agg":{"highest":{"max":85.88512253636422,"mean":59.95385418281583,"min":37.59961008402652},"medium":{"max":77.10732678766597,"mean":49.646949204317174,"min":10.636544202241724},"none":{"max":70.16961646402447,"mean":44.77941641806791,"min":6.646568053595592}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":85.88512253636422,"expected_score":51.33697436500317,"reasoning_variance":15.174437764747921,"reliability_score":98.25094909939372,"uncertainty_avg":1.7490509006062767,"uncertainty_penalty":-0.12309890339712837},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.88512253636422,"expected_score":55.44044596031439,"reliability_score":98.15425015414941,"uncertainty_avg":1.8457498458505928,"uncertainty_penalty":-4.51340822250144},"medium":{"ceiling_score":77.10732678766597,"expected_score":50.994001152753796,"reliability_score":98.0351123620861,"uncertainty_avg":1.9648876379139057,"uncertainty_penalty":1.3470519484366221},"none":{"ceiling_score":70.16961646402447,"expected_score":47.57647598194135,"reliability_score":98.56348478194568,"uncertainty_avg":1.4365152180543317,"uncertainty_penalty":2.7970595638734395}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:94ba2258c434ca13","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":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},"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"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},"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},"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},"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},"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":52.51262927626637,"highest":65.15382836806302,"medium":46.19996042414856,"none":37.161284828496534},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":976201,"total_reasoning_output_tokens":819733,"total_visible_output_tokens":156468,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"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}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-09-10T11:11:29Z","match_totals_all":{"draws":1407,"losses":1379,"wins":2166},"match_totals_tracks":{"highest":{"draws":227,"losses":321,"wins":920},"medium":{"draws":598,"losses":442,"wins":716},"none":{"draws":582,"losses":616,"wins":530}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":48.791985606250556,"min":8.247425935777672},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":91.89049593436994,"GB2-03":26.86648580703239,"GB2-04":38.841449244307675,"GB2-05":90.58932194330986,"GB2-06":79.65866479600288,"GB2-07":79.3166000382083,"GB2-08":48.913780813210096},"per_game_all":{"GB2-01":85.3339963012607,"GB2-03":26.881546114068232,"GB2-04":22.710705709421593,"GB2-05":73.75523194727351,"GB2-06":70.30975859966283,"GB2-07":53.49922153382375,"GB2-08":35.09794472835399},"per_game_match_totals_all":{"GB2-01":{"draws":21,"losses":67,"wins":520},"GB2-02":{"draws":304,"losses":35,"wins":12},"GB2-03":{"draws":345,"losses":230,"wins":173},"GB2-04":{"draws":332,"losses":177,"wins":108},"GB2-05":{"draws":0,"losses":203,"wins":427},"GB2-06":{"draws":55,"losses":182,"wins":413},"GB2-07":{"draws":0,"losses":292,"wins":354},"GB2-08":{"draws":350,"losses":193,"wins":159}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":11,"wins":187},"GB2-03":{"draws":84,"losses":79,"wins":79},"GB2-04":{"draws":90,"losses":36,"wins":60},"GB2-05":{"draws":0,"losses":22,"wins":186},"GB2-06":{"draws":22,"losses":40,"wins":150},"GB2-07":{"draws":0,"losses":48,"wins":162},"GB2-08":{"draws":27,"losses":85,"wins":96}},"medium":{"GB2-01":{"draws":2,"losses":4,"wins":196},"GB2-02":{"draws":157,"losses":18,"wins":8},"GB2-03":{"draws":146,"losses":83,"wins":63},"GB2-04":{"draws":104,"losses":62,"wins":20},"GB2-05":{"draws":0,"losses":69,"wins":139},"GB2-06":{"draws":16,"losses":52,"wins":140},"GB2-07":{"draws":0,"losses":112,"wins":100},"GB2-08":{"draws":173,"losses":42,"wins":50}},"none":{"GB2-01":{"draws":15,"losses":52,"wins":137},"GB2-02":{"draws":147,"losses":17,"wins":4},"GB2-03":{"draws":115,"losses":68,"wins":31},"GB2-04":{"draws":138,"losses":79,"wins":28},"GB2-05":{"draws":0,"losses":112,"wins":102},"GB2-06":{"draws":17,"losses":90,"wins":123},"GB2-07":{"draws":0,"losses":132,"wins":92},"GB2-08":{"draws":150,"losses":66,"wins":13}}},"per_game_raw_elo_all":{"GB2-01":2002.8096456007695,"GB2-03":1382.2048353315542,"GB2-04":1441.4738372473942,"GB2-05":1807.936858252315,"GB2-06":1757.8730207177857,"GB2-07":1533.4679726038837,"GB2-08":1452.7660779301723},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2082.5792261697334,"GB2-03":1382.2840850584937,"GB2-04":1540.1929099684971,"GB2-05":2022.8237873577302,"GB2-06":1877.695734805393,"GB2-07":1843.711746417953,"GB2-08":1604.0284164228153},"medium":{"GB2-01":2181.186817301249,"GB2-02":1449.1968175126713,"GB2-03":1408.118451422626,"GB2-04":1362.819635098196,"GB2-05":1818.8623378508958,"GB2-06":1766.52793989414,"GB2-07":1389.9379293174322,"GB2-08":1409.8641566204983},"none":{"GB2-01":1744.6628933313261,"GB2-02":1429.894017870154,"GB2-03":1356.2119695135434,"GB2-04":1421.4089666754899,"GB2-05":1582.1244495483195,"GB2-06":1629.395387453824,"GB2-07":1366.7542420762652,"GB2-08":1344.405660747203}},"per_game_tracks":{"highest":{"GB2-01":91.89049593436994,"GB2-03":26.86648580703239,"GB2-04":38.841449244307675,"GB2-05":90.58932194330986,"GB2-06":79.65866479600288,"GB2-07":79.3166000382083,"GB2-08":48.913780813210096},"medium":{"GB2-01":100.0,"GB2-02":11.95411986023037,"GB2-03":29.79281756153531,"GB2-04":9.48709633237125,"GB2-05":74.60148377480539,"GB2-06":70.9445905573761,"GB2-07":41.52534176853236,"GB2-08":31.294233538337693},"none":{"GB2-01":64.11149296941215,"GB2-02":8.247425935777672,"GB2-03":23.985334973637,"GB2-04":19.803571551585858,"GB2-05":56.074890123705295,"GB2-06":60.326020445609515,"GB2-07":39.6557227947306,"GB2-08":25.08581983351418}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.01471156610656,"medium":46.19996042414856,"none":37.161284828496534},"reasoning_agg":{"highest":{"max":91.89049593436994,"mean":63.01471156610656,"min":26.86648580703239},"medium":{"max":100.0,"mean":46.19996042414856,"min":9.48709633237125},"none":{"max":64.11149296941215,"mean":37.161284828496534,"min":8.247425935777672}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":50.92640225156522,"reasoning_variance":25.85342673761003,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1344166453146656},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":91.89049593436994,"expected_score":59.55970020109676,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.4550113650098027},"medium":{"ceiling_score":100.0,"expected_score":45.17544274840512,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0245176757434393},"none":{"ceiling_score":64.11149296941215,"expected_score":38.151580885446286,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9902960569497523}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:d44a6fc0597186af","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"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},"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},"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},"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},"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},"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},"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":47.21221876040718,"highest":53.08560240806504,"medium":56.21231506536722,"none":32.338738807789284},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-09-10T11:06:41Z","match_totals_all":{"draws":876,"losses":1071,"wins":1175},"match_totals_tracks":{"highest":{"draws":242,"losses":371,"wins":471},"medium":{"draws":196,"losses":307,"wins":481},"none":{"draws":438,"losses":393,"wins":223}},"model_slug":"x-ai-grok-4-6","overall":{"max":82.4874985834472,"mean":47.21221876040718,"min":9.318441010342715},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":51.1641017896463,"GB2-02":64.57723496573112,"GB2-03":35.43919418965659,"GB2-04":23.843971005685763,"GB2-05":82.4874985834472,"GB2-06":58.886001713839136,"GB2-07":72.63465025280209,"GB2-08":35.65216676371213},"per_game_all":{"GB2-01":50.58102441990628,"GB2-02":30.75345710770108,"GB2-03":38.9457063335995,"GB2-04":26.78977119711466,"GB2-05":70.15934089620266,"GB2-06":50.335605535213325,"GB2-07":66.41946437000801,"GB2-08":43.71338022351193},"per_game_match_totals_all":{"GB2-01":{"draws":92,"losses":161,"wins":143},"GB2-02":{"draws":191,"losses":40,"wins":87},"GB2-03":{"draws":209,"losses":124,"wins":129},"GB2-04":{"draws":186,"losses":91,"wins":83},"GB2-05":{"draws":0,"losses":129,"wins":233},"GB2-06":{"draws":40,"losses":195,"wins":139},"GB2-07":{"draws":0,"losses":198,"wins":236},"GB2-08":{"draws":158,"losses":133,"wins":125}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":42,"losses":35,"wins":43},"GB2-02":{"draws":22,"losses":15,"wins":67},"GB2-03":{"draws":50,"losses":73,"wins":75},"GB2-04":{"draws":53,"losses":42,"wins":33},"GB2-05":{"draws":0,"losses":22,"wins":98},"GB2-06":{"draws":19,"losses":69,"wins":50},"GB2-07":{"draws":0,"losses":49,"wins":75},"GB2-08":{"draws":56,"losses":66,"wins":30}},"medium":{"GB2-01":{"draws":33,"losses":59,"wins":58},"GB2-02":{"draws":67,"losses":21,"wins":16},"GB2-03":{"draws":39,"losses":39,"wins":54},"GB2-04":{"draws":39,"losses":35,"wins":40},"GB2-05":{"draws":0,"losses":31,"wins":89},"GB2-06":{"draws":18,"losses":37,"wins":63},"GB2-07":{"draws":0,"losses":49,"wins":75},"GB2-08":{"draws":0,"losses":36,"wins":86}},"none":{"GB2-01":{"draws":17,"losses":67,"wins":42},"GB2-02":{"draws":102,"losses":4,"wins":4},"GB2-03":{"draws":120,"losses":12,"wins":0},"GB2-04":{"draws":94,"losses":14,"wins":10},"GB2-05":{"draws":0,"losses":76,"wins":46},"GB2-06":{"draws":3,"losses":89,"wins":26},"GB2-07":{"draws":0,"losses":100,"wins":86},"GB2-08":{"draws":102,"losses":31,"wins":9}}},"per_game_raw_elo_all":{"GB2-01":1587.00496665616,"GB2-02":1562.7824533792343,"GB2-03":1505.2969082707339,"GB2-04":1474.5153031820385,"GB2-05":1770.7887511024662,"GB2-06":1511.0821186415271,"GB2-07":1694.959779261021,"GB2-08":1553.9315261607928},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1595.6553927632428,"GB2-02":1750.965809215415,"GB2-03":1467.3750031545576,"GB2-04":1455.5379926925962,"GB2-05":1928.1615545368238,"GB2-06":1618.5910337917292,"GB2-07":1771.7419329089944,"GB2-08":1464.9229355470898},"medium":{"GB2-01":1621.1494007222223,"GB2-02":1494.3429910044993,"GB2-03":1657.7631805155133,"GB2-04":1533.4049458340203,"GB2-05":1820.235845616354,"GB2-06":1817.3175803869053,"GB2-07":1764.710116676486,"GB2-08":1803.034470342118},"none":{"GB2-01":1544.2101064830151,"GB2-02":1443.0385599177885,"GB2-03":1390.7525411421307,"GB2-04":1434.6029710194987,"GB2-05":1563.9688531542206,"GB2-06":1097.337741745947,"GB2-07":1548.4272881975826,"GB2-08":1393.8371725931713}},"per_game_tracks":{"highest":{"GB2-01":51.1641017896463,"GB2-02":64.57723496573112,"GB2-03":35.43919418965659,"GB2-04":23.843971005685763,"GB2-05":82.4874985834472,"GB2-06":58.886001713839136,"GB2-07":72.63465025280209,"GB2-08":35.65216676371213},"medium":{"GB2-01":53.57424063188693,"GB2-02":18.364695347029407,"GB2-03":54.5892798029273,"GB2-04":36.38596009636121,"GB2-05":74.02757258952171,"GB2-06":74.21271794604775,"GB2-07":72.04885820287524,"GB2-08":66.49519590628826},"none":{"GB2-01":47.0047308381856,"GB2-02":9.318441010342715,"GB2-03":26.808645008214626,"GB2-04":20.139382489297006,"GB2-05":53.96295151563907,"GB2-06":17.908096945753098,"GB2-07":54.57488465434671,"GB2-08":28.992778000535424}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.08560240806504,"medium":56.21231506536722,"none":32.338738807789284},"reasoning_agg":{"highest":{"max":82.4874985834472,"mean":53.08560240806504,"min":23.843971005685763},"medium":{"max":74.21271794604775,"mean":56.21231506536722,"min":18.364695347029407},"none":{"max":54.57488465434671,"mean":32.338738807789284,"min":9.318441010342715}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":82.4874985834472,"expected_score":45.55427819221204,"reasoning_variance":23.873576257577938,"reliability_score":98.60243284307568,"uncertainty_avg":1.397567156924323,"uncertainty_penalty":-1.6579405681951442},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.4874985834472,"expected_score":46.24084324640257,"reliability_score":98.78775007215067,"uncertainty_avg":1.2122499278493215,"uncertainty_penalty":-6.8447591616624734},"medium":{"ceiling_score":74.21271794604775,"expected_score":59.192061821793544,"reliability_score":98.24818054390428,"uncertainty_avg":1.7518194560957234,"uncertainty_penalty":2.979746756426323},"none":{"ceiling_score":54.57488465434671,"expected_score":31.229929508440005,"reliability_score":98.77136791317207,"uncertainty_avg":1.2286320868279244,"uncertainty_penalty":-1.1088092993492786}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:e15e99a40699c049","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"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},"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},"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2555334390339119}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"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},"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},"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},"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":46.76433524376487,"highest":52.4147765736809,"medium":47.189592263291324,"none":40.688636894322386},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-09-10T11:10:07Z","match_totals_all":{"draws":753,"losses":1170,"wins":1179},"match_totals_tracks":{"highest":{"draws":149,"losses":421,"wins":421},"medium":{"draws":335,"losses":322,"wins":389},"none":{"draws":269,"losses":427,"wins":369}},"model_slug":"google-gemini-3-8-flash","overall":{"max":79.59975068636147,"mean":46.76433524376487,"min":6.964348588339904},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.61951452356562,"GB2-02":35.81130147891559,"GB2-03":55.29646688144744,"GB2-04":42.45466162285314,"GB2-05":58.12885664164453,"GB2-06":79.59975068636147,"GB2-07":63.05535349326236,"GB2-08":39.35230726139709},"per_game_all":{"GB2-01":49.704998672694096,"GB2-02":16.892824749765992,"GB2-03":54.35736196260745,"GB2-04":35.128621830377945,"GB2-05":54.96119016398753,"GB2-06":74.86495956102432,"GB2-07":50.23705269776847,"GB2-08":37.96767231189313},"per_game_match_totals_all":{"GB2-01":{"draws":77,"losses":199,"wins":138},"GB2-02":{"draws":234,"losses":38,"wins":40},"GB2-03":{"draws":88,"losses":118,"wins":206},"GB2-04":{"draws":143,"losses":151,"wins":86},"GB2-05":{"draws":0,"losses":223,"wins":187},"GB2-06":{"draws":39,"losses":116,"wins":199},"GB2-07":{"draws":0,"losses":179,"wins":215},"GB2-08":{"draws":172,"losses":146,"wins":108}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":89,"wins":53},"GB2-02":{"draws":47,"losses":20,"wins":37},"GB2-03":{"draws":13,"losses":40,"wins":78},"GB2-04":{"draws":19,"losses":59,"wins":36},"GB2-05":{"draws":0,"losses":65,"wins":55},"GB2-06":{"draws":19,"losses":26,"wins":73},"GB2-07":{"draws":0,"losses":67,"wins":57},"GB2-08":{"draws":41,"losses":55,"wins":32}},"medium":{"GB2-01":{"draws":15,"losses":49,"wins":56},"GB2-02":{"draws":93,"losses":9,"wins":2},"GB2-03":{"draws":35,"losses":14,"wins":83},"GB2-04":{"draws":63,"losses":40,"wins":31},"GB2-05":{"draws":0,"losses":74,"wins":60},"GB2-06":{"draws":11,"losses":39,"wins":68},"GB2-07":{"draws":0,"losses":55,"wins":75},"GB2-08":{"draws":118,"losses":42,"wins":14}},"none":{"GB2-01":{"draws":52,"losses":61,"wins":29},"GB2-02":{"draws":94,"losses":9,"wins":1},"GB2-03":{"draws":40,"losses":64,"wins":45},"GB2-04":{"draws":61,"losses":52,"wins":19},"GB2-05":{"draws":0,"losses":84,"wins":72},"GB2-06":{"draws":9,"losses":51,"wins":58},"GB2-07":{"draws":0,"losses":57,"wins":83},"GB2-08":{"draws":13,"losses":49,"wins":62}}},"per_game_raw_elo_all":{"GB2-01":1575.6002449952655,"GB2-02":1486.1695475229672,"GB2-03":1654.9029922918926,"GB2-04":1523.9776741913283,"GB2-05":1574.8747620827726,"GB2-06":1825.6579404561664,"GB2-07":1501.909065526311,"GB2-08":1491.4323593050983},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1524.210378608972,"GB2-02":1591.2257260959202,"GB2-03":1664.6913668946706,"GB2-04":1570.0749915745469,"GB2-05":1617.4113539089935,"GB2-06":1886.2027783372537,"GB2-07":1656.7525702876383,"GB2-08":1507.9177376052087},"medium":{"GB2-01":1661.8397195918333,"GB2-02":1436.2471822852578,"GB2-03":1816.03943786734,"GB2-04":1507.4638147130581,"GB2-05":1578.0415953119314,"GB2-06":1837.9129732888766,"GB2-07":1502.9116984620532,"GB2-08":1380.4579125856314},"none":{"GB2-01":1540.7506367849912,"GB2-02":1431.0357341877234,"GB2-03":1483.9781721136667,"GB2-04":1494.39421628638,"GB2-05":1529.1713370273924,"GB2-06":1752.85806974237,"GB2-07":1346.062927829242,"GB2-08":1585.921427724455}},"per_game_tracks":{"highest":{"GB2-01":45.61951452356562,"GB2-02":35.81130147891559,"GB2-03":55.29646688144744,"GB2-04":42.45466162285314,"GB2-05":58.12885664164453,"GB2-06":79.59975068636147,"GB2-07":63.05535349326236,"GB2-08":39.35230726139709},"medium":{"GB2-01":56.60711141333341,"GB2-02":7.902824182042486,"GB2-03":71.05684421340891,"GB2-04":32.568416069453946,"GB2-05":55.194640367743276,"GB2-06":75.82334053498934,"GB2-07":50.3085497072,"GB2-08":28.05501161815919},"none":{"GB2-01":46.88837008118324,"GB2-02":6.964348588339904,"GB2-03":36.71877479296601,"GB2-04":30.362787798826755,"GB2-05":51.56007348257478,"GB2-06":69.17178746172216,"GB2-07":37.34725489284307,"GB2-08":46.49569805612314}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.4147765736809,"medium":47.189592263291324,"none":40.688636894322386},"reasoning_agg":{"highest":{"max":79.59975068636147,"mean":52.4147765736809,"min":35.81130147891559},"medium":{"max":75.82334053498934,"mean":47.189592263291324,"min":7.902824182042486},"none":{"max":69.17178746172216,"mean":40.688636894322386,"min":6.964348588339904}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":79.59975068636147,"expected_score":46.12900473133347,"reasoning_variance":11.726139679358518,"reliability_score":98.75460911525454,"uncertainty_avg":1.245390884745462,"uncertainty_penalty":-0.6353305124314019},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.59975068636147,"expected_score":46.264196146342826,"reliability_score":98.38079759604058,"uncertainty_avg":1.619202403959421,"uncertainty_penalty":-6.1505804273380775},"medium":{"ceiling_score":75.82334053498934,"expected_score":48.44464691198972,"reliability_score":98.89569075582716,"uncertainty_avg":1.1043092441728364,"uncertainty_penalty":1.2550546486983976},"none":{"ceiling_score":69.17178746172216,"expected_score":43.67817113566784,"reliability_score":98.98733899389588,"uncertainty_avg":1.0126610061041286,"uncertainty_penalty":2.989534241345453}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:4f9a7620e16b0214","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"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-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628249999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"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-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":7.44989}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":48.302373143980425,"highest":58.213545390771856,"medium":42.12697825585987,"none":43.264323114773916},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":31,"output_token_observations":25,"total_output_tokens":356249},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"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,"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}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-08-05T03:49:27Z","match_totals_all":{"draws":414,"losses":383,"wins":691},"match_totals_tracks":{"highest":{"draws":56,"losses":115,"wins":275},"medium":{"draws":228,"losses":134,"wins":210},"none":{"draws":130,"losses":134,"wins":206}},"model_slug":"claude-opus-4-8","overall":{"max":70.79490986212144,"mean":46.757715568855076,"min":10.886852859373011},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.97475225210645,"GB2-02":57.70515067638105,"GB2-04":48.94611757043748,"GB2-05":50.59206002860415,"GB2-06":70.79490986212144,"GB2-07":68.43443121361176,"GB2-08":58.04739613214064},"per_game_all":{"GB2-01":48.853893480242306,"GB2-02":27.893280770467314,"GB2-04":33.41785979531261,"GB2-05":49.8753978900228,"GB2-06":64.76970910633513,"GB2-07":63.7994985766048,"GB2-08":49.50697238887803},"per_game_match_totals_all":{"GB2-01":{"draws":45,"losses":61,"wins":104},"GB2-02":{"draws":126,"losses":5,"wins":35},"GB2-03":{"draws":27,"losses":10,"wins":9},"GB2-04":{"draws":144,"losses":31,"wins":37},"GB2-05":{"draws":0,"losses":124,"wins":142},"GB2-06":{"draws":9,"losses":37,"wins":120},"GB2-07":{"draws":0,"losses":63,"wins":141},"GB2-08":{"draws":63,"losses":52,"wins":103}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":20,"wins":39},"GB2-02":{"draws":18,"losses":1,"wins":31},"GB2-04":{"draws":24,"losses":10,"wins":28},"GB2-05":{"draws":0,"losses":46,"wins":46},"GB2-06":{"draws":1,"losses":5,"wins":34},"GB2-07":{"draws":0,"losses":14,"wins":46},"GB2-08":{"draws":0,"losses":19,"wins":51}},"medium":{"GB2-01":{"draws":15,"losses":26,"wins":33},"GB2-02":{"draws":54,"losses":3,"wins":1},"GB2-03":{"draws":27,"losses":10,"wins":9},"GB2-04":{"draws":69,"losses":10,"wins":5},"GB2-05":{"draws":0,"losses":40,"wins":56},"GB2-06":{"draws":0,"losses":9,"wins":51},"GB2-07":{"draws":0,"losses":20,"wins":50},"GB2-08":{"draws":63,"losses":16,"wins":5}},"none":{"GB2-01":{"draws":17,"losses":15,"wins":32},"GB2-02":{"draws":54,"losses":1,"wins":3},"GB2-04":{"draws":51,"losses":11,"wins":4},"GB2-05":{"draws":0,"losses":38,"wins":40},"GB2-06":{"draws":8,"losses":23,"wins":35},"GB2-07":{"draws":0,"losses":29,"wins":45},"GB2-08":{"draws":0,"losses":17,"wins":47}}},"per_game_raw_elo_all":{"GB2-01":1578.740214766977,"GB2-02":1561.6076125208601,"GB2-04":1525.7197589347186,"GB2-05":1518.1211140907026,"GB2-06":1714.0837764101695,"GB2-07":1678.1995067807147,"GB2-08":1629.6146389907237},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1628.124836644718,"GB2-02":1729.7796436772644,"GB2-04":1622.394595844658,"GB2-05":1526.3767034116547,"GB2-06":1799.4148654160863,"GB2-07":1736.7603940051758,"GB2-08":1722.852641589118},"medium":{"GB2-01":1507.3231224366134,"GB2-02":1465.8573511124794,"GB2-03":1474.0280879589282,"GB2-04":1471.2736621572235,"GB2-05":1589.0366798457355,"GB2-06":1783.9848192621998,"GB2-07":1738.437095863048,"GB2-08":1414.7365888718184},"none":{"GB2-01":1600.772685219599,"GB2-02":1489.1858427728368,"GB2-04":1483.4910188022745,"GB2-05":1438.9499590147173,"GB2-06":1558.851644552222,"GB2-07":1559.40103047392,"GB2-08":1751.2546865112345}},"per_game_tracks":{"highest":{"GB2-01":52.97475225210645,"GB2-02":57.70515067638105,"GB2-04":48.94611757043748,"GB2-05":50.59206002860415,"GB2-06":70.79490986212144,"GB2-07":68.43443121361176,"GB2-08":58.04739613214064},"medium":{"GB2-01":43.09168274262431,"GB2-02":10.886852859373011,"GB2-03":33.01106956211032,"GB2-04":25.09637172241155,"GB2-05":55.57150390760981,"GB2-06":70.46838917607434,"GB2-07":68.88596501989264,"GB2-08":30.00399105678296},"none":{"GB2-01":50.49524544599616,"GB2-02":15.08783877564788,"GB2-04":26.2110900930888,"GB2-05":43.46262973385445,"GB2-06":53.0458282808096,"GB2-07":54.07809949631,"GB2-08":60.46952997771049}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.302290501137556,"medium":42.12697825585987,"none":41.84387794956778},"reasoning_agg":{"highest":{"max":70.79490986212144,"mean":56.302290501137556,"min":48.94611757043748},"medium":{"max":70.46838917607434,"mean":42.12697825585987,"min":10.886852859373011},"none":{"max":60.46952997771049,"mean":41.84387794956778,"min":15.08783877564788}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":70.79490986212144,"expected_score":49.02290281871394,"reasoning_variance":14.458412551569772,"reliability_score":83.01055980742782,"uncertainty_avg":16.989440192572168,"uncertainty_penalty":2.2651872498588617},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.79490986212144,"expected_score":55.378050123540525,"reliability_score":80.20419354409972,"uncertainty_avg":19.795806455900276,"uncertainty_penalty":-0.9242403775970303},"medium":{"ceiling_score":70.46838917607434,"expected_score":43.43706098563221,"reliability_score":83.95599522494106,"uncertainty_avg":16.044004775058934,"uncertainty_penalty":1.3100827297723399},"none":{"ceiling_score":60.46952997771049,"expected_score":46.815879557630055,"reliability_score":82.99456337125866,"uncertainty_avg":17.005436628741343,"uncertainty_penalty":4.972001608062271}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:a74ca6e1542043ee","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"evidence_basis":"Provider-reported","max":0.273243,"mean":0.18666160714285715,"median":0.20966,"min":0.0,"recorded_attempt_count":7,"run_count":7,"total":1.30663125},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"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},"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110974999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"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},"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"evidence_basis":"Provider-reported","max":0.273243,"mean":0.18666160714285715,"median":0.20966,"min":0.0,"recorded_attempt_count":7,"run_count":7,"total":1.3066312500000001}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":23,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","max":0.273243,"mean":0.0832670543478261,"median":0.04626,"min":0.0,"recorded_attempt_count":24,"run_count":23,"total":1.9151422500000004},"codegen_latency_ms":{"attempt_count":23,"max_ms":386315,"mean_ms":129456.54545454546,"min_ms":18724,"run_count":22},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":6,"max_ms":386315,"mean_ms":316724.3333333333,"min_ms":225323,"run_count":6},"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":24,"output_max":62136,"output_mean":17319.304347826088,"output_min":242,"run_count":23},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":7,"output_max":62136,"output_mean":41969.57142857143,"output_min":242,"run_count":7},"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":46.107244510527174,"highest":54.944564738186564,"medium":51.9876898864305,"none":30.330821034598397},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":24,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":25,"reconciliation_get_attempts":116,"total_output_tokens":398344,"total_reasoning_output_tokens":309189,"total_visible_output_tokens":88913,"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":"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":"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":6,"evaluated_cells":6,"first_pass_admitted":6,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-04","GB2-05"],"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}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-09-10T11:12:08Z","match_totals_all":{"draws":665,"losses":1029,"wins":1119},"match_totals_tracks":{"highest":{"draws":131,"losses":252,"wins":340},"medium":{"draws":146,"losses":432,"wins":441},"none":{"draws":388,"losses":345,"wins":338}},"model_slug":"meta-muse-spark-1-3","overall":{"max":79.56504037106075,"mean":45.75435855307182,"min":10.355871463342384},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":11,"overall_ranking_status":"partial","per_game":{"GB2-01":63.4289408206194,"GB2-02":18.420844285465474,"GB2-03":45.63980066610449,"GB2-06":79.56504037106075,"GB2-07":59.36839361358854,"GB2-08":63.24436867228078},"per_game_all":{"GB2-01":47.38728647546092,"GB2-02":20.236349631182815,"GB2-03":40.743077149653885,"GB2-06":66.71497470657228,"GB2-07":51.626643015843705,"GB2-08":49.93513608444943},"per_game_match_totals_all":{"GB2-01":{"draws":46,"losses":152,"wins":162},"GB2-02":{"draws":240,"losses":57,"wins":31},"GB2-03":{"draws":109,"losses":150,"wins":164},"GB2-04":{"draws":114,"losses":60,"wins":54},"GB2-05":{"draws":0,"losses":175,"wins":129},"GB2-06":{"draws":29,"losses":113,"wins":228},"GB2-07":{"draws":0,"losses":229,"wins":191},"GB2-08":{"draws":127,"losses":93,"wins":160}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":42,"wins":77},"GB2-02":{"draws":69,"losses":28,"wins":7},"GB2-03":{"draws":46,"losses":41,"wins":44},"GB2-06":{"draws":14,"losses":25,"wins":79},"GB2-07":{"draws":0,"losses":78,"wins":50},"GB2-08":{"draws":1,"losses":38,"wins":83}},"medium":{"GB2-01":{"draws":0,"losses":54,"wins":65},"GB2-02":{"draws":67,"losses":18,"wins":19},"GB2-03":{"draws":25,"losses":54,"wins":55},"GB2-04":{"draws":38,"losses":40,"wins":36},"GB2-05":{"draws":0,"losses":80,"wins":60},"GB2-06":{"draws":8,"losses":39,"wins":71},"GB2-07":{"draws":0,"losses":98,"wins":70},"GB2-08":{"draws":8,"losses":49,"wins":65}},"none":{"GB2-01":{"draws":45,"losses":56,"wins":20},"GB2-02":{"draws":104,"losses":11,"wins":5},"GB2-03":{"draws":38,"losses":55,"wins":65},"GB2-04":{"draws":76,"losses":20,"wins":18},"GB2-05":{"draws":0,"losses":95,"wins":69},"GB2-06":{"draws":7,"losses":49,"wins":78},"GB2-07":{"draws":0,"losses":53,"wins":71},"GB2-08":{"draws":118,"losses":6,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1549.7317922999243,"GB2-02":1503.8456841187601,"GB2-03":1523.652170672366,"GB2-06":1720.6951126562271,"GB2-07":1517.70730887003,"GB2-08":1622.8687582203972},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.789818576751,"GB2-02":1494.65479163134,"GB2-03":1571.8773387262142,"GB2-06":1885.758929737167,"GB2-07":1611.935450984356,"GB2-08":1767.790823738796},"medium":{"GB2-01":1679.7741147045783,"GB2-02":1569.6854300230325,"GB2-03":1536.6857905884385,"GB2-04":1552.1136000673366,"GB2-05":1552.5287428396603,"GB2-06":1849.1694453365888,"GB2-07":1552.3496621939992,"GB2-08":1729.0069973801026},"none":{"GB2-01":1224.6314436184432,"GB2-02":1447.1968307019079,"GB2-03":1462.393382702446,"GB2-04":1433.5683313615027,"GB2-05":1453.4581407186583,"GB2-06":1427.156962894926,"GB2-07":1388.8368134317343,"GB2-08":1371.8084535422936}},"per_game_tracks":{"highest":{"GB2-01":63.4289408206194,"GB2-02":18.420844285465474,"GB2-03":45.63980066610449,"GB2-06":79.56504037106075,"GB2-07":59.36839361358854,"GB2-08":63.24436867228078},"medium":{"GB2-01":58.069604157521695,"GB2-02":31.93233314474059,"GB2-03":42.018834351295574,"GB2-04":39.48214490364818,"GB2-05":53.252816096613515,"GB2-06":76.70363100762701,"GB2-07":54.77515547852249,"GB2-08":59.66699995147499},"none":{"GB2-01":20.663314448241664,"GB2-02":10.355871463342384,"GB2-03":34.5705964315616,"GB2-04":19.863520529847257,"GB2-05":45.686593077752605,"GB2-06":43.876252741029056,"GB2-07":40.73637995542009,"GB2-08":26.894039629592516}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.944564738186564,"medium":51.9876898864305,"none":30.330821034598397},"reasoning_agg":{"highest":{"max":79.56504037106075,"mean":54.944564738186564,"min":18.420844285465474},"medium":{"max":76.70363100762701,"mean":51.9876898864305,"min":31.93233314474059},"none":{"max":45.686593077752605,"mean":30.330821034598397,"min":10.355871463342384}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.56504037106075,"expected_score":45.2779332329944,"reasoning_variance":24.613743703588167,"reliability_score":98.61159801556619,"uncertainty_avg":1.3884019844338171,"uncertainty_penalty":-0.4764253200774178},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.56504037106075,"expected_score":50.571806589363085,"reliability_score":98.25991649949408,"uncertainty_avg":1.7400835005059163,"uncertainty_penalty":-4.372758148823479},"medium":{"ceiling_score":76.70363100762701,"expected_score":54.248486058299946,"reliability_score":98.34597536212645,"uncertainty_avg":1.6540246378735468,"uncertainty_penalty":2.260796171869444},"none":{"ceiling_score":45.686593077752605,"expected_score":29.591602852512512,"reliability_score":99.11637269527297,"uncertainty_avg":0.883627304727026,"uncertainty_penalty":-0.7392181820858852}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:36b95fae38939a0e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087456},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998544},"codegen_latency_ms":{"attempt_count":34,"max_ms":187781,"mean_ms":106806.625,"min_ms":66051,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":187781,"mean_ms":116991.125,"min_ms":74353,"run_count":8},"medium":{"attempt_count":9,"max_ms":137371,"mean_ms":104700.625,"min_ms":79776,"run_count":8},"none":{"attempt_count":14,"max_ms":128385,"mean_ms":98728.125,"min_ms":66051,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":15570,"output_mean":7807.958333333333,"output_min":4284,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":15570,"output_mean":8557.875,"output_min":4867,"run_count":8},"medium":{"attempt_count":9,"output_max":9385,"output_mean":7450.25,"output_min":5674,"run_count":8},"none":{"attempt_count":14,"output_max":10165,"output_mean":7415.75,"output_min":4284,"run_count":8}},"display_name":"Grok 4.5","economics":{"all":45.595722368714796,"highest":51.6937015030495,"medium":47.885604863809434,"none":37.20786073928545},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-09-10T10:39:02Z","match_totals_all":{"draws":1249,"losses":1531,"wins":2245},"match_totals_tracks":{"highest":{"draws":407,"losses":599,"wins":1138},"medium":{"draws":146,"losses":173,"wins":335},"none":{"draws":696,"losses":759,"wins":772}},"model_slug":"x-ai-grok-4-5","overall":{"max":81.02581011754175,"mean":45.595722368714796,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":73.17261948899618,"GB2-02":35.41194233918621,"GB2-03":31.138548110434098,"GB2-04":14.194010354631436,"GB2-05":72.09489879437513,"GB2-06":50.694607148650334,"GB2-07":55.81717567058087,"GB2-08":81.02581011754175},"per_game_all":{"GB2-01":61.81741948354477,"GB2-02":20.17409916537943,"GB2-03":22.547256880622086,"GB2-04":19.502476819579627,"GB2-05":59.06016270649524,"GB2-06":47.713609034387694,"GB2-07":58.59703895668582,"GB2-08":75.35371590302368},"per_game_match_totals_all":{"GB2-01":{"draws":263,"losses":130,"wins":285},"GB2-02":{"draws":363,"losses":94,"wins":88},"GB2-03":{"draws":209,"losses":268,"wins":105},"GB2-04":{"draws":356,"losses":109,"wins":99},"GB2-05":{"draws":0,"losses":225,"wins":372},"GB2-06":{"draws":53,"losses":305,"wins":357},"GB2-07":{"draws":0,"losses":289,"wins":423},"GB2-08":{"draws":5,"losses":111,"wins":516}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":56,"losses":31,"wins":175},"GB2-02":{"draws":109,"losses":46,"wins":69},"GB2-03":{"draws":119,"losses":74,"wins":65},"GB2-04":{"draws":103,"losses":76,"wins":63},"GB2-05":{"draws":0,"losses":72,"wins":170},"GB2-06":{"draws":16,"losses":114,"wins":158},"GB2-07":{"draws":0,"losses":153,"wins":203},"GB2-08":{"draws":4,"losses":33,"wins":235}},"medium":{"GB2-01":{"draws":7,"losses":9,"wins":60},"GB2-02":{"draws":52,"losses":11,"wins":9},"GB2-03":{"draws":13,"losses":20,"wins":23},"GB2-04":{"draws":66,"losses":11,"wins":11},"GB2-05":{"draws":0,"losses":31,"wins":57},"GB2-06":{"draws":7,"losses":49,"wins":48},"GB2-07":{"draws":0,"losses":32,"wins":54},"GB2-08":{"draws":1,"losses":10,"wins":73}},"none":{"GB2-01":{"draws":200,"losses":90,"wins":50},"GB2-02":{"draws":202,"losses":37,"wins":10},"GB2-03":{"draws":77,"losses":174,"wins":17},"GB2-04":{"draws":187,"losses":22,"wins":25},"GB2-05":{"draws":0,"losses":122,"wins":145},"GB2-06":{"draws":30,"losses":142,"wins":151},"GB2-07":{"draws":0,"losses":104,"wins":166},"GB2-08":{"draws":0,"losses":68,"wins":208}}},"per_game_raw_elo_all":{"GB2-01":1719.4677072123484,"GB2-02":1498.281902647305,"GB2-03":1349.1850985700546,"GB2-04":1425.4708873931675,"GB2-05":1623.7599288636472,"GB2-06":1470.0621269556025,"GB2-07":1596.909120261949,"GB2-08":1893.5497476033015},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1851.5695914706555,"GB2-02":1576.638708912993,"GB2-03":1422.539339692124,"GB2-04":1387.6702135204537,"GB2-05":1784.876545788455,"GB2-06":1503.4476857106802,"GB2-07":1555.2590306763939,"GB2-08":1948.7095603306732},"medium":{"GB2-01":1796.9255894755222,"GB2-02":1483.9101853302607,"GB2-03":1502.227845346718,"GB2-04":1473.6741891937638,"GB2-05":1643.1446974256544,"GB2-06":1430.2718722969803,"GB2-07":1628.2563386094778,"GB2-08":1906.4614489539558},"none":{"GB2-01":1509.9079406908675,"GB2-02":1434.2968136986608,"GB2-03":1122.7881106713216,"GB2-04":1415.0682594652842,"GB2-05":1443.2585433768318,"GB2-06":1476.4668228591477,"GB2-07":1607.2119914999753,"GB2-08":1825.4782335252758}},"per_game_tracks":{"highest":{"GB2-01":73.17261948899618,"GB2-02":35.41194233918621,"GB2-03":31.138548110434098,"GB2-04":14.194010354631436,"GB2-05":72.09489879437513,"GB2-06":50.694607148650334,"GB2-07":55.81717567058087,"GB2-08":81.02581011754175},"medium":{"GB2-01":66.95829181437593,"GB2-02":15.084858110615464,"GB2-03":36.50322253143216,"GB2-04":25.656853491070645,"GB2-05":59.672841954852146,"GB2-06":43.7593724232428,"GB2-07":60.08935840000744,"GB2-08":75.36004018487888},"none":{"GB2-01":45.3213471472622,"GB2-02":10.025497046336621,"GB2-03":0.0,"GB2-04":18.656566613036805,"GB2-05":45.41274737025844,"GB2-06":48.68684753126993,"GB2-07":59.88458279946914,"GB2-08":69.67529740665044}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.6937015030495,"medium":47.885604863809434,"none":37.20786073928545},"reasoning_agg":{"highest":{"max":81.02581011754175,"mean":51.6937015030495,"min":14.194010354631436},"medium":{"max":75.36004018487888,"mean":47.885604863809434,"min":15.084858110615464},"none":{"max":69.67529740665044,"mean":37.20786073928545,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":81.02581011754175,"expected_score":43.71766193560719,"reasoning_variance":14.485840763764052,"reliability_score":96.06831197809363,"uncertainty_avg":3.931688021906371,"uncertainty_penalty":-1.8780604331076063},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.02581011754175,"expected_score":44.7080368216546,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.985664681394901},"medium":{"ceiling_score":75.36004018487888,"expected_score":50.254504802277935,"reliability_score":88.20493593428088,"uncertainty_avg":11.795064065719114,"uncertainty_penalty":2.368899938468502},"none":{"ceiling_score":69.67529740665044,"expected_score":36.19044418288904,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0174165563964124}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:88a334b93dec2dd0","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":3.542855},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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-2026-08-08":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},"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":3.542855},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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-2026-08-08":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},"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-2026-08-08":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},"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-2026-08-08":26},"run_count":24,"token_priced_attempt_count":26,"total":26.56635},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":47.51736875743084,"highest":59.0535146259817,"medium":45.65211067782296,"none":34.83562498827739},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"total_output_tokens":851788},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"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,"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}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:23:57Z","match_totals_all":{"draws":551,"losses":396,"wins":591},"match_totals_tracks":{"highest":{"draws":80,"losses":92,"wins":252},"medium":{"draws":196,"losses":155,"wins":229},"none":{"draws":275,"losses":149,"wins":110}},"model_slug":"gpt-5-5","overall":{"max":82.05925729033785,"mean":45.48623392985055,"min":13.936024036303673},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.47607649312432,"GB2-03":37.83597213035345,"GB2-04":17.140349376902293,"GB2-05":77.00277079448404,"GB2-06":73.97350967200747,"GB2-07":82.05925729033785,"GB2-08":64.88666662466245},"per_game_all":{"GB2-01":53.28720928414132,"GB2-03":32.41713354177612,"GB2-04":23.247747060781325,"GB2-05":62.97655783329005,"GB2-07":64.82166982400253,"GB2-08":48.353895000593724},"per_game_match_totals_all":{"GB2-01":{"draws":149,"losses":28,"wins":57},"GB2-02":{"draws":87,"losses":11,"wins":14},"GB2-03":{"draws":75,"losses":60,"wins":41},"GB2-04":{"draws":134,"losses":53,"wins":29},"GB2-05":{"draws":0,"losses":65,"wins":131},"GB2-06":{"draws":2,"losses":61,"wins":81},"GB2-07":{"draws":0,"losses":68,"wins":152},"GB2-08":{"draws":104,"losses":50,"wins":86}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":11,"wins":28},"GB2-03":{"draws":16,"losses":20,"wins":18},"GB2-04":{"draws":35,"losses":23,"wins":4},"GB2-05":{"draws":0,"losses":11,"wins":53},"GB2-06":{"draws":1,"losses":6,"wins":37},"GB2-07":{"draws":0,"losses":5,"wins":61},"GB2-08":{"draws":7,"losses":16,"wins":51}},"medium":{"GB2-01":{"draws":52,"losses":2,"wins":22},"GB2-02":{"draws":29,"losses":5,"wins":14},"GB2-03":{"draws":29,"losses":18,"wins":11},"GB2-04":{"draws":50,"losses":15,"wins":15},"GB2-05":{"draws":0,"losses":23,"wins":43},"GB2-06":{"draws":1,"losses":55,"wins":44},"GB2-07":{"draws":0,"losses":20,"wins":46},"GB2-08":{"draws":35,"losses":17,"wins":34}},"none":{"GB2-01":{"draws":76,"losses":15,"wins":7},"GB2-02":{"draws":58,"losses":6,"wins":0},"GB2-03":{"draws":30,"losses":22,"wins":12},"GB2-04":{"draws":49,"losses":15,"wins":10},"GB2-05":{"draws":0,"losses":31,"wins":35},"GB2-07":{"draws":0,"losses":43,"wins":45},"GB2-08":{"draws":62,"losses":17,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1630.7745337151784,"GB2-03":1461.8486870590993,"GB2-04":1463.7265244456385,"GB2-05":1692.0077189192841,"GB2-07":1688.8900723578972,"GB2-08":1614.7955255256757},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1723.735552560467,"GB2-03":1515.9921221734,"GB2-04":1430.2086777568848,"GB2-05":1871.4415622354468,"GB2-06":1837.2193099629035,"GB2-07":1897.9650985373178,"GB2-08":1795.716933688497},"medium":{"GB2-01":1653.6326315257897,"GB2-02":1580.7065130209066,"GB2-03":1440.4311911915072,"GB2-04":1461.3238586920036,"GB2-05":1681.0811589466743,"GB2-06":1492.4542538973014,"GB2-07":1708.9421639300028,"GB2-08":1619.4173554954286},"none":{"GB2-01":1514.9554170592792,"GB2-02":1480.3280306730896,"GB2-03":1429.1227478123901,"GB2-04":1499.6470368880275,"GB2-05":1523.5004355757312,"GB2-07":1459.7629546063713,"GB2-08":1429.2522873931011}},"per_game_tracks":{"highest":{"GB2-01":60.47607649312432,"GB2-03":37.83597213035345,"GB2-04":17.140349376902293,"GB2-05":77.00277079448404,"GB2-06":73.97350967200747,"GB2-07":82.05925729033785,"GB2-08":64.88666662466245},"medium":{"GB2-01":55.17385603478494,"GB2-02":30.656330153885765,"GB2-03":30.16793741587809,"GB2-04":23.27457919744084,"GB2-05":62.139557449757454,"GB2-06":48.5623612264452,"GB2-07":66.31252434317867,"GB2-08":48.92973960121274},"none":{"GB2-01":44.211695324514714,"GB2-02":13.936024036303673,"GB2-03":29.247491079096818,"GB2-04":29.32831260800084,"GB2-05":49.787345255628644,"GB2-07":46.093227838491046,"GB2-08":31.245278775905984}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":57.11468204292295,"medium":45.65211067782296,"none":33.69190906880573},"reasoning_agg":{"highest":{"max":82.05925729033785,"mean":57.11468204292295,"min":17.140349376902293},"medium":{"max":66.31252434317867,"mean":45.65211067782296,"min":23.27457919744084},"none":{"max":49.787345255628644,"mean":33.69190906880573,"min":13.936024036303673}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":82.05925729033785,"expected_score":47.56909707489092,"reasoning_variance":23.422772974117223,"reliability_score":84.39891952645011,"uncertainty_avg":15.60108047354988,"uncertainty_penalty":2.0828631450403705},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.05925729033785,"expected_score":54.74186695994839,"reliability_score":79.49211133009203,"uncertainty_avg":20.50788866990797,"uncertainty_penalty":-2.3728150829745616},"medium":{"ceiling_score":66.31252434317867,"expected_score":48.058057811066256,"reliability_score":84.42677483586846,"uncertainty_avg":15.573225164131538,"uncertainty_penalty":2.405947133243295},"none":{"ceiling_score":49.787345255628644,"expected_score":37.88338688610256,"reliability_score":86.3697394278346,"uncertainty_avg":13.630260572165403,"uncertainty_penalty":4.191477817296835}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:9aca75dd26e8e2c9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.11920932499999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"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},"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847899999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.11920932499999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"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":45.44850498009302,"highest":49.69482600982666,"medium":48.74706488440559,"none":37.903624046046815},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-09-10T10:37:14Z","match_totals_all":{"draws":892,"losses":1020,"wins":1083},"match_totals_tracks":{"highest":{"draws":232,"losses":348,"wins":378},"medium":{"draws":292,"losses":336,"wins":387},"none":{"draws":368,"losses":336,"wins":318}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":75.69077551550029,"mean":45.44850498009302,"min":8.088342646823264},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.834472121274,"GB2-02":52.67280906849635,"GB2-03":50.41209692545726,"GB2-04":71.64471752845151,"GB2-05":71.52812741168269,"GB2-06":17.540748548543018,"GB2-07":61.15230806980508,"GB2-08":22.773328404903395},"per_game_all":{"GB2-01":45.69254608536088,"GB2-02":24.796784302031273,"GB2-03":47.63216985734243,"GB2-04":58.93073461618138,"GB2-05":52.91507565251647,"GB2-06":46.52768198732867,"GB2-07":66.33816264183866,"GB2-08":20.754884698144377},"per_game_match_totals_all":{"GB2-01":{"draws":91,"losses":152,"wins":135},"GB2-02":{"draws":256,"losses":50,"wins":48},"GB2-03":{"draws":131,"losses":142,"wins":142},"GB2-04":{"draws":78,"losses":90,"wins":174},"GB2-05":{"draws":0,"losses":171,"wins":205},"GB2-06":{"draws":39,"losses":175,"wins":170},"GB2-07":{"draws":0,"losses":177,"wins":195},"GB2-08":{"draws":297,"losses":63,"wins":14}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":63,"wins":58},"GB2-02":{"draws":58,"losses":14,"wins":32},"GB2-03":{"draws":39,"losses":44,"wins":49},"GB2-04":{"draws":18,"losses":23,"wins":73},"GB2-05":{"draws":0,"losses":45,"wins":75},"GB2-06":{"draws":6,"losses":82,"wins":30},"GB2-07":{"draws":0,"losses":65,"wins":59},"GB2-08":{"draws":110,"losses":12,"wins":2}},"medium":{"GB2-01":{"draws":4,"losses":58,"wins":58},"GB2-02":{"draws":105,"losses":32,"wins":9},"GB2-03":{"draws":43,"losses":35,"wins":53},"GB2-04":{"draws":20,"losses":40,"wins":54},"GB2-05":{"draws":0,"losses":69,"wins":67},"GB2-06":{"draws":14,"losses":40,"wins":64},"GB2-07":{"draws":0,"losses":51,"wins":73},"GB2-08":{"draws":106,"losses":11,"wins":9}},"none":{"GB2-01":{"draws":86,"losses":31,"wins":19},"GB2-02":{"draws":93,"losses":4,"wins":7},"GB2-03":{"draws":49,"losses":63,"wins":40},"GB2-04":{"draws":40,"losses":27,"wins":47},"GB2-05":{"draws":0,"losses":57,"wins":63},"GB2-06":{"draws":19,"losses":53,"wins":76},"GB2-07":{"draws":0,"losses":61,"wins":63},"GB2-08":{"draws":81,"losses":40,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1528.2952325878884,"GB2-02":1528.0461662450118,"GB2-03":1590.1572581796493,"GB2-04":1669.6314366645154,"GB2-05":1550.167873698495,"GB2-06":1462.0032512563778,"GB2-07":1696.159234584411,"GB2-08":1306.7596826870183},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1579.1908972997724,"GB2-02":1684.8593509221103,"GB2-03":1617.6146281467568,"GB2-04":1746.4555040374125,"GB2-05":1788.349704659587,"GB2-06":1092.640375258977,"GB2-07":1633.9085154706795,"GB2-08":1328.7367936612352},"medium":{"GB2-01":1596.763908226237,"GB2-02":1462.001763083591,"GB2-03":1616.442752927784,"GB2-04":1636.7722908196843,"GB2-05":1479.0833874264852,"GB2-06":1836.2178346014025,"GB2-07":1770.5152776722223,"GB2-08":1359.5561479367261},"none":{"GB2-01":1408.9308922376556,"GB2-02":1437.2773847293352,"GB2-03":1536.4143934644067,"GB2-04":1625.6665151364496,"GB2-05":1383.0705290094131,"GB2-06":1457.1515439087545,"GB2-07":1684.0539106103315,"GB2-08":1231.9861064630934}},"per_game_tracks":{"highest":{"GB2-01":49.834472121274,"GB2-02":52.67280906849635,"GB2-03":50.41209692545726,"GB2-04":71.64471752845151,"GB2-05":71.52812741168269,"GB2-06":17.540748548543018,"GB2-07":61.15230806980508,"GB2-08":22.773328404903395},"medium":{"GB2-01":51.25526627861526,"GB2-02":13.629201190774216,"GB2-03":50.27652787410777,"GB2-04":53.49271716840484,"GB2-05":47.45741606820675,"GB2-06":75.69077551550029,"GB2-07":72.53246258720579,"GB2-08":25.64215239242983},"none":{"GB2-01":35.9878998561934,"GB2-02":8.088342646823264,"GB2-03":42.207884772462265,"GB2-04":51.654769151687816,"GB2-05":39.75968347765998,"GB2-06":46.3515218979427,"GB2-07":65.32971726850512,"GB2-08":13.849173297099911}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.69482600982666,"medium":48.74706488440559,"none":37.903624046046815},"reasoning_agg":{"highest":{"max":71.64471752845151,"mean":49.69482600982666,"min":17.540748548543018},"medium":{"max":75.69077551550029,"mean":48.74706488440559,"min":13.629201190774216},"none":{"max":65.32971726850512,"mean":37.903624046046815,"min":8.088342646823264}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":75.69077551550029,"expected_score":44.12254489368276,"reasoning_variance":11.791201963779848,"reliability_score":98.5496950186869,"uncertainty_avg":1.450304981313091,"uncertainty_penalty":-1.3259600864102623},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":71.64471752845151,"expected_score":43.1095053464028,"reliability_score":98.1267606001548,"uncertainty_avg":1.873239399845198,"uncertainty_penalty":-6.585320663423865},"medium":{"ceiling_score":75.69077551550029,"expected_score":49.18351318139857,"reliability_score":98.96826303265335,"uncertainty_avg":1.0317369673466503,"uncertainty_penalty":0.43644829699297816},"none":{"ceiling_score":65.32971726850512,"expected_score":40.074616153246915,"reliability_score":98.55406142325258,"uncertainty_avg":1.4459385767474253,"uncertainty_penalty":2.1709921072000995}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:64b986c8d9e0b166","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"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},"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.12751812499999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.0866157440000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"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},"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.9693815250000001}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"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":2.183515394},"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":46.55819280764448,"highest":54.78773402205262,"medium":48.51069202035984,"none":33.54804237444562},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":131,"total_output_tokens":812278,"total_reasoning_output_tokens":673611,"total_visible_output_tokens":138667,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-09-10T11:05:01Z","match_totals_all":{"draws":892,"losses":1020,"wins":1166},"match_totals_tracks":{"highest":{"draws":310,"losses":317,"wins":401},"medium":{"draws":178,"losses":362,"wins":420},"none":{"draws":404,"losses":341,"wins":345}},"model_slug":"tencent-hy4-preview","overall":{"max":86.09465836643398,"mean":45.08459185672779,"min":7.401997425923536},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":48.137358293252255,"GB2-02":61.13700892804711,"GB2-03":58.05033727237247,"GB2-04":44.22932296614858,"GB2-05":60.00550031591886,"GB2-06":73.34304806796328,"GB2-07":65.71219838826845,"GB2-08":27.68709794444988},"per_game_all":{"GB2-01":45.708624833288134,"GB2-03":43.366232610739075,"GB2-04":23.74684309947231,"GB2-05":51.215306291948366,"GB2-06":56.591454255389465,"GB2-07":58.26794152940456,"GB2-08":47.010947033269446},"per_game_match_totals_all":{"GB2-01":{"draws":111,"losses":184,"wins":159},"GB2-02":{"draws":140,"losses":17,"wins":57},"GB2-03":{"draws":162,"losses":117,"wins":117},"GB2-04":{"draws":207,"losses":74,"wins":61},"GB2-05":{"draws":0,"losses":200,"wins":242},"GB2-06":{"draws":23,"losses":197,"wins":210},"GB2-07":{"draws":0,"losses":192,"wins":196},"GB2-08":{"draws":249,"losses":39,"wins":124}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":71,"losses":52,"wins":41},"GB2-02":{"draws":38,"losses":12,"wins":54},"GB2-03":{"draws":14,"losses":43,"wins":75},"GB2-04":{"draws":43,"losses":33,"wins":38},"GB2-05":{"draws":0,"losses":57,"wins":63},"GB2-06":{"draws":12,"losses":40,"wins":66},"GB2-07":{"draws":0,"losses":70,"wins":54},"GB2-08":{"draws":132,"losses":10,"wins":10}},"medium":{"GB2-01":{"draws":10,"losses":86,"wins":50},"GB2-03":{"draws":93,"losses":25,"wins":14},"GB2-04":{"draws":73,"losses":28,"wins":13},"GB2-05":{"draws":0,"losses":55,"wins":91},"GB2-06":{"draws":2,"losses":101,"wins":73},"GB2-07":{"draws":0,"losses":47,"wins":77},"GB2-08":{"draws":0,"losses":20,"wins":102}},"none":{"GB2-01":{"draws":30,"losses":46,"wins":68},"GB2-02":{"draws":102,"losses":5,"wins":3},"GB2-03":{"draws":55,"losses":49,"wins":28},"GB2-04":{"draws":91,"losses":13,"wins":10},"GB2-05":{"draws":0,"losses":88,"wins":88},"GB2-06":{"draws":9,"losses":56,"wins":71},"GB2-07":{"draws":0,"losses":75,"wins":65},"GB2-08":{"draws":117,"losses":9,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1525.4056974757605,"GB2-03":1549.8940469032689,"GB2-04":1457.0332547280152,"GB2-05":1525.9898745910311,"GB2-06":1588.958611842658,"GB2-07":1598.5877311940642,"GB2-08":1589.8411893065943},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1553.627998089601,"GB2-02":1731.8618926517001,"GB2-03":1691.0287691045999,"GB2-04":1580.7983584016195,"GB2-05":1641.3522369713987,"GB2-06":1806.1969162678647,"GB2-07":1688.6451933819492,"GB2-08":1378.5701242686011},"medium":{"GB2-01":1529.6533895280302,"GB2-03":1407.3610086540643,"GB2-04":1369.3199862945683,"GB2-05":1450.2778157227672,"GB2-06":1539.6481680538632,"GB2-07":1756.8345831771405,"GB2-08":2015.5208557563683},"none":{"GB2-01":1492.93570480965,"GB2-02":1432.3963585232377,"GB2-03":1551.2923629511429,"GB2-04":1420.9814194878577,"GB2-05":1486.3395710789268,"GB2-06":1421.0307512062466,"GB2-07":1350.283417023103,"GB2-08":1375.432587894814}},"per_game_tracks":{"highest":{"GB2-01":48.137358293252255,"GB2-02":61.13700892804711,"GB2-03":58.05033727237247,"GB2-04":44.22932296614858,"GB2-05":60.00550031591886,"GB2-06":73.34304806796328,"GB2-07":65.71219838826845,"GB2-08":27.68709794444988},"medium":{"GB2-01":46.013416130569944,"GB2-03":28.53664270722644,"GB2-04":9.230754142229273,"GB2-05":45.29216666489487,"GB2-06":53.0144266368767,"GB2-07":71.39277949428767,"GB2-08":86.09465836643398},"none":{"GB2-01":42.97510007604222,"GB2-02":7.401997425923536,"GB2-03":43.511717852618325,"GB2-04":17.78045219003907,"GB2-05":48.348251895031375,"GB2-06":43.41688806132841,"GB2-07":37.698846705657566,"GB2-08":27.25108478892449}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.78773402205262,"medium":46.917999173685125,"none":33.54804237444562},"reasoning_agg":{"highest":{"max":73.34304806796328,"mean":54.78773402205262,"min":27.68709794444988},"medium":{"max":86.09465836643398,"mean":46.917999173685125,"min":9.230754142229273},"none":{"max":48.348251895031375,"mean":33.54804237444562,"min":7.401997425923536}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":86.09465836643398,"expected_score":44.77366700068411,"reasoning_variance":21.239691647606996,"reliability_score":99.25279083926827,"uncertainty_avg":0.7472091607317283,"uncertainty_penalty":-0.3109248560436839},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.34304806796328,"expected_score":48.52771708946725,"reliability_score":98.41486576057572,"uncertainty_avg":1.5851342394242718,"uncertainty_penalty":-6.260016932585366},"medium":{"ceiling_score":86.09465836643398,"expected_score":49.713247661315116,"reliability_score":99.25998832923099,"uncertainty_avg":0.7400116707690138,"uncertainty_penalty":2.7952484876299906},"none":{"ceiling_score":48.348251895031375,"expected_score":33.9320869207929,"reliability_score":99.17710747504492,"uncertainty_avg":0.82289252495508,"uncertainty_penalty":0.38404454634727614}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:0604b840849e2584","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.531673125,"mean":0.47737264687500003,"median":0.48302475,"min":0.3855675,"recorded_attempt_count":53,"run_count":16,"total":7.63796235},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000001},"historical-provider-setting-intensive":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.531673125,"mean":0.47737264687500003,"median":0.48302475,"min":0.3855675,"recorded_attempt_count":53,"run_count":16,"total":7.6379623500000005}},"codegen_cost_usd":{"admitted_cell_count":42,"cell_count":24,"cost_basis_counts":{"provider_reported":126},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.531673125,"mean":0.264606278125,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":126,"run_count":48,"total":12.701101349999997},"codegen_latency_ms":{"attempt_count":122,"max_ms":348942,"mean_ms":136127.20833333334,"min_ms":17298,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":49,"max_ms":348942,"mean_ms":238985.4375,"min_ms":149523,"run_count":16},"medium":{"attempt_count":44,"max_ms":261708,"mean_ms":136549.0,"min_ms":44747,"run_count":16},"none":{"attempt_count":29,"max_ms":50160,"mean_ms":32847.1875,"min_ms":17298,"run_count":16}},"codegen_output_tokens":{"attempt_count":126,"output_max":100087,"output_mean":32301.520833333332,"output_min":2060,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":100087,"output_mean":61701.5625,"output_min":36597,"run_count":16},"medium":{"attempt_count":44,"output_max":63652,"output_mean":30566.4375,"output_min":8874,"run_count":16},"none":{"attempt_count":29,"output_max":7962,"output_mean":4636.5625,"output_min":2060,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":47.53797300598492,"highest":55.68219526351658,"medium":46.76079180174214,"none":31.213596289340646},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":122,"finish_reasons":["length","stop"],"indexed_attempts":126,"output_token_observations":126,"reasoning_token_observations":82,"total_output_tokens":1550473,"total_reasoning_output_tokens":771353,"total_visible_output_tokens":207435,"visible_token_observations":82},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-07"],"first_pass_admitted":8,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-09-10T10:59:04Z","match_totals_all":{"draws":2885,"losses":3367,"wins":4145},"match_totals_tracks":{"highest":{"draws":566,"losses":885,"wins":1572},"medium":{"draws":730,"losses":807,"wins":1386},"none":{"draws":1589,"losses":1675,"wins":1187}},"model_slug":"google-gemini-3-6-flash","overall":{"max":85.6020891745296,"mean":42.75242302612431,"min":6.451833831046862},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.1763070086701,"GB2-03":43.44619039396651,"GB2-04":42.02102497124446,"GB2-05":83.5278688201069,"GB2-06":85.6020891745296,"GB2-07":52.151765643097974,"GB2-08":38.850120833000595},"per_game_all":{"GB2-01":42.83376631410176,"GB2-03":38.441859319956315,"GB2-04":28.501734829393182,"GB2-05":67.65177604828101,"GB2-06":63.8802183480262,"GB2-07":50.10912666204251,"GB2-08":41.34732952009342},"per_game_match_totals_all":{"GB2-01":{"draws":508,"losses":499,"wins":416},"GB2-02":{"draws":486,"losses":45,"wins":5},"GB2-03":{"draws":317,"losses":480,"wins":484},"GB2-04":{"draws":740,"losses":299,"wins":270},"GB2-05":{"draws":0,"losses":517,"wins":1126},"GB2-06":{"draws":138,"losses":544,"wins":888},"GB2-07":{"draws":0,"losses":585,"wins":620},"GB2-08":{"draws":696,"losses":398,"wins":336}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":174,"losses":179,"wins":161},"GB2-03":{"draws":23,"losses":73,"wins":130},"GB2-04":{"draws":131,"losses":147,"wins":197},"GB2-05":{"draws":0,"losses":85,"wins":399},"GB2-06":{"draws":26,"losses":107,"wins":375},"GB2-07":{"draws":0,"losses":144,"wins":130},"GB2-08":{"draws":212,"losses":150,"wins":180}},"medium":{"GB2-01":{"draws":187,"losses":48,"wins":121},"GB2-02":{"draws":68,"losses":5,"wins":1},"GB2-03":{"draws":125,"losses":215,"wins":152},"GB2-04":{"draws":252,"losses":51,"wins":34},"GB2-05":{"draws":0,"losses":141,"wins":383},"GB2-06":{"draws":51,"losses":81,"wins":380},"GB2-07":{"draws":0,"losses":177,"wins":201},"GB2-08":{"draws":47,"losses":89,"wins":114}},"none":{"GB2-01":{"draws":147,"losses":272,"wins":134},"GB2-02":{"draws":418,"losses":40,"wins":4},"GB2-03":{"draws":169,"losses":192,"wins":202},"GB2-04":{"draws":357,"losses":101,"wins":39},"GB2-05":{"draws":0,"losses":291,"wins":344},"GB2-06":{"draws":61,"losses":356,"wins":133},"GB2-07":{"draws":0,"losses":264,"wins":289},"GB2-08":{"draws":437,"losses":159,"wins":42}}},"per_game_raw_elo_all":{"GB2-01":1486.1615819114904,"GB2-03":1493.1539587051448,"GB2-04":1476.5030252761755,"GB2-05":1726.7984960347028,"GB2-06":1673.2192585185887,"GB2-07":1492.0959320119362,"GB2-08":1518.342742676877},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1499.2581565241724,"GB2-03":1542.5270863810842,"GB2-04":1556.0651238854534,"GB2-05":1930.7302324494935,"GB2-06":1951.3393726264744,"GB2-07":1514.210308630917,"GB2-08":1491.5632904173685},"medium":{"GB2-01":1676.8379285851024,"GB2-02":1435.3417075004436,"GB2-03":1436.8610019118303,"GB2-04":1425.4671288080813,"GB2-05":1790.0700567199,"GB2-06":1850.8283392924154,"GB2-07":1482.5103578202652,"GB2-08":1707.404877029335},"none":{"GB2-01":1282.3886606251967,"GB2-02":1428.613616977331,"GB2-03":1500.0737878225204,"GB2-04":1447.9768231349922,"GB2-05":1459.5951989347143,"GB2-06":1217.4900636368764,"GB2-07":1479.5671295846262,"GB2-08":1356.0600605839268}},"per_game_tracks":{"highest":{"GB2-01":44.1763070086701,"GB2-03":43.44619039396651,"GB2-04":42.02102497124446,"GB2-05":83.5278688201069,"GB2-06":85.6020891745296,"GB2-07":52.151765643097974,"GB2-08":38.850120833000595},"medium":{"GB2-01":57.908198892761675,"GB2-02":6.451833831046862,"GB2-03":32.56614014388901,"GB2-04":19.256845011483584,"GB2-05":72.57999142955795,"GB2-06":77.74963744928857,"GB2-07":48.90130757412859,"GB2-08":58.67238008178089},"none":{"GB2-01":26.416793040873507,"GB2-02":8.821204616548417,"GB2-03":39.31324742201342,"GB2-04":24.22733450545151,"GB2-05":46.84746789517817,"GB2-06":28.288928420260433,"GB2-07":49.274306768900956,"GB2-08":26.519487645498753}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.81812147770044,"medium":45.225551311331834,"none":31.213596289340646},"reasoning_agg":{"highest":{"max":85.6020891745296,"mean":51.81812147770044,"min":38.850120833000595},"medium":{"max":77.74963744928857,"mean":45.225551311331834,"min":6.451833831046862},"none":{"max":49.274306768900956,"mean":31.213596289340646,"min":8.821204616548417}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":85.6020891745296,"expected_score":44.43478429603738,"reasoning_variance":20.60452518835979,"reliability_score":99.37671983636963,"uncertainty_avg":0.6232801636303643,"uncertainty_penalty":1.6823612699130663},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.6020891745296,"expected_score":47.87472857594896,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.94339290175148},"medium":{"ceiling_score":77.74963744928857,"expected_score":47.44020127341089,"reliability_score":96.61576120559997,"uncertainty_avg":3.3842387944000274,"uncertainty_penalty":2.214649962079058},"none":{"ceiling_score":49.274306768900956,"expected_score":28.61246814210085,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.6011281472397947}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:71508839738a1256","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.526117125,"median":0.5491332,"min":0.330054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":8,"total":4.208937},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.526117125,"median":0.5491332,"min":0.330054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":8,"total":4.208937}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.2975122,"median":0.2990655,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":40},"recorded_attempt_count":40,"run_count":24,"total":7.1402928},"codegen_latency_ms":{"attempt_count":40,"max_ms":1201344,"mean_ms":515468.5833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":1201344,"mean_ms":973286.5,"min_ms":605299,"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":40,"output_max":40000,"output_mean":17970.666666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":40000,"output_mean":33312.25,"output_min":20000,"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":36.51073629900371,"highest":44.59194591921063,"medium":37.79492618629287,"none":45.45362312867519},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":40,"finish_reasons":["length","stop"],"indexed_attempts":41,"output_token_observations":40,"reasoning_token_observations":40,"total_output_tokens":431296,"total_reasoning_output_tokens":338477,"total_visible_output_tokens":92819,"visible_token_observations":40},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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":7,"failed_game_aliases":["GB2-05","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"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":4,"repaired_rate":0.5714285714285714}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-09-10T10:37:23Z","match_totals_all":{"draws":1825,"losses":1980,"wins":2073},"match_totals_tracks":{"highest":{"draws":413,"losses":419,"wins":470},"medium":{"draws":758,"losses":792,"wins":670},"none":{"draws":654,"losses":769,"wins":933}},"model_slug":"moonshotai-kimi-k3","overall":{"max":89.21089685186311,"mean":41.41431270485983,"min":6.485222218768579},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":17,"overall_ranking_status":"partial","per_game":{"GB2-01":55.82678776607858,"GB2-02":13.442672880681176,"GB2-03":33.72808628713718,"GB2-04":65.77337510145159,"GB2-07":54.18880756070461},"per_game_all":{"GB2-01":52.5421268706963,"GB2-02":10.43174194383995,"GB2-03":39.44849580964052,"GB2-04":40.155417410745265,"GB2-07":39.97589946009654},"per_game_match_totals_all":{"GB2-01":{"draws":270,"losses":292,"wins":303},"GB2-02":{"draws":568,"losses":102,"wins":28},"GB2-03":{"draws":276,"losses":255,"wins":242},"GB2-04":{"draws":395,"losses":155,"wins":223},"GB2-05":{"draws":0,"losses":305,"wins":360},"GB2-06":{"draws":70,"losses":281,"wins":299},"GB2-07":{"draws":0,"losses":503,"wins":343},"GB2-08":{"draws":246,"losses":87,"wins":275}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":108,"wins":135},"GB2-02":{"draws":185,"losses":35,"wins":10},"GB2-03":{"draws":124,"losses":86,"wins":52},"GB2-04":{"draws":75,"losses":47,"wins":118},"GB2-07":{"draws":0,"losses":143,"wins":155}},"medium":{"GB2-01":{"draws":43,"losses":99,"wins":112},"GB2-02":{"draws":165,"losses":27,"wins":8},"GB2-03":{"draws":81,"losses":64,"wins":96},"GB2-04":{"draws":191,"losses":39,"wins":37},"GB2-05":{"draws":0,"losses":151,"wins":179},"GB2-06":{"draws":32,"losses":165,"wins":135},"GB2-07":{"draws":0,"losses":180,"wins":86},"GB2-08":{"draws":246,"losses":67,"wins":17}},"none":{"GB2-01":{"draws":198,"losses":85,"wins":56},"GB2-02":{"draws":218,"losses":40,"wins":10},"GB2-03":{"draws":71,"losses":105,"wins":94},"GB2-04":{"draws":129,"losses":69,"wins":68},"GB2-05":{"draws":0,"losses":154,"wins":181},"GB2-06":{"draws":38,"losses":116,"wins":164},"GB2-07":{"draws":0,"losses":180,"wins":102},"GB2-08":{"draws":0,"losses":20,"wins":258}}},"per_game_raw_elo_all":{"GB2-01":1599.6982382734739,"GB2-02":1437.561284934072,"GB2-03":1502.4468343579967,"GB2-04":1543.7748997550677,"GB2-07":1367.7275360860667},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1640.1968317903131,"GB2-02":1454.2925767129848,"GB2-03":1447.238678577864,"GB2-04":1699.4440706751725,"GB2-07":1537.6745398626697},"medium":{"GB2-01":1661.6676787014649,"GB2-02":1417.5529196297932,"GB2-03":1532.8658749771148,"GB2-04":1444.1765238688329,"GB2-05":1532.290670637824,"GB2-06":1621.172337112724,"GB2-07":1265.4548452950958,"GB2-08":1372.3124171079544},"none":{"GB2-01":1497.2302043286434,"GB2-02":1440.8383584594383,"GB2-03":1527.2359495190115,"GB2-04":1487.7041047211976,"GB2-05":1571.0784225753098,"GB2-06":1567.1387534647272,"GB2-07":1300.0532231004343,"GB2-08":2037.1859548088862}},"per_game_tracks":{"highest":{"GB2-01":55.82678776607858,"GB2-02":13.442672880681176,"GB2-03":33.72808628713718,"GB2-04":65.77337510145159,"GB2-07":54.18880756070461},"medium":{"GB2-01":57.5234825792159,"GB2-02":6.485222218768579,"GB2-03":42.5279830685233,"GB2-04":23.748427314763532,"GB2-05":52.5835528465637,"GB2-06":60.02690569508898,"GB2-07":31.399076922756784,"GB2-08":28.06475884466223},"none":{"GB2-01":44.276110266794404,"GB2-02":11.367330732070096,"GB2-03":42.089418073261065,"GB2-04":30.944449816020683,"GB2-05":55.636862652973036,"GB2-06":55.764102739590896,"GB2-07":34.33981389682823,"GB2-08":89.21089685186311}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.99438879961144,"medium":37.79492618629287,"none":45.45362312867519},"reasoning_agg":{"highest":{"max":65.77337510145159,"mean":40.99438879961144,"min":13.442672880681176},"medium":{"max":60.02690569508898,"mean":37.79492618629287,"min":6.485222218768579},"none":{"max":89.21089685186311,"mean":45.45362312867519,"min":11.367330732070096}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":89.21089685186311,"expected_score":33.259341477324206,"reasoning_variance":7.658696942382321,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.154971227535626},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.77337510145159,"expected_score":37.89019956836008,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.104189231251361},"medium":{"ceiling_score":60.02690569508898,"expected_score":35.92544194564068,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8694842406521914},"none":{"ceiling_score":89.21089685186311,"expected_score":46.83931615592161,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3856930272464183}}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:ffd76b5b23c55ff5","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"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},"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},"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},"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},"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},"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},"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":41.96738502513636,"highest":56.86801757531599,"medium":36.85392471914304,"none":32.180212780950036},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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","GB2-06"],"first_pass_admitted":21,"first_pass_rate":0.7,"model_code_failure_rate":0.13333333333333333,"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":0.16666666666666666},"baseline":{"admitted_plugins":28,"evaluated_cells":30,"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"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,"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}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-09-10T11:12:08Z","match_totals_all":{"draws":2838,"losses":3854,"wins":3777},"match_totals_tracks":{"highest":{"draws":474,"losses":1116,"wins":1528},"medium":{"draws":847,"losses":1488,"wins":1265},"none":{"draws":1517,"losses":1250,"wins":984}},"model_slug":"stealth-ox-alpha","overall":{"max":63.32717677815119,"mean":41.352237179328434,"min":10.84501570624497},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":47.83064684889641,"GB2-02":55.57987941105307,"GB2-03":54.34658467999775,"GB2-04":61.078178953791536,"GB2-05":57.13595607705878,"GB2-06":63.32717677815119,"GB2-07":59.42904163978228,"GB2-08":56.216676213796916},"per_game_all":{"GB2-01":43.61883753239016,"GB2-02":27.79119637501803,"GB2-03":42.159045086343745,"GB2-04":41.939032201684356,"GB2-05":49.89949265014605,"GB2-06":42.48269226773487,"GB2-07":47.49556707042826,"GB2-08":40.35321701734538},"per_game_match_totals_all":{"GB2-01":{"draws":205,"losses":444,"wins":409},"GB2-02":{"draws":659,"losses":121,"wins":152},"GB2-03":{"draws":973,"losses":885,"wins":992},"GB2-04":{"draws":508,"losses":243,"wins":318},"GB2-05":{"draws":0,"losses":593,"wins":587},"GB2-06":{"draws":99,"losses":578,"wins":491},"GB2-07":{"draws":0,"losses":621,"wins":541},"GB2-08":{"draws":394,"losses":369,"wins":287}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":176,"wins":183},"GB2-02":{"draws":82,"losses":23,"wins":103},"GB2-03":{"draws":148,"losses":173,"wins":311},"GB2-04":{"draws":112,"losses":64,"wins":166},"GB2-05":{"draws":0,"losses":221,"wins":165},"GB2-06":{"draws":62,"losses":119,"wins":227},"GB2-07":{"draws":0,"losses":191,"wins":203},"GB2-08":{"draws":49,"losses":149,"wins":170}},"medium":{"GB2-01":{"draws":64,"losses":114,"wins":100},"GB2-02":{"draws":280,"losses":55,"wins":37},"GB2-03":{"draws":206,"losses":412,"wins":424},"GB2-04":{"draws":145,"losses":118,"wins":99},"GB2-05":{"draws":0,"losses":198,"wins":208},"GB2-06":{"draws":20,"losses":192,"wins":98},"GB2-07":{"draws":0,"losses":207,"wins":189},"GB2-08":{"draws":132,"losses":192,"wins":110}},"none":{"GB2-01":{"draws":120,"losses":154,"wins":126},"GB2-02":{"draws":297,"losses":43,"wins":12},"GB2-03":{"draws":619,"losses":300,"wins":257},"GB2-04":{"draws":251,"losses":61,"wins":53},"GB2-05":{"draws":0,"losses":174,"wins":214},"GB2-06":{"draws":17,"losses":267,"wins":166},"GB2-07":{"draws":0,"losses":223,"wins":149},"GB2-08":{"draws":213,"losses":28,"wins":7}}},"per_game_raw_elo_all":{"GB2-01":1502.256737452396,"GB2-02":1545.1232881959786,"GB2-03":1537.4139803258158,"GB2-04":1566.249603937815,"GB2-05":1510.9700166666582,"GB2-06":1407.9664659952498,"GB2-07":1469.323783496572,"GB2-08":1518.5687308949844},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1554.229696147544,"GB2-02":1701.0026010053057,"GB2-03":1656.300862782808,"GB2-04":1682.6073396219508,"GB2-05":1603.5972040555732,"GB2-06":1675.6494431146332,"GB2-07":1612.2752770256213,"GB2-08":1691.5039555971996},"medium":{"GB2-01":1557.5471242852395,"GB2-02":1483.8477800060446,"GB2-03":1538.0029662977238,"GB2-04":1541.4198741744876,"GB2-05":1426.8517046947445,"GB2-06":1149.9302789153699,"GB2-07":1418.2360449335408,"GB2-08":1518.3224253686287},"none":{"GB2-01":1394.9933919244042,"GB2-02":1450.5194835765851,"GB2-03":1417.9381118969159,"GB2-04":1474.7215980170065,"GB2-05":1502.461141249657,"GB2-06":1398.3196759557468,"GB2-07":1377.4600285305544,"GB2-08":1345.8798117191247}},"per_game_tracks":{"highest":{"GB2-01":47.83064684889641,"GB2-02":55.57987941105307,"GB2-03":54.34658467999775,"GB2-04":61.078178953791536,"GB2-05":57.13595607705878,"GB2-06":63.32717677815119,"GB2-07":59.42904163978228,"GB2-08":56.216676213796916},"medium":{"GB2-01":48.22093354536652,"GB2-02":16.948694007756043,"GB2-03":42.32178294840338,"GB2-04":37.87091498905499,"GB2-05":43.3483500632467,"GB2-06":22.36329166385045,"GB2-07":43.26903335828475,"GB2-08":40.48839717718149},"none":{"GB2-01":34.80493220290756,"GB2-02":10.84501570624497,"GB2-03":29.80876763063011,"GB2-04":26.868002662206536,"GB2-05":49.214171810132676,"GB2-06":41.75760836120296,"GB2-07":39.78862621321775,"GB2-08":24.354577661057732}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.86801757531599,"medium":35.55877308298843,"none":31.629920879680903},"reasoning_agg":{"highest":{"max":63.32717677815119,"mean":56.86801757531599,"min":47.83064684889641},"medium":{"max":48.22093354536652,"mean":35.55877308298843,"min":16.948694007756043},"none":{"max":49.214171810132676,"mean":31.629920879680903,"min":10.84501570624497}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":63.32717677815119,"expected_score":39.897362117737956,"reasoning_variance":25.238096695635086,"reliability_score":98.81426491839116,"uncertainty_avg":1.1857350816088388,"uncertainty_penalty":-1.454875061590478},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":63.32717677815119,"expected_score":51.34153070067267,"reliability_score":98.39740164577785,"uncertainty_avg":1.602598354222148,"uncertainty_penalty":-5.526486874643318},"medium":{"ceiling_score":48.22093354536652,"expected_score":36.170044736737076,"reliability_score":99.02591447547452,"uncertainty_avg":0.9740855245254815,"uncertainty_penalty":0.6112716537486449},"none":{"ceiling_score":49.214171810132676,"expected_score":32.18051091580412,"reliability_score":99.01947863392111,"uncertainty_avg":0.9805213660788873,"uncertainty_penalty":0.5505900361232179}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:c745ec618c97d50e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.779305}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"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-2026-08-08":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},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.7793050000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"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-2026-08-08":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":{"highest":40.5842067414882,"medium":42.256499987447725},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"total_output_tokens":349054},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:06Z","match_totals_all":{"draws":303,"losses":336,"wins":359},"match_totals_tracks":{"highest":{"draws":165,"losses":176,"wins":173},"medium":{"draws":138,"losses":160,"wins":186}},"model_slug":"gpt-5","overall":{"max":65.51337979360243,"mean":40.726675100434214,"min":12.515897799774466},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":19,"overall_ranking_status":"partial","per_game":{"GB2-01":46.42515101914064,"GB2-02":12.515897799774466,"GB2-03":31.59173778794821,"GB2-04":24.862265180138433,"GB2-05":57.46936546828877,"GB2-06":65.51337979360243,"GB2-07":57.519301106513744,"GB2-08":28.776555776498935},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":80,"wins":56},"GB2-02":{"draws":43,"losses":9,"wins":2},"GB2-03":{"draws":41,"losses":29,"wins":18},"GB2-04":{"draws":96,"losses":21,"wins":21},"GB2-05":{"draws":0,"losses":59,"wins":73},"GB2-06":{"draws":9,"losses":46,"wins":83},"GB2-07":{"draws":0,"losses":52,"wins":88},"GB2-08":{"draws":96,"losses":40,"wins":18}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":40,"wins":39},"GB2-02":{"draws":43,"losses":9,"wins":2},"GB2-03":{"draws":17,"losses":15,"wins":10},"GB2-04":{"draws":48,"losses":13,"wins":5},"GB2-05":{"draws":0,"losses":31,"wins":31},"GB2-06":{"draws":3,"losses":17,"wins":34},"GB2-07":{"draws":0,"losses":27,"wins":41},"GB2-08":{"draws":49,"losses":24,"wins":11}},"medium":{"GB2-01":{"draws":13,"losses":40,"wins":17},"GB2-03":{"draws":24,"losses":14,"wins":8},"GB2-04":{"draws":48,"losses":8,"wins":16},"GB2-05":{"draws":0,"losses":28,"wins":42},"GB2-06":{"draws":6,"losses":29,"wins":49},"GB2-07":{"draws":0,"losses":25,"wins":47},"GB2-08":{"draws":47,"losses":16,"wins":7}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1545.0545313969262,"GB2-02":1476.764023922726,"GB2-03":1463.0397619411053,"GB2-04":1475.340762765141,"GB2-05":1623.0296620496733,"GB2-06":1723.3452380747874,"GB2-07":1602.6753490524998,"GB2-08":1401.429423608086},"medium":{"GB2-01":1292.4869742782632,"GB2-03":1413.8505029015237,"GB2-04":1534.830093500697,"GB2-05":1661.473206220661,"GB2-06":1601.8729234393843,"GB2-07":1690.0437032215139,"GB2-08":1377.804308515359}},"per_game_tracks":{"highest":{"GB2-01":46.42515101914064,"GB2-02":12.515897799774466,"GB2-03":31.59173778794821,"GB2-04":24.862265180138433,"GB2-05":57.46936546828877,"GB2-06":65.51337979360243,"GB2-07":57.519301106513744,"GB2-08":28.776555776498935},"medium":{"GB2-01":25.31798930091367,"GB2-03":26.750002522868716,"GB2-04":35.04692207446579,"GB2-05":60.71202505477096,"GB2-06":56.83890819619163,"GB2-07":64.90905738242017,"GB2-08":26.220595380503127}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.5842067414882,"medium":40.869143459380226},"reasoning_agg":{"highest":{"max":65.51337979360243,"mean":40.5842067414882,"min":12.515897799774466},"medium":{"max":64.90905738242017,"mean":40.869143459380226,"min":25.31798930091367}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":65.51337979360243,"reasoning_variance":0.28493671789202324},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.51337979360243,"expected_score":34.532853670272935,"reliability_score":80.7717232344766,"uncertainty_avg":19.228276765523407,"uncertainty_penalty":-6.051353071215267},"medium":{"ceiling_score":64.90905738242017,"expected_score":43.22797638459556,"reliability_score":83.43235626731145,"uncertainty_avg":16.567643732688556,"uncertainty_penalty":2.3588329252153315}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:c1f7759c0d0f3c47","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"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},"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},"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},"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},"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.22795366666666664,"median":0.16679960729572763,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":5.4708879999999995},"codegen_output_tokens":{"attempt_count":27,"output_max":128921,"output_mean":35057.208333333336,"output_min":6291,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":128921,"output_mean":72806.0,"output_min":45821,"run_count":8},"medium":{"attempt_count":8,"output_max":25498,"output_mean":11826.75,"output_min":6291,"run_count":8},"none":{"attempt_count":9,"output_max":34088,"output_mean":20538.875,"output_min":10484,"run_count":8}},"display_name":"Qwen3.8 2.4t A95B","economics":{"all":40.564939321453636,"highest":53.26667306538265,"medium":33.21730372205993,"none":35.210841176918336},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-09-10T10:47:44Z","match_totals_all":{"draws":976,"losses":1052,"wins":1113},"match_totals_tracks":{"highest":{"draws":267,"losses":312,"wins":430},"medium":{"draws":428,"losses":375,"wins":328},"none":{"draws":281,"losses":365,"wins":355}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":85.08829766988379,"mean":40.564939321453636,"min":8.285036037313507},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":43.44845781533551,"GB2-02":29.297101237978474,"GB2-03":42.87343571896586,"GB2-04":32.24296791137236,"GB2-05":57.716645393220304,"GB2-06":72.64513505242988,"GB2-07":62.82134372387497,"GB2-08":85.08829766988379},"per_game_all":{"GB2-01":39.70235872885978,"GB2-02":17.832365146892048,"GB2-03":38.27110413624026,"GB2-04":20.955086901213082,"GB2-05":43.76463126146211,"GB2-06":55.66272592295024,"GB2-07":49.243892100213905,"GB2-08":59.087350373797676},"per_game_match_totals_all":{"GB2-01":{"draws":158,"losses":138,"wins":113},"GB2-02":{"draws":240,"losses":80,"wins":38},"GB2-03":{"draws":175,"losses":164,"wins":107},"GB2-04":{"draws":235,"losses":73,"wins":54},"GB2-05":{"draws":0,"losses":177,"wins":227},"GB2-06":{"draws":49,"losses":160,"wins":183},"GB2-07":{"draws":0,"losses":182,"wins":194},"GB2-08":{"draws":119,"losses":78,"wins":197}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":50,"losses":38,"wins":67},"GB2-02":{"draws":59,"losses":22,"wins":23},"GB2-03":{"draws":69,"losses":36,"wins":27},"GB2-04":{"draws":70,"losses":38,"wins":26},"GB2-05":{"draws":0,"losses":55,"wins":65},"GB2-06":{"draws":18,"losses":37,"wins":63},"GB2-07":{"draws":0,"losses":66,"wins":58},"GB2-08":{"draws":1,"losses":20,"wins":101}},"medium":{"GB2-01":{"draws":41,"losses":61,"wins":32},"GB2-02":{"draws":91,"losses":31,"wins":2},"GB2-03":{"draws":84,"losses":67,"wins":32},"GB2-04":{"draws":80,"losses":22,"wins":12},"GB2-05":{"draws":0,"losses":62,"wins":102},"GB2-06":{"draws":16,"losses":49,"wins":73},"GB2-07":{"draws":0,"losses":61,"wins":63},"GB2-08":{"draws":116,"losses":22,"wins":12}},"none":{"GB2-01":{"draws":67,"losses":39,"wins":14},"GB2-02":{"draws":90,"losses":27,"wins":13},"GB2-03":{"draws":22,"losses":61,"wins":48},"GB2-04":{"draws":85,"losses":13,"wins":16},"GB2-05":{"draws":0,"losses":60,"wins":60},"GB2-06":{"draws":15,"losses":74,"wins":47},"GB2-07":{"draws":0,"losses":55,"wins":73},"GB2-08":{"draws":2,"losses":36,"wins":84}}},"per_game_raw_elo_all":{"GB2-01":1454.1945121919591,"GB2-02":1488.9379899364255,"GB2-03":1499.2344655949753,"GB2-04":1439.2062149572382,"GB2-05":1432.421573483487,"GB2-06":1578.3699926882002,"GB2-07":1490.7741807725,"GB2-08":1721.551012572502},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1497.4989415222879,"GB2-02":1555.0517257485558,"GB2-03":1545.1575815875583,"GB2-04":1505.4972986814284,"GB2-05":1612.1526564637534,"GB2-06":1797.2725457387294,"GB2-07":1653.943529613308,"GB2-08":2004.6104572049926},"medium":{"GB2-01":1585.9593303575618,"GB2-02":1460.2230129143188,"GB2-03":1481.1251507851525,"GB2-04":1363.6054976163036,"GB2-05":1467.1691456804797,"GB2-06":1390.83708850739,"GB2-07":1403.884604633261,"GB2-08":1377.2103402805674},"none":{"GB2-01":1279.1252646960281,"GB2-02":1451.5392311464016,"GB2-03":1471.4206644122155,"GB2-04":1448.5158485739823,"GB2-05":1217.9429183062275,"GB2-06":1547.0003438184813,"GB2-07":1414.4944080709313,"GB2-08":1782.8322402319461}},"per_game_tracks":{"highest":{"GB2-01":43.44845781533551,"GB2-02":29.297101237978474,"GB2-03":42.87343571896586,"GB2-04":32.24296791137236,"GB2-05":57.716645393220304,"GB2-06":72.64513505242988,"GB2-07":62.82134372387497,"GB2-08":85.08829766988379},"medium":{"GB2-01":50.52600493863421,"GB2-02":12.807246879163486,"GB2-03":36.7519074126838,"GB2-04":8.285036037313507,"GB2-05":46.761351709774466,"GB2-06":41.07494801160975,"GB2-07":41.98995032235631,"GB2-08":27.541984464943933},"none":{"GB2-01":25.13261343260962,"GB2-02":11.392747323534184,"GB2-03":35.18796927707111,"GB2-04":22.337256754953387,"GB2-05":26.815896681391532,"GB2-06":53.268094704811084,"GB2-07":42.920382254410434,"GB2-08":64.6317689865653}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.26667306538265,"medium":33.21730372205993,"none":35.210841176918336},"reasoning_agg":{"highest":{"max":85.08829766988379,"mean":53.26667306538265,"min":29.297101237978474},"medium":{"max":50.52600493863421,"mean":33.21730372205993,"min":8.285036037313507},"none":{"max":64.6317689865653,"mean":35.210841176918336,"min":11.392747323534184}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":85.08829766988379,"expected_score":38.463627004627874,"reasoning_variance":20.049369343322716,"reliability_score":99.00634862002013,"uncertainty_avg":0.9936513799798663,"uncertainty_penalty":-2.101312316825762},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.08829766988379,"expected_score":47.400373898189656,"reliability_score":98.60758559540623,"uncertainty_avg":1.3924144045937625,"uncertainty_penalty":-5.866299167192992},"medium":{"ceiling_score":50.52600493863421,"expected_score":31.85309362377548,"reliability_score":99.39775506099909,"uncertainty_avg":0.6022449390009099,"uncertainty_penalty":-1.3642100982844525},"none":{"ceiling_score":64.6317689865653,"expected_score":36.13741349191848,"reliability_score":99.01370520365508,"uncertainty_avg":0.9862947963449264,"uncertainty_penalty":0.9265723150001435}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:eebfed4239db54b7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"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-2026-08-08":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},"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-2026-08-08":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},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.9739300000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"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},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"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},"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-2026-08-08":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},"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-2026-08-08":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":39.67603526846738,"highest":35.14311845280274,"medium":42.43578753789422,"none":41.44919981470518},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"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}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-09-10T11:05:01Z","match_totals_all":{"draws":1420,"losses":1735,"wins":1835},"match_totals_tracks":{"highest":{"draws":705,"losses":809,"wins":734},"medium":{"draws":517,"losses":753,"wins":898},"none":{"draws":198,"losses":173,"wins":203}},"model_slug":"claude-opus-4-5","overall":{"max":59.105299689263475,"mean":39.67603526846738,"min":4.775250900350241},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":21,"overall_ranking_status":"partial","per_game":{"GB2-01":54.54022332767149,"GB2-02":4.775250900350241,"GB2-03":26.438809841777037,"GB2-04":20.028370513249424,"GB2-05":47.82596170566252,"GB2-06":53.59615975953049,"GB2-07":50.61905487171679,"GB2-08":23.32111670246394},"per_game_all":{"GB2-01":47.60779778134761,"GB2-02":10.508219516173808,"GB2-03":35.58397804783979,"GB2-04":27.362654644061355,"GB2-05":52.58978804891543,"GB2-06":50.63065600096312,"GB2-07":48.78962931896592,"GB2-08":44.33555878947201},"per_game_match_totals_all":{"GB2-01":{"draws":185,"losses":199,"wins":251},"GB2-02":{"draws":471,"losses":52,"wins":13},"GB2-03":{"draws":247,"losses":192,"wins":168},"GB2-04":{"draws":253,"losses":124,"wins":51},"GB2-05":{"draws":0,"losses":301,"wins":381},"GB2-06":{"draws":62,"losses":319,"wins":325},"GB2-07":{"draws":0,"losses":364,"wins":374},"GB2-08":{"draws":202,"losses":184,"wins":272}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":39,"losses":80,"wins":124},"GB2-02":{"draws":203,"losses":31,"wins":6},"GB2-03":{"draws":74,"losses":84,"wins":92},"GB2-04":{"draws":167,"losses":100,"wins":32},"GB2-05":{"draws":0,"losses":140,"wins":148},"GB2-06":{"draws":28,"losses":132,"wins":148},"GB2-07":{"draws":0,"losses":143,"wins":157},"GB2-08":{"draws":194,"losses":99,"wins":27}},"medium":{"GB2-01":{"draws":84,"losses":99,"wins":115},"GB2-02":{"draws":210,"losses":13,"wins":3},"GB2-03":{"draws":130,"losses":95,"wins":66},"GB2-04":{"draws":59,"losses":13,"wins":9},"GB2-05":{"draws":0,"losses":131,"wins":185},"GB2-06":{"draws":29,"losses":155,"wins":142},"GB2-07":{"draws":0,"losses":180,"wins":174},"GB2-08":{"draws":5,"losses":67,"wins":204}},"none":{"GB2-01":{"draws":62,"losses":20,"wins":12},"GB2-02":{"draws":58,"losses":8,"wins":4},"GB2-03":{"draws":43,"losses":13,"wins":10},"GB2-04":{"draws":27,"losses":11,"wins":10},"GB2-05":{"draws":0,"losses":30,"wins":48},"GB2-06":{"draws":5,"losses":32,"wins":35},"GB2-07":{"draws":0,"losses":41,"wins":43},"GB2-08":{"draws":3,"losses":18,"wins":41}}},"per_game_raw_elo_all":{"GB2-01":1545.9752134028638,"GB2-02":1444.9413528091957,"GB2-03":1472.9192574952806,"GB2-04":1483.0513801785555,"GB2-05":1540.7172818615252,"GB2-06":1509.664421046772,"GB2-07":1478.9543322793781,"GB2-08":1558.9769065926373},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1625.9511140533318,"GB2-02":1405.6097196384471,"GB2-03":1377.7612868151043,"GB2-04":1420.3582535632365,"GB2-05":1473.1401355707098,"GB2-06":1539.7762840301411,"GB2-07":1494.746440183285,"GB2-08":1321.2243425653037},"medium":{"GB2-01":1562.931340214569,"GB2-02":1434.5467518430132,"GB2-03":1521.0234426696943,"GB2-04":1481.3132261970989,"GB2-05":1533.0248082619837,"GB2-06":1501.2475127581479,"GB2-07":1480.3897304730226,"GB2-08":1710.8842433394993},"none":{"GB2-01":1449.0431859406906,"GB2-02":1494.6675869461267,"GB2-03":1519.9730430010436,"GB2-04":1547.4826607753314,"GB2-05":1615.986901751882,"GB2-06":1487.9694663520272,"GB2-07":1461.726826181827,"GB2-08":1644.8221338731084}},"per_game_tracks":{"highest":{"GB2-01":54.54022332767149,"GB2-02":4.775250900350241,"GB2-03":26.438809841777037,"GB2-04":20.028370513249424,"GB2-05":47.82596170566252,"GB2-06":53.59615975953049,"GB2-07":50.61905487171679,"GB2-08":23.32111670246394},"medium":{"GB2-01":49.56099324474412,"GB2-02":9.845278217768804,"GB2-03":41.5356517346492,"GB2-04":26.62770249214871,"GB2-05":52.6034542376244,"GB2-06":50.63276325737119,"GB2-07":49.57515742958389,"GB2-08":59.105299689263475},"none":{"GB2-01":38.72217677162721,"GB2-02":16.904129430402378,"GB2-03":38.77747256709314,"GB2-04":35.43189092678594,"GB2-05":57.33994820345935,"GB2-06":47.6630449859877,"GB2-07":46.17467565559709,"GB2-08":50.580259976688616}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.14311845280274,"medium":42.43578753789422,"none":41.44919981470518},"reasoning_agg":{"highest":{"max":54.54022332767149,"mean":35.14311845280274,"min":4.775250900350241},"medium":{"max":59.105299689263475,"mean":42.43578753789422,"min":9.845278217768804},"none":{"max":57.33994820345935,"mean":41.44919981470518,"min":16.904129430402378}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"reasoning_settings":{"balanced":"medium","intensive":"high"},"score_diagnostics":{"ceiling_score":59.105299689263475,"expected_score":37.58707088830281,"reasoning_variance":7.292669085091482,"reliability_score":94.30755337116669,"uncertainty_avg":5.692446628833309,"uncertainty_penalty":-2.088964380164569},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.54022332767149,"expected_score":25.19505654419567,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.94806190860707},"medium":{"ceiling_score":59.105299689263475,"expected_score":41.924542997684625,"reliability_score":98.5667796203221,"uncertainty_avg":1.4332203796779086,"uncertainty_penalty":-0.5112445402095958},"none":{"ceiling_score":57.33994820345935,"expected_score":45.641613123028144,"reliability_score":84.35588049317798,"uncertainty_avg":15.644119506822017,"uncertainty_penalty":4.192413308322962}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:621e8d10c5a4ba0a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":2,"cell_count":2,"cost_basis_counts":{"provider_reported":2},"evidence_basis":"Provider-reported","max":0.143734,"mean":0.123945875,"median":0.123945875,"min":0.10415775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":2},"recorded_attempt_count":2,"run_count":2,"total":0.24789175},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"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},"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},"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},"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":2,"cell_count":2,"cost_basis_counts":{"provider_reported":2},"evidence_basis":"Provider-reported","max":0.143734,"mean":0.123945875,"median":0.123945875,"min":0.10415775,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":2},"recorded_attempt_count":2,"run_count":2,"total":0.24789175}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":18,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143734,"mean":0.04530390277777777,"median":0.035486000000000004,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20},"recorded_attempt_count":20,"run_count":18,"total":0.8154702500000001},"codegen_latency_ms":{"attempt_count":20,"max_ms":328036,"mean_ms":53436.555555555555,"min_ms":14709,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":2,"max_ms":328036,"mean_ms":222798.5,"min_ms":117561,"run_count":2},"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":20,"output_max":31468,"output_mean":8149.833333333333,"output_min":2554,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":2,"output_max":31468,"output_mean":26858.0,"output_min":22248,"run_count":2},"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":43.184302591371846,"highest":43.05120520009523,"medium":42.735701184984805,"none":33.482296955476336},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":20,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":20,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":20,"reconciliation_get_attempt_observations":26,"reconciliation_get_attempts":125,"total_output_tokens":146697,"total_reasoning_output_tokens":76794,"total_visible_output_tokens":69903,"visible_token_observations":20},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"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":"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"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":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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":2,"evaluated_cells":2,"first_pass_admitted":2,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":6,"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}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-09-10T11:08:49Z","match_totals_all":{"draws":846,"losses":1511,"wins":1331},"match_totals_tracks":{"highest":{"draws":51,"losses":190,"wins":179},"medium":{"draws":379,"losses":549,"wins":612},"none":{"draws":416,"losses":772,"wins":540}},"model_slug":"meta-muse-spark-1-2","overall":{"max":64.21230002498487,"mean":39.288704593155906,"min":3.906687867060584},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":22,"overall_ranking_status":"partial","per_game":{"GB2-01":51.675962062161574,"GB2-03":34.42644833802889},"per_game_all":{"GB2-01":49.09449241524701,"GB2-03":37.274112767496675},"per_game_match_totals_all":{"GB2-01":{"draws":127,"losses":214,"wins":269},"GB2-02":{"draws":287,"losses":73,"wins":23},"GB2-03":{"draws":142,"losses":296,"wins":275},"GB2-04":{"draws":240,"losses":100,"wins":66},"GB2-05":{"draws":0,"losses":269,"wins":241},"GB2-06":{"draws":0,"losses":148,"wins":60},"GB2-07":{"draws":0,"losses":210,"wins":204},"GB2-08":{"draws":50,"losses":201,"wins":193}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":101,"wins":87},"GB2-03":{"draws":29,"losses":89,"wins":92}},"medium":{"GB2-01":{"draws":7,"losses":45,"wins":146},"GB2-02":{"draws":157,"losses":40,"wins":18},"GB2-03":{"draws":72,"losses":97,"wins":80},"GB2-04":{"draws":101,"losses":53,"wins":30},"GB2-05":{"draws":0,"losses":138,"wins":126},"GB2-07":{"draws":0,"losses":99,"wins":109},"GB2-08":{"draws":42,"losses":77,"wins":103}},"none":{"GB2-01":{"draws":98,"losses":68,"wins":36},"GB2-02":{"draws":130,"losses":33,"wins":5},"GB2-03":{"draws":41,"losses":110,"wins":103},"GB2-04":{"draws":139,"losses":47,"wins":36},"GB2-05":{"draws":0,"losses":131,"wins":115},"GB2-06":{"draws":0,"losses":148,"wins":60},"GB2-07":{"draws":0,"losses":111,"wins":95},"GB2-08":{"draws":8,"losses":124,"wins":90}}},"per_game_raw_elo_all":{"GB2-01":1562.1152817310867,"GB2-03":1482.6173240611708},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1593.052861841246,"GB2-03":1456.8229907189177},"medium":{"GB2-01":1746.306694043386,"GB2-02":1465.9244064409238,"GB2-03":1507.8099657675816,"GB2-04":1390.1989659365513,"GB2-05":1554.5881102767514,"GB2-07":1620.0527433433303,"GB2-08":1623.6330641273657},"none":{"GB2-01":1346.9862893086279,"GB2-02":1405.789468639564,"GB2-03":1483.219015697014,"GB2-04":1472.1129279334805,"GB2-05":1545.8020800815002,"GB2-06":1202.5637405728094,"GB2-07":1350.9626991135992,"GB2-08":1600.6634489201153}},"per_game_tracks":{"highest":{"GB2-01":51.675962062161574,"GB2-03":34.42644833802889},"medium":{"GB2-01":64.21230002498487,"GB2-02":15.37552954010579,"GB2-03":39.96423888645114,"GB2-04":13.992136416293384,"GB2-05":54.128679364952525,"GB2-07":60.67352692884251,"GB2-08":50.80349713326343},"none":{"GB2-01":31.395215158594592,"GB2-02":3.906687867060584,"GB2-03":37.43165107800999,"GB2-04":27.982497616728754,"GB2-05":53.37102488938938,"GB2-06":26.84086876363679,"GB2-07":38.245619988996886,"GB2-08":48.684810281393695}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.05120520009523,"medium":41.33261162389615,"none":33.482296955476336},"reasoning_agg":{"highest":{"max":51.675962062161574,"mean":43.05120520009523,"min":34.42644833802889},"medium":{"max":64.21230002498487,"mean":41.33261162389615,"min":13.992136416293384},"none":{"max":53.37102488938938,"mean":33.482296955476336,"min":3.906687867060584}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":64.21230002498487,"expected_score":40.048006946856894,"reasoning_variance":9.568908244618896,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.7593023537009884},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.675962062161574,"expected_score":32.19070180519054,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.86050339490469},"medium":{"ceiling_score":64.21230002498487,"expected_score":42.559702269456885,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.227090645560736},"none":{"ceiling_score":53.37102488938938,"expected_score":31.47273359811806,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.0095633573582745}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:2975b362b8c181f7","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.02955606902857143,"median":0.0063034062,"min":0.0057139812,"recorded_attempt_count":10,"run_count":7,"total":0.2068924832}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.02955606902857143,"median":0.0063034062,"min":0.0057139812,"recorded_attempt_count":10,"run_count":7,"total":0.2068924832}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":15,"cost_basis_counts":{"provider_reported":27},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.2996388,"mean":0.08564151856,"median":0.0495450162,"min":0.0057139812,"recorded_attempt_count":27,"run_count":15,"total":1.2846227783999995},"codegen_latency_ms":{"attempt_count":27,"max_ms":2144825,"mean_ms":717544.7333333333,"min_ms":43161,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":10,"max_ms":886851,"mean_ms":212184.85714285713,"min_ms":43161,"run_count":7}},"codegen_output_tokens":{"attempt_count":27,"output_max":131072,"output_mean":42903.2,"output_min":2846,"run_count":15},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":10,"output_max":42691,"output_mean":10496.0,"output_min":2846,"run_count":7}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":44.10609034219564,"none":37.325437581403314},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["error","length","stop"],"indexed_attempts":27,"output_token_observations":27,"total_output_tokens":643548},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"model_code_failure_rate":0.25,"model_code_failures":2,"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},"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5714285714285714,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"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":2,"repaired_rate":0.2857142857142857}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:01Z","match_totals_all":{"draws":196,"losses":318,"wins":322},"match_totals_tracks":{"medium":{"draws":92,"losses":152,"wins":154},"none":{"draws":104,"losses":166,"wins":168}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":70.02330483752023,"mean":38.47985425221955,"min":16.473094673491183},"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","fixed_coverage_incomplete"],"overall_official_rank":23,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":45,"wins":25},"GB2-02":{"draws":49,"losses":5,"wins":4},"GB2-03":{"draws":28,"losses":12,"wins":12},"GB2-04":{"draws":38,"losses":12,"wins":14},"GB2-05":{"draws":0,"losses":96,"wins":74},"GB2-06":{"draws":1,"losses":56,"wins":97},"GB2-07":{"draws":0,"losses":76,"wins":94},"GB2-08":{"draws":54,"losses":16,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":38,"losses":12,"wins":14},"GB2-05":{"draws":0,"losses":59,"wins":33},"GB2-06":{"draws":0,"losses":19,"wins":55},"GB2-07":{"draws":0,"losses":46,"wins":50},"GB2-08":{"draws":54,"losses":16,"wins":2}},"none":{"GB2-01":{"draws":26,"losses":45,"wins":25},"GB2-02":{"draws":49,"losses":5,"wins":4},"GB2-03":{"draws":28,"losses":12,"wins":12},"GB2-05":{"draws":0,"losses":37,"wins":41},"GB2-06":{"draws":1,"losses":37,"wins":42},"GB2-07":{"draws":0,"losses":30,"wins":44}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1565.6849655511323,"GB2-05":1322.9127343144567,"GB2-06":1773.266695390409,"GB2-07":1488.1477983527448,"GB2-08":1391.7465030285916},"none":{"GB2-01":1417.1690382660745,"GB2-02":1496.8783062336413,"GB2-03":1462.1418660952263,"GB2-05":1431.8923348583521,"GB2-06":1429.373702874258,"GB2-07":1546.9374591439505}},"per_game_tracks":{"medium":{"GB2-04":39.69028173978519,"GB2-05":34.643217642393346,"GB2-06":70.02330483752023,"GB2-07":48.60664400355754,"GB2-08":27.56700348772194},"none":{"GB2-01":36.13581747923515,"GB2-02":16.473094673491183,"GB2-03":32.12832035449617,"GB2-05":42.90940679325011,"GB2-06":43.26617619713358,"GB2-07":53.03980999081365}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.04534198844345,"none":35.91436651599566},"reasoning_agg":{"medium":{"max":70.02330483752023,"mean":41.04534198844345,"min":27.56700348772194},"none":{"max":53.03980999081365,"mean":35.91436651599566,"min":16.473094673491183}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":70.02330483752023,"reasoning_variance":5.130975472447787},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":70.02330483752023,"expected_score":45.03179808344573,"reliability_score":87.57242783903314,"uncertainty_avg":12.427572160966859,"uncertainty_penalty":3.986456095002282},"none":{"ceiling_score":53.03980999081365,"expected_score":40.41787491606849,"reliability_score":84.73549612629054,"uncertainty_avg":15.264503873709456,"uncertainty_penalty":4.503508400072832}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:73d75d50d9e31317","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239874999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.72882375},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112225},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":40.38266609921668,"none":39.16034768625658},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"total_output_tokens":178317},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"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,"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}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:11Z","match_totals_all":{"draws":367,"losses":332,"wins":339},"match_totals_tracks":{"medium":{"draws":206,"losses":170,"wins":190},"none":{"draws":161,"losses":162,"wins":149}},"model_slug":"qwen-qwen3-7-max","overall":{"max":71.61968219996771,"mean":38.46573713577355,"min":12.895585775886488},"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":24,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":45,"losses":50,"wins":45},"GB2-02":{"draws":106,"losses":11,"wins":11},"GB2-03":{"draws":37,"losses":5,"wins":4},"GB2-04":{"draws":52,"losses":16,"wins":16},"GB2-05":{"draws":0,"losses":93,"wins":91},"GB2-06":{"draws":12,"losses":70,"wins":78},"GB2-07":{"draws":0,"losses":32,"wins":84},"GB2-08":{"draws":115,"losses":55,"wins":10}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":24,"losses":38,"wins":10},"GB2-02":{"draws":61,"losses":6,"wins":3},"GB2-04":{"draws":52,"losses":16,"wins":16},"GB2-05":{"draws":0,"losses":49,"wins":53},"GB2-06":{"draws":10,"losses":25,"wins":51},"GB2-07":{"draws":0,"losses":10,"wins":48},"GB2-08":{"draws":59,"losses":26,"wins":9}},"none":{"GB2-01":{"draws":21,"losses":12,"wins":35},"GB2-02":{"draws":45,"losses":5,"wins":8},"GB2-03":{"draws":37,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":44,"wins":38},"GB2-06":{"draws":2,"losses":45,"wins":27},"GB2-07":{"draws":0,"losses":22,"wins":36},"GB2-08":{"draws":56,"losses":29,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1267.5817664088527,"GB2-02":1472.4077462615205,"GB2-04":1505.912180056845,"GB2-05":1560.9179428825034,"GB2-06":1629.0069225523212,"GB2-07":1775.8567877936537,"GB2-08":1429.143126017843},"none":{"GB2-01":1655.1143223765005,"GB2-02":1503.3189852487574,"GB2-03":1453.388701186896,"GB2-05":1520.989498345392,"GB2-06":1317.7760054622622,"GB2-07":1630.9732967737627,"GB2-08":1377.4330339898045}},"per_game_tracks":{"medium":{"GB2-01":23.323632491834545,"GB2-02":12.895585775886488,"GB2-04":30.82886597508527,"GB2-05":53.46148943250204,"GB2-06":59.000095631169074,"GB2-07":71.61968219996771,"GB2-08":31.549311188071584},"none":{"GB2-01":55.08434421637588,"GB2-02":17.63292970387716,"GB2-03":30.86368222336517,"GB2-05":49.97948143649212,"GB2-06":34.4025425756531,"GB2-07":59.55002702144701,"GB2-08":26.609426626585595}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.05683089161168,"none":37.87464337993543},"reasoning_agg":{"medium":{"max":71.61968219996771,"mean":39.05683089161168,"min":12.895585775886488},"none":{"max":59.55002702144701,"mean":37.87464337993543,"min":17.63292970387716}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":71.61968219996771,"reasoning_variance":1.1821875116762541},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":71.61968219996771,"expected_score":41.4157483735555,"reliability_score":87.84175218468629,"uncertainty_avg":12.158247815313718,"uncertainty_penalty":2.35891748194382},"none":{"ceiling_score":59.55002702144701,"expected_score":43.41658707283817,"reliability_score":82.38755472452097,"uncertainty_avg":17.612445275479033,"uncertainty_penalty":5.541943692902741}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:9a2f1affb126d4fe","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031539999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031539999998},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":41.10005622496815},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":18,"finish_reasons":["length","stop"],"indexed_attempts":18,"output_token_observations":18,"total_output_tokens":308283},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k2.7-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-06"],"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:26:41Z","match_totals_all":{"draws":143,"losses":159,"wins":190},"match_totals_tracks":{"medium":{"draws":143,"losses":159,"wins":190}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":55.31987902290327,"mean":38.247912032324855,"min":15.971215353629413},"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":25,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":37,"wins":45},"GB2-02":{"draws":75,"losses":12,"wins":3},"GB2-04":{"draws":58,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":40,"wins":42},"GB2-07":{"draws":0,"losses":40,"wins":50},"GB2-08":{"draws":6,"losses":23,"wins":43}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":37,"wins":45},"GB2-02":{"draws":75,"losses":12,"wins":3},"GB2-04":{"draws":58,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":40,"wins":42},"GB2-07":{"draws":0,"losses":40,"wins":50},"GB2-08":{"draws":6,"losses":23,"wins":43}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1515.2417696657326,"GB2-02":1483.9471496450988,"GB2-04":1491.0137499861821,"GB2-05":1589.1184862164962,"GB2-07":1510.4961528383703,"GB2-08":1668.9996561249077}},"per_game_tracks":{"medium":{"GB2-01":44.01459558203363,"GB2-02":15.971215353629413,"GB2-04":27.795545497153316,"GB2-05":55.31987902290327,"GB2-07":50.35863516788991,"GB2-08":53.14046672619939}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.247912032324855},"reasoning_agg":{"medium":{"max":55.31987902290327,"mean":38.247912032324855,"min":15.971215353629413}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":55.31987902290327},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":55.31987902290327,"expected_score":43.71048968987924,"reliability_score":88.69043539915711,"uncertainty_avg":11.309564600842888,"uncertainty_penalty":5.462577657554384}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:3c7e1f4e41b6571d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"evidence_basis":"Standard list-price estimate","max":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},"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478314},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"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},"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545000000001},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"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},"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},"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":38.210250252668835,"highest":48.242638257789736,"medium":42.70271893536102,"none":23.68539356485576},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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":5,"first_pass_rate":0.625,"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},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-09-10T11:08:39Z","match_totals_all":{"draws":937,"losses":1169,"wins":987},"match_totals_tracks":{"highest":{"draws":230,"losses":378,"wins":414},"medium":{"draws":323,"losses":407,"wins":319},"none":{"draws":384,"losses":384,"wins":254}},"model_slug":"google-gemini-3-5-flash","overall":{"max":82.02311872112153,"mean":38.210250252668835,"min":8.860426297576485},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":26,"overall_ranking_status":"partial","per_game":{"GB2-01":82.02311872112153,"GB2-02":29.081754776942507,"GB2-03":41.08785360578334,"GB2-04":19.436408028603687,"GB2-05":50.68357221574452,"GB2-06":73.08683178535341,"GB2-07":52.78791504126206,"GB2-08":37.75365188750678},"per_game_all":{"GB2-01":58.7317425942098,"GB2-02":16.681988757978285,"GB2-03":32.43585723761161,"GB2-04":19.951806402295137,"GB2-05":41.0981911916367,"GB2-06":65.0997676996697,"GB2-07":46.340279158472036,"GB2-08":25.342368979477428},"per_game_match_totals_all":{"GB2-01":{"draws":46,"losses":111,"wins":211},"GB2-02":{"draws":298,"losses":53,"wins":31},"GB2-03":{"draws":119,"losses":162,"wins":114},"GB2-04":{"draws":219,"losses":77,"wins":74},"GB2-05":{"draws":0,"losses":250,"wins":134},"GB2-06":{"draws":20,"losses":193,"wins":181},"GB2-07":{"draws":0,"losses":209,"wins":191},"GB2-08":{"draws":235,"losses":114,"wins":51}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":18,"wins":92},"GB2-02":{"draws":55,"losses":20,"wins":29},"GB2-03":{"draws":45,"losses":46,"wins":41},"GB2-04":{"draws":67,"losses":17,"wins":32},"GB2-05":{"draws":0,"losses":91,"wins":53},"GB2-06":{"draws":6,"losses":49,"wins":63},"GB2-07":{"draws":0,"losses":79,"wins":61},"GB2-08":{"draws":49,"losses":58,"wins":43}},"medium":{"GB2-01":{"draws":2,"losses":56,"wins":62},"GB2-02":{"draws":131,"losses":28,"wins":1},"GB2-03":{"draws":35,"losses":44,"wins":52},"GB2-04":{"draws":70,"losses":44,"wins":26},"GB2-05":{"draws":0,"losses":62,"wins":58},"GB2-06":{"draws":10,"losses":56,"wins":52},"GB2-07":{"draws":0,"losses":69,"wins":67},"GB2-08":{"draws":75,"losses":48,"wins":1}},"none":{"GB2-01":{"draws":36,"losses":37,"wins":57},"GB2-02":{"draws":112,"losses":5,"wins":1},"GB2-03":{"draws":39,"losses":72,"wins":21},"GB2-04":{"draws":82,"losses":16,"wins":16},"GB2-05":{"draws":0,"losses":97,"wins":23},"GB2-06":{"draws":4,"losses":88,"wins":66},"GB2-07":{"draws":0,"losses":61,"wins":63},"GB2-08":{"draws":111,"losses":8,"wins":7}}},"per_game_raw_elo_all":{"GB2-01":1687.303802270628,"GB2-02":1481.7055377707447,"GB2-03":1444.8816083948634,"GB2-04":1432.7903659566189,"GB2-05":1399.09777538809,"GB2-06":1699.1396127037353,"GB2-07":1454.874453748819,"GB2-08":1355.4194326311354},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1971.1902035562755,"GB2-02":1553.8558854814169,"GB2-03":1527.9956475562567,"GB2-04":1430.6673306827304,"GB2-05":1519.2842748535527,"GB2-06":1802.9206210982431,"GB2-07":1531.4117810372288,"GB2-08":1487.919514273735},"medium":{"GB2-01":1665.395177936089,"GB2-02":1452.0639490111673,"GB2-03":1586.9153526524012,"GB2-04":1489.2374098132043,"GB2-05":1660.6856082501972,"GB2-06":1757.9430530119864,"GB2-07":1521.2495664877445,"GB2-08":1220.0518609352368},"none":{"GB2-01":1425.3260253195192,"GB2-02":1439.1967788196498,"GB2-03":1219.7338249759325,"GB2-04":1378.4663573739215,"GB2-05":1017.3234430605204,"GB2-06":1536.5551640009767,"GB2-07":1311.9620137214838,"GB2-08":1358.2869226844339}},"per_game_tracks":{"highest":{"GB2-01":82.02311872112153,"GB2-02":29.081754776942507,"GB2-03":41.08785360578334,"GB2-04":19.436408028603687,"GB2-05":50.68357221574452,"GB2-06":73.08683178535341,"GB2-07":52.78791504126206,"GB2-08":37.75365188750678},"medium":{"GB2-01":56.899512876213336,"GB2-02":12.10378519941586,"GB2-03":47.204403387185614,"GB2-04":29.674580273173802,"GB2-05":61.52097695135376,"GB2-06":69.56944867447089,"GB2-07":51.90066980814227,"GB2-08":12.748374312932619},"none":{"GB2-01":37.2725961852945,"GB2-02":8.860426297576485,"GB2-03":9.01531471986587,"GB2-04":10.74443090510793,"GB2-05":11.090024407811828,"GB2-06":52.643022639184814,"GB2-07":34.33225262601179,"GB2-08":25.52508073799289}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.242638257789736,"medium":42.70271893536102,"none":23.68539356485576},"reasoning_agg":{"highest":{"max":82.02311872112153,"mean":48.242638257789736,"min":19.436408028603687},"medium":{"max":69.56944867447089,"mean":42.70271893536102,"min":12.10378519941586},"none":{"max":52.643022639184814,"mean":23.68539356485576,"min":8.860426297576485}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":82.02311872112153,"expected_score":35.720913485931256,"reasoning_variance":24.557244692933974,"reliability_score":98.89961913534914,"uncertainty_avg":1.1003808646508628,"uncertainty_penalty":-2.48933676673758},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.02311872112153,"expected_score":42.089125106311386,"reliability_score":98.53876628720622,"uncertainty_avg":1.461233712793778,"uncertainty_penalty":-6.15351315147835},"medium":{"ceiling_score":69.56944867447089,"expected_score":42.41473782009479,"reliability_score":99.19182808618784,"uncertainty_avg":0.8081719138121601,"uncertainty_penalty":-0.28798111526622705},"none":{"ceiling_score":52.643022639184814,"expected_score":22.658877531387617,"reliability_score":98.96826303265335,"uncertainty_avg":1.0317369673466503,"uncertainty_penalty":-1.0265160334681447}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:65623d2d6810d868","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"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},"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"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":0.9576840000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"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":0.8354799999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.957684},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"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},"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":6.452750000000002},"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":38.5184845793749,"highest":42.05605079183701,"medium":39.97699964131566,"none":33.52240330497203},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.8,"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"model_code_failure_rate":0.2,"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}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-09-10T11:05:04Z","match_totals_all":{"draws":1099,"losses":1205,"wins":1072},"match_totals_tracks":{"highest":{"draws":305,"losses":420,"wins":396},"medium":{"draws":371,"losses":410,"wins":354},"none":{"draws":423,"losses":375,"wins":322}},"model_slug":"qwen-qwen3-8-max","overall":{"max":88.76990902930297,"mean":37.75785336349297,"min":6.07109411954341},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":23.733671873464495,"GB2-02":22.390163615050678,"GB2-03":39.20691764507233,"GB2-04":50.55866652707872,"GB2-05":47.821376524556854,"GB2-06":50.937559609413256,"GB2-07":73.66211615758745,"GB2-08":28.137934382472274},"per_game_all":{"GB2-01":26.151251252951607,"GB2-02":13.8195019827384,"GB2-03":34.81425547063705,"GB2-04":29.0939353628487,"GB2-05":66.07133986642707,"GB2-06":40.07821153034174,"GB2-07":60.043825464289405,"GB2-08":38.0755557047652},"per_game_match_totals_all":{"GB2-01":{"draws":134,"losses":172,"wins":81},"GB2-02":{"draws":307,"losses":56,"wins":19},"GB2-03":{"draws":146,"losses":167,"wins":125},"GB2-04":{"draws":250,"losses":64,"wins":70},"GB2-05":{"draws":0,"losses":153,"wins":268},"GB2-06":{"draws":47,"losses":280,"wins":144},"GB2-07":{"draws":0,"losses":175,"wins":250},"GB2-08":{"draws":215,"losses":138,"wins":115}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":60,"wins":29},"GB2-02":{"draws":82,"losses":19,"wins":12},"GB2-03":{"draws":22,"losses":74,"wins":55},"GB2-04":{"draws":52,"losses":26,"wins":49},"GB2-05":{"draws":0,"losses":71,"wins":83},"GB2-06":{"draws":20,"losses":103,"wins":54},"GB2-07":{"draws":0,"losses":46,"wins":94},"GB2-08":{"draws":97,"losses":21,"wins":20}},"medium":{"GB2-01":{"draws":62,"losses":34,"wins":38},"GB2-02":{"draws":122,"losses":28,"wins":2},"GB2-03":{"draws":48,"losses":56,"wins":40},"GB2-04":{"draws":95,"losses":22,"wins":10},"GB2-05":{"draws":0,"losses":66,"wins":68},"GB2-06":{"draws":15,"losses":84,"wins":61},"GB2-07":{"draws":0,"losses":66,"wins":82},"GB2-08":{"draws":29,"losses":54,"wins":53}},"none":{"GB2-01":{"draws":40,"losses":78,"wins":14},"GB2-02":{"draws":103,"losses":9,"wins":5},"GB2-03":{"draws":76,"losses":37,"wins":30},"GB2-04":{"draws":103,"losses":16,"wins":11},"GB2-05":{"draws":0,"losses":16,"wins":117},"GB2-06":{"draws":12,"losses":93,"wins":29},"GB2-07":{"draws":0,"losses":63,"wins":74},"GB2-08":{"draws":89,"losses":63,"wins":42}}},"per_game_raw_elo_all":{"GB2-01":1290.256169788162,"GB2-02":1465.6085784838388,"GB2-03":1466.0118255791197,"GB2-04":1487.2624075252495,"GB2-05":1716.07560318436,"GB2-06":1376.1414388124174,"GB2-07":1618.3271339380287,"GB2-08":1491.1066961505933},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1261.9654836736365,"GB2-02":1515.1242452926706,"GB2-03":1507.677115528226,"GB2-04":1617.0984767902028,"GB2-05":1481.6810024880726,"GB2-06":1513.006229205502,"GB2-07":1781.9845675213576,"GB2-08":1385.047314059996},"medium":{"GB2-01":1428.6091705822635,"GB2-02":1457.8391048767317,"GB2-03":1531.1049810468219,"GB2-04":1435.633225132272,"GB2-05":1660.04663503317,"GB2-06":1543.9232121385512,"GB2-07":1392.6769732770667,"GB2-08":1632.9127357518287},"none":{"GB2-01":1180.193855108586,"GB2-02":1423.8623852821136,"GB2-03":1359.2533801623117,"GB2-04":1409.0555206532733,"GB2-05":2006.4991720318374,"GB2-06":1071.4948750931987,"GB2-07":1680.3198610156614,"GB2-08":1455.3600386399553}},"per_game_tracks":{"highest":{"GB2-01":23.733671873464495,"GB2-02":22.390163615050678,"GB2-03":39.20691764507233,"GB2-04":50.55866652707872,"GB2-05":47.821376524556854,"GB2-06":50.937559609413256,"GB2-07":73.66211615758745,"GB2-08":28.137934382472274},"medium":{"GB2-01":37.585502632645984,"GB2-02":12.997248213621113,"GB2-03":41.5639073510403,"GB2-04":20.5271127751659,"GB2-05":61.62273404542139,"GB2-06":53.23468310597876,"GB2-07":41.30685657778837,"GB2-08":50.977952428863446},"none":{"GB2-01":17.134579252744338,"GB2-02":6.07109411954341,"GB2-03":23.67194141579853,"GB2-04":16.196026786301488,"GB2-05":88.76990902930297,"GB2-06":16.062391875633203,"GB2-07":65.16250365749241,"GB2-08":35.11078030295988}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.77415714419122,"medium":39.97699964131566,"none":33.52240330497203},"reasoning_agg":{"highest":{"max":73.66211615758745,"mean":39.77415714419122,"min":22.390163615050678},"medium":{"max":61.62273404542139,"mean":39.97699964131566,"min":12.997248213621113},"none":{"max":88.76990902930297,"mean":33.52240330497203,"min":6.07109411954341}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":88.76990902930297,"expected_score":34.81817267548308,"reasoning_variance":6.454596336343627,"reliability_score":99.67648991068423,"uncertainty_avg":0.3235100893157731,"uncertainty_penalty":-2.9396806880098865},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.66211615758745,"expected_score":33.52652675704636,"reliability_score":99.36983282193711,"uncertainty_avg":0.630167178062897,"uncertainty_penalty":-6.247630387144859},"medium":{"ceiling_score":61.62273404542139,"expected_score":40.32298267359882,"reliability_score":99.9444782719801,"uncertainty_avg":0.05552172801990163,"uncertainty_penalty":0.34598303228316496},"none":{"ceiling_score":88.76990902930297,"expected_score":30.605008595804065,"reliability_score":99.71515863813548,"uncertainty_avg":0.2848413618645207,"uncertainty_penalty":-2.917394709167965}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:bf80275c6345b0be","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.913572594249},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.372620130294},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"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}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"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},"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},"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.913572594249}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640004},"codegen_latency_ms":{"attempt_count":35,"max_ms":1560134,"mean_ms":432334.7916666667,"min_ms":52746,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1560134,"mean_ms":818090.375,"min_ms":426935,"run_count":8},"medium":{"attempt_count":12,"max_ms":673313,"mean_ms":392142.875,"min_ms":86869,"run_count":8},"none":{"attempt_count":12,"max_ms":170011,"mean_ms":86771.125,"min_ms":52746,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":74570,"output_mean":21422.416666666668,"output_min":2493,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":74570,"output_mean":43080.25,"output_min":21434,"run_count":8},"medium":{"attempt_count":12,"output_max":23131,"output_mean":16655.5,"output_min":5286,"run_count":8},"none":{"attempt_count":12,"output_max":8274,"output_mean":4531.5,"output_min":2493,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"all":39.17049918780878,"highest":38.9734452809923,"medium":40.91602273478811,"none":33.97145389410562},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":514138,"total_reasoning_output_tokens":410486,"total_visible_output_tokens":103652,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-09-10T10:50:08Z","match_totals_all":{"draws":919,"losses":1001,"wins":981},"match_totals_tracks":{"highest":{"draws":348,"losses":388,"wins":329},"medium":{"draws":237,"losses":354,"wins":427},"none":{"draws":334,"losses":259,"wins":225}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":70.6332524935784,"mean":37.167822693466015,"min":8.46888583743832},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":23.77634202676228,"GB2-02":10.858956125600434,"GB2-03":36.03496399223896,"GB2-04":30.628175763052685,"GB2-05":48.81033417432173,"GB2-06":70.6332524935784,"GB2-07":63.292091931054706,"GB2-08":27.753445741329188},"per_game_all":{"GB2-01":33.722154531139175,"GB2-03":30.612650272713648,"GB2-04":24.813490856498394,"GB2-05":47.15444821884315,"GB2-07":59.29369454872184,"GB2-08":39.426556698936466},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":217,"wins":115},"GB2-02":{"draws":198,"losses":18,"wins":10},"GB2-03":{"draws":160,"losses":140,"wins":104},"GB2-04":{"draws":249,"losses":83,"wins":60},"GB2-05":{"draws":0,"losses":187,"wins":237},"GB2-06":{"draws":19,"losses":87,"wins":130},"GB2-07":{"draws":0,"losses":198,"wins":226},"GB2-08":{"draws":232,"losses":71,"wins":99}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":7,"losses":81,"wins":33},"GB2-02":{"draws":102,"losses":12,"wins":8},"GB2-03":{"draws":49,"losses":44,"wins":39},"GB2-04":{"draws":64,"losses":52,"wins":24},"GB2-05":{"draws":0,"losses":77,"wins":85},"GB2-06":{"draws":14,"losses":42,"wins":62},"GB2-07":{"draws":0,"losses":54,"wins":70},"GB2-08":{"draws":112,"losses":26,"wins":8}},"medium":{"GB2-01":{"draws":8,"losses":83,"wins":59},"GB2-02":{"draws":96,"losses":6,"wins":2},"GB2-03":{"draws":43,"losses":59,"wins":30},"GB2-04":{"draws":84,"losses":20,"wins":22},"GB2-05":{"draws":0,"losses":53,"wins":89},"GB2-06":{"draws":5,"losses":45,"wins":68},"GB2-07":{"draws":0,"losses":55,"wins":69},"GB2-08":{"draws":1,"losses":33,"wins":88}},"none":{"GB2-01":{"draws":46,"losses":53,"wins":23},"GB2-03":{"draws":68,"losses":37,"wins":35},"GB2-04":{"draws":101,"losses":11,"wins":14},"GB2-05":{"draws":0,"losses":57,"wins":63},"GB2-07":{"draws":0,"losses":89,"wins":87},"GB2-08":{"draws":119,"losses":12,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1382.1504416754422,"GB2-03":1426.981562289383,"GB2-04":1461.0697993729557,"GB2-05":1474.7586113865134,"GB2-07":1609.694069977965,"GB2-08":1507.9995881241996},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1262.4843318048977,"GB2-02":1449.6936587759922,"GB2-03":1479.430332315426,"GB2-04":1494.9994974820688,"GB2-05":1493.4990644868933,"GB2-06":1771.5461514507922,"GB2-07":1659.5943657506098,"GB2-08":1379.9427905062857},"medium":{"GB2-01":1527.056868577737,"GB2-02":1439.390578828434,"GB2-03":1385.0409301782825,"GB2-04":1447.2604001496738,"GB2-05":1492.6092653665523,"GB2-06":1481.0349225157022,"GB2-07":1686.0872386532578,"GB2-08":1758.5557003334645},"none":{"GB2-01":1356.9101246436917,"GB2-03":1416.4734243744404,"GB2-04":1440.9495004871246,"GB2-05":1438.1675043060943,"GB2-07":1483.4006055300267,"GB2-08":1385.5002735328487}},"per_game_tracks":{"highest":{"GB2-01":23.77634202676228,"GB2-02":10.858956125600434,"GB2-03":36.03496399223896,"GB2-04":30.628175763052685,"GB2-05":48.81033417432173,"GB2-06":70.6332524935784,"GB2-07":63.292091931054706,"GB2-08":27.753445741329188},"medium":{"GB2-01":45.836055739473956,"GB2-02":8.46888583743832,"GB2-03":26.214390866699837,"GB2-04":22.42835891103803,"GB2-05":48.574464166754886,"GB2-06":47.91438765370183,"GB2-07":65.49910556920233,"GB2-08":62.39253313399566},"none":{"GB2-01":31.55406582718129,"GB2-03":29.588595959202145,"GB2-04":21.38393789540447,"GB2-05":44.07854631545282,"GB2-07":49.08988614590849,"GB2-08":28.13369122148454}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.9734452809923,"medium":40.91602273478811,"none":31.61400006461763},"reasoning_agg":{"highest":{"max":70.6332524935784,"mean":38.9734452809923,"min":10.858956125600434},"medium":{"max":65.49910556920233,"mean":40.91602273478811,"min":8.46888583743832},"none":{"max":49.08988614590849,"mean":31.61400006461763,"min":21.38393789540447}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":70.6332524935784,"expected_score":35.88377350986374,"reasoning_variance":9.302022670170476,"reliability_score":99.4962360008805,"uncertainty_avg":0.5037639991194961,"uncertainty_penalty":-1.2840491836022778},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.6332524935784,"expected_score":30.21719434256549,"reliability_score":99.26154510549534,"uncertainty_avg":0.7384548945046554,"uncertainty_penalty":-8.75625093842681},"medium":{"ceiling_score":65.49910556920233,"expected_score":40.717567128111405,"reliability_score":98.74342559337371,"uncertainty_avg":1.2565744066262918,"uncertainty_penalty":-0.1984556066767027},"none":{"ceiling_score":49.08988614590849,"expected_score":33.75082936885701,"reliability_score":99.39069122354621,"uncertainty_avg":0.6093087764537941,"uncertainty_penalty":2.136829304239381}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:c2223bad538b65f0","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"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},"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":{"medium":47.54012688882566,"none":26.70950374619811},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":22,"finish_reasons":["stop"],"indexed_attempts":22,"output_token_observations":22,"provider_post_attempt_observations":22,"provider_post_attempts":22,"reasoning_token_observations":22,"reconciliation_get_attempt_observations":22,"reconciliation_get_attempts":100,"total_output_tokens":640481,"total_reasoning_output_tokens":544948,"total_visible_output_tokens":95533,"visible_token_observations":22},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-09-10T11:08:50Z","match_totals_all":{"draws":781,"losses":757,"wins":576},"match_totals_tracks":{"medium":{"draws":346,"losses":337,"wins":367},"none":{"draws":435,"losses":420,"wins":209}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":72.14023042347958,"mean":37.12481531751189,"min":8.345895178371906},"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":29,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":108,"losses":84,"wins":93},"GB2-02":{"draws":188,"losses":42,"wins":18},"GB2-03":{"draws":85,"losses":105,"wins":95},"GB2-04":{"draws":162,"losses":41,"wins":25},"GB2-05":{"draws":0,"losses":137,"wins":103},"GB2-06":{"draws":29,"losses":112,"wins":133},"GB2-07":{"draws":0,"losses":160,"wins":88},"GB2-08":{"draws":209,"losses":76,"wins":21}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":65,"losses":47,"wins":53},"GB2-02":{"draws":58,"losses":29,"wins":17},"GB2-03":{"draws":32,"losses":40,"wins":59},"GB2-04":{"draws":78,"losses":21,"wins":15},"GB2-05":{"draws":0,"losses":48,"wins":72},"GB2-06":{"draws":24,"losses":32,"wins":62},"GB2-07":{"draws":0,"losses":51,"wins":73},"GB2-08":{"draws":89,"losses":69,"wins":16}},"none":{"GB2-01":{"draws":43,"losses":37,"wins":40},"GB2-02":{"draws":130,"losses":13,"wins":1},"GB2-03":{"draws":53,"losses":65,"wins":36},"GB2-04":{"draws":84,"losses":20,"wins":10},"GB2-05":{"draws":0,"losses":89,"wins":31},"GB2-06":{"draws":5,"losses":80,"wins":71},"GB2-07":{"draws":0,"losses":109,"wins":15},"GB2-08":{"draws":120,"losses":7,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1488.517249176712,"GB2-02":1510.8092095628847,"GB2-03":1674.4366977746672,"GB2-04":1429.8842293634966,"GB2-05":1737.7777429081157,"GB2-06":1790.8162168118583,"GB2-07":1735.5902511796148,"GB2-08":1415.7391422180938},"none":{"GB2-01":1386.0107501750101,"GB2-02":1432.8897885177287,"GB2-03":1516.3440787059294,"GB2-04":1429.006254461214,"GB2-05":1162.6706570017993,"GB2-06":1529.1409844045036,"GB2-07":1027.8258491263755,"GB2-08":1373.0820244530325}},"per_game_tracks":{"medium":{"GB2-01":42.79036526143108,"GB2-02":21.32992572991054,"GB2-03":56.31040205184428,"GB2-04":19.25382084260791,"GB2-05":67.56396485889975,"GB2-06":72.14023042347958,"GB2-07":69.62300048148802,"GB2-08":31.30930546094415},"none":{"GB2-01":33.92289285331455,"GB2-02":8.345895178371906,"GB2-03":40.141482789051,"GB2-04":19.108520570352844,"GB2-05":22.483293774914944,"GB2-06":52.04746013492715,"GB2-07":10.662022800175135,"GB2-08":26.964461868477382}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":47.54012688882566,"none":26.70950374619811},"reasoning_agg":{"medium":{"max":72.14023042347958,"mean":47.54012688882566,"min":19.25382084260791},"none":{"max":52.04746013492715,"mean":26.70950374619811,"min":8.345895178371906}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":72.14023042347958,"reasoning_variance":20.83062314262755},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":72.14023042347958,"expected_score":49.000123926404,"reliability_score":98.41486576057572,"uncertainty_avg":1.5851342394242718,"uncertainty_penalty":1.45999703757834},"none":{"ceiling_score":52.04746013492715,"expected_score":26.46670572175381,"reliability_score":99.0930386411122,"uncertainty_avg":0.9069613588878,"uncertainty_penalty":-0.24279802444429777}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:4d974e631781e828","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.50466,"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},"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},"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},"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.52499},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337000000000003},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.8079499999999995}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.8263099999999994},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":36.77264902241198,"highest":43.54754891745874,"medium":33.75922437630374,"none":33.01117377347347},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-09-10T10:49:31Z","match_totals_all":{"draws":1458,"losses":1850,"wins":1780},"match_totals_tracks":{"highest":{"draws":376,"losses":619,"wins":662},"medium":{"draws":573,"losses":573,"wins":587},"none":{"draws":509,"losses":658,"wins":531}},"model_slug":"claude-sonnet-5","overall":{"max":74.33339438299416,"mean":36.77264902241199,"min":7.484704864315055},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.70826959385252,"GB2-02":7.484704864315055,"GB2-03":41.97211414971662,"GB2-04":39.02653543609264,"GB2-05":51.4429639826475,"GB2-06":25.64947969953627,"GB2-07":63.76292923051514,"GB2-08":74.33339438299416},"per_game_all":{"GB2-01":41.06373834639097,"GB2-02":10.722411083165897,"GB2-03":38.022332123789035,"GB2-04":28.38039556531139,"GB2-05":42.149216974864544,"GB2-06":35.84686930093976,"GB2-07":52.52198965708059,"GB2-08":45.474239127753684},"per_game_match_totals_all":{"GB2-01":{"draws":119,"losses":279,"wins":295},"GB2-02":{"draws":468,"losses":31,"wins":9},"GB2-03":{"draws":243,"losses":232,"wins":180},"GB2-04":{"draws":336,"losses":133,"wins":109},"GB2-05":{"draws":0,"losses":335,"wins":301},"GB2-06":{"draws":38,"losses":332,"wins":284},"GB2-07":{"draws":0,"losses":318,"wins":376},"GB2-08":{"draws":254,"losses":190,"wins":226}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":28,"losses":108,"wins":106},"GB2-02":{"draws":155,"losses":10,"wins":1},"GB2-03":{"draws":90,"losses":84,"wins":59},"GB2-04":{"draws":90,"losses":42,"wins":52},"GB2-05":{"draws":0,"losses":109,"wins":101},"GB2-06":{"draws":11,"losses":129,"wins":68},"GB2-07":{"draws":0,"losses":85,"wins":123},"GB2-08":{"draws":2,"losses":52,"wins":152}},"medium":{"GB2-01":{"draws":50,"losses":74,"wins":97},"GB2-02":{"draws":164,"losses":6,"wins":6},"GB2-03":{"draws":80,"losses":69,"wins":63},"GB2-04":{"draws":109,"losses":59,"wins":30},"GB2-05":{"draws":0,"losses":91,"wins":129},"GB2-06":{"draws":13,"losses":107,"wins":94},"GB2-07":{"draws":0,"losses":123,"wins":147},"GB2-08":{"draws":157,"losses":44,"wins":21}},"none":{"GB2-01":{"draws":41,"losses":97,"wins":92},"GB2-02":{"draws":149,"losses":15,"wins":2},"GB2-03":{"draws":73,"losses":79,"wins":58},"GB2-04":{"draws":137,"losses":32,"wins":27},"GB2-05":{"draws":0,"losses":135,"wins":71},"GB2-06":{"draws":14,"losses":96,"wins":122},"GB2-07":{"draws":0,"losses":110,"wins":106},"GB2-08":{"draws":95,"losses":94,"wins":53}}},"per_game_raw_elo_all":{"GB2-01":1462.7510658890262,"GB2-02":1443.525858460127,"GB2-03":1490.8784799330235,"GB2-04":1476.4854573163373,"GB2-05":1404.6061817718507,"GB2-06":1317.1079887311873,"GB2-07":1520.9070893503424,"GB2-08":1565.8195599822748},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1506.4520159219408,"GB2-02":1425.8422506070183,"GB2-03":1527.9590436872616,"GB2-04":1541.4689786625354,"GB2-05":1523.290997711097,"GB2-06":1187.329180941812,"GB2-07":1657.1377622614993,"GB2-08":1879.7469609720076},"medium":{"GB2-01":1427.215755307793,"GB2-02":1458.1315122058427,"GB2-03":1451.3066313675868,"GB2-04":1453.1966197661275,"GB2-05":1445.8378450569335,"GB2-06":1333.976725690619,"GB2-07":1497.6086176884314,"GB2-08":1362.738639703256},"none":{"GB2-01":1454.585426437345,"GB2-02":1446.6038125675204,"GB2-03":1493.3697647442227,"GB2-04":1434.7907735203491,"GB2-05":1244.6897025475216,"GB2-06":1430.0180595611305,"GB2-07":1407.974888101097,"GB2-08":1454.9730792715607}},"per_game_tracks":{"highest":{"GB2-01":44.70826959385252,"GB2-02":7.484704864315055,"GB2-03":41.97211414971662,"GB2-04":39.02653543609264,"GB2-05":51.4429639826475,"GB2-06":25.64947969953627,"GB2-07":63.76292923051514,"GB2-08":74.33339438299416},"medium":{"GB2-01":38.09431108312192,"GB2-02":13.459089329828975,"GB2-03":33.86599146220886,"GB2-04":24.592241653411964,"GB2-05":45.42107820004769,"GB2-06":37.148171051976554,"GB2-07":50.753970891959106,"GB2-08":26.738941337874866},"none":{"GB2-01":40.38863436219846,"GB2-02":11.223439055353664,"GB2-03":38.22889075944164,"GB2-04":21.52240960642956,"GB2-05":29.583608741898452,"GB2-06":44.742957151306456,"GB2-07":43.04906884876752,"GB2-08":35.35038166239203}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.54754891745874,"medium":33.75922437630374,"none":33.01117377347347},"reasoning_agg":{"highest":{"max":74.33339438299416,"mean":43.54754891745874,"min":7.484704864315055},"medium":{"max":50.753970891959106,"mean":33.75922437630374,"min":13.459089329828975},"none":{"max":44.742957151306456,"mean":33.01117377347347,"min":11.223439055353664}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.33339438299416,"expected_score":33.25324573064024,"reasoning_variance":10.536375143985268,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.519403291771752},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.33339438299416,"expected_score":35.65367421075004,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.893874706708701},"medium":{"ceiling_score":50.753970891959106,"expected_score":31.452182211577888,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.3070421647258534},"none":{"ceiling_score":44.742957151306456,"expected_score":32.65388076959279,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.3572930038806845}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:7f7e7232e01df2a7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"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},"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},"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},"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},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137424999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"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},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.45800250000000003,"mean":0.18569479166666666,"median":0.091314375,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":28},"run_count":24,"token_priced_attempt_count":28,"total":4.456675},"codegen_output_tokens":{"attempt_count":28,"output_max":28998,"output_mean":10500.666666666666,"output_min":2419,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":28998,"output_mean":23512.0,"output_min":18631,"run_count":8},"medium":{"attempt_count":9,"output_max":6917,"output_mean":4677.5,"output_min":3936,"run_count":8},"none":{"attempt_count":9,"output_max":6065,"output_mean":3312.5,"output_min":2419,"run_count":8}},"display_name":"GPT-5.6 Terra","economics":{"all":35.547271647026804,"highest":39.668834509119144,"medium":37.628448345284106,"none":32.581399173722424},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"total_output_tokens":252016,"total_reasoning_output_tokens":152800,"total_visible_output_tokens":99216,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-09-10T11:12:01Z","match_totals_all":{"draws":1028,"losses":1129,"wins":964},"match_totals_tracks":{"highest":{"draws":326,"losses":380,"wins":394},"medium":{"draws":301,"losses":443,"wins":314},"none":{"draws":401,"losses":306,"wins":256}},"model_slug":"gpt-5-6-terra","overall":{"max":69.43940999034174,"mean":36.269658792302785,"min":9.955451026536553},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":47.93196838089745,"GB2-02":22.56130308677311,"GB2-03":28.37278067295601,"GB2-04":17.367291620527613,"GB2-05":48.96749514971631,"GB2-06":69.43940999034174,"GB2-07":49.789511908530514,"GB2-08":32.920915263210404},"per_game_all":{"GB2-01":50.51514781571706,"GB2-02":14.31959923660345,"GB2-03":24.643465766070833,"GB2-04":23.51514402093513,"GB2-06":52.537066917406634,"GB2-07":50.47330113231323,"GB2-08":32.82717664014129},"per_game_match_totals_all":{"GB2-01":{"draws":86,"losses":110,"wins":201},"GB2-02":{"draws":252,"losses":38,"wins":26},"GB2-03":{"draws":228,"losses":133,"wins":65},"GB2-04":{"draws":236,"losses":97,"wins":53},"GB2-05":{"draws":0,"losses":127,"wins":161},"GB2-06":{"draws":39,"losses":161,"wins":192},"GB2-07":{"draws":0,"losses":231,"wins":195},"GB2-08":{"draws":187,"losses":232,"wins":71}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":24,"losses":43,"wins":57},"GB2-02":{"draws":60,"losses":23,"wins":21},"GB2-03":{"draws":71,"losses":54,"wins":37},"GB2-04":{"draws":82,"losses":17,"wins":15},"GB2-05":{"draws":0,"losses":47,"wins":101},"GB2-06":{"draws":17,"losses":38,"wins":63},"GB2-07":{"draws":0,"losses":73,"wins":65},"GB2-08":{"draws":72,"losses":85,"wins":35}},"medium":{"GB2-01":{"draws":2,"losses":43,"wins":73},"GB2-02":{"draws":91,"losses":10,"wins":5},"GB2-03":{"draws":78,"losses":42,"wins":12},"GB2-04":{"draws":71,"losses":38,"wins":21},"GB2-05":{"draws":0,"losses":80,"wins":60},"GB2-06":{"draws":21,"losses":65,"wins":60},"GB2-07":{"draws":0,"losses":76,"wins":62},"GB2-08":{"draws":38,"losses":89,"wins":21}},"none":{"GB2-01":{"draws":60,"losses":24,"wins":71},"GB2-02":{"draws":101,"losses":5,"wins":0},"GB2-03":{"draws":79,"losses":37,"wins":16},"GB2-04":{"draws":83,"losses":42,"wins":17},"GB2-06":{"draws":1,"losses":58,"wins":69},"GB2-07":{"draws":0,"losses":82,"wins":68},"GB2-08":{"draws":77,"losses":58,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":1586.2243471968638,"GB2-02":1471.6358086676846,"GB2-03":1368.8241557745166,"GB2-04":1453.5657022262476,"GB2-06":1538.4373609821757,"GB2-07":1503.4100876753919,"GB2-08":1433.3290412522983},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1555.767687387719,"GB2-02":1517.647170216129,"GB2-03":1402.4320852241547,"GB2-04":1418.484902413154,"GB2-05":1496.9428710696504,"GB2-06":1756.280219142349,"GB2-07":1495.6605915888285,"GB2-08":1431.7667844873795},"medium":{"GB2-01":1725.6940221336674,"GB2-02":1449.9811763064577,"GB2-03":1330.0461612539777,"GB2-04":1453.8661207582813,"GB2-05":1523.634012263492,"GB2-06":1461.3776071905042,"GB2-07":1551.253062152687,"GB2-08":1431.9863882384893},"none":{"GB2-01":1477.2113320692047,"GB2-02":1447.2790794804664,"GB2-03":1373.9942208454174,"GB2-04":1488.3460835073072,"GB2-06":1397.6542566136736,"GB2-07":1463.3166092846598,"GB2-08":1436.233951031026}},"per_game_tracks":{"highest":{"GB2-01":47.93196838089745,"GB2-02":22.56130308677311,"GB2-03":28.37278067295601,"GB2-04":17.367291620527613,"GB2-05":48.96749514971631,"GB2-06":69.43940999034174,"GB2-07":49.789511908530514,"GB2-08":32.920915263210404},"medium":{"GB2-01":61.83347349707339,"GB2-02":10.442043596500689,"GB2-03":20.492560475629574,"GB2-04":23.611947649463634,"GB2-05":50.98785731400378,"GB2-06":46.66463879800661,"GB2-07":54.42069483699623,"GB2-08":32.57437059459893},"none":{"GB2-01":41.780001569180335,"GB2-02":9.955451026536553,"GB2-03":25.065056149626912,"GB2-04":29.566192792814146,"GB2-06":41.50715196387154,"GB2-07":47.20969665141295,"GB2-08":32.98624406261454}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.668834509119144,"medium":37.628448345284106,"none":31.51169352250512},"reasoning_agg":{"highest":{"max":69.43940999034174,"mean":39.668834509119144,"min":17.367291620527613},"medium":{"max":61.83347349707339,"mean":37.628448345284106,"min":10.442043596500689},"none":{"max":47.20969665141295,"mean":31.51169352250512,"min":9.955451026536553}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":69.43940999034174,"expected_score":32.20212971736946,"reasoning_variance":8.157140986614024,"reliability_score":98.92820726032825,"uncertainty_avg":1.071792739671754,"uncertainty_penalty":-4.067529074933326},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":69.43940999034174,"expected_score":31.40972101891215,"reliability_score":98.62793394239391,"uncertainty_avg":1.3720660576060895,"uncertainty_penalty":-8.259113490206992},"medium":{"ceiling_score":61.83347349707339,"expected_score":36.15392040612762,"reliability_score":99.16603133703828,"uncertainty_avg":0.8339686629617182,"uncertainty_penalty":-1.4745279391564878},"none":{"ceiling_score":47.20969665141295,"expected_score":32.73401846827222,"reliability_score":99.30580431877652,"uncertainty_avg":0.6941956812234817,"uncertainty_penalty":1.2223249457670988}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:5e8f4f6f136095e6","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.45756399999999997}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4575640000000001}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.45756399999999997},"codegen_latency_ms":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8}},"codegen_output_tokens":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8}},"display_name":"GPT 4.1","economics":{"none":35.80056693008479},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":11,"finish_reasons":["stop"],"indexed_attempts":11,"output_token_observations":11,"total_output_tokens":35469},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:31Z","match_totals_all":{"draws":196,"losses":198,"wins":177},"match_totals_tracks":{"none":{"draws":196,"losses":198,"wins":177}},"model_slug":"gpt-4-1","overall":{"max":55.88308492443146,"mean":35.80056693008479,"min":11.682283349084813},"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":32,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":5,"losses":31,"wins":45},"GB2-02":{"draws":52,"losses":11,"wins":1},"GB2-03":{"draws":18,"losses":19,"wins":21},"GB2-04":{"draws":48,"losses":12,"wins":2},"GB2-05":{"draws":0,"losses":50,"wins":26},"GB2-06":{"draws":9,"losses":27,"wins":40},"GB2-07":{"draws":0,"losses":33,"wins":31},"GB2-08":{"draws":64,"losses":15,"wins":11}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":5,"losses":31,"wins":45},"GB2-02":{"draws":52,"losses":11,"wins":1},"GB2-03":{"draws":18,"losses":19,"wins":21},"GB2-04":{"draws":48,"losses":12,"wins":2},"GB2-05":{"draws":0,"losses":50,"wins":26},"GB2-06":{"draws":9,"losses":27,"wins":40},"GB2-07":{"draws":0,"losses":33,"wins":31},"GB2-08":{"draws":64,"losses":15,"wins":11}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1635.2135372709856,"GB2-02":1467.8127849964237,"GB2-03":1564.346999402338,"GB2-04":1419.8618510492545,"GB2-05":1222.6598405913285,"GB2-06":1591.8487355395282,"GB2-07":1517.0750056649872,"GB2-08":1411.5680581389895}},"per_game_tracks":{"none":{"GB2-01":53.77515864460839,"GB2-02":11.682283349084813,"GB2-03":43.06053158843793,"GB2-04":15.428003461676202,"GB2-05":26.4628692919667,"GB2-06":55.88308492443146,"GB2-07":50.266694773888176,"GB2-08":29.845909406584692}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":35.80056693008479},"reasoning_agg":{"none":{"max":55.88308492443146,"mean":35.80056693008479,"min":11.682283349084813}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":55.88308492443146},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":55.88308492443146,"expected_score":39.71096534609022,"reliability_score":84.53576871904392,"uncertainty_avg":15.464231280956088,"uncertainty_penalty":3.910398416005428}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:8cf52f82ea7b1615","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"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},"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},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784000002},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.1725616482799999}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.3773764379599998},"codegen_latency_ms":{"attempt_count":31,"max_ms":1461124,"mean_ms":482100.7083333333,"min_ms":19301,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1461124,"mean_ms":902169.625,"min_ms":499972,"run_count":8},"medium":{"attempt_count":9,"max_ms":676490,"mean_ms":489467.75,"min_ms":326732,"run_count":8},"none":{"attempt_count":12,"max_ms":131002,"mean_ms":54664.75,"min_ms":19301,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":106197,"output_mean":33246.666666666664,"output_min":2345,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":106197,"output_mean":60744.125,"output_min":32963,"run_count":8},"medium":{"attempt_count":9,"output_max":42157,"output_mean":35085.125,"output_min":20989,"run_count":8},"none":{"attempt_count":12,"output_max":10866,"output_mean":3910.75,"output_min":2345,"run_count":8}},"display_name":"DeepSeek V4 Pro 0813","economics":{"all":37.528469829748616,"highest":41.37071157031049,"medium":34.223607878349945,"none":33.372176280108306},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":31,"finish_reasons":["stop"],"indexed_attempts":31,"output_token_observations":31,"provider_post_attempt_observations":31,"provider_post_attempts":31,"reasoning_token_observations":31,"reconciliation_get_attempt_observations":31,"reconciliation_get_attempts":150,"total_output_tokens":797920,"total_reasoning_output_tokens":686933,"total_visible_output_tokens":110987,"visible_token_observations":31},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-09-10T11:10:07Z","match_totals_all":{"draws":975,"losses":1066,"wins":957},"match_totals_tracks":{"highest":{"draws":333,"losses":334,"wins":407},"medium":{"draws":348,"losses":435,"wins":365},"none":{"draws":294,"losses":297,"wins":185}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":74.8155896456324,"mean":35.55020961791368,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":34.13620303413409,"GB2-02":9.963827021369582,"GB2-03":48.442947626880404,"GB2-04":24.841660594454027,"GB2-05":67.60918311081942,"GB2-06":52.36547411825162,"GB2-07":74.8155896456324,"GB2-08":18.79080741094235},"per_game_all":{"GB2-01":35.15542533487818,"GB2-03":36.82502475307225,"GB2-04":17.395493378810624,"GB2-06":51.94965998170964,"GB2-07":59.16145810714705,"GB2-08":24.683757422873967},"per_game_match_totals_all":{"GB2-01":{"draws":155,"losses":116,"wins":141},"GB2-02":{"draws":177,"losses":32,"wins":5},"GB2-03":{"draws":120,"losses":193,"wins":141},"GB2-04":{"draws":227,"losses":142,"wins":61},"GB2-05":{"draws":0,"losses":93,"wins":155},"GB2-06":{"draws":22,"losses":222,"wins":208},"GB2-07":{"draws":0,"losses":167,"wins":205},"GB2-08":{"draws":274,"losses":101,"wins":41}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":48,"wins":70},"GB2-02":{"draws":96,"losses":6,"wins":2},"GB2-03":{"draws":22,"losses":52,"wins":58},"GB2-04":{"draws":99,"losses":53,"wins":32},"GB2-05":{"draws":0,"losses":46,"wins":74},"GB2-06":{"draws":10,"losses":68,"wins":86},"GB2-07":{"draws":0,"losses":39,"wins":85},"GB2-08":{"draws":102,"losses":22,"wins":0}},"medium":{"GB2-01":{"draws":117,"losses":18,"wins":33},"GB2-02":{"draws":81,"losses":26,"wins":3},"GB2-03":{"draws":30,"losses":99,"wins":61},"GB2-04":{"draws":46,"losses":50,"wins":18},"GB2-05":{"draws":0,"losses":47,"wins":81},"GB2-06":{"draws":11,"losses":66,"wins":69},"GB2-07":{"draws":0,"losses":56,"wins":68},"GB2-08":{"draws":63,"losses":73,"wins":32}},"none":{"GB2-01":{"draws":34,"losses":50,"wins":38},"GB2-03":{"draws":68,"losses":42,"wins":22},"GB2-04":{"draws":82,"losses":39,"wins":11},"GB2-06":{"draws":1,"losses":88,"wins":53},"GB2-07":{"draws":0,"losses":72,"wins":52},"GB2-08":{"draws":109,"losses":6,"wins":9}}},"per_game_raw_elo_all":{"GB2-01":1398.9350379871455,"GB2-03":1485.110113079087,"GB2-04":1415.1528441526177,"GB2-06":1528.49394386741,"GB2-07":1610.0104596919173,"GB2-08":1347.7793085497533},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1388.3076463525476,"GB2-02":1447.6921355670459,"GB2-03":1598.6883574866376,"GB2-04":1455.7570669799688,"GB2-05":1738.35460515231,"GB2-06":1532.4239830449544,"GB2-07":1797.9218119745026,"GB2-08":1285.5605334671657},"medium":{"GB2-01":1472.6924784481903,"GB2-02":1435.930131541753,"GB2-03":1445.207793643488,"GB2-04":1313.5432809915524,"GB2-05":1434.282174092201,"GB2-06":1442.7153447051658,"GB2-07":1762.832763073679,"GB2-08":1404.3061764466815},"none":{"GB2-01":1335.8049891606988,"GB2-03":1411.4341881071348,"GB2-04":1476.158184486332,"GB2-06":1610.3425038521104,"GB2-07":1269.2768040275703,"GB2-08":1353.4712157354127}},"per_game_tracks":{"highest":{"GB2-01":34.13620303413409,"GB2-02":9.963827021369582,"GB2-03":48.442947626880404,"GB2-04":24.841660594454027,"GB2-05":67.60918311081942,"GB2-06":52.36547411825162,"GB2-07":74.8155896456324,"GB2-08":18.79080741094235},"medium":{"GB2-01":41.51169686092654,"GB2-02":8.038357928704011,"GB2-03":33.071697400705354,"GB2-04":0.0,"GB2-05":43.86378827356518,"GB2-06":45.2051929082044,"GB2-07":71.89246349927906,"GB2-08":30.205666155415027},"none":{"GB2-01":29.818376109573915,"GB2-03":28.960429231630975,"GB2-04":27.34481954197784,"GB2-06":58.27831291867289,"GB2-07":30.7763211765297,"GB2-08":25.054798702264524}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.37071157031049,"medium":34.223607878349945,"none":31.056309405080622},"reasoning_agg":{"highest":{"max":74.8155896456324,"mean":41.37071157031049,"min":9.963827021369582},"medium":{"max":71.89246349927906,"mean":34.223607878349945,"min":0.0},"none":{"max":58.27831291867289,"mean":31.056309405080622,"min":25.054798702264524}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":74.8155896456324,"expected_score":33.85561318772318,"reasoning_variance":10.314402165229868,"reliability_score":99.42227768729234,"uncertainty_avg":0.5777223127076608,"uncertainty_penalty":-1.6945964301905008},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.8155896456324,"expected_score":33.26391359706614,"reliability_score":98.74678125808309,"uncertainty_avg":1.253218741916916,"uncertainty_penalty":-8.106797973244348},"medium":{"ceiling_score":71.89246349927906,"expected_score":32.57704926492369,"reliability_score":99.02161936676029,"uncertainty_avg":0.9783806332397038,"uncertainty_penalty":-1.646558613426258},"none":{"ceiling_score":58.27831291867289,"expected_score":33.744254250056066,"reliability_score":99.45396652777279,"uncertainty_avg":0.5460334722272009,"uncertainty_penalty":2.687944844975444}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:f893c31f7fbbffea","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528459999999995}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.4852846}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528459999999995},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"medium":35.20852304594772},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":17,"finish_reasons":["stop"],"indexed_attempts":17,"output_token_observations":17,"total_output_tokens":179458},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:34:43Z","match_totals_all":{"draws":230,"losses":205,"wins":185},"match_totals_tracks":{"medium":{"draws":230,"losses":205,"wins":185}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":65.57660382357807,"mean":35.20852304594772,"min":12.336802440575292},"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":34,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":17,"losses":27,"wins":38},"GB2-02":{"draws":62,"losses":1,"wins":1},"GB2-03":{"draws":19,"losses":17,"wins":14},"GB2-04":{"draws":65,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":37,"wins":51},"GB2-06":{"draws":0,"losses":53,"wins":43},"GB2-07":{"draws":0,"losses":54,"wins":28},"GB2-08":{"draws":67,"losses":11,"wins":6}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":17,"losses":27,"wins":38},"GB2-02":{"draws":62,"losses":1,"wins":1},"GB2-03":{"draws":19,"losses":17,"wins":14},"GB2-04":{"draws":65,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":37,"wins":51},"GB2-06":{"draws":0,"losses":53,"wins":43},"GB2-07":{"draws":0,"losses":54,"wins":28},"GB2-08":{"draws":67,"losses":11,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1505.378396323981,"GB2-02":1471.4473944599374,"GB2-03":1424.2542829519666,"GB2-04":1486.6086038147535,"GB2-05":1718.4606854659032,"GB2-06":1428.1758902452225,"GB2-07":1276.8149612185298,"GB2-08":1427.5973144153943}},"per_game_tracks":{"medium":{"GB2-01":43.119446315546206,"GB2-02":12.336802440575292,"GB2-03":28.075364138283934,"GB2-04":27.170519861988716,"GB2-05":65.57660382357807,"GB2-06":43.47206803669905,"GB2-07":30.72713242170736,"GB2-08":31.19024732920317}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":35.20852304594772},"reasoning_agg":{"medium":{"max":65.57660382357807,"mean":35.20852304594772,"min":12.336802440575292}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":65.57660382357807},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":65.57660382357807,"expected_score":35.87769716087495,"reliability_score":86.55869061045992,"uncertainty_avg":13.441309389540079,"uncertainty_penalty":0.6691741149272303}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:d159cf528f6e5fa3","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"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-2026-08-08":1,"boardgame-list-prices-2026-09-08":2},"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},"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.14705250000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"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-2026-08-08":1,"boardgame-list-prices-2026-09-08":2},"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},"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-2026-08-08":20,"boardgame-list-prices-2026-09-08":2},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.168810400000001},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":41.94270122706257,"none":28.42341314043818},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":21,"finish_reasons":["incomplete","stop"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":2,"total_output_tokens":1096010,"total_reasoning_output_tokens":255888,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:18Z","match_totals_all":{"draws":432,"losses":387,"wins":356},"match_totals_tracks":{"medium":{"draws":182,"losses":182,"wins":255},"none":{"draws":250,"losses":205,"wins":101}},"model_slug":"gpt-5-4-mini","overall":{"max":56.015466910410275,"mean":35.18305718375038,"min":12.418449045966476},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":35,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":39,"losses":56,"wins":59},"GB2-02":{"draws":125,"losses":2,"wins":3},"GB2-03":{"draws":88,"losses":18,"wins":15},"GB2-04":{"draws":85,"losses":15,"wins":30},"GB2-05":{"draws":0,"losses":88,"wins":82},"GB2-06":{"draws":15,"losses":66,"wins":79},"GB2-07":{"draws":0,"losses":98,"wins":58},"GB2-08":{"draws":80,"losses":44,"wins":30}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":22,"wins":42},"GB2-02":{"draws":66,"losses":1,"wins":3},"GB2-03":{"draws":33,"losses":14,"wins":14},"GB2-04":{"draws":39,"losses":5,"wins":18},"GB2-05":{"draws":0,"losses":39,"wins":57},"GB2-06":{"draws":10,"losses":30,"wins":44},"GB2-07":{"draws":0,"losses":39,"wins":47},"GB2-08":{"draws":30,"losses":32,"wins":30}},"none":{"GB2-01":{"draws":35,"losses":34,"wins":17},"GB2-02":{"draws":59,"losses":1,"wins":0},"GB2-03":{"draws":55,"losses":4,"wins":1},"GB2-04":{"draws":46,"losses":10,"wins":12},"GB2-05":{"draws":0,"losses":49,"wins":25},"GB2-06":{"draws":5,"losses":36,"wins":35},"GB2-07":{"draws":0,"losses":59,"wins":11},"GB2-08":{"draws":50,"losses":12,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1642.0222732482737,"GB2-02":1486.9829898555085,"GB2-03":1489.3280415856061,"GB2-04":1575.2825468133171,"GB2-05":1565.90982985875,"GB2-06":1591.3433947162612,"GB2-07":1483.4064114364373,"GB2-08":1430.99548468218},"none":{"GB2-01":1409.332536316064,"GB2-02":1473.5016442990093,"GB2-03":1479.7645713367565,"GB2-04":1479.1917518609623,"GB2-05":1295.479782930378,"GB2-06":1387.7364854445989,"GB2-07":1132.1434855724015,"GB2-08":1413.8326222252044}},"per_game_tracks":{"medium":{"GB2-01":54.00765200217118,"GB2-02":15.520290105513986,"GB2-03":35.38802948398163,"GB2-04":41.14931890005339,"GB2-05":53.75866949290433,"GB2-06":56.015466910410275,"GB2-07":48.02249928924504,"GB2-08":31.679683632220694},"none":{"GB2-01":35.304603292582,"GB2-02":12.418449045966476,"GB2-03":34.349868844232375,"GB2-04":25.617653837866694,"GB2-05":32.123645602053834,"GB2-06":39.92088394835182,"GB2-07":18.37810686686219,"GB2-08":29.27409368559002}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.94270122706257,"none":28.42341314043818},"reasoning_agg":{"medium":{"max":56.015466910410275,"mean":41.94270122706257,"min":15.520290105513986},"none":{"max":39.92088394835182,"mean":28.42341314043818,"min":12.418449045966476}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":56.015466910410275,"reasoning_variance":13.519288086624393},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":56.015466910410275,"expected_score":43.11412595649124,"reliability_score":86.69008925283754,"uncertainty_avg":13.309910747162462,"uncertainty_penalty":1.1714247294286722},"none":{"ceiling_score":39.92088394835182,"expected_score":29.984895243682846,"reliability_score":83.88951123612304,"uncertainty_avg":16.110488763876965,"uncertainty_penalty":1.5614821032446677}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:802f6446e1922474","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-09-08":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-09-08":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-09-08":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425},"codegen_latency_ms":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1}},"codegen_output_tokens":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1}},"display_name":"GPT 4.1 Nano","economics":{"none":35.18099307381629},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":1,"finish_reasons":["stop"],"indexed_attempts":2,"output_token_observations":2,"reasoning_token_observations":1,"total_output_tokens":2006,"total_visible_output_tokens":64,"visible_token_observations":1},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"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}}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-09-10T01:47:37Z","match_totals_all":{"draws":65,"losses":103,"wins":110},"match_totals_tracks":{"none":{"draws":65,"losses":103,"wins":110}},"model_slug":"gpt-4-1-nano","overall":{"max":35.18099307381629,"mean":35.18099307381629,"min":35.18099307381629},"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":36,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":103,"wins":110}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":65,"losses":103,"wins":110}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1388.89236890581}},"per_game_tracks":{"none":{"GB2-01":35.18099307381629}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":35.18099307381629},"reasoning_agg":{"none":{"max":35.18099307381629,"mean":35.18099307381629,"min":35.18099307381629}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":35.18099307381629},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":35.18099307381629,"expected_score":30.173191926349926,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.007801147466363}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:ace24c78c399f116","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"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-2026-08-08":1,"boardgame-list-prices-2026-09-08":2},"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},"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-2026-08-08":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"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-2026-08-08":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"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-2026-08-08":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},"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-2026-08-08":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"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-2026-08-08":1,"boardgame-list-prices-2026-09-08":2},"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},"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-2026-08-08":53,"boardgame-list-prices-2026-09-08":2},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821379},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":39.62662596514345,"none":34.89630279530046},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["incomplete","stop"],"indexed_attempts":57,"output_token_observations":57,"reasoning_token_observations":2,"total_output_tokens":752982,"total_reasoning_output_tokens":128000,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"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,"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}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:07Z","match_totals_all":{"draws":436,"losses":680,"wins":626},"match_totals_tracks":{"medium":{"draws":172,"losses":344,"wins":366},"none":{"draws":264,"losses":336,"wins":260}},"model_slug":"gpt-5-4-nano","overall":{"max":60.07944202124918,"mean":34.67569980949435,"min":12.179369637744257},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":37,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":75,"losses":133,"wins":90},"GB2-02":{"draws":180,"losses":10,"wins":2},"GB2-03":{"draws":25,"losses":24,"wins":21},"GB2-04":{"draws":46,"losses":3,"wins":23},"GB2-05":{"draws":0,"losses":181,"wins":117},"GB2-06":{"draws":4,"losses":111,"wins":183},"GB2-07":{"draws":0,"losses":135,"wins":99},"GB2-08":{"draws":106,"losses":83,"wins":91}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":26,"losses":88,"wins":28},"GB2-02":{"draws":59,"losses":1,"wins":0},"GB2-04":{"draws":46,"losses":3,"wins":23},"GB2-05":{"draws":0,"losses":72,"wins":84},"GB2-06":{"draws":4,"losses":52,"wins":102},"GB2-07":{"draws":0,"losses":83,"wins":69},"GB2-08":{"draws":37,"losses":45,"wins":60}},"none":{"GB2-01":{"draws":49,"losses":45,"wins":62},"GB2-02":{"draws":121,"losses":9,"wins":2},"GB2-03":{"draws":25,"losses":24,"wins":21},"GB2-05":{"draws":0,"losses":109,"wins":33},"GB2-06":{"draws":0,"losses":59,"wins":81},"GB2-07":{"draws":0,"losses":52,"wins":30},"GB2-08":{"draws":69,"losses":38,"wins":31}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1258.698860860387,"GB2-02":1476.4584951256152,"GB2-04":1590.6223690206723,"GB2-05":1530.8163667007361,"GB2-06":1644.7113224940283,"GB2-07":1427.6299185770467,"GB2-08":1568.270065288822},"none":{"GB2-01":1580.3713321653136,"GB2-02":1469.8925253457724,"GB2-03":1502.2178560792047,"GB2-05":1193.9987947074715,"GB2-06":1539.7984680553782,"GB2-07":1330.5150146991402,"GB2-08":1472.7535435217649}},"per_game_tracks":{"medium":{"GB2-01":22.50128480022854,"GB2-02":12.950917619586493,"GB2-04":44.28025300648413,"GB2-05":50.607779083394135,"GB2-06":60.07944202124918,"GB2-07":43.15012153636137,"GB2-08":43.81658368870027},"none":{"GB2-01":49.18855338448374,"GB2-02":12.179369637744257,"GB2-03":37.07546402146493,"GB2-05":24.093974048156653,"GB2-06":51.6471832448803,"GB2-07":35.20066576920315,"GB2-08":34.88890946117016}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.87673067298392,"none":32.47466894600478},"reasoning_agg":{"medium":{"max":60.07944202124918,"mean":36.87673067298392,"min":12.950917619586493},"none":{"max":51.6471832448803,"mean":32.47466894600478,"min":12.179369637744257}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":60.07944202124918,"reasoning_variance":4.4020617269791344},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":60.07944202124918,"expected_score":41.59313949141755,"reliability_score":84.95797964542608,"uncertainty_avg":15.042020354573927,"uncertainty_penalty":4.716408818433635},"none":{"ceiling_score":51.6471832448803,"expected_score":39.13876710468672,"reliability_score":85.05388186832882,"uncertainty_avg":14.946118131671186,"uncertainty_penalty":6.664098158681938}}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:561d98a4c5ea6b70","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8,"boardgame-list-prices-2026-09-08":32},"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},"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-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"estimated":8,"local_standard_estimate":13},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":4,"max":0.17217,"mean":0.11039474999999999,"median":0.10846,"min":0.07562,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"token_priced_attempt_count":13,"total":0.8831579999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.39097600000000005},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"estimated":8,"local_standard_estimate":13},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":4,"max":0.17217,"mean":0.11039474999999999,"median":0.10846,"min":0.07562,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"token_priced_attempt_count":13,"total":0.8831579999999999},"historical-provider-setting-intensive":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8,"boardgame-list-prices-2026-09-08":32},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_cost_usd":{"admitted_cell_count":29,"cell_count":24,"cost_basis_counts":{"estimated":40,"local_standard_estimate":29},"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":19,"max":0.17217,"mean":0.08358424999999998,"median":0.0865375,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-08-08":16,"boardgame-list-prices-2026-09-08":40},"recorded_attempt_count":40,"run_count":48,"token_priced_attempt_count":29,"total":4.201686},"codegen_latency_ms":{"attempt_count":29,"max_ms":130647,"mean_ms":59683.958333333336,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":13,"max_ms":130647,"mean_ms":108464.0,"min_ms":46796,"run_count":8}},"codegen_output_tokens":{"attempt_count":69,"output_max":15813,"output_mean":8194.3125,"output_min":2653,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":21,"output_max":14517,"output_mean":8935.125,"output_min":5431,"run_count":8}},"display_name":"O3","economics":{"all":40.10579299590647,"highest":42.65797926498379,"medium":46.63103950637711,"none":26.102373200502253},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":93,"output_token_observations":69,"reasoning_token_observations":13,"total_output_tokens":393327,"total_reasoning_output_tokens":26752,"total_visible_output_tokens":24077,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_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":4,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.5,"model_code_failures":4,"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":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.59375,"model_code_failure_rate":0.40625,"model_code_failures":13,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-09-10T10:09:01Z","match_totals_all":{"draws":1046,"losses":2980,"wins":2708},"match_totals_tracks":{"highest":{"draws":590,"losses":2264,"wins":2274},"medium":{"draws":127,"losses":152,"wins":217},"none":{"draws":329,"losses":564,"wins":217}},"model_slug":"o3","overall":{"max":64.65603985716929,"mean":34.26336589604531,"min":13.652811210043236},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":38,"overall_ranking_status":"partial","per_game":{"GB2-01":47.71717706185117,"GB2-03":31.45724153790146,"GB2-05":49.93788221593318,"GB2-06":42.97644177549341,"GB2-07":44.43538755960546,"GB2-08":39.423745439118036},"per_game_all":{"GB2-01":35.21005342386163,"GB2-06":40.88377502160767,"GB2-07":51.29084125918326,"GB2-08":33.0385022789733},"per_game_match_totals_all":{"GB2-01":{"draws":175,"losses":500,"wins":411},"GB2-03":{"draws":89,"losses":90,"wins":61},"GB2-04":{"draws":51,"losses":9,"wins":8},"GB2-05":{"draws":0,"losses":536,"wins":589},"GB2-06":{"draws":78,"losses":761,"wins":652},"GB2-07":{"draws":0,"losses":791,"wins":747},"GB2-08":{"draws":653,"losses":293,"wins":240}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":78,"losses":298,"wins":364},"GB2-03":{"draws":89,"losses":90,"wins":61},"GB2-05":{"draws":0,"losses":499,"wins":536},"GB2-06":{"draws":30,"losses":541,"wins":566},"GB2-07":{"draws":0,"losses":631,"wins":543},"GB2-08":{"draws":393,"losses":205,"wins":204}},"medium":{"GB2-01":{"draws":16,"losses":30,"wins":34},"GB2-04":{"draws":51,"losses":9,"wins":8},"GB2-05":{"draws":0,"losses":37,"wins":53},"GB2-06":{"draws":8,"losses":27,"wins":47},"GB2-07":{"draws":0,"losses":25,"wins":51},"GB2-08":{"draws":52,"losses":24,"wins":24}},"none":{"GB2-01":{"draws":81,"losses":172,"wins":13},"GB2-06":{"draws":40,"losses":193,"wins":39},"GB2-07":{"draws":0,"losses":135,"wins":153},"GB2-08":{"draws":208,"losses":64,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1396.7477752153234,"GB2-06":1385.0868033804509,"GB2-07":1510.5932484775196,"GB2-08":1433.575621027092},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1542.8030567183832,"GB2-03":1426.5139023514475,"GB2-05":1501.3768543058302,"GB2-06":1404.9750860855493,"GB2-07":1420.8637837101146,"GB2-08":1497.9587134875176},"medium":{"GB2-01":1519.7878014821274,"GB2-04":1461.7140351902344,"GB2-05":1579.92232517005,"GB2-06":1620.6162562438012,"GB2-07":1685.7742661744414,"GB2-08":1466.6927837582004},"none":{"GB2-01":1127.6524674454595,"GB2-06":1129.6690678120026,"GB2-07":1425.1416955480029,"GB2-08":1336.0753658355584}},"per_game_tracks":{"highest":{"GB2-01":47.71717706185117,"GB2-03":31.45724153790146,"GB2-05":49.93788221593318,"GB2-06":42.97644177549341,"GB2-07":44.43538755960546,"GB2-08":39.423745439118036},"medium":{"GB2-01":44.26017199969047,"GB2-04":22.72518278425092,"GB2-05":54.753782941211256,"GB2-06":58.26405875417527,"GB2-07":64.65603985716929,"GB2-08":35.12700070176546},"none":{"GB2-01":13.652811210043236,"GB2-06":21.41082453515432,"GB2-07":44.781096360775045,"GB2-08":24.564760696036405}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.44563368460245,"medium":43.3950719496165,"none":21.94939205391697},"reasoning_agg":{"highest":{"max":49.93788221593318,"mean":37.44563368460245,"min":31.45724153790146},"medium":{"max":64.65603985716929,"mean":43.3950719496165,"min":22.72518278425092},"none":{"max":44.781096360775045,"mean":21.94939205391697,"min":13.652811210043236}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":64.65603985716929,"expected_score":34.89248137398319,"reasoning_variance":21.44567989569953,"reliability_score":96.4858472257734,"uncertainty_avg":3.5141527742265963,"uncertainty_penalty":0.62911547793788},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.93788221593318,"expected_score":32.74813758241517,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.69749610218728},"medium":{"ceiling_score":64.65603985716929,"expected_score":47.97198046837469,"reliability_score":88.78716638838338,"uncertainty_avg":11.212833611616611,"uncertainty_penalty":4.576908518758188},"none":{"ceiling_score":44.781096360775045,"expected_score":18.082339392343954,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.867052661573016}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:9b5bb4ae0cfde398","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0092087,"mean":0.006571171428571429,"median":0.00666192,"min":0.00456754,"recorded_attempt_count":15,"run_count":7,"total":0.0459982},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00391754,"mean":0.0023617857142857143,"median":0.00186618,"min":0.00144036,"recorded_attempt_count":8,"run_count":7,"total":0.0165325}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0092087,"mean":0.006571171428571429,"median":0.00666192,"min":0.00456754,"recorded_attempt_count":15,"run_count":7,"total":0.0459982},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00391754,"mean":0.0023617857142857143,"median":0.00186618,"min":0.00144036,"recorded_attempt_count":8,"run_count":7,"total":0.0165325}},"codegen_cost_usd":{"admitted_cell_count":10,"cell_count":14,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0092087,"mean":0.004466478571428571,"median":0.0042425399999999995,"min":0.00144036,"recorded_attempt_count":23,"run_count":14,"total":0.0625307},"codegen_latency_ms":{"attempt_count":23,"max_ms":550842,"mean_ms":222264.07142857142,"min_ms":41984,"run_count":14},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":550842,"mean_ms":354649.85714285716,"min_ms":219950,"run_count":7},"none":{"attempt_count":8,"max_ms":161392,"mean_ms":89878.28571428571,"min_ms":41984,"run_count":7}},"codegen_output_tokens":{"attempt_count":23,"output_max":12552,"output_mean":5500.928571428572,"output_min":1283,"run_count":14},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":12552,"output_mean":8851.57142857143,"output_min":6019,"run_count":7},"none":{"attempt_count":8,"output_max":4235,"output_mean":2150.285714285714,"output_min":1283,"run_count":7}},"display_name":"Gemma 4 31B","economics":{"medium":42.376858418550654,"none":32.242665330503485},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":23,"total_output_tokens":77013},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":4,"evaluated_cells":7,"failed_game_aliases":["GB2-02","GB2-03","GB2-08"],"infra_excluded_game_aliases":["GB2-01"],"infra_failures_excluded":1,"model_code_failure_rate":0.42857142857142855,"model_code_failures":3,"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":4,"repaired_rate":0.5714285714285714},"baseline":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.7142857142857143,"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"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}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-08-05T03:57:18Z","match_totals_all":{"draws":197,"losses":341,"wins":266},"match_totals_tracks":{"medium":{"draws":55,"losses":143,"wins":134},"none":{"draws":142,"losses":198,"wins":132}},"model_slug":"google-gemma-4-31b-it","overall":{"max":57.095657519959566,"mean":33.933977912569986,"min":24.766615824644276},"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":39,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":19,"losses":30,"wins":47},"GB2-04":{"draws":110,"losses":10,"wins":12},"GB2-05":{"draws":0,"losses":96,"wins":76},"GB2-06":{"draws":2,"losses":97,"wins":65},"GB2-07":{"draws":0,"losses":89,"wins":63},"GB2-08":{"draws":66,"losses":19,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":55,"losses":2,"wins":5},"GB2-05":{"draws":0,"losses":45,"wins":53},"GB2-06":{"draws":0,"losses":56,"wins":32},"GB2-07":{"draws":0,"losses":40,"wins":44}},"none":{"GB2-01":{"draws":19,"losses":30,"wins":47},"GB2-04":{"draws":55,"losses":8,"wins":7},"GB2-05":{"draws":0,"losses":51,"wins":23},"GB2-06":{"draws":2,"losses":41,"wins":33},"GB2-07":{"draws":0,"losses":49,"wins":19},"GB2-08":{"draws":66,"losses":19,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1491.0433924004185,"GB2-05":1608.0684118194988,"GB2-06":1375.9572202695874,"GB2-07":1459.0882405137008},"none":{"GB2-01":1555.8128707841634,"GB2-04":1483.423921097945,"GB2-05":1201.6240382292942,"GB2-06":1351.780972077647,"GB2-07":1227.6442414952623,"GB2-08":1428.1732099119702}},"per_game_tracks":{"medium":{"GB2-04":27.208177713775562,"GB2-05":57.095657519959566,"GB2-06":39.24873264001045,"GB2-07":45.954865800457036},"none":{"GB2-01":47.537908439761935,"GB2-04":26.431101136188207,"GB2-05":24.766615824644276,"GB2-06":37.109053054838675,"GB2-07":26.276982761125968,"GB2-08":31.33433076646184}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.84420968400358,"none":31.02374614113639},"reasoning_agg":{"medium":{"max":57.095657519959566,"mean":36.84420968400358,"min":27.208177713775562},"none":{"max":47.537908439761935,"mean":31.02374614113639,"min":24.766615824644276}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":57.095657519959566,"reasoning_variance":5.820463542867191},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":57.095657519959566,"expected_score":43.55171503520597,"reliability_score":88.63038048679654,"uncertainty_avg":11.369619513203464,"uncertainty_penalty":6.707505351202393},"none":{"ceiling_score":47.537908439761935,"expected_score":31.68751886659894,"reliability_score":87.41424552360704,"uncertainty_avg":12.585754476392962,"uncertainty_penalty":0.6637727254625503}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:8ed5b674f4d47981","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"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},"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},"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666662,"min":0.013816857666666668,"recorded_attempt_count":37,"run_count":24,"total":0.5651094239}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"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},"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},"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},"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.20593804350000003},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"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":33.71521001940188,"highest":30.60405657846155,"medium":38.64130225632867,"none":31.90027122341541},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-09-10T11:06:45Z","match_totals_all":{"draws":1576,"losses":1551,"wins":1183},"match_totals_tracks":{"highest":{"draws":335,"losses":444,"wins":259},"medium":{"draws":573,"losses":467,"wins":404},"none":{"draws":668,"losses":640,"wins":520}},"model_slug":"z-ai-glm-5-2","overall":{"max":72.14085667254591,"mean":33.71521001940187,"min":3.385411727320254},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.243564635376174,"GB2-02":20.87099389668296,"GB2-03":26.677941438624654,"GB2-04":29.515021005587823,"GB2-05":54.56042710751232,"GB2-06":39.919571760376535,"GB2-07":3.385411727320254,"GB2-08":24.65952105621167},"per_game_all":{"GB2-01":37.39415664672041,"GB2-02":16.364375236483696,"GB2-03":26.60128304116056,"GB2-04":24.677201737061363,"GB2-05":47.35219245797017,"GB2-06":52.67963619853621,"GB2-07":36.27564975186662,"GB2-08":28.377185085416},"per_game_match_totals_all":{"GB2-01":{"draws":234,"losses":206,"wins":176},"GB2-02":{"draws":362,"losses":56,"wins":40},"GB2-03":{"draws":278,"losses":152,"wins":78},"GB2-04":{"draws":272,"losses":161,"wins":91},"GB2-05":{"draws":0,"losses":351,"wins":217},"GB2-06":{"draws":43,"losses":191,"wins":288},"GB2-07":{"draws":0,"losses":340,"wins":244},"GB2-08":{"draws":387,"losses":94,"wins":49}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":55,"losses":68,"wins":41},"GB2-02":{"draws":52,"losses":27,"wins":25},"GB2-03":{"draws":78,"losses":28,"wins":26},"GB2-04":{"draws":37,"losses":58,"wins":25},"GB2-05":{"draws":0,"losses":80,"wins":54},"GB2-06":{"draws":6,"losses":59,"wins":71},"GB2-07":{"draws":0,"losses":109,"wins":15},"GB2-08":{"draws":107,"losses":15,"wins":2}},"medium":{"GB2-01":{"draws":110,"losses":42,"wins":60},"GB2-02":{"draws":112,"losses":24,"wins":14},"GB2-03":{"draws":104,"losses":59,"wins":5},"GB2-04":{"draws":96,"losses":59,"wins":33},"GB2-05":{"draws":0,"losses":120,"wins":76},"GB2-06":{"draws":13,"losses":36,"wins":113},"GB2-07":{"draws":0,"losses":90,"wins":102},"GB2-08":{"draws":138,"losses":37,"wins":1}},"none":{"GB2-01":{"draws":69,"losses":96,"wins":75},"GB2-02":{"draws":198,"losses":5,"wins":1},"GB2-03":{"draws":96,"losses":65,"wins":47},"GB2-04":{"draws":139,"losses":44,"wins":33},"GB2-05":{"draws":0,"losses":151,"wins":87},"GB2-06":{"draws":24,"losses":96,"wins":104},"GB2-07":{"draws":0,"losses":141,"wins":127},"GB2-08":{"draws":142,"losses":42,"wins":46}}},"per_game_raw_elo_all":{"GB2-01":1430.3834982470041,"GB2-02":1489.2825472912973,"GB2-03":1398.843728013849,"GB2-04":1467.7284074698466,"GB2-05":1484.3849473874798,"GB2-06":1548.0220935505367,"GB2-07":1340.4983728677114,"GB2-08":1395.8524039518481},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1518.440886827866,"GB2-02":1508.2607155527892,"GB2-03":1389.496297577414,"GB2-04":1490.9508346481748,"GB2-05":1569.950754355836,"GB2-06":1376.3097819269658,"GB2-07":940.4778015280162,"GB2-08":1349.1858370718082},"medium":{"GB2-01":1431.1271705787317,"GB2-02":1502.2858557746495,"GB2-03":1364.168727478889,"GB2-04":1486.996413725924,"GB2-05":1550.3347621659645,"GB2-06":1802.3044945588013,"GB2-07":1564.420023753623,"GB2-08":1359.0107627204068},"none":{"GB2-01":1341.5824373344149,"GB2-02":1457.301070546453,"GB2-03":1442.8661589852445,"GB2-04":1425.2379740354415,"GB2-05":1332.8693256406384,"GB2-06":1465.452004165843,"GB2-07":1516.5972933214946,"GB2-08":1479.360612063329}},"per_game_tracks":{"highest":{"GB2-01":45.243564635376174,"GB2-02":20.87099389668296,"GB2-03":26.677941438624654,"GB2-04":29.515021005587823,"GB2-05":54.56042710751232,"GB2-06":39.919571760376535,"GB2-07":3.385411727320254,"GB2-08":24.65952105621167},"medium":{"GB2-01":37.27778068209783,"GB2-02":18.056375254178352,"GB2-03":22.42619957772019,"GB2-04":27.5668099847064,"GB2-05":52.29644206798784,"GB2-06":72.14085667254591,"GB2-07":54.68417033513214,"GB2-08":24.681783476260748},"none":{"GB2-01":29.661124622687225,"GB2-02":10.165756558589774,"GB2-03":30.699708107136836,"GB2-04":16.949774220889857,"GB2-05":35.199708198410335,"GB2-06":45.97848016268618,"GB2-07":50.75736719314747,"GB2-08":35.79025072377557}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.60405657846155,"medium":38.64130225632867,"none":31.900271223415405},"reasoning_agg":{"highest":{"max":54.56042710751232,"mean":30.60405657846155,"min":3.385411727320254},"medium":{"max":72.14085667254591,"mean":38.64130225632867,"min":18.056375254178352},"none":{"max":50.75736719314747,"mean":31.900271223415405,"min":10.165756558589774}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":72.14085667254591,"expected_score":31.423705344711504,"reasoning_variance":8.037245677867123,"reliability_score":90.48689328548548,"uncertainty_avg":9.513106714514526,"uncertainty_penalty":-2.291504674690369},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.56042710751232,"expected_score":21.668448874350698,"reliability_score":98.91346647475453,"uncertainty_avg":1.0865335252454644,"uncertainty_penalty":-8.93560770411085},"medium":{"ceiling_score":72.14085667254591,"expected_score":39.28018507349892,"reliability_score":86.31862225270915,"uncertainty_avg":13.681377747290856,"uncertainty_penalty":0.6388828171702485},"none":{"ceiling_score":50.75736719314747,"expected_score":33.32248208628489,"reliability_score":86.22859112899273,"uncertainty_avg":13.771408871007264,"uncertainty_penalty":1.4222108628694876}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:8997dfac4b0e4cf4","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":44.42570551005691,"none":27.57407026128659},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"total_output_tokens":343242},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"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,"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}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-08-05T03:48:47Z","match_totals_all":{"draws":293,"losses":347,"wins":276},"match_totals_tracks":{"medium":{"draws":150,"losses":158,"wins":178},"none":{"draws":143,"losses":189,"wins":98}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":70.99957787144118,"mean":33.12938127623754,"min":14.181701766649182},"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":41,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":39,"losses":75,"wins":48},"GB2-02":{"draws":133,"losses":2,"wins":1},"GB2-04":{"draws":45,"losses":8,"wins":3},"GB2-05":{"draws":0,"losses":84,"wins":92},"GB2-06":{"draws":2,"losses":67,"wins":69},"GB2-07":{"draws":0,"losses":95,"wins":63},"GB2-08":{"draws":74,"losses":16,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":17,"losses":32,"wins":31},"GB2-02":{"draws":59,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":48,"wins":50},"GB2-06":{"draws":0,"losses":15,"wins":49},"GB2-07":{"draws":0,"losses":45,"wins":47},"GB2-08":{"draws":74,"losses":16,"wins":0}},"none":{"GB2-01":{"draws":22,"losses":43,"wins":17},"GB2-02":{"draws":74,"losses":0,"wins":0},"GB2-04":{"draws":45,"losses":8,"wins":3},"GB2-05":{"draws":0,"losses":36,"wins":42},"GB2-06":{"draws":2,"losses":52,"wins":20},"GB2-07":{"draws":0,"losses":50,"wins":16}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1496.5386153907175,"GB2-02":1488.1517568183824,"GB2-05":1657.1023897142595,"GB2-06":1789.1763903140825,"GB2-07":1462.8109077124877,"GB2-08":1420.1673033832565},"none":{"GB2-01":1360.7360649255008,"GB2-02":1478.2664311879878,"GB2-04":1467.4292622210753,"GB2-05":1527.1416526227213,"GB2-06":1248.3796837667817,"GB2-07":1126.7838784610865}},"per_game_tracks":{"medium":{"GB2-01":42.34815521713447,"GB2-02":15.204208993992154,"GB2-05":60.93926279553979,"GB2-06":70.99957787144118,"GB2-07":46.42393579584542,"GB2-08":30.639092386388416},"none":{"GB2-01":31.224037847715838,"GB2-02":14.181701766649182,"GB2-04":22.87218750063355,"GB2-05":50.37567398128637,"GB2-06":28.97553839834991,"GB2-07":17.815282073084678}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":41.34277741669788,"none":24.915985135777202},"reasoning_agg":{"medium":{"max":70.99957787144118,"mean":41.34277741669788,"min":15.204208993992154},"none":{"max":50.37567398128637,"mean":24.915985135777202,"min":14.181701766649182}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":70.99957787144118,"reasoning_variance":16.426792280920676},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":70.99957787144118,"expected_score":45.910808124015404,"reliability_score":87.9032134965652,"uncertainty_avg":12.096786503434794,"uncertainty_penalty":4.568030707317526},"none":{"ceiling_score":50.37567398128637,"expected_score":25.211196831743887,"reliability_score":84.76368018158728,"uncertainty_avg":15.236319818412719,"uncertainty_penalty":0.2952116959666853}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:13806a60945d43bf","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.079473456,"mean":0.042855077875,"median":0.0387132625,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.342840623},"none":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.045896320000000004,"mean":0.021958409999999998,"median":0.019045885,"min":0.011539076,"recorded_attempt_count":15,"run_count":8,"total":0.17566727999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.079473456,"mean":0.042855077875,"median":0.0387132625,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.34284062299999996},"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.045896320000000004,"mean":0.021958409999999998,"median":0.019045885,"min":0.011539076,"recorded_attempt_count":15,"run_count":8,"total":0.17566728000000004},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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":14,"cell_count":24,"cost_basis_counts":{"provider_reported":41},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.3521656,"mean":0.08683453949999999,"median":0.042413385,"min":0.0,"recorded_attempt_count":41,"run_count":24,"total":2.084028948},"codegen_latency_ms":{"attempt_count":41,"max_ms":2128037,"mean_ms":557159.5833333334,"min_ms":84532,"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":15,"max_ms":552808,"mean_ms":296150.0,"min_ms":144070,"run_count":8},"none":{"attempt_count":15,"max_ms":184099,"mean_ms":115436.875,"min_ms":84532,"run_count":8}},"codegen_output_tokens":{"attempt_count":40,"output_max":142524,"output_mean":34415.13043478261,"output_min":3853,"run_count":23},"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":14,"output_max":27551,"output_mean":16708.285714285714,"output_min":7740,"run_count":7},"none":{"attempt_count":15,"output_max":14298,"output_mean":6451.75,"output_min":3853,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"highest":50.590074067871484,"medium":34.62654964999745,"none":23.705963362379308},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":40,"finish_reasons":["stop"],"indexed_attempts":41,"output_token_observations":40,"provider_post_attempt_observations":41,"provider_post_attempts":41,"reasoning_token_observations":41,"reconciliation_get_attempt_observations":41,"reconciliation_get_attempts":199,"total_output_tokens":791548,"total_reasoning_output_tokens":610979,"total_visible_output_tokens":185807,"visible_token_observations":41},"generation_policy":{"generation_policy":"quality_generation_policy","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/qwen3.8-27b","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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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":["GB2-02","GB2-04"],"first_pass_admitted":2,"first_pass_rate":0.2857142857142857,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"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":3,"repaired_rate":0.42857142857142855},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-05","GB2-06","GB2-07"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":false,"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,"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}},"id":"qwen/qwen3.8-27b","is_recent_addition":false,"last_measured_at":"2026-09-10T10:06:23Z","match_totals_all":{"draws":407,"losses":690,"wins":618},"match_totals_tracks":{"highest":{"draws":107,"losses":316,"wins":344},"medium":{"draws":120,"losses":322,"wins":250},"none":{"draws":180,"losses":52,"wins":24}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":74.97439218948013,"mean":32.48775375004117,"min":18.550918857121076},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","generation_incomplete"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":61.64418656956991,"GB2-04":55.90738193032783,"GB2-05":49.36302826110043,"GB2-06":29.853834414688254,"GB2-07":74.97439218948013,"GB2-08":31.79762104206238},"per_game_match_totals_all":{"GB2-01":{"draws":78,"losses":84,"wins":78},"GB2-03":{"draws":39,"losses":69,"wins":37},"GB2-04":{"draws":115,"losses":66,"wins":65},"GB2-05":{"draws":0,"losses":104,"wins":152},"GB2-06":{"draws":14,"losses":140,"wins":132},"GB2-07":{"draws":0,"losses":135,"wins":113},"GB2-08":{"draws":161,"losses":92,"wins":41}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":54,"wins":61},"GB2-04":{"draws":36,"losses":30,"wins":48},"GB2-05":{"draws":0,"losses":50,"wins":72},"GB2-06":{"draws":7,"losses":59,"wins":52},"GB2-07":{"draws":0,"losses":47,"wins":77},"GB2-08":{"draws":60,"losses":76,"wins":34}},"medium":{"GB2-01":{"draws":74,"losses":30,"wins":17},"GB2-03":{"draws":39,"losses":69,"wins":37},"GB2-05":{"draws":0,"losses":54,"wins":80},"GB2-06":{"draws":7,"losses":81,"wins":80},"GB2-07":{"draws":0,"losses":88,"wins":36}},"none":{"GB2-04":{"draws":79,"losses":36,"wins":17},"GB2-08":{"draws":101,"losses":16,"wins":7}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1723.2392832402293,"GB2-04":1651.3628695260552,"GB2-05":1505.2863092900893,"GB2-06":1250.09057059966,"GB2-07":1799.8280691620685,"GB2-08":1421.3847926961248},"medium":{"GB2-01":1280.5318378187312,"GB2-03":1467.9893251701199,"GB2-05":1424.7633280592884,"GB2-06":1510.7368874771566,"GB2-07":1127.7345872672606},"none":{"GB2-04":1450.0204773592366,"GB2-08":1346.2937799317099}},"per_game_tracks":{"highest":{"GB2-01":61.64418656956991,"GB2-04":55.90738193032783,"GB2-05":49.36302826110043,"GB2-06":29.853834414688254,"GB2-07":74.97439218948013,"GB2-08":31.79762104206238},"medium":{"GB2-01":25.260571807798776,"GB2-03":35.009010479559414,"GB2-05":43.17968294559612,"GB2-06":50.69846903136761,"GB2-07":18.985013985665347},"none":{"GB2-04":23.019165184642294,"GB2-08":24.392761540116325}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.079368749896325,"medium":31.832973643106108,"none":18.550918857121076},"reasoning_agg":{"highest":{"max":74.97439218948013,"mean":47.079368749896325,"min":29.853834414688254},"medium":{"max":50.69846903136761,"mean":31.832973643106108,"min":18.985013985665347},"none":{"max":24.392761540116325,"mean":18.550918857121076,"min":23.019165184642294}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.97439218948013,"reasoning_variance":28.52844989277525},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.97439218948013,"expected_score":44.162860719331945,"reliability_score":98.47357449907375,"uncertainty_avg":1.526425500926251,"uncertainty_penalty":-2.91650803056438},"medium":{"ceiling_score":50.69846903136761,"expected_score":33.723794499264564,"reliability_score":99.50215348574899,"uncertainty_avg":0.49784651425101245,"uncertainty_penalty":1.8908208561584559},"none":{"ceiling_score":24.392761540116325,"expected_score":22.276854947083187,"reliability_score":99.51432022500211,"uncertainty_avg":0.48567977499789805,"uncertainty_penalty":3.7259360899621115}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:f0f52491401ad45b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139173999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725612999999995},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":34.085726250217604,"none":33.64300657853923},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"total_output_tokens":130744},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"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,"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}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-08-05T05:11:51Z","match_totals_all":{"draws":294,"losses":297,"wins":255},"match_totals_tracks":{"highest":{"draws":116,"losses":187,"wins":139},"none":{"draws":178,"losses":110,"wins":116}},"model_slug":"tencent-hy3-preview","overall":{"max":64.07635846709539,"mean":31.65920071627273,"min":7.405950095136704},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":43,"overall_ranking_status":"partial","per_game":{"GB2-01":50.032819133002,"GB2-02":7.834028495391087,"GB2-04":19.361118709233534,"GB2-05":58.73748205542807,"GB2-06":33.417976363713066,"GB2-07":33.99435555624251,"GB2-08":35.22230343851298},"per_game_match_totals_all":{"GB2-01":{"draws":27,"losses":30,"wins":75},"GB2-02":{"draws":86,"losses":11,"wins":1},"GB2-03":{"draws":22,"losses":24,"wins":22},"GB2-04":{"draws":70,"losses":20,"wins":16},"GB2-05":{"draws":0,"losses":77,"wins":67},"GB2-06":{"draws":0,"losses":38,"wins":18},"GB2-07":{"draws":0,"losses":44,"wins":28},"GB2-08":{"draws":89,"losses":53,"wins":28}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":23,"wins":28},"GB2-02":{"draws":39,"losses":6,"wins":1},"GB2-04":{"draws":40,"losses":14,"wins":6},"GB2-05":{"draws":0,"losses":29,"wins":33},"GB2-06":{"draws":0,"losses":38,"wins":18},"GB2-07":{"draws":0,"losses":44,"wins":28},"GB2-08":{"draws":22,"losses":33,"wins":25}},"none":{"GB2-01":{"draws":12,"losses":7,"wins":47},"GB2-02":{"draws":47,"losses":5,"wins":0},"GB2-03":{"draws":22,"losses":24,"wins":22},"GB2-04":{"draws":30,"losses":6,"wins":10},"GB2-05":{"draws":0,"losses":48,"wins":34},"GB2-08":{"draws":67,"losses":20,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1594.4036920144524,"GB2-02":1455.1751466918467,"GB2-04":1444.4471348945187,"GB2-05":1639.2073900533328,"GB2-06":1311.979408855983,"GB2-07":1318.9452867243672,"GB2-08":1472.3689594436266},"none":{"GB2-01":1765.1662409309436,"GB2-02":1449.3962138369807,"GB2-03":1447.4673153903937,"GB2-04":1517.7254552578606,"GB2-05":1362.0329257769195,"GB2-08":1426.684392050828}},"per_game_tracks":{"highest":{"GB2-01":50.032819133002,"GB2-02":7.834028495391087,"GB2-04":19.361118709233534,"GB2-05":58.73748205542807,"GB2-06":33.417976363713066,"GB2-07":33.99435555624251,"GB2-08":35.22230343851298},"none":{"GB2-01":64.07635846709539,"GB2-02":7.405950095136704,"GB2-03":31.307974629209557,"GB2-04":30.308115130799013,"GB2-05":37.51942114475686,"GB2-08":31.240220004237862}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.010056035752946,"none":31.308345396792507},"reasoning_agg":{"highest":{"max":58.73748205542807,"mean":32.010056035752946,"min":7.834028495391087},"none":{"max":64.07635846709539,"mean":31.308345396792507,"min":7.405950095136704}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":64.07635846709539,"reasoning_variance":0.7017106389604386},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.73748205542807,"expected_score":28.89960017652184,"reliability_score":80.7025023235297,"uncertainty_avg":19.2974976764703,"uncertainty_penalty":-3.110455859231106},"none":{"ceiling_score":64.07635846709539,"expected_score":39.568227168970964,"reliability_score":82.05220028745498,"uncertainty_avg":17.947799712545017,"uncertainty_penalty":8.259881772178456}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:bcc0bd9ea9d81a91","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":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},"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"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},"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},"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},"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.33399885},"codegen_output_tokens":{"attempt_count":25,"output_max":29793,"output_mean":9924.083333333334,"output_min":1845,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":29793,"output_mean":24080.5,"output_min":19109,"run_count":8},"medium":{"attempt_count":9,"output_max":6277,"output_mean":3473.625,"output_min":2113,"run_count":8},"none":{"attempt_count":8,"output_max":2721,"output_mean":2218.125,"output_min":1845,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":31.5347122936316,"highest":45.30312374197206,"medium":33.21050354010995,"none":16.090509598812808},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-09-10T11:05:04Z","match_totals_all":{"draws":1692,"losses":1917,"wins":1401},"match_totals_tracks":{"highest":{"draws":576,"losses":458,"wins":648},"medium":{"draws":590,"losses":614,"wins":520},"none":{"draws":526,"losses":845,"wins":233}},"model_slug":"gpt-5-6-luna","overall":{"max":79.12179151899733,"mean":31.53471229363161,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":75.49834308214069,"GB2-02":10.237515749847217,"GB2-03":33.06553227928354,"GB2-04":17.294684637089965,"GB2-05":54.03153887048955,"GB2-06":79.12179151899733,"GB2-07":75.33510562810226,"GB2-08":17.840478169825914},"per_game_all":{"GB2-01":45.34384978455651,"GB2-02":10.878284267496683,"GB2-03":27.63197510003211,"GB2-04":21.913436974477538,"GB2-05":41.17695903890985,"GB2-06":50.56468140535163,"GB2-07":40.72226718859142,"GB2-08":14.046244589637068},"per_game_match_totals_all":{"GB2-01":{"draws":87,"losses":276,"wins":280},"GB2-02":{"draws":481,"losses":26,"wins":15},"GB2-03":{"draws":344,"losses":228,"wins":132},"GB2-04":{"draws":370,"losses":117,"wins":75},"GB2-05":{"draws":0,"losses":360,"wins":327},"GB2-06":{"draws":57,"losses":294,"wins":293},"GB2-07":{"draws":0,"losses":372,"wins":254},"GB2-08":{"draws":353,"losses":244,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":58,"wins":142},"GB2-02":{"draws":147,"losses":10,"wins":9},"GB2-03":{"draws":115,"losses":70,"wins":52},"GB2-04":{"draws":116,"losses":45,"wins":23},"GB2-05":{"draws":0,"losses":124,"wins":150},"GB2-06":{"draws":34,"losses":38,"wins":133},"GB2-07":{"draws":0,"losses":72,"wins":136},"GB2-08":{"draws":164,"losses":41,"wins":3}},"medium":{"GB2-01":{"draws":37,"losses":93,"wins":111},"GB2-02":{"draws":171,"losses":6,"wins":5},"GB2-03":{"draws":103,"losses":84,"wins":70},"GB2-04":{"draws":122,"losses":42,"wins":26},"GB2-05":{"draws":0,"losses":99,"wins":108},"GB2-06":{"draws":9,"losses":108,"wins":114},"GB2-07":{"draws":0,"losses":132,"wins":76},"GB2-08":{"draws":148,"losses":50,"wins":10}},"none":{"GB2-01":{"draws":50,"losses":125,"wins":27},"GB2-02":{"draws":163,"losses":10,"wins":1},"GB2-03":{"draws":126,"losses":74,"wins":10},"GB2-04":{"draws":132,"losses":30,"wins":26},"GB2-05":{"draws":0,"losses":137,"wins":69},"GB2-06":{"draws":14,"losses":148,"wins":46},"GB2-07":{"draws":0,"losses":168,"wins":42},"GB2-08":{"draws":41,"losses":153,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1515.8541121946892,"GB2-02":1443.9871838059541,"GB2-03":1390.1042249212849,"GB2-04":1437.8038269648005,"GB2-05":1391.34009766317,"GB2-06":1505.5232795088612,"GB2-07":1380.515081145838,"GB2-08":1226.0585816353207},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1883.3980174205028,"GB2-02":1441.1288826180637,"GB2-03":1442.133702959996,"GB2-04":1410.1545682656892,"GB2-05":1552.897963944819,"GB2-06":1871.2923877720345,"GB2-07":1796.0495447757285,"GB2-08":1267.149087461531},"medium":{"GB2-01":1467.15171118097,"GB2-02":1450.6916419866793,"GB2-03":1426.6322402370815,"GB2-04":1482.5368821382333,"GB2-05":1440.6706022597677,"GB2-06":1519.7437375270322,"GB2-07":1252.9129029601745,"GB2-08":1337.1606904094851},"none":{"GB2-01":1197.0126079825945,"GB2-02":1440.1410268131199,"GB2-03":1301.546731566777,"GB2-04":1420.720030490479,"GB2-05":1180.4517267849226,"GB2-06":1125.533713227516,"GB2-07":1092.582795701611,"GB2-08":1073.865967034946}},"per_game_tracks":{"highest":{"GB2-01":75.49834308214069,"GB2-02":10.237515749847217,"GB2-03":33.06553227928354,"GB2-04":17.294684637089965,"GB2-05":54.03153887048955,"GB2-06":79.12179151899733,"GB2-07":75.33510562810226,"GB2-08":17.840478169825914},"medium":{"GB2-01":41.4718506514852,"GB2-02":12.208818148161988,"GB2-03":31.559379754277902,"GB2-04":29.350634971233603,"GB2-05":44.951124002900116,"GB2-06":51.75536719315471,"GB2-07":30.08859800058072,"GB2-08":24.298255599085287},"none":{"GB2-01":19.061355620043653,"GB2-02":10.188518904480844,"GB2-03":18.271013266534894,"GB2-04":19.09499131510905,"GB2-05":24.54821424333988,"GB2-06":20.816885503902856,"GB2-07":16.743097937091278,"GB2-08":0.0}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.30312374197206,"medium":33.21050354010995,"none":16.090509598812808},"reasoning_agg":{"highest":{"max":79.12179151899733,"mean":45.30312374197206,"min":10.237515749847217},"medium":{"max":51.75536719315471,"mean":33.21050354010995,"min":12.208818148161988},"none":{"max":24.54821424333988,"mean":16.090509598812808,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.12179151899733,"expected_score":26.497532034383624,"reasoning_variance":29.21261414315925,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.037180259247986},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.12179151899733,"expected_score":37.391551591670456,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.911572150301602},"medium":{"ceiling_score":51.75536719315471,"expected_score":30.997106024128193,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.213397515981754},"none":{"ceiling_score":24.54821424333988,"expected_score":11.103938487352222,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.986571111460586}}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:98784e253f1f8550","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":27.094189624924688,"none":36.383144914207264},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"total_output_tokens":596080},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"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,"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}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-08-05T04:33:21Z","match_totals_all":{"draws":292,"losses":442,"wins":296},"match_totals_tracks":{"medium":{"draws":191,"losses":262,"wins":123},"none":{"draws":101,"losses":180,"wins":173}},"model_slug":"minimax-minimax-m3","overall":{"max":48.5556009285104,"mean":30.03148516557112,"min":5.046768034226976},"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":45,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":27,"losses":81,"wins":74},"GB2-02":{"draws":106,"losses":10,"wins":0},"GB2-03":{"draws":26,"losses":20,"wins":24},"GB2-04":{"draws":59,"losses":3,"wins":6},"GB2-05":{"draws":0,"losses":132,"wins":44},"GB2-06":{"draws":0,"losses":57,"wins":33},"GB2-07":{"draws":0,"losses":86,"wins":82},"GB2-08":{"draws":74,"losses":53,"wins":33}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":49,"wins":24},"GB2-02":{"draws":54,"losses":8,"wins":0},"GB2-04":{"draws":59,"losses":3,"wins":6},"GB2-05":{"draws":0,"losses":86,"wins":0},"GB2-06":{"draws":0,"losses":57,"wins":33},"GB2-07":{"draws":0,"losses":45,"wins":53},"GB2-08":{"draws":71,"losses":14,"wins":7}},"none":{"GB2-01":{"draws":20,"losses":32,"wins":50},"GB2-02":{"draws":52,"losses":2,"wins":0},"GB2-03":{"draws":26,"losses":20,"wins":24},"GB2-05":{"draws":0,"losses":46,"wins":44},"GB2-07":{"draws":0,"losses":41,"wins":29},"GB2-08":{"draws":3,"losses":39,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1350.9691174196694,"GB2-02":1438.5933872534667,"GB2-04":1506.5088333178212,"GB2-05":946.7487485340107,"GB2-06":1363.2498048504203,"GB2-07":1487.1227460326932,"GB2-08":1423.3080306183583},"none":{"GB2-01":1537.7263032874123,"GB2-02":1474.9568968469735,"GB2-03":1499.939205942563,"GB2-05":1473.8637902645755,"GB2-07":1400.0415201193246,"GB2-08":1484.3473690224341}},"per_game_tracks":{"medium":{"GB2-01":30.37649642208813,"GB2-02":6.27975662875229,"GB2-04":30.138488502474974,"GB2-05":5.046768034226976,"GB2-06":38.29161379644027,"GB2-07":48.5556009285104,"GB2-08":30.97060306197978},"none":{"GB2-01":46.149209979529324,"GB2-02":12.190471042456242,"GB2-03":36.838386025548644,"GB2-05":46.440218311437484,"GB2-07":40.695604031124134,"GB2-08":35.98498009514775}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.204638884565124,"none":33.85833144657712},"reasoning_agg":{"medium":{"max":48.5556009285104,"mean":26.204638884565124,"min":5.046768034226976},"none":{"max":46.440218311437484,"mean":33.85833144657712,"min":12.190471042456242}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":48.5556009285104,"reasoning_variance":7.653692562011994},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":48.5556009285104,"expected_score":25.96475731674864,"reliability_score":88.48401356988873,"uncertainty_avg":11.515986430111266,"uncertainty_penalty":-0.23988156781648584},"none":{"ceiling_score":46.440218311437484,"expected_score":40.706558809099995,"reliability_score":85.75470260784921,"uncertainty_avg":14.245297392150784,"uncertainty_penalty":6.848227362522877}}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:097f668cb006b9b1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.31476170000000003},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.3147617},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.11219570000000001,"mean":0.0416694575,"median":0.033877925,"min":0.00984735,"recorded_attempt_count":59,"run_count":24,"total":1.0000669800000002},"codegen_latency_ms":{"attempt_count":59,"max_ms":511905,"mean_ms":204675.625,"min_ms":73907,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":20,"max_ms":511905,"mean_ms":284845.75,"min_ms":132388,"run_count":8},"medium":{"attempt_count":19,"max_ms":302393,"mean_ms":201389.625,"min_ms":134501,"run_count":8},"none":{"attempt_count":20,"max_ms":209946,"mean_ms":127791.5,"min_ms":73907,"run_count":8}},"codegen_output_tokens":{"attempt_count":59,"output_max":93362,"output_mean":33067.75,"output_min":6729,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":20,"output_max":93362,"output_mean":49316.75,"output_min":16213,"run_count":8},"medium":{"attempt_count":19,"output_max":59186,"output_mean":30987.25,"output_min":18109,"run_count":8},"none":{"attempt_count":20,"output_max":28972,"output_mean":18899.25,"output_min":6729,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":42.83098335454592,"highest":35.767705313356814,"medium":31.49301590711204,"none":35.63407345020555},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":59,"finish_reasons":["stop"],"indexed_attempts":59,"output_token_observations":59,"reasoning_token_observations":20,"total_output_tokens":793626,"total_reasoning_output_tokens":89090,"total_visible_output_tokens":62104,"visible_token_observations":20},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03","GB2-07","GB2-08"],"model_code_failure_rate":0.5,"model_code_failures":4,"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":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.5,"model_code_failures":4,"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},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-09-10T11:06:38Z","match_totals_all":{"draws":390,"losses":806,"wins":569},"match_totals_tracks":{"highest":{"draws":54,"losses":167,"wins":118},"medium":{"draws":120,"losses":120,"wins":80},"none":{"draws":216,"losses":519,"wins":371}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":49.98510602874532,"mean":29.41647191950841,"min":15.266282350907517},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":46,"overall_ranking_status":"partial","per_game":{"GB2-01":17.73358084856714,"GB2-05":44.46448138749022,"GB2-06":45.69828843610223,"GB2-07":42.61480276704312,"GB2-08":28.327373127581367},"per_game_all":{"GB2-05":44.14919194471904,"GB2-06":41.51277476437281},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":43,"wins":11},"GB2-02":{"draws":58,"losses":5,"wins":1},"GB2-04":{"draws":61,"losses":7,"wins":8},"GB2-05":{"draws":0,"losses":237,"wins":189},"GB2-06":{"draws":27,"losses":232,"wins":213},"GB2-07":{"draws":0,"losses":202,"wins":147},"GB2-08":{"draws":238,"losses":80,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":43,"wins":11},"GB2-05":{"draws":0,"losses":31,"wins":45},"GB2-06":{"draws":2,"losses":40,"wins":32},"GB2-07":{"draws":0,"losses":39,"wins":30},"GB2-08":{"draws":46,"losses":14,"wins":0}},"medium":{"GB2-02":{"draws":58,"losses":5,"wins":1},"GB2-04":{"draws":61,"losses":7,"wins":8},"GB2-05":{"draws":0,"losses":48,"wins":46},"GB2-06":{"draws":1,"losses":60,"wins":25}},"none":{"GB2-05":{"draws":0,"losses":158,"wins":98},"GB2-06":{"draws":24,"losses":132,"wins":156},"GB2-07":{"draws":0,"losses":163,"wins":117},"GB2-08":{"draws":192,"losses":66,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1439.8966742619775,"GB2-06":1399.7354069360783},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1204.0077738517675,"GB2-05":1452.3115832325407,"GB2-06":1462.2172455852156,"GB2-07":1423.4173564751177,"GB2-08":1404.3882975295737},"medium":{"GB2-02":1487.71508709671,"GB2-04":1500.9648602725551,"GB2-05":1518.1946829738897,"GB2-06":1271.9140813081422},"none":{"GB2-05":1349.1837565795022,"GB2-06":1465.074893914877,"GB2-07":1319.3894482362023,"GB2-08":1296.7353446789812}},"per_game_tracks":{"highest":{"GB2-01":17.73358084856714,"GB2-05":44.46448138749022,"GB2-06":45.69828843610223,"GB2-07":42.61480276704312,"GB2-08":28.327373127581367},"medium":{"GB2-02":15.266282350907517,"GB2-04":29.646329769358474,"GB2-05":49.98510602874532,"GB2-06":31.07434547943685},"none":{"GB2-05":37.997988417921604,"GB2-06":47.765690377579354,"GB2-07":35.94359963093725,"GB2-08":20.829015374383967}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":31.802486951541095,"medium":26.48236418181872,"none":29.96456462516541},"reasoning_agg":{"highest":{"max":45.69828843610223,"mean":31.802486951541095,"min":17.73358084856714},"medium":{"max":49.98510602874532,"mean":26.48236418181872,"min":15.266282350907517},"none":{"max":47.765690377579354,"mean":29.96456462516541,"min":20.829015374383967}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":49.98510602874532,"expected_score":39.91155100186281,"reasoning_variance":5.320122769722374,"reliability_score":92.56335675084517,"uncertainty_avg":7.436643249154832,"uncertainty_penalty":10.495079082354401},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":45.69828843610223,"expected_score":27.54675929510381,"reliability_score":83.24727489032057,"uncertainty_avg":16.75272510967944,"uncertainty_penalty":-4.2557276564372835},"medium":{"ceiling_score":49.98510602874532,"expected_score":32.03764923535021,"reliability_score":87.77445003235734,"uncertainty_avg":12.22554996764266,"uncertainty_penalty":5.555285053531488},"none":{"ceiling_score":47.765690377579354,"expected_score":34.4488205393326,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.484255914167193}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:3140add484494bcc","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"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},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.03062629,"mean":0.020124273158333334,"median":0.017895481666666668,"min":0.012095886733333333,"recorded_attempt_count":52,"run_count":24,"total":0.48618750699999996},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.0016912200000000002,"recorded_attempt_count":37,"run_count":24,"total":0.06890521579999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0265755425,"mean":0.018416099712499998,"median":0.017703669999999998,"min":0.0109615788,"recorded_attempt_count":32,"run_count":15,"total":0.27207317540000003},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.2141143316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.0306854728},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.19736108440000003}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":16,"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":29.503340891363234,"highest":29.66033164309214,"medium":32.790258691009186,"none":34.497841045473734},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["length","stop"],"indexed_attempts":32,"output_token_observations":32,"total_output_tokens":734523},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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":12,"failed_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.08333333333333333,"infra_excluded_game_aliases":["GB2-03","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.3333333333333333,"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":0.5833333333333334},"baseline":{"admitted_plugins":11,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"model_code_failure_rate":0.3125,"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":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-05","GB2-07"],"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}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:45Z","match_totals_all":{"draws":897,"losses":911,"wins":732},"match_totals_tracks":{"highest":{"draws":178,"losses":63,"wins":41},"medium":{"draws":422,"losses":418,"wins":310},"none":{"draws":297,"losses":430,"wins":381}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":55.88030293196678,"mean":29.13819034227683,"min":10.940010823479835},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":47,"overall_ranking_status":"partial","per_game":{"GB2-01":23.780667328407972,"GB2-02":14.876831236011256,"GB2-04":24.5961118118581,"GB2-06":55.88030293196678,"GB2-08":29.167744907216587},"per_game_all":{"GB2-01":34.1175719468382,"GB2-02":13.67031888739765,"GB2-04":25.887076348001674,"GB2-06":46.53479200005622,"GB2-08":27.306945274522423},"per_game_match_totals_all":{"GB2-01":{"draws":104,"losses":200,"wins":164},"GB2-02":{"draws":254,"losses":22,"wins":8},"GB2-03":{"draws":27,"losses":19,"wins":14},"GB2-04":{"draws":286,"losses":50,"wins":32},"GB2-05":{"draws":0,"losses":194,"wins":190},"GB2-06":{"draws":10,"losses":175,"wins":161},"GB2-07":{"draws":0,"losses":154,"wins":138},"GB2-08":{"draws":216,"losses":97,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":39,"losses":19,"wins":2},"GB2-02":{"draws":40,"losses":8,"wins":2},"GB2-04":{"draws":42,"losses":7,"wins":5},"GB2-06":{"draws":4,"losses":26,"wins":30},"GB2-08":{"draws":53,"losses":3,"wins":2}},"medium":{"GB2-01":{"draws":16,"losses":81,"wins":69},"GB2-02":{"draws":169,"losses":13,"wins":6},"GB2-04":{"draws":163,"losses":38,"wins":9},"GB2-05":{"draws":0,"losses":98,"wins":92},"GB2-06":{"draws":3,"losses":58,"wins":33},"GB2-07":{"draws":0,"losses":76,"wins":80},"GB2-08":{"draws":71,"losses":54,"wins":21}},"none":{"GB2-01":{"draws":49,"losses":100,"wins":93},"GB2-02":{"draws":45,"losses":1,"wins":0},"GB2-03":{"draws":27,"losses":19,"wins":14},"GB2-04":{"draws":81,"losses":5,"wins":18},"GB2-05":{"draws":0,"losses":96,"wins":98},"GB2-06":{"draws":3,"losses":91,"wins":98},"GB2-07":{"draws":0,"losses":78,"wins":58},"GB2-08":{"draws":92,"losses":40,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1398.1791713400314,"GB2-02":1484.0386439166687,"GB2-04":1484.7446913250153,"GB2-06":1473.7687211804296,"GB2-08":1391.1763298161623},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1277.5373789071825,"GB2-02":1491.949735935574,"GB2-04":1478.8007459421844,"GB2-06":1597.443682966158,"GB2-08":1414.3599497088626},"medium":{"GB2-01":1390.5996054009402,"GB2-02":1487.7432210455304,"GB2-04":1460.6010053359187,"GB2-05":1467.241945584617,"GB2-06":1369.4305277949966,"GB2-07":1449.689002618837,"GB2-08":1397.0111643133864},"none":{"GB2-01":1526.400529711971,"GB2-02":1472.4229747689012,"GB2-03":1475.5650571562767,"GB2-04":1514.8323226969433,"GB2-05":1526.3456577110624,"GB2-06":1454.431952780135,"GB2-07":1348.8770201939483,"GB2-08":1362.1578754262378}},"per_game_tracks":{"highest":{"GB2-01":23.780667328407972,"GB2-02":14.876831236011256,"GB2-04":24.5961118118581,"GB2-06":55.88030293196678,"GB2-08":29.167744907216587},"medium":{"GB2-01":33.69985907503834,"GB2-02":15.194114602701864,"GB2-04":22.692328669404453,"GB2-05":45.99727906392186,"GB2-06":38.84474260375074,"GB2-07":45.02896848324199,"GB2-08":28.07451833900503},"none":{"GB2-01":44.87218943706828,"GB2-02":10.940010823479835,"GB2-03":33.912938053620756,"GB2-04":30.37278856274247,"GB2-05":49.95050528925342,"GB2-06":44.87933046445113,"GB2-07":36.376393155828296,"GB2-08":24.67857257734565}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.37217852791834,"medium":29.629343452081027,"none":31.413049046831127},"reasoning_agg":{"highest":{"max":55.88030293196678,"mean":26.37217852791834,"min":14.876831236011256},"medium":{"max":45.99727906392186,"mean":29.629343452081027,"min":15.194114602701864},"none":{"max":49.95050528925342,"mean":31.413049046831127,"min":10.940010823479835}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":55.88030293196678,"expected_score":28.2562502066336,"reasoning_variance":5.0408705189127865,"reliability_score":81.461805643185,"uncertainty_avg":18.538194356814998,"uncertainty_penalty":-0.8819401356432301},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.88030293196678,"expected_score":23.047937161866304,"reliability_score":77.63693482579347,"uncertainty_avg":22.363065174206522,"uncertainty_penalty":-3.3242413660520356},"medium":{"ceiling_score":45.99727906392186,"expected_score":33.16379197424153,"reliability_score":87.56666475271727,"uncertainty_avg":12.43333524728273,"uncertainty_penalty":3.534448522160506},"none":{"ceiling_score":49.95050528925342,"expected_score":37.88743248136085,"reliability_score":80.71226012661492,"uncertainty_avg":19.28773987338508,"uncertainty_penalty":6.47438343452972}}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:32ef0b4e4a037e65","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"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},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.31772779999999995},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"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},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.5047206500000001}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.21164085},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":38.68186035978409,"highest":30.269331289367823,"medium":33.17879341527922,"none":34.63718896016983},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":56,"finish_reasons":["error","length","stop"],"indexed_attempts":56,"output_token_observations":56,"total_output_tokens":194565},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":9,"failed_game_aliases":["GB2-03","GB2-04","GB2-05"],"model_code_failure_rate":0.4444444444444444,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"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":0.5555555555555556},"baseline":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"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":16,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-06","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.125,"model_code_failure_rate":0.4375,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-08-05T04:29:54Z","match_totals_all":{"draws":516,"losses":473,"wins":328},"match_totals_tracks":{"highest":{"draws":252,"losses":196,"wins":125},"medium":{"draws":135,"losses":127,"wins":102},"none":{"draws":129,"losses":150,"wins":101}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":58.942903698869344,"mean":29.12884239004842,"min":10.53671511272001},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":48,"overall_ranking_status":"partial","per_game":{"GB2-01":34.81038879854182,"GB2-02":11.68296478061394,"GB2-04":16.95013592673012,"GB2-05":47.23542996577578,"GB2-06":41.07194976252669,"GB2-08":29.865118502018596},"per_game_all":{"GB2-01":40.97989849710483,"GB2-06":43.77885851516677,"GB2-08":31.286824067080687},"per_game_match_totals_all":{"GB2-01":{"draws":47,"losses":86,"wins":67},"GB2-02":{"draws":144,"losses":11,"wins":3},"GB2-03":{"draws":24,"losses":7,"wins":3},"GB2-04":{"draws":81,"losses":19,"wins":8},"GB2-05":{"draws":0,"losses":93,"wins":113},"GB2-06":{"draws":12,"losses":103,"wins":88},"GB2-07":{"draws":0,"losses":99,"wins":27},"GB2-08":{"draws":208,"losses":55,"wins":19}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":32,"wins":17},"GB2-02":{"draws":84,"losses":8,"wins":2},"GB2-04":{"draws":48,"losses":13,"wins":3},"GB2-05":{"draws":0,"losses":69,"wins":75},"GB2-06":{"draws":5,"losses":41,"wins":19},"GB2-08":{"draws":96,"losses":33,"wins":9}},"medium":{"GB2-01":{"draws":16,"losses":27,"wins":29},"GB2-02":{"draws":60,"losses":3,"wins":1},"GB2-06":{"draws":7,"losses":26,"wins":45},"GB2-07":{"draws":0,"losses":52,"wins":18},"GB2-08":{"draws":52,"losses":19,"wins":9}},"none":{"GB2-01":{"draws":12,"losses":27,"wins":21},"GB2-03":{"draws":24,"losses":7,"wins":3},"GB2-04":{"draws":33,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":24,"wins":38},"GB2-06":{"draws":0,"losses":36,"wins":24},"GB2-07":{"draws":0,"losses":47,"wins":9},"GB2-08":{"draws":60,"losses":3,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1484.1853578229632,"GB2-06":1439.9699972150381,"GB2-08":1432.607615409149},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1408.5929703577895,"GB2-02":1475.947102088648,"GB2-04":1428.2779463608167,"GB2-05":1489.012787457223,"GB2-06":1406.1077884272852,"GB2-08":1417.834665740927},"medium":{"GB2-01":1492.0591958988462,"GB2-02":1461.451330904213,"GB2-06":1630.394611108272,"GB2-07":1176.2953930743706,"GB2-08":1443.6513922439997},"none":{"GB2-01":1551.903907212254,"GB2-03":1424.039014779849,"GB2-04":1488.14911205402,"GB2-05":1621.0647466868909,"GB2-06":1283.4075921095573,"GB2-07":1205.2540746232235,"GB2-08":1436.3367882425214}},"per_game_tracks":{"highest":{"GB2-01":34.81038879854182,"GB2-02":11.68296478061394,"GB2-04":16.95013592673012,"GB2-05":47.23542996577578,"GB2-06":41.07194976252669,"GB2-08":29.865118502018596},"medium":{"GB2-01":41.78469219527432,"GB2-02":10.53671511272001,"GB2-06":58.942903698869344,"GB2-07":22.05622295359803,"GB2-08":32.57343311593441},"none":{"GB2-01":46.34461449749834,"GB2-03":26.845947820192375,"GB2-04":25.201140195303772,"GB2-05":57.3153424952665,"GB2-06":31.321722084104252,"GB2-07":24.0096350455345,"GB2-08":31.42192058328905}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.21400985215971,"medium":28.644580216192928,"none":32.52793710179262},"reasoning_agg":{"highest":{"max":47.23542996577578,"mean":26.21400985215971,"min":11.68296478061394},"medium":{"max":58.942903698869344,"mean":28.644580216192928,"min":10.53671511272001},"none":{"max":57.3153424952665,"mean":32.52793710179262,"min":24.0096350455345}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":58.942903698869344,"expected_score":35.99385003423502,"reasoning_variance":6.313927249632908,"reliability_score":83.51548588974241,"uncertainty_avg":16.48451411025759,"uncertainty_penalty":6.865007644186598},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":47.23542996577578,"expected_score":23.05652318615385,"reliability_score":81.31778082325225,"uncertainty_avg":18.682219176747754,"uncertainty_penalty":-3.157486666005859},"medium":{"ceiling_score":58.942903698869344,"expected_score":33.213525270821904,"reliability_score":85.41260511915621,"uncertainty_avg":14.587394880843785,"uncertainty_penalty":4.568945054628976},"none":{"ceiling_score":57.3153424952665,"expected_score":36.586545820524485,"reliability_score":75.4177187659331,"uncertainty_avg":24.582281234066894,"uncertainty_penalty":4.058608718731868}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:bc21de560c0fa311","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.008042989573333334,"mean":0.0037891845841666666,"median":0.0032265161666666666,"min":0.002126702,"recorded_attempt_count":36,"run_count":24,"total":0.09094043001999999},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.01067159692}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.050973330659999996},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"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},"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},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.01423672,"mean":0.004144189362222222,"median":0.0032265161666666666,"min":0.0008945895,"recorded_attempt_count":59,"run_count":40,"total":0.16008749804000003},"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":29.646560735707567,"highest":30.607605316675038,"medium":32.48806112461729,"none":26.614508029189267},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":339820,"total_reasoning_output_tokens":258096,"total_visible_output_tokens":81724,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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":["GB2-03","GB2-04"],"first_pass_admitted":10,"first_pass_rate":0.625,"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":4,"repaired_rate":0.25},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"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,"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}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-09-10T10:26:14Z","match_totals_all":{"draws":1289,"losses":1364,"wins":1041},"match_totals_tracks":{"highest":{"draws":380,"losses":273,"wins":219},"medium":{"draws":626,"losses":720,"wins":550},"none":{"draws":283,"losses":371,"wins":272}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":73.77217005426371,"mean":28.921609624469905,"min":2.2211281793648086},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":16.69444518264546,"GB2-02":2.2211281793648086,"GB2-03":30.23086777854394,"GB2-04":18.38304555561166,"GB2-06":73.77217005426371,"GB2-07":46.33821644839612,"GB2-08":26.61336401789957},"per_game_all":{"GB2-01":23.987622543107037,"GB2-02":6.867045042495373,"GB2-03":29.159591170599395,"GB2-06":53.57297678593557,"GB2-07":35.75459938612795,"GB2-08":28.537529485980098},"per_game_match_totals_all":{"GB2-01":{"draws":108,"losses":289,"wins":117},"GB2-02":{"draws":394,"losses":28,"wins":10},"GB2-03":{"draws":218,"losses":121,"wins":99},"GB2-04":{"draws":215,"losses":45,"wins":32},"GB2-05":{"draws":0,"losses":194,"wins":192},"GB2-06":{"draws":27,"losses":271,"wins":308},"GB2-07":{"draws":0,"losses":301,"wins":239},"GB2-08":{"draws":327,"losses":115,"wins":44}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":39,"losses":76,"wins":5},"GB2-02":{"draws":88,"losses":9,"wins":7},"GB2-03":{"draws":62,"losses":45,"wins":31},"GB2-04":{"draws":72,"losses":20,"wins":22},"GB2-06":{"draws":15,"losses":38,"wins":65},"GB2-07":{"draws":0,"losses":74,"wins":80},"GB2-08":{"draws":104,"losses":11,"wins":9}},"medium":{"GB2-01":{"draws":31,"losses":144,"wins":99},"GB2-02":{"draws":210,"losses":13,"wins":1},"GB2-03":{"draws":94,"losses":34,"wins":40},"GB2-04":{"draws":143,"losses":25,"wins":10},"GB2-05":{"draws":0,"losses":151,"wins":115},"GB2-06":{"draws":6,"losses":141,"wins":139},"GB2-07":{"draws":0,"losses":140,"wins":122},"GB2-08":{"draws":142,"losses":72,"wins":24}},"none":{"GB2-01":{"draws":38,"losses":69,"wins":13},"GB2-02":{"draws":96,"losses":6,"wins":2},"GB2-03":{"draws":62,"losses":42,"wins":28},"GB2-05":{"draws":0,"losses":43,"wins":77},"GB2-06":{"draws":6,"losses":92,"wins":104},"GB2-07":{"draws":0,"losses":87,"wins":37},"GB2-08":{"draws":81,"losses":32,"wins":11}}},"per_game_raw_elo_all":{"GB2-01":1267.2330280391163,"GB2-02":1432.9884628661778,"GB2-03":1418.8355600543139,"GB2-06":1552.0411767156947,"GB2-07":1330.2381139786025,"GB2-08":1394.020920912864},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1176.5212783168986,"GB2-02":1404.6961605830274,"GB2-03":1422.8880325254963,"GB2-04":1424.6225816346569,"GB2-06":1811.6841955171515,"GB2-07":1452.4326426470998,"GB2-08":1370.3683072257907},"medium":{"GB2-01":1445.3815698323801,"GB2-02":1457.006280236537,"GB2-03":1467.6499572297143,"GB2-04":1452.8038436465395,"GB2-05":1416.884374010715,"GB2-06":1370.7779398356788,"GB2-07":1399.6303650912164,"GB2-08":1464.4991366421373},"none":{"GB2-01":1179.7962359680705,"GB2-02":1437.2629477789696,"GB2-03":1365.9686904077316,"GB2-05":1445.3534727627618,"GB2-06":1473.6613947942544,"GB2-07":1138.6513341974915,"GB2-08":1347.1953188706636}},"per_game_tracks":{"highest":{"GB2-01":16.69444518264546,"GB2-02":2.2211281793648086,"GB2-03":30.23086777854394,"GB2-04":18.38304555561166,"GB2-06":73.77217005426371,"GB2-07":46.33821644839612,"GB2-08":26.61336401789957},"medium":{"GB2-01":38.30464422301185,"GB2-02":10.294264101835623,"GB2-03":33.01785125489565,"GB2-04":21.796361705747216,"GB2-05":41.99995218852661,"GB2-06":38.93697150240678,"GB2-07":41.03113787699098,"GB2-08":34.52330614352358},"none":{"GB2-01":16.963778223663805,"GB2-02":8.085742846285687,"GB2-03":24.230054478358582,"GB2-05":44.64182972536665,"GB2-06":48.009788801136246,"GB2-07":19.894443832996753,"GB2-08":24.475918296517147}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.60270285061144,"medium":31.421419928614725,"none":25.740706094183555},"reasoning_agg":{"highest":{"max":73.77217005426371,"mean":29.60270285061144,"min":2.2211281793648086},"medium":{"max":41.99995218852661,"mean":31.421419928614725,"min":10.294264101835623},"none":{"max":48.009788801136246,"mean":25.740706094183555,"min":8.085742846285687}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":73.77217005426371,"expected_score":25.981924717783244,"reasoning_variance":5.68071383443117,"reliability_score":94.43646715372822,"uncertainty_avg":5.563532846271777,"uncertainty_penalty":-2.9396849066866615},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.77217005426371,"expected_score":21.28973123198789,"reliability_score":98.18841801208654,"uncertainty_avg":1.8115819879134534,"uncertainty_penalty":-8.31297161862355},"medium":{"ceiling_score":41.99995218852661,"expected_score":32.45618960991406,"reliability_score":87.19867817425387,"uncertainty_avg":12.801321825746136,"uncertainty_penalty":1.0347696812993377},"none":{"ceiling_score":48.009788801136246,"expected_score":25.97645921252909,"reliability_score":98.51474090621298,"uncertainty_avg":1.485259093787025,"uncertainty_penalty":0.23575311834553503}}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:ee2aa4f5e2c2d7e9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"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},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760899999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.42810400000000004},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"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},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"codegen_latency_ms":{"attempt_count":34,"max_ms":395404,"mean_ms":199903.16666666666,"min_ms":55601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":395404,"mean_ms":251379.375,"min_ms":180439,"run_count":8},"medium":{"attempt_count":14,"max_ms":353826,"mean_ms":258198.75,"min_ms":158866,"run_count":8},"none":{"attempt_count":9,"max_ms":131809,"mean_ms":90131.375,"min_ms":55601,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22808,"output_mean":12018.333333333334,"output_min":2752,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":22808,"output_mean":15068.125,"output_min":11085,"run_count":8},"medium":{"attempt_count":14,"output_max":21381,"output_mean":15556.75,"output_min":10057,"run_count":8},"none":{"attempt_count":9,"output_max":8609,"output_mean":5430.125,"output_min":2752,"run_count":8}},"display_name":"Seed 2.0 Code","economics":{"all":30.424922602787547,"highest":30.297799008678222,"medium":32.72437884008807,"none":23.90857395896249},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":157,"total_output_tokens":288440,"total_reasoning_output_tokens":204471,"total_visible_output_tokens":83969,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"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,"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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-09-10T11:06:39Z","match_totals_all":{"draws":911,"losses":1123,"wins":797},"match_totals_tracks":{"highest":{"draws":377,"losses":391,"wins":307},"medium":{"draws":245,"losses":334,"wins":319},"none":{"draws":289,"losses":398,"wins":171}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":74.84224837474918,"mean":28.357130200643297,"min":5.142930493219368},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":50,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.19570452330597,"GB2-02":7.518607942495322,"GB2-03":31.56709410597149,"GB2-04":18.355372189033734,"GB2-05":49.72447731658255,"GB2-06":19.960373147257805,"GB2-07":45.64654917987288,"GB2-08":37.414213664906036},"per_game_all":{"GB2-01":28.331096330530155,"GB2-03":35.85207030198321,"GB2-04":19.69881780837811,"GB2-05":35.60455526579792,"GB2-06":17.176916052710567,"GB2-08":45.88607985732532},"per_game_match_totals_all":{"GB2-01":{"draws":141,"losses":155,"wins":98},"GB2-02":{"draws":188,"losses":18,"wins":2},"GB2-03":{"draws":133,"losses":182,"wins":115},"GB2-04":{"draws":265,"losses":44,"wins":32},"GB2-05":{"draws":0,"losses":233,"wins":183},"GB2-06":{"draws":4,"losses":251,"wins":99},"GB2-07":{"draws":0,"losses":160,"wins":142},"GB2-08":{"draws":180,"losses":80,"wins":126}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":73,"losses":25,"wins":24},"GB2-02":{"draws":98,"losses":6,"wins":0},"GB2-03":{"draws":57,"losses":34,"wins":41},"GB2-04":{"draws":85,"losses":17,"wins":11},"GB2-05":{"draws":0,"losses":89,"wins":81},"GB2-06":{"draws":1,"losses":80,"wins":37},"GB2-07":{"draws":0,"losses":91,"wins":87},"GB2-08":{"draws":63,"losses":49,"wins":26}},"medium":{"GB2-01":{"draws":28,"losses":56,"wins":68},"GB2-02":{"draws":90,"losses":12,"wins":2},"GB2-03":{"draws":41,"losses":84,"wins":37},"GB2-04":{"draws":84,"losses":16,"wins":14},"GB2-05":{"draws":0,"losses":50,"wins":76},"GB2-06":{"draws":1,"losses":90,"wins":27},"GB2-08":{"draws":1,"losses":26,"wins":95}},"none":{"GB2-01":{"draws":40,"losses":74,"wins":6},"GB2-03":{"draws":35,"losses":64,"wins":37},"GB2-04":{"draws":96,"losses":11,"wins":7},"GB2-05":{"draws":0,"losses":94,"wins":26},"GB2-06":{"draws":2,"losses":81,"wins":35},"GB2-07":{"draws":0,"losses":69,"wins":55},"GB2-08":{"draws":116,"losses":5,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1316.5764463101511,"GB2-03":1476.384444496139,"GB2-04":1432.6275308038369,"GB2-05":1327.8476141464878,"GB2-06":1087.9879673928374,"GB2-08":1578.6980689478635},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1364.7121364177256,"GB2-02":1434.1135913809594,"GB2-03":1436.4878724405924,"GB2-04":1424.61860583031,"GB2-05":1504.4193979704903,"GB2-06":1123.5806586176955,"GB2-07":1441.8985365440951,"GB2-08":1485.6155341744773},"medium":{"GB2-01":1421.2377140826875,"GB2-02":1420.9212187647054,"GB2-03":1525.3993880554747,"GB2-04":1422.2957587674696,"GB2-05":1412.4135684859086,"GB2-06":1004.422711902854,"GB2-08":1893.5285342223358},"none":{"GB2-01":1163.7794884300404,"GB2-03":1467.26607299235,"GB2-04":1450.9682278137316,"GB2-05":1066.7098759830644,"GB2-06":1135.9605316579625,"GB2-07":1294.2455644828358,"GB2-08":1356.9501384467774}},"per_game_tracks":{"highest":{"GB2-01":32.19570452330597,"GB2-02":7.518607942495322,"GB2-03":31.56709410597149,"GB2-04":18.355372189033734,"GB2-05":49.72447731658255,"GB2-06":19.960373147257805,"GB2-07":45.64654917987288,"GB2-08":37.414213664906036},"medium":{"GB2-01":37.15102612381427,"GB2-02":5.142930493219368,"GB2-03":41.16668933391658,"GB2-04":17.99796849337146,"GB2-05":42.1279310571795,"GB2-06":10.641858004366158,"GB2-08":74.84224837474918},"none":{"GB2-01":15.646558344470218,"GB2-03":34.82242746606155,"GB2-04":22.743112742729135,"GB2-05":14.961257423631709,"GB2-06":20.92851700650774,"GB2-07":32.856367197016354,"GB2-08":25.40177753232075}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#fff8f8","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.297799008678222,"medium":31.649978910509514,"none":23.12361268274216},"reasoning_agg":{"highest":{"max":49.72447731658255,"mean":30.297799008678222,"min":7.518607942495322},"medium":{"max":74.84224837474918,"mean":31.649978910509514,"min":5.142930493219368},"none":{"max":34.82242746606155,"mean":23.12361268274216,"min":14.961257423631709}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":74.84224837474918,"expected_score":25.785318581939165,"reasoning_variance":8.526366227767355,"reliability_score":98.75576381806704,"uncertainty_avg":1.2442361819329613,"uncertainty_penalty":-2.5718116187041318},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.72447731658255,"expected_score":20.891427230020643,"reliability_score":98.5571623985883,"uncertainty_avg":1.4428376014116928,"uncertainty_penalty":-9.40637177865758},"medium":{"ceiling_score":74.84224837474918,"expected_score":32.434486492335445,"reliability_score":98.29193198356711,"uncertainty_avg":1.7080680164328894,"uncertainty_penalty":0.784507581825931},"none":{"ceiling_score":34.82242746606155,"expected_score":20.786008757579733,"reliability_score":98.57736554381162,"uncertainty_avg":1.4226344561883801,"uncertainty_penalty":-2.3376039251624263}}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:d976839d396cf2ac","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796000000001},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999999},"codegen_latency_ms":{"attempt_count":68,"max_ms":490920,"mean_ms":122427.25,"min_ms":29915,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":490920,"mean_ms":129686.92857142857,"min_ms":29915,"run_count":14},"none":{"attempt_count":33,"max_ms":199208,"mean_ms":115167.57142857143,"min_ms":46525,"run_count":14}},"codegen_output_tokens":{"attempt_count":68,"output_max":42038,"output_mean":8274.82142857143,"output_min":1701,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":35,"output_max":42038,"output_mean":9630.357142857143,"output_min":1701,"run_count":14},"none":{"attempt_count":33,"output_max":12644,"output_mean":6919.285714285715,"output_min":2544,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"medium":24.290531112031516,"none":34.67716153953121},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.21428571428571427,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"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":0.2857142857142857},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-09-10T10:57:42Z","match_totals_all":{"draws":1731,"losses":1527,"wins":938},"match_totals_tracks":{"medium":{"draws":1302,"losses":1119,"wins":564},"none":{"draws":429,"losses":408,"wins":374}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":54.10090278289114,"mean":28.11776160671457,"min":9.449979970240136},"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":51,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":92,"losses":194,"wins":188},"GB2-02":{"draws":528,"losses":48,"wins":4},"GB2-03":{"draws":372,"losses":310,"wins":207},"GB2-04":{"draws":153,"losses":71,"wins":26},"GB2-05":{"draws":0,"losses":428,"wins":305},"GB2-06":{"draws":15,"losses":248,"wins":109},"GB2-07":{"draws":0,"losses":87,"wins":65},"GB2-08":{"draws":571,"losses":141,"wins":34}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":49,"losses":116,"wins":117},"GB2-02":{"draws":446,"losses":45,"wins":1},"GB2-03":{"draws":223,"losses":201,"wins":112},"GB2-04":{"draws":153,"losses":71,"wins":26},"GB2-05":{"draws":0,"losses":373,"wins":208},"GB2-06":{"draws":11,"losses":201,"wins":72},"GB2-08":{"draws":420,"losses":112,"wins":28}},"none":{"GB2-01":{"draws":43,"losses":78,"wins":71},"GB2-02":{"draws":82,"losses":3,"wins":3},"GB2-03":{"draws":149,"losses":109,"wins":95},"GB2-05":{"draws":0,"losses":55,"wins":97},"GB2-06":{"draws":4,"losses":47,"wins":37},"GB2-07":{"draws":0,"losses":87,"wins":65},"GB2-08":{"draws":151,"losses":29,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1449.3853679490633,"GB2-02":1445.952322485975,"GB2-03":1391.963147228935,"GB2-04":1368.0246720541775,"GB2-05":1273.9436592054853,"GB2-06":1112.70739237112,"GB2-08":1356.3901100732774},"none":{"GB2-01":1511.9064973950458,"GB2-02":1448.2026041849722,"GB2-03":1417.6522280882073,"GB2-05":1575.3504369194993,"GB2-06":1229.8219327403026,"GB2-07":1511.128045469491,"GB2-08":1388.7043408168872}},"per_game_tracks":{"medium":{"GB2-01":40.16991479649198,"GB2-02":12.080494482193536,"GB2-03":28.00561511750182,"GB2-04":11.01099847514966,"GB2-05":32.2189735823991,"GB2-06":20.124655747942903,"GB2-08":26.423065582541604},"none":{"GB2-01":43.92223550931248,"GB2-02":9.449979970240136,"GB2-03":29.541446134255093,"GB2-05":54.10090278289114,"GB2-06":27.820507101588568,"GB2-07":50.106011352032695,"GB2-08":27.79904792639838}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":22.86931587697147,"none":33.36620733645767},"reasoning_agg":{"medium":{"max":40.16991479649198,"mean":22.86931587697147,"min":11.01099847514966},"none":{"max":54.10090278289114,"mean":33.36620733645767,"min":9.449979970240136}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":54.10090278289114,"reasoning_variance":10.4968914594862},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.16991479649198,"expected_score":20.030150845783226,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.8391650311882444},"none":{"ceiling_score":54.10090278289114,"expected_score":35.889079830364935,"reliability_score":90.37085767469797,"uncertainty_avg":9.629142325302032,"uncertainty_penalty":2.522872493907265}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:8b44dc7bcfc24a61","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000001},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519748999999999},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":28.38961288815105,"highest":28.216737067230966,"medium":23.147895521816984,"none":33.8042060754052},"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_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,"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,"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}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-09-10T11:06:39Z","match_totals_all":{"draws":3522,"losses":4506,"wins":2832},"match_totals_tracks":{"highest":{"draws":883,"losses":1385,"wins":1024},"medium":{"draws":1277,"losses":1589,"wins":705},"none":{"draws":1362,"losses":1532,"wins":1103}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":65.89914757897805,"mean":27.647134655398105,"min":9.623986038775216},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.35795274164543,"GB2-02":12.3621226468018,"GB2-03":29.338111214731462,"GB2-04":15.758295958987606,"GB2-05":21.63668679667324,"GB2-06":41.536391992160105,"GB2-07":48.1277645295087,"GB2-08":23.616570657339402},"per_game_all":{"GB2-01":36.257543787540754,"GB2-02":11.31789636655031,"GB2-03":31.643663403839707,"GB2-04":22.590873785237317,"GB2-05":15.80173696938833,"GB2-06":37.759535306906116,"GB2-07":46.90743395485723,"GB2-08":24.838219530888633},"per_game_match_totals_all":{"GB2-01":{"draws":310,"losses":592,"wins":529},"GB2-02":{"draws":797,"losses":60,"wins":22},"GB2-03":{"draws":431,"losses":439,"wins":423},"GB2-04":{"draws":870,"losses":220,"wins":160},"GB2-05":{"draws":0,"losses":1262,"wins":332},"GB2-06":{"draws":40,"losses":993,"wins":625},"GB2-07":{"draws":0,"losses":652,"wins":677},"GB2-08":{"draws":1074,"losses":288,"wins":64}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":57,"losses":116,"wins":69},"GB2-02":{"draws":163,"losses":24,"wins":19},"GB2-03":{"draws":120,"losses":181,"wins":209},"GB2-04":{"draws":318,"losses":98,"wins":49},"GB2-05":{"draws":0,"losses":372,"wins":136},"GB2-06":{"draws":25,"losses":293,"wins":242},"GB2-07":{"draws":0,"losses":246,"wins":287},"GB2-08":{"draws":200,"losses":55,"wins":13}},"medium":{"GB2-01":{"draws":120,"losses":237,"wins":259},"GB2-02":{"draws":215,"losses":4,"wins":0},"GB2-03":{"draws":233,"losses":162,"wins":104},"GB2-04":{"draws":266,"losses":35,"wins":26},"GB2-05":{"draws":0,"losses":426,"wins":116},"GB2-06":{"draws":7,"losses":428,"wins":97},"GB2-07":{"draws":0,"losses":190,"wins":76},"GB2-08":{"draws":436,"losses":107,"wins":27}},"none":{"GB2-01":{"draws":133,"losses":239,"wins":201},"GB2-02":{"draws":419,"losses":32,"wins":3},"GB2-03":{"draws":78,"losses":96,"wins":110},"GB2-04":{"draws":286,"losses":87,"wins":85},"GB2-05":{"draws":0,"losses":464,"wins":80},"GB2-06":{"draws":8,"losses":272,"wins":286},"GB2-07":{"draws":0,"losses":216,"wins":314},"GB2-08":{"draws":438,"losses":126,"wins":24}}},"per_game_raw_elo_all":{"GB2-01":1402.0731245641975,"GB2-02":1443.2674340849826,"GB2-03":1427.2161949305262,"GB2-04":1441.4405305734151,"GB2-05":1065.572560783767,"GB2-06":1338.5749630297166,"GB2-07":1451.6258714949365,"GB2-08":1339.1242369633624},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1368.4377311620217,"GB2-02":1449.7760281162512,"GB2-03":1405.4432366699407,"GB2-04":1397.6493104991137,"GB2-05":1140.5555835818523,"GB2-06":1386.774966776137,"GB2-07":1466.2476393987372,"GB2-08":1326.4900962723918},"medium":{"GB2-01":1445.1140497986676,"GB2-02":1446.7511685714164,"GB2-03":1398.7777990120844,"GB2-04":1438.4959236408645,"GB2-05":1062.4837451299554,"GB2-06":1063.2432752679865,"GB2-07":1208.9920377589156,"GB2-08":1339.9247736299953},"none":{"GB2-01":1392.6675927319038,"GB2-02":1433.2751055672807,"GB2-03":1477.427549109553,"GB2-04":1488.1763575802674,"GB2-05":993.6783536394931,"GB2-06":1565.7066470450266,"GB2-07":1679.6379373271573,"GB2-08":1350.9578409877}},"per_game_tracks":{"highest":{"GB2-01":33.35795274164543,"GB2-02":12.3621226468018,"GB2-03":29.338111214731462,"GB2-04":15.758295958987606,"GB2-05":21.63668679667324,"GB2-06":41.536391992160105,"GB2-07":48.1277645295087,"GB2-08":23.616570657339402},"medium":{"GB2-01":39.89414504066892,"GB2-02":11.967580414073916,"GB2-03":28.622810270087797,"GB2-04":21.30546578772129,"GB2-05":15.579243027156668,"GB2-06":16.1949707891289,"GB2-07":26.69538975608495,"GB2-08":24.923559089613434},"none":{"GB2-01":35.52053358030793,"GB2-02":9.623986038775216,"GB2-03":36.970068726699864,"GB2-04":30.70885960900305,"GB2-05":10.189281084335075,"GB2-06":55.547243139429334,"GB2-07":65.89914757897805,"GB2-08":25.974528845713063}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.290331085130802,"medium":22.38790868020074,"none":33.26316420086277},"reasoning_agg":{"highest":{"max":48.1277645295087,"mean":27.290331085130802,"min":12.3621226468018},"medium":{"max":39.89414504066892,"mean":22.38790868020074,"min":11.967580414073916},"none":{"max":65.89914757897805,"mean":33.26316420086277,"min":9.623986038775216}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":65.89914757897805,"expected_score":23.299459339168873,"reasoning_variance":10.875255520662026,"reliability_score":99.8483117435837,"uncertainty_avg":0.15168825641631004,"uncertainty_penalty":-4.347675316229232},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.1277645295087,"expected_score":16.871147231506935,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.419183853623867},"medium":{"ceiling_score":39.89414504066892,"expected_score":19.08646494687141,"reliability_score":99.54493523075107,"uncertainty_avg":0.45506476924893013,"uncertainty_penalty":-3.3014437333293323},"none":{"ceiling_score":65.89914757897805,"expected_score":33.94076583912828,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6776016382655143}}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:89d5714ff2045319","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.214047204}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.6004064599999999},"codegen_latency_ms":{"attempt_count":87,"max_ms":1635062,"mean_ms":598630.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":49,"max_ms":1635062,"mean_ms":1021590.9375,"min_ms":525940,"run_count":16},"none":{"attempt_count":38,"max_ms":457140,"mean_ms":175670.5625,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":110598,"output_mean":38325.9375,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":59,"output_max":110598,"output_mean":68392.8125,"output_min":16796,"run_count":16},"none":{"attempt_count":38,"output_max":22812,"output_mean":8259.0625,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"medium":27.242268163777958,"none":30.345518662237996},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"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,"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}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-09-10T10:39:01Z","match_totals_all":{"draws":1277,"losses":2011,"wins":1116},"match_totals_tracks":{"medium":{"draws":862,"losses":1567,"wins":801},"none":{"draws":415,"losses":444,"wins":315}},"model_slug":"meituan-longcat-2-0","overall":{"max":44.89316223345493,"mean":27.3505040481569,"min":5.565460776989309},"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":53,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":71,"losses":80,"wins":59},"GB2-02":{"draws":307,"losses":31,"wins":2},"GB2-03":{"draws":183,"losses":121,"wins":93},"GB2-04":{"draws":314,"losses":157,"wins":55},"GB2-05":{"draws":0,"losses":456,"wins":260},"GB2-06":{"draws":55,"losses":443,"wins":248},"GB2-07":{"draws":0,"losses":437,"wins":301},"GB2-08":{"draws":347,"losses":286,"wins":98}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":230,"losses":26,"wins":2},"GB2-03":{"draws":123,"losses":81,"wins":63},"GB2-04":{"draws":277,"losses":141,"wins":40},"GB2-05":{"draws":0,"losses":345,"wins":217},"GB2-06":{"draws":39,"losses":353,"wins":170},"GB2-07":{"draws":0,"losses":356,"wins":216},"GB2-08":{"draws":193,"losses":265,"wins":93}},"none":{"GB2-01":{"draws":71,"losses":80,"wins":59},"GB2-02":{"draws":77,"losses":5,"wins":0},"GB2-03":{"draws":60,"losses":40,"wins":30},"GB2-04":{"draws":37,"losses":16,"wins":15},"GB2-05":{"draws":0,"losses":111,"wins":43},"GB2-06":{"draws":16,"losses":90,"wins":78},"GB2-07":{"draws":0,"losses":81,"wins":85},"GB2-08":{"draws":154,"losses":21,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1453.9009704052921,"GB2-03":1429.2272237880622,"GB2-04":1336.279199723666,"GB2-05":1406.9234581653127,"GB2-06":1248.2559899500977,"GB2-07":1375.6177949642233,"GB2-08":1348.152961397977},"none":{"GB2-01":1390.4482752690915,"GB2-02":1447.1572953479408,"GB2-03":1394.540988611574,"GB2-04":1558.1767288584622,"GB2-05":1142.237542324819,"GB2-06":1447.3276839958567,"GB2-07":1415.0098278142677,"GB2-08":1391.4561955324614}},"per_game_tracks":{"medium":{"GB2-02":13.63565896036477,"GB2-03":31.878168765270942,"GB2-04":5.565460776989309,"GB2-05":42.612280911763705,"GB2-06":30.7144277981412,"GB2-07":40.64504874231809,"GB2-08":25.64483119159765},"none":{"GB2-01":34.08227841090624,"GB2-02":8.990579277651428,"GB2-03":25.677678742623275,"GB2-04":38.689256035103924,"GB2-05":20.179848697832213,"GB2-06":44.89316223345493,"GB2-07":42.26122886658135,"GB2-08":27.9901170337506}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":25.351787126174198,"none":29.3492209701396},"reasoning_agg":{"medium":{"max":42.612280911763705,"mean":25.351787126174198,"min":5.565460776989309},"none":{"max":44.89316223345493,"mean":29.3492209701396,"min":8.990579277651428}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":44.89316223345493,"reasoning_variance":3.9974338439654034},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":42.612280911763705,"expected_score":23.696707141587446,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6550799845867523},"none":{"ceiling_score":44.89316223345493,"expected_score":32.06444233096406,"reliability_score":88.63108164081859,"uncertainty_avg":11.368918359181407,"uncertainty_penalty":2.7152213608244615}}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:6bc8ed75bf8e498c","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.81977125},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":12,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.4057992500000003},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":28.879374910115267,"none":34.363072647101255},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":53,"finish_reasons":["length","stop"],"indexed_attempts":53,"output_token_observations":53,"total_output_tokens":2639964},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-04"],"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"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":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"model_code_failure_rate":0.5625,"model_code_failures":9,"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":7,"repaired_rate":0.4375}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-08-05T05:35:20Z","match_totals_all":{"draws":265,"losses":360,"wins":219},"match_totals_tracks":{"medium":{"draws":43,"losses":223,"wins":102},"none":{"draws":222,"losses":137,"wins":117}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":60.77934776395481,"mean":26.812441583286457,"min":7.328898964258992},"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":54,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-02":{"draws":55,"losses":7,"wins":2},"GB2-03":{"draws":49,"losses":24,"wins":17},"GB2-04":{"draws":67,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":94,"wins":72},"GB2-06":{"draws":11,"losses":107,"wins":30},"GB2-07":{"draws":0,"losses":61,"wins":89},"GB2-08":{"draws":83,"losses":61,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":23,"losses":16,"wins":9},"GB2-05":{"draws":0,"losses":56,"wins":30},"GB2-06":{"draws":9,"losses":59,"wins":14},"GB2-07":{"draws":0,"losses":41,"wins":45},"GB2-08":{"draws":11,"losses":51,"wins":4}},"none":{"GB2-02":{"draws":55,"losses":7,"wins":2},"GB2-03":{"draws":26,"losses":8,"wins":8},"GB2-04":{"draws":67,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":38,"wins":42},"GB2-06":{"draws":2,"losses":48,"wins":16},"GB2-07":{"draws":0,"losses":20,"wins":44},"GB2-08":{"draws":72,"losses":10,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1425.750666950453,"GB2-05":1328.357377257976,"GB2-06":1211.2987002752848,"GB2-07":1480.0240469090763,"GB2-08":1174.3876372219918},"none":{"GB2-02":1470.9810619922746,"GB2-03":1483.8177473760302,"GB2-04":1487.8528084385841,"GB2-05":1523.644299345217,"GB2-06":1212.3309448675193,"GB2-07":1643.2683262324292,"GB2-08":1416.2008821131521}},"per_game_tracks":{"medium":{"GB2-03":28.11331182821081,"GB2-05":34.95975901608025,"GB2-06":26.254176503754234,"GB2-07":47.74072823827207,"GB2-08":7.328898964258992},"none":{"GB2-02":12.252825466946847,"GB2-03":33.75354537169144,"GB2-04":27.572458734081646,"GB2-05":50.1453521622104,"GB2-06":25.946851868730132,"GB2-07":60.77934776395481,"GB2-08":30.091127162093525}},"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":25.677798888726322,"none":27.947084277846592},"reasoning_agg":{"medium":{"max":47.74072823827207,"mean":25.677798888726322,"min":7.328898964258992},"none":{"max":60.77934776395481,"mean":27.947084277846592,"min":12.252825466946847}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":60.77934776395481,"reasoning_variance":2.2692853891202702},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":47.74072823827207,"expected_score":25.9854494888354,"reliability_score":84.82866458293026,"uncertainty_avg":15.171335417069738,"uncertainty_penalty":0.30765060010907774},"none":{"ceiling_score":60.77934776395481,"expected_score":36.55624135237799,"reliability_score":82.59845392423352,"uncertainty_avg":17.401546075766472,"uncertainty_penalty":8.609157074531396}}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:c4cb188aa646b3a5","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":30,"run_count":16,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":30,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":45},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":45,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":45,"max_ms":905283,"mean_ms":194374.625,"min_ms":21975,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":905283,"mean_ms":509118.375,"min_ms":288605,"run_count":8},"none":{"attempt_count":30,"max_ms":62079,"mean_ms":37002.75,"min_ms":21975,"run_count":16}},"codegen_output_tokens":{"attempt_count":45,"output_max":52275,"output_mean":12297.333333333334,"output_min":1733,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":52275,"output_mean":30105.875,"output_min":9014,"run_count":8},"none":{"attempt_count":30,"output_max":6330,"output_mean":3393.0625,"output_min":1733,"run_count":16}},"display_name":"North Mini Code","economics":{"medium":33.971196577578915,"none":29.334470894205833},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":45,"finish_reasons":["stop"],"indexed_attempts":45,"output_token_observations":45,"total_output_tokens":295136},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.25,"model_code_failures":2,"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},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":5,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.1875,"model_code_failure_rate":0.6875,"model_code_failures":11,"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":0.125}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":303,"losses":388,"wins":219},"match_totals_tracks":{"medium":{"draws":147,"losses":190,"wins":149},"none":{"draws":156,"losses":198,"wins":70}},"model_slug":"cohere-north-mini-code","overall":{"max":49.11080098947388,"mean":26.77319662715879,"min":21.93263264971003},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold","fixed_coverage_incomplete"],"overall_official_rank":55,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":84,"losses":80,"wins":18},"GB2-03":{"draws":17,"losses":18,"wins":3},"GB2-04":{"draws":69,"losses":5,"wins":6},"GB2-05":{"draws":0,"losses":44,"wins":60},"GB2-06":{"draws":1,"losses":55,"wins":30},"GB2-07":{"draws":0,"losses":150,"wins":98},"GB2-08":{"draws":132,"losses":36,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":17,"losses":18,"wins":3},"GB2-04":{"draws":69,"losses":5,"wins":6},"GB2-05":{"draws":0,"losses":44,"wins":60},"GB2-06":{"draws":1,"losses":55,"wins":30},"GB2-07":{"draws":0,"losses":52,"wins":50},"GB2-08":{"draws":60,"losses":16,"wins":0}},"none":{"GB2-01":{"draws":84,"losses":80,"wins":18},"GB2-07":{"draws":0,"losses":98,"wins":48},"GB2-08":{"draws":72,"losses":20,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1408.8618585327608,"GB2-04":1507.3158309109629,"GB2-05":1522.461307692719,"GB2-06":1356.0188073823756,"GB2-07":1431.9512232436878,"GB2-08":1386.7126894336147},"none":{"GB2-01":1297.9536523160737,"GB2-07":1307.793294134663,"GB2-08":1398.0183446522383}},"per_game_tracks":{"medium":{"GB2-03":22.98682614510266,"GB2-04":27.751123392297373,"GB2-05":49.11080098947388,"GB2-06":36.17363038802949,"GB2-07":42.60735748459359,"GB2-08":25.197441065976513},"none":{"GB2-01":26.207095835838984,"GB2-07":33.07868627119113,"GB2-08":28.71763057558737}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.613760604607553,"none":21.93263264971003},"reasoning_agg":{"medium":{"max":49.11080098947388,"mean":31.613760604607553,"min":22.98682614510266},"none":{"max":33.07868627119113,"mean":21.93263264971003,"min":26.207095835838984}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":49.11080098947388,"reasoning_variance":9.681127954897523},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":49.11080098947388,"expected_score":35.73437310339029,"reliability_score":61.44557779015955,"uncertainty_avg":38.55442220984045,"uncertainty_penalty":4.120612498782737},"none":{"ceiling_score":33.07868627119113,"expected_score":26.713504154340466,"reliability_score":89.83466551180463,"uncertainty_avg":10.165334488195368,"uncertainty_penalty":4.780871504630436}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:cac04a72708dea25","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.08108399999999999},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.08108399999999999},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.047068750000000006},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"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":0.348093},"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":29.2467903881461,"highest":31.10122013544669,"medium":31.22469222252498,"none":21.823970921280427},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":150003},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.25,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"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,"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"],"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}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-08-05T05:18:42Z","match_totals_all":{"draws":296,"losses":591,"wins":262},"match_totals_tracks":{"highest":{"draws":101,"losses":179,"wins":69},"medium":{"draws":128,"losses":245,"wins":137},"none":{"draws":67,"losses":167,"wins":56}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":45.56327909407335,"mean":25.371913023508757,"min":13.765200753063453},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":56,"overall_ranking_status":"partial","per_game":{"GB2-04":24.98788364443893,"GB2-05":24.238563997706606,"GB2-06":32.05797596367991,"GB2-07":45.56327909407335,"GB2-08":28.658397977334666},"per_game_all":{"GB2-05":25.3155833521145,"GB2-06":37.715417038742764,"GB2-07":24.70937077358104},"per_game_match_totals_all":{"GB2-01":{"draws":56,"losses":62,"wins":28},"GB2-02":{"draws":48,"losses":1,"wins":1},"GB2-04":{"draws":104,"losses":17,"wins":11},"GB2-05":{"draws":0,"losses":153,"wins":53},"GB2-06":{"draws":0,"losses":136,"wins":91},"GB2-07":{"draws":0,"losses":163,"wins":41},"GB2-08":{"draws":88,"losses":59,"wins":37}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":47,"losses":15,"wins":4},"GB2-05":{"draws":0,"losses":52,"wins":14},"GB2-06":{"draws":0,"losses":44,"wins":21},"GB2-07":{"draws":0,"losses":50,"wins":26},"GB2-08":{"draws":54,"losses":18,"wins":4}},"medium":{"GB2-01":{"draws":37,"losses":25,"wins":22},"GB2-04":{"draws":57,"losses":2,"wins":7},"GB2-05":{"draws":0,"losses":53,"wins":25},"GB2-06":{"draws":0,"losses":63,"wins":39},"GB2-07":{"draws":0,"losses":61,"wins":11},"GB2-08":{"draws":34,"losses":41,"wins":33}},"none":{"GB2-01":{"draws":19,"losses":37,"wins":6},"GB2-02":{"draws":48,"losses":1,"wins":1},"GB2-05":{"draws":0,"losses":48,"wins":14},"GB2-06":{"draws":0,"losses":29,"wins":31},"GB2-07":{"draws":0,"losses":52,"wins":4}}},"per_game_raw_elo_all":{"GB2-05":1210.528205603797,"GB2-06":1360.571960484396,"GB2-07":1209.1330315996772},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1476.0998106127977,"GB2-05":1197.5672854163643,"GB2-06":1290.844080299784,"GB2-07":1456.5857937905953,"GB2-08":1402.3465620036277},"medium":{"GB2-01":1488.886972534093,"GB2-04":1500.4791598953682,"GB2-05":1241.5251670106486,"GB2-06":1408.4761224416814,"GB2-07":1076.1156014586118,"GB2-08":1439.346762921776},"none":{"GB2-01":1195.0228351994263,"GB2-02":1489.7142636458952,"GB2-05":1192.492164384378,"GB2-06":1382.3956787117227,"GB2-07":1094.6976995498242}},"per_game_tracks":{"highest":{"GB2-04":24.98788364443893,"GB2-05":24.238563997706606,"GB2-06":32.05797596367991,"GB2-07":45.56327909407335,"GB2-08":28.658397977334666},"medium":{"GB2-01":41.80592199500637,"GB2-04":29.022538939196433,"GB2-05":27.987177717585375,"GB2-06":42.02538255150319,"GB2-07":13.765200753063453,"GB2-08":32.74193137879505},"none":{"GB2-01":17.062052955412074,"GB2-02":14.474268235287061,"GB2-05":23.721008341051526,"GB2-06":39.06289260104517,"GB2-07":14.799632473606307}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.653329696976403,"medium":29.057850306249282,"none":19.404559067300582},"reasoning_agg":{"highest":{"max":45.56327909407335,"mean":27.653329696976403,"min":24.238563997706606},"medium":{"max":42.02538255150319,"mean":29.057850306249282,"min":13.765200753063453},"none":{"max":39.06289260104517,"mean":19.404559067300582,"min":14.474268235287061}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":45.56327909407335,"expected_score":25.590069623133967,"reasoning_variance":9.6532912389487,"reliability_score":84.09540832168994,"uncertainty_avg":15.90459167831005,"uncertainty_penalty":0.2181565996252104},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":45.56327909407335,"expected_score":22.509648299626313,"reliability_score":84.2148467388781,"uncertainty_avg":15.785153261121902,"uncertainty_penalty":-5.14368139735009},"medium":{"ceiling_score":42.02538255150319,"expected_score":31.110612536699776,"reliability_score":89.20831942559077,"uncertainty_avg":10.791680574409227,"uncertainty_penalty":2.0527622304504938},"none":{"ceiling_score":39.06289260104517,"expected_score":20.12817668826404,"reliability_score":78.50055606183139,"uncertainty_avg":21.499443938168614,"uncertainty_penalty":0.7236176209634593}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:e28d1f44c6bb63d9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.058501660000000004},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539000000004},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":28.292802278412065,"highest":29.80850611716221,"medium":22.81328793344419,"none":26.077506622187926},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":164,"total_output_tokens":154154,"total_reasoning_output_tokens":105962,"total_visible_output_tokens":48432,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"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,"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}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-09-10T10:39:06Z","match_totals_all":{"draws":1099,"losses":913,"wins":594},"match_totals_tracks":{"highest":{"draws":410,"losses":266,"wins":222},"medium":{"draws":407,"losses":346,"wins":205},"none":{"draws":282,"losses":301,"wins":167}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":49.03370945933072,"mean":25.30366060580623,"min":6.990073492948425},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":57,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.440657653090735,"GB2-02":8.569180028204126,"GB2-03":25.84781475496612,"GB2-04":25.60464432138626,"GB2-05":49.03370945933072,"GB2-07":46.08417494737303,"GB2-08":24.079361655784513},"per_game_all":{"GB2-01":31.180957613108745,"GB2-03":27.20102415163487,"GB2-04":24.095755691557702,"GB2-05":23.185997782049782,"GB2-07":39.73905547751812,"GB2-08":24.354022954603163},"per_game_match_totals_all":{"GB2-01":{"draws":145,"losses":138,"wins":87},"GB2-02":{"draws":203,"losses":7,"wins":2},"GB2-03":{"draws":184,"losses":116,"wins":96},"GB2-04":{"draws":232,"losses":97,"wins":47},"GB2-05":{"draws":0,"losses":278,"wins":96},"GB2-06":{"draws":2,"losses":82,"wins":34},"GB2-07":{"draws":0,"losses":179,"wins":209},"GB2-08":{"draws":333,"losses":16,"wins":23}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":54,"losses":44,"wins":24},"GB2-02":{"draws":102,"losses":3,"wins":1},"GB2-03":{"draws":66,"losses":39,"wins":27},"GB2-04":{"draws":78,"losses":41,"wins":21},"GB2-05":{"draws":0,"losses":82,"wins":52},"GB2-07":{"draws":0,"losses":52,"wins":88},"GB2-08":{"draws":110,"losses":5,"wins":9}},"medium":{"GB2-01":{"draws":48,"losses":54,"wins":18},"GB2-02":{"draws":101,"losses":4,"wins":1},"GB2-03":{"draws":53,"losses":42,"wins":37},"GB2-04":{"draws":92,"losses":10,"wins":12},"GB2-05":{"draws":0,"losses":90,"wins":30},"GB2-06":{"draws":2,"losses":82,"wins":34},"GB2-07":{"draws":0,"losses":58,"wins":66},"GB2-08":{"draws":111,"losses":6,"wins":7}},"none":{"GB2-01":{"draws":43,"losses":40,"wins":45},"GB2-03":{"draws":65,"losses":35,"wins":32},"GB2-04":{"draws":62,"losses":46,"wins":14},"GB2-05":{"draws":0,"losses":106,"wins":14},"GB2-07":{"draws":0,"losses":69,"wins":55},"GB2-08":{"draws":112,"losses":5,"wins":7}}},"per_game_raw_elo_all":{"GB2-01":1352.1893457452702,"GB2-03":1394.5238518675917,"GB2-04":1457.5257134703381,"GB2-05":1170.9895482033837,"GB2-07":1376.1679804886346,"GB2-08":1345.873797902688},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1331.2121180284705,"GB2-02":1439.5809790659166,"GB2-03":1381.5176225686357,"GB2-04":1464.6448776444101,"GB2-05":1499.4448278723703,"GB2-07":1450.9404458311392,"GB2-08":1342.896074063688},"medium":{"GB2-01":1303.0183569125913,"GB2-02":1441.700789284466,"GB2-03":1392.9860745205874,"GB2-04":1435.3664247023332,"GB2-05":1048.5046266155819,"GB2-06":1134.8331246095388,"GB2-07":1378.0542771114426,"GB2-08":1353.3431681451975},"none":{"GB2-01":1422.3375622947487,"GB2-03":1409.0678585135524,"GB2-04":1472.5658380642715,"GB2-05":965.0191901221987,"GB2-07":1299.509218523322,"GB2-08":1341.382151499178}},"per_game_tracks":{"highest":{"GB2-01":29.440657653090735,"GB2-02":8.569180028204126,"GB2-03":25.84781475496612,"GB2-04":25.60464432138626,"GB2-05":49.03370945933072,"GB2-07":46.08417494737303,"GB2-08":24.079361655784513},"medium":{"GB2-01":27.097585157882463,"GB2-02":8.950914647096557,"GB2-03":27.04102891334411,"GB2-04":20.161095610049934,"GB2-05":13.534210393870193,"GB2-06":20.84035033409872,"GB2-07":39.83813064889331,"GB2-08":25.042987762318226},"none":{"GB2-01":37.00463002835304,"GB2-03":28.71422878659438,"GB2-04":26.52152714323692,"GB2-05":6.990073492948425,"GB2-07":33.294860836288024,"GB2-08":23.93971944570675}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.829839508099237,"medium":22.81328793344419,"none":24.267854375875263},"reasoning_agg":{"highest":{"max":49.03370945933072,"mean":28.829839508099237,"min":8.569180028204126},"medium":{"max":39.83813064889331,"mean":22.81328793344419,"min":8.950914647096557},"none":{"max":37.00463002835304,"mean":24.267854375875263,"min":6.990073492948425}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":49.03370945933072,"expected_score":23.906768982910155,"reasoning_variance":6.016551574655047,"reliability_score":99.12304537174137,"uncertainty_avg":0.8769546282586368,"uncertainty_penalty":-1.3968916228960744},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.03370945933072,"expected_score":20.001846169080444,"reliability_score":99.01547632347848,"uncertainty_avg":0.9845236765215125,"uncertainty_penalty":-8.827993339018793},"medium":{"ceiling_score":39.83813064889331,"expected_score":19.913799764870404,"reliability_score":98.137650034401,"uncertainty_avg":1.8623499655989928,"uncertainty_penalty":-2.899488168573786},"none":{"ceiling_score":37.00463002835304,"expected_score":25.86372140574619,"reliability_score":99.12445139930169,"uncertainty_avg":0.8755486006983096,"uncertainty_penalty":1.5958670298709272}}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:6f4e74d7b4b7c6e2","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855891}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"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},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.015120192000000001,"mean":0.0032700552500000003,"median":0.0013951725,"min":0.00046744,"recorded_attempt_count":33,"run_count":24,"total":0.078481326},"codegen_latency_ms":{"attempt_count":33,"max_ms":1105859,"mean_ms":161415.45833333334,"min_ms":22661,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1105859,"mean_ms":300420.375,"min_ms":56038,"run_count":8},"medium":{"attempt_count":10,"max_ms":291211,"mean_ms":111417.625,"min_ms":22661,"run_count":8},"none":{"attempt_count":12,"max_ms":151123,"mean_ms":72408.375,"min_ms":26216,"run_count":8}},"codegen_output_tokens":{"attempt_count":33,"output_max":63626,"output_mean":9305.125,"output_min":1487,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":63626,"output_mean":22255.875,"output_min":2344,"run_count":8},"medium":{"attempt_count":10,"output_max":5420,"output_mean":3175.75,"output_min":2107,"run_count":8},"none":{"attempt_count":12,"output_max":4178,"output_mean":2483.75,"output_min":1487,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":24.61529179108438,"highest":27.433152416942608,"medium":24.648172544378482,"none":25.417909395473753},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":33,"finish_reasons":["stop"],"indexed_attempts":33,"output_token_observations":33,"provider_post_attempt_observations":33,"provider_post_attempts":33,"reasoning_token_observations":33,"reconciliation_get_attempt_observations":33,"reconciliation_get_attempts":158,"total_output_tokens":223323,"total_reasoning_output_tokens":139050,"total_visible_output_tokens":87482,"visible_token_observations":33},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"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,"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,"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}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-09-10T10:39:05Z","match_totals_all":{"draws":1078,"losses":949,"wins":620},"match_totals_tracks":{"highest":{"draws":386,"losses":305,"wins":216},"medium":{"draws":400,"losses":376,"wins":214},"none":{"draws":292,"losses":268,"wins":190}},"model_slug":"openai-gpt-oss-120b","overall":{"max":53.690628075980555,"mean":24.94489181914878,"min":9.761584645888398},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-02":12.913154477319852,"GB2-03":25.724889026864293,"GB2-04":21.24043269755691,"GB2-05":53.690628075980555,"GB2-06":21.57553878118651,"GB2-07":31.54023439724443,"GB2-08":25.347189462445694},"per_game_all":{"GB2-02":10.826866854614638,"GB2-03":25.983810676725792,"GB2-05":29.828614681111123,"GB2-07":32.00677633765198,"GB2-08":24.430390405318366},"per_game_match_totals_all":{"GB2-01":{"draws":63,"losses":98,"wins":121},"GB2-02":{"draws":309,"losses":30,"wins":3},"GB2-03":{"draws":175,"losses":119,"wins":103},"GB2-04":{"draws":191,"losses":35,"wins":28},"GB2-05":{"draws":0,"losses":251,"wins":119},"GB2-06":{"draws":3,"losses":147,"wins":86},"GB2-07":{"draws":0,"losses":224,"wins":148},"GB2-08":{"draws":337,"losses":45,"wins":12}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":105,"losses":26,"wins":3},"GB2-03":{"draws":63,"losses":34,"wins":36},"GB2-04":{"draws":106,"losses":14,"wins":20},"GB2-05":{"draws":0,"losses":72,"wins":58},"GB2-06":{"draws":0,"losses":77,"wins":41},"GB2-07":{"draws":0,"losses":68,"wins":56},"GB2-08":{"draws":112,"losses":14,"wins":2}},"medium":{"GB2-01":{"draws":34,"losses":47,"wins":55},"GB2-02":{"draws":102,"losses":2,"wins":0},"GB2-03":{"draws":63,"losses":41,"wins":28},"GB2-04":{"draws":85,"losses":21,"wins":8},"GB2-05":{"draws":0,"losses":90,"wins":30},"GB2-06":{"draws":3,"losses":70,"wins":45},"GB2-07":{"draws":0,"losses":86,"wins":38},"GB2-08":{"draws":113,"losses":19,"wins":10}},"none":{"GB2-01":{"draws":29,"losses":51,"wins":66},"GB2-02":{"draws":102,"losses":2,"wins":0},"GB2-03":{"draws":49,"losses":44,"wins":39},"GB2-05":{"draws":0,"losses":89,"wins":31},"GB2-07":{"draws":0,"losses":70,"wins":54},"GB2-08":{"draws":112,"losses":12,"wins":0}}},"per_game_raw_elo_all":{"GB2-02":1450.9481866395452,"GB2-03":1382.7815124317756,"GB2-05":1255.905203566359,"GB2-07":1284.0471215428622,"GB2-08":1345.7395781196167},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1459.4605593091374,"GB2-03":1380.206473148802,"GB2-04":1438.2741887633456,"GB2-05":1559.3761215959112,"GB2-06":1144.2341444565989,"GB2-07":1278.4467772054588,"GB2-08":1356.0821010691934},"medium":{"GB2-01":1445.0391376524533,"GB2-02":1446.814937022176,"GB2-03":1370.6296442485063,"GB2-04":1456.061245609558,"GB2-05":1076.3642382857881,"GB2-06":1207.1538729649988,"GB2-07":1277.4160766202162,"GB2-08":1366.298434717585},"none":{"GB2-01":1464.316176854037,"GB2-02":1446.5690635873218,"GB2-03":1397.508419898018,"GB2-05":1131.9752508173779,"GB2-07":1296.2785108029113,"GB2-08":1314.8381985720714}},"per_game_tracks":{"highest":{"GB2-02":12.913154477319852,"GB2-03":25.724889026864293,"GB2-04":21.24043269755691,"GB2-05":53.690628075980555,"GB2-06":21.57553878118651,"GB2-07":31.54023439724443,"GB2-08":25.347189462445694},"medium":{"GB2-01":38.95744773414053,"GB2-02":9.805861440635663,"GB2-03":24.714994916497854,"GB2-04":23.58598065433972,"GB2-05":15.718029757272555,"GB2-06":26.49605360253772,"GB2-07":31.45437091777823,"GB2-08":26.452641331825593},"none":{"GB2-01":40.640073310441565,"GB2-02":9.761584645888398,"GB2-03":27.51154808681522,"GB2-05":20.07718621008026,"GB2-07":33.02572369793326,"GB2-08":21.491340421683823}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.532472921423068,"medium":24.648172544378482,"none":23.65402999164478},"reasoning_agg":{"highest":{"max":53.690628075980555,"mean":26.532472921423068,"min":12.913154477319852},"medium":{"max":38.95744773414053,"mean":24.648172544378482,"min":9.805861440635663},"none":{"max":40.640073310441565,"mean":23.65402999164478,"min":9.761584645888398}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":53.690628075980555,"expected_score":20.88913589374473,"reasoning_variance":2.878442929778288,"reliability_score":98.82286121865276,"uncertainty_avg":1.1771387813472418,"uncertainty_penalty":-4.05575592540405},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.690628075980555,"expected_score":17.451383165785927,"reliability_score":99.52445289747321,"uncertainty_avg":0.475547102526794,"uncertainty_penalty":-9.08108975563714},"medium":{"ceiling_score":38.95744773414053,"expected_score":21.900541634595314,"reliability_score":98.41486576057572,"uncertainty_avg":1.5851342394242718,"uncertainty_penalty":-2.747630909783169},"none":{"ceiling_score":40.640073310441565,"expected_score":26.453273988363346,"reliability_score":98.55128863300605,"uncertainty_avg":1.4487113669939526,"uncertainty_penalty":2.799243996718566}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:e81035030b907e0c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.302804525,"mean":0.259828169375,"median":0.2529231275,"min":0.22308452,"recorded_attempt_count":53,"run_count":16,"total":4.15725071},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.2552692799999998},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.25526928},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.302804525,"mean":0.259828169375,"median":0.2529231275,"min":0.22308452,"recorded_attempt_count":53,"run_count":16,"total":4.15725071}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"provider_reported":145},"evidence_basis":"Provider-reported","failed_cell_count":21,"max":0.302804525,"mean":0.12502029041666668,"median":0.082332765,"min":0.01945095,"recorded_attempt_count":145,"run_count":48,"total":6.00097394},"codegen_latency_ms":{"attempt_count":145,"max_ms":712912,"mean_ms":234062.20833333334,"min_ms":20774,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":712912,"mean_ms":506639.625,"min_ms":278552,"run_count":16},"medium":{"attempt_count":53,"max_ms":476873,"mean_ms":144633.375,"min_ms":47325,"run_count":16},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":145,"output_max":80000,"output_mean":25786.458333333332,"output_min":1372,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":80000,"output_mean":58672.9375,"output_min":35008,"run_count":16},"medium":{"attempt_count":53,"output_max":32558,"output_mean":14052.75,"output_min":3762,"run_count":16},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":28.538060906077064,"highest":26.43318592739723,"medium":26.690393057085753,"none":31.709014387195165},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":145,"finish_reasons":["length","stop"],"indexed_attempts":145,"output_token_observations":145,"reasoning_token_observations":102,"total_output_tokens":1237750,"total_reasoning_output_tokens":697293,"total_visible_output_tokens":161414,"visible_token_observations":99},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.625,"model_code_failures":10,"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":0.0625},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"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":9,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.25,"model_code_failure_rate":0.4375,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-09-10T10:39:04Z","match_totals_all":{"draws":1559,"losses":2099,"wins":1052},"match_totals_tracks":{"highest":{"draws":773,"losses":1108,"wins":485},"medium":{"draws":495,"losses":588,"wins":281},"none":{"draws":291,"losses":403,"wins":286}},"model_slug":"thinkingmachines-inkling","overall":{"max":60.57535339573391,"mean":24.428911562338516,"min":9.050334687326071},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":59,"overall_ranking_status":"partial","per_game":{"GB2-01":15.234974053366383,"GB2-02":9.050334687326071,"GB2-03":34.083009309825044,"GB2-04":24.416847410892895,"GB2-05":16.775466878832237,"GB2-06":55.3334397747058,"GB2-07":32.54088523137084,"GB2-08":24.03053007285857},"per_game_all":{"GB2-01":20.730258941191405,"GB2-03":38.031360759517696,"GB2-04":21.070790800534187,"GB2-05":27.18621380504906,"GB2-07":27.51357342002299,"GB2-08":36.69616771014706},"per_game_match_totals_all":{"GB2-01":{"draws":242,"losses":366,"wins":78},"GB2-02":{"draws":265,"losses":18,"wins":5},"GB2-03":{"draws":228,"losses":218,"wins":227},"GB2-04":{"draws":425,"losses":93,"wins":68},"GB2-05":{"draws":0,"losses":582,"wins":224},"GB2-06":{"draws":16,"losses":203,"wins":197},"GB2-07":{"draws":0,"losses":449,"wins":169},"GB2-08":{"draws":383,"losses":170,"wins":84}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":95,"losses":139,"wins":8},"GB2-02":{"draws":200,"losses":11,"wins":3},"GB2-03":{"draws":122,"losses":107,"wins":73},"GB2-04":{"draws":146,"losses":39,"wins":37},"GB2-05":{"draws":0,"losses":405,"wins":117},"GB2-06":{"draws":15,"losses":152,"wins":153},"GB2-07":{"draws":0,"losses":177,"wins":91},"GB2-08":{"draws":195,"losses":78,"wins":3}},"medium":{"GB2-01":{"draws":76,"losses":120,"wins":50},"GB2-03":{"draws":51,"losses":80,"wins":116},"GB2-04":{"draws":184,"losses":28,"wins":10},"GB2-05":{"draws":0,"losses":70,"wins":40},"GB2-07":{"draws":0,"losses":225,"wins":41},"GB2-08":{"draws":184,"losses":65,"wins":24}},"none":{"GB2-01":{"draws":71,"losses":107,"wins":20},"GB2-02":{"draws":65,"losses":7,"wins":2},"GB2-03":{"draws":55,"losses":31,"wins":38},"GB2-04":{"draws":95,"losses":26,"wins":21},"GB2-05":{"draws":0,"losses":107,"wins":67},"GB2-06":{"draws":1,"losses":51,"wins":44},"GB2-07":{"draws":0,"losses":47,"wins":37},"GB2-08":{"draws":4,"losses":27,"wins":57}}},"per_game_raw_elo_all":{"GB2-01":1219.6021249253201,"GB2-03":1496.85898638192,"GB2-04":1437.1349947571591,"GB2-05":1221.418111784757,"GB2-07":1225.0852427786447,"GB2-08":1474.1028151362725},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1148.0712009628478,"GB2-02":1430.8631926503854,"GB2-03":1448.964326697737,"GB2-04":1450.5675354682323,"GB2-05":1078.209332432158,"GB2-06":1561.5618918252717,"GB2-07":1279.0698787444887,"GB2-08":1330.6232524994457},"medium":{"GB2-01":1301.8495200374323,"GB2-03":1543.8740996061813,"GB2-04":1409.148036085779,"GB2-05":1258.6306450543475,"GB2-07":1075.9620883310313,"GB2-08":1346.4972068552136},"none":{"GB2-01":1208.8856537756806,"GB2-02":1468.0193405271866,"GB2-03":1497.7385328418418,"GB2-04":1451.689412717466,"GB2-05":1327.4143578677654,"GB2-06":1318.239164434667,"GB2-07":1320.2237612604144,"GB2-08":1745.1879860541585}},"per_game_tracks":{"highest":{"GB2-01":15.234974053366383,"GB2-02":9.050334687326071,"GB2-03":34.083009309825044,"GB2-04":24.416847410892895,"GB2-05":16.775466878832237,"GB2-06":55.3334397747058,"GB2-07":32.54088523137084,"GB2-08":24.03053007285857},"medium":{"GB2-01":27.89888466985854,"GB2-03":43.70587386646689,"GB2-04":17.562136050360625,"GB2-05":29.879639110693958,"GB2-07":15.613204983285852,"GB2-08":25.482619661848684},"none":{"GB2-01":19.0569181003493,"GB2-02":12.336409573070739,"GB2-03":36.30519910226115,"GB2-04":21.233388940349045,"GB2-05":34.903535425620994,"GB2-06":34.87468051476392,"GB2-07":34.386630045412275,"GB2-08":60.57535339573391}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":22.891810516083325,"medium":20.886361304870018,"none":29.508562866062203},"reasoning_agg":{"highest":{"max":55.3334397747058,"mean":22.891810516083325,"min":9.050334687326071},"medium":{"max":43.70587386646689,"mean":20.886361304870018,"min":15.613204983285852},"none":{"max":60.57535339573391,"mean":29.508562866062203,"min":12.336409573070739}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":60.57535339573391,"expected_score":23.756808565921187,"reasoning_variance":8.622201561192185,"reliability_score":95.90613229925182,"uncertainty_avg":4.093867700748177,"uncertainty_penalty":-0.6721029964173297},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.3334397747058,"expected_score":14.690839765669324,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.200970750414001},"medium":{"ceiling_score":43.70587386646689,"expected_score":25.296441990718886,"reliability_score":99.38201670206251,"uncertainty_avg":0.6179832979374922,"uncertainty_penalty":4.410080685848868},"none":{"ceiling_score":60.57535339573391,"expected_score":32.25392940977083,"reliability_score":88.62699324981428,"uncertainty_avg":11.37300675018572,"uncertainty_penalty":2.7453665437086237}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:da2ad9b9e5446839","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"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},"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},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.07206399999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"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},"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":23.998441917660323,"highest":30.174245478812885,"medium":21.132069816135214,"none":20.689010458032868},"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":"other","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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"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,"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","GB2-06"],"first_pass_admitted":6,"first_pass_rate":0.6,"model_code_failure_rate":0.2,"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":0.2}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-09-10T10:54:12Z","match_totals_all":{"draws":1317,"losses":1347,"wins":772},"match_totals_tracks":{"highest":{"draws":426,"losses":362,"wins":335},"medium":{"draws":409,"losses":543,"wins":246},"none":{"draws":482,"losses":442,"wins":191}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":54.086740109183,"mean":23.048206727876472,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":60,"overall_ranking_status":"ranked","per_game":{"GB2-01":26.03875004306578,"GB2-02":10.341010847452775,"GB2-03":33.68895206775385,"GB2-04":28.17902200488099,"GB2-05":42.23525046231568,"GB2-06":49.240345149208736,"GB2-07":23.05886622894134,"GB2-08":28.611767026883896},"per_game_all":{"GB2-01":15.420480931299158,"GB2-02":9.9923616268405,"GB2-03":29.265294921024623,"GB2-04":25.22315195259196,"GB2-05":17.611979832844785,"GB2-06":30.34266721198396,"GB2-07":36.35990335276232,"GB2-08":27.771695511935274},"per_game_match_totals_all":{"GB2-01":{"draws":92,"losses":234,"wins":66},"GB2-02":{"draws":347,"losses":22,"wins":1},"GB2-03":{"draws":210,"losses":113,"wins":138},"GB2-04":{"draws":300,"losses":80,"wins":79},"GB2-05":{"draws":0,"losses":313,"wins":92},"GB2-06":{"draws":7,"losses":246,"wins":179},"GB2-07":{"draws":0,"losses":279,"wins":194},"GB2-08":{"draws":361,"losses":60,"wins":23}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":46,"losses":44,"wins":30},"GB2-02":{"draws":114,"losses":4,"wins":0},"GB2-03":{"draws":51,"losses":51,"wins":70},"GB2-04":{"draws":92,"losses":19,"wins":22},"GB2-05":{"draws":0,"losses":69,"wins":70},"GB2-06":{"draws":4,"losses":51,"wins":101},"GB2-07":{"draws":0,"losses":101,"wins":35},"GB2-08":{"draws":119,"losses":23,"wins":7}},"medium":{"GB2-01":{"draws":17,"losses":114,"wins":5},"GB2-02":{"draws":113,"losses":3,"wins":0},"GB2-03":{"draws":67,"losses":41,"wins":37},"GB2-04":{"draws":99,"losses":46,"wins":39},"GB2-05":{"draws":0,"losses":116,"wins":16},"GB2-06":{"draws":2,"losses":95,"wins":40},"GB2-07":{"draws":0,"losses":102,"wins":99},"GB2-08":{"draws":111,"losses":26,"wins":10}},"none":{"GB2-01":{"draws":29,"losses":76,"wins":31},"GB2-02":{"draws":120,"losses":15,"wins":1},"GB2-03":{"draws":92,"losses":21,"wins":31},"GB2-04":{"draws":109,"losses":15,"wins":18},"GB2-05":{"draws":0,"losses":128,"wins":6},"GB2-06":{"draws":1,"losses":100,"wins":38},"GB2-07":{"draws":0,"losses":76,"wins":60},"GB2-08":{"draws":131,"losses":11,"wins":6}}},"per_game_raw_elo_all":{"GB2-01":1159.570944623456,"GB2-02":1444.7553412352906,"GB2-03":1411.9245951698456,"GB2-04":1461.1246391646412,"GB2-05":1098.4679635908021,"GB2-06":1252.9334144559227,"GB2-07":1332.6889077201793,"GB2-08":1379.9188461751492},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1290.1434413527058,"GB2-02":1447.4186117447339,"GB2-03":1452.6089243701294,"GB2-04":1481.0691796694814,"GB2-05":1412.0945828140425,"GB2-06":1493.2457744100418,"GB2-07":1175.0341089574347,"GB2-08":1388.9166480313115},"medium":{"GB2-01":971.3356846908011,"GB2-02":1437.1998400127345,"GB2-03":1384.5499476251923,"GB2-04":1428.112805928553,"GB2-05":1009.4016134129805,"GB2-06":1129.6109725111855,"GB2-07":1541.4606321797407,"GB2-08":1390.0220829331531},"none":{"GB2-01":1217.2337078268613,"GB2-02":1449.6475719484033,"GB2-03":1398.6149135142155,"GB2-04":1474.191931895889,"GB2-05":873.907694545383,"GB2-06":1135.9434964465404,"GB2-07":1281.5719820233626,"GB2-08":1360.8178075609835}},"per_game_tracks":{"highest":{"GB2-01":26.03875004306578,"GB2-02":10.341010847452775,"GB2-03":33.68895206775385,"GB2-04":28.17902200488099,"GB2-05":42.23525046231568,"GB2-06":49.240345149208736,"GB2-07":23.05886622894134,"GB2-08":28.611767026883896},"medium":{"GB2-01":0.0,"GB2-02":8.444620292408556,"GB2-03":26.327712683660216,"GB2-04":20.26667941148646,"GB2-05":10.600689036218679,"GB2-06":20.636672560776855,"GB2-07":54.086740109183,"GB2-08":28.69344443534794},"none":{"GB2-01":20.22269275083169,"GB2-02":11.191453740660169,"GB2-03":27.77922001165981,"GB2-04":27.223754441408413,"GB2-05":0.0,"GB2-06":21.15098392596629,"GB2-07":31.934103720162618,"GB2-08":26.00987507357398}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.537039469589303,"medium":20.518892029756675,"none":20.08868868428344},"reasoning_agg":{"highest":{"max":49.240345149208736,"mean":28.537039469589303,"min":10.341010847452775},"medium":{"max":54.086740109183,"mean":20.518892029756675,"min":0.0},"none":{"max":31.934103720162618,"mean":20.08868868428344,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":54.086740109183,"expected_score":18.735621366025793,"reasoning_variance":8.448350785305863,"reliability_score":99.7389797225809,"uncertainty_avg":0.2610202774191021,"uncertainty_penalty":-4.3125853618506795},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.240345149208736,"expected_score":20.573449694096304,"reliability_score":99.5263162117555,"uncertainty_avg":0.4736837882445033,"uncertainty_penalty":-7.9635897754929985},"medium":{"ceiling_score":54.086740109183,"expected_score":17.771366872452298,"reliability_score":99.6906229559872,"uncertainty_avg":0.30937704401280297,"uncertainty_penalty":-2.747525157304377},"none":{"ceiling_score":31.934103720162618,"expected_score":17.86204753152877,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.22664115275467}}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:e189ecaee6c08cd0","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"none":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":92},"evidence_basis":"Provider-reported","failed_cell_count":15,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":92,"run_count":32,"total":0.0},"codegen_latency_ms":{"attempt_count":93,"max_ms":410978,"mean_ms":158095.9375,"min_ms":18717,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":53,"max_ms":410978,"mean_ms":269539.1875,"min_ms":161500,"run_count":16},"none":{"attempt_count":40,"max_ms":90441,"mean_ms":46652.6875,"min_ms":18717,"run_count":16}},"codegen_output_tokens":{"attempt_count":92,"output_max":92074,"output_mean":33594.125,"output_min":2036,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":52,"output_max":92074,"output_mean":60516.0,"output_min":20000,"run_count":16},"none":{"attempt_count":40,"output_max":17378,"output_mean":6672.25,"output_min":2036,"run_count":16}},"display_name":"Ling 3.0 Flash","economics":{"medium":23.90120559075741,"none":22.86688675022906},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":93,"finish_reasons":["length","stop","unknown"],"indexed_attempts":94,"output_token_observations":93,"reasoning_token_observations":65,"total_output_tokens":1075012,"total_reasoning_output_tokens":626571,"total_visible_output_tokens":109787,"visible_token_observations":55},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":15,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.06666666666666667,"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":1,"model_code_failure_rate":0.6,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.3333333333333333},"baseline":{"admitted_plugins":10,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":6,"first_pass_rate":0.375,"model_code_failure_rate":0.375,"model_code_failures":6,"official_qualification":{"fixed_coverage_complete":true,"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}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:59Z","match_totals_all":{"draws":1000,"losses":1142,"wins":544},"match_totals_tracks":{"medium":{"draws":467,"losses":783,"wins":370},"none":{"draws":533,"losses":359,"wins":174}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":43.412761651647685,"mean":19.669893064192422,"min":6.242872745526706},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold","fixed_coverage_incomplete"],"overall_official_rank":61,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":153,"losses":264,"wins":97},"GB2-02":{"draws":281,"losses":34,"wins":5},"GB2-03":{"draws":64,"losses":63,"wins":29},"GB2-04":{"draws":289,"losses":44,"wins":29},"GB2-06":{"draws":7,"losses":360,"wins":129},"GB2-07":{"draws":0,"losses":342,"wins":250},"GB2-08":{"draws":206,"losses":35,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":70,"losses":167,"wins":13},"GB2-02":{"draws":191,"losses":27,"wins":4},"GB2-04":{"draws":203,"losses":39,"wins":22},"GB2-06":{"draws":3,"losses":208,"wins":81},"GB2-07":{"draws":0,"losses":342,"wins":250}},"none":{"GB2-01":{"draws":83,"losses":97,"wins":84},"GB2-02":{"draws":90,"losses":7,"wins":1},"GB2-03":{"draws":64,"losses":63,"wins":29},"GB2-04":{"draws":86,"losses":5,"wins":7},"GB2-06":{"draws":4,"losses":152,"wins":48},"GB2-08":{"draws":206,"losses":35,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1277.318453124216,"GB2-02":1450.4013902664049,"GB2-04":1423.2708927832791,"GB2-06":1243.933403264033,"GB2-07":1428.556676770801},"none":{"GB2-01":1423.3866478960922,"GB2-02":1432.4826319119566,"GB2-03":1363.2902103171728,"GB2-04":1468.8882535679693,"GB2-06":1103.9436983097544,"GB2-08":1371.8937477883032}},"per_game_tracks":{"medium":{"GB2-01":23.818807678882663,"GB2-02":6.242872745526706,"GB2-04":17.068321646037397,"GB2-06":28.963264231692612,"GB2-07":43.412761651647685},"none":{"GB2-01":37.1347934270453,"GB2-02":7.0150208382150785,"GB2-03":22.87323324614359,"GB2-04":25.22863025415459,"GB2-06":18.209581535374213,"GB2-08":26.740061200441602}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":19.00792918857275,"none":20.331856939812095},"reasoning_agg":{"medium":{"max":43.412761651647685,"mean":19.00792918857275,"min":6.242872745526706},"none":{"max":37.1347934270453,"mean":20.331856939812095,"min":7.0150208382150785}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":43.412761651647685,"reasoning_variance":1.3239277512393457},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.412761651647685,"expected_score":23.691620984590834,"reliability_score":77.82846544227553,"uncertainty_avg":22.17153455772447,"uncertainty_penalty":4.683691796018085},"none":{"ceiling_score":37.1347934270453,"expected_score":21.515654052672627,"reliability_score":94.62550382925605,"uncertainty_avg":5.374496170743953,"uncertainty_penalty":1.1837971128605318}}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:3aa5fb5362d4d302","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.01012224},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"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},"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},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.007612509999999999},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.02831297},"codegen_latency_ms":{"attempt_count":37,"max_ms":49328,"mean_ms":21505.916666666668,"min_ms":9355,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":47445,"mean_ms":22491.5,"min_ms":13295,"run_count":8},"medium":{"attempt_count":12,"max_ms":49328,"mean_ms":23044.25,"min_ms":13295,"run_count":8},"none":{"attempt_count":14,"max_ms":24913,"mean_ms":18982.0,"min_ms":9355,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":11394,"output_mean":4854.291666666667,"output_min":1030,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":11185,"output_mean":6150.25,"output_min":2902,"run_count":8},"medium":{"attempt_count":12,"output_max":11394,"output_mean":5469.5,"output_min":3022,"run_count":8},"none":{"attempt_count":14,"output_max":4416,"output_mean":2943.125,"output_min":1030,"run_count":8}},"display_name":"Mercury 2.5 Preview","economics":{"all":15.622337973558052,"highest":17.46211413058019,"medium":19.044072383738698,"none":23.962159689024865},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"provider_post_attempt_observations":37,"provider_post_attempts":37,"reasoning_token_observations":37,"reconciliation_get_attempt_observations":37,"reconciliation_get_attempts":176,"total_output_tokens":116503,"total_reasoning_output_tokens":61584,"total_visible_output_tokens":54919,"visible_token_observations":37},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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,"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,"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,"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}},"id":"inception/mercury-2.5-preview","is_recent_addition":false,"last_measured_at":"2026-09-10T10:39:02Z","match_totals_all":{"draws":896,"losses":840,"wins":344},"match_totals_tracks":{"highest":{"draws":323,"losses":317,"wins":78},"medium":{"draws":315,"losses":306,"wins":100},"none":{"draws":258,"losses":217,"wins":166}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":39.11032563550241,"mean":18.426180718347165,"min":6.865539546300709},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":62,"overall_ranking_status":"ranked","per_game":{"GB2-01":23.315031767294062,"GB2-02":10.683228762592293,"GB2-04":24.270432377976235,"GB2-06":11.54212333087466,"GB2-07":12.540979465146396,"GB2-08":22.420889079597504},"per_game_all":{"GB2-02":9.761984286098794,"GB2-04":20.167680278718972,"GB2-06":16.937349355856387},"per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":63,"wins":22},"GB2-02":{"draws":300,"losses":44,"wins":0},"GB2-03":{"draws":50,"losses":49,"wins":44},"GB2-04":{"draws":294,"losses":61,"wins":24},"GB2-05":{"draws":0,"losses":140,"wins":100},"GB2-06":{"draws":5,"losses":247,"wins":102},"GB2-07":{"draws":0,"losses":204,"wins":44},"GB2-08":{"draws":212,"losses":32,"wins":8}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":35,"losses":63,"wins":22},"GB2-02":{"draws":99,"losses":9,"wins":0},"GB2-04":{"draws":92,"losses":27,"wins":5},"GB2-06":{"draws":2,"losses":93,"wins":23},"GB2-07":{"draws":0,"losses":99,"wins":25},"GB2-08":{"draws":95,"losses":26,"wins":3}},"medium":{"GB2-02":{"draws":100,"losses":4,"wins":0},"GB2-04":{"draws":96,"losses":23,"wins":8},"GB2-05":{"draws":0,"losses":88,"wins":32},"GB2-06":{"draws":2,"losses":80,"wins":36},"GB2-07":{"draws":0,"losses":105,"wins":19},"GB2-08":{"draws":117,"losses":6,"wins":5}},"none":{"GB2-02":{"draws":101,"losses":31,"wins":0},"GB2-03":{"draws":50,"losses":49,"wins":44},"GB2-04":{"draws":106,"losses":11,"wins":11},"GB2-05":{"draws":0,"losses":52,"wins":68},"GB2-06":{"draws":1,"losses":74,"wins":43}}},"per_game_raw_elo_all":{"GB2-02":1444.8797642803763,"GB2-04":1433.556174460293,"GB2-06":1084.9245742169217},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1257.0243633029106,"GB2-02":1450.9640933137862,"GB2-04":1458.6739310726407,"GB2-06":1015.9346068947455,"GB2-07":1050.380743783233,"GB2-08":1324.9158440579301},"medium":{"GB2-02":1430.4870377723773,"GB2-04":1424.6094997952396,"GB2-05":1267.6313790429688,"GB2-06":1130.7908652219028,"GB2-07":1039.7885406295645,"GB2-08":1361.0186166921785},"none":{"GB2-02":1453.1881617549652,"GB2-03":1445.9077002269778,"GB2-04":1417.3850925129989,"GB2-05":1374.7864842662034,"GB2-06":1108.0482505341167}},"per_game_tracks":{"highest":{"GB2-01":23.315031767294062,"GB2-02":10.683228762592293,"GB2-04":24.270432377976235,"GB2-06":11.54212333087466,"GB2-07":12.540979465146396,"GB2-08":22.420889079597504},"medium":{"GB2-02":6.865539546300709,"GB2-04":18.70274366327956,"GB2-05":30.71080462121027,"GB2-06":20.524233311661888,"GB2-07":11.658586041674393,"GB2-08":25.802527118305367},"none":{"GB2-02":11.73718454940338,"GB2-03":32.687732040284814,"GB2-04":17.529864794901115,"GB2-05":39.11032563550241,"GB2-06":18.745691425032618}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":16.25032826011336,"medium":17.722506297399335,"none":21.305707597528798},"reasoning_agg":{"highest":{"max":24.270432377976235,"mean":16.25032826011336,"min":10.683228762592293},"medium":{"max":30.71080462121027,"mean":17.722506297399335,"min":6.865539546300709},"none":{"max":39.11032563550241,"mean":21.305707597528798,"min":11.73718454940338}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":39.11032563550241,"expected_score":9.159136711371238,"reasoning_variance":5.055379337415438,"reliability_score":98.09675876076088,"uncertainty_avg":1.903241239239127,"uncertainty_penalty":-9.267044006975928},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":24.270432377976235,"expected_score":8.310754258244692,"reliability_score":98.1925227971665,"uncertainty_avg":1.8074772028334978,"uncertainty_penalty":-7.939574001868667},"medium":{"ceiling_score":30.71080462121027,"expected_score":16.38307365802182,"reliability_score":98.24624122603018,"uncertainty_avg":1.7537587739698157,"uncertainty_penalty":-1.3394326393775131},"none":{"ceiling_score":39.11032563550241,"expected_score":22.12375938855214,"reliability_score":99.18759687555256,"uncertainty_avg":0.8124031244474441,"uncertainty_penalty":0.8180517910233434}}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:49adcc62fd4c0638","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.010999479999999999,"mean":0.007405580000000001,"median":0.00734207,"min":0.0037107299999999998,"recorded_attempt_count":17,"run_count":8,"total":0.059244639999999994},"medium":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00272269,"mean":0.001801155,"median":0.001648355,"min":0.00126116,"recorded_attempt_count":18,"run_count":8,"total":0.01440924},"none":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"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":2,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00272269,"mean":0.001801155,"median":0.001648355,"min":0.00126116,"recorded_attempt_count":18,"run_count":8,"total":0.01440924},"historical-provider-setting-baseline":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"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":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.010999479999999999,"mean":0.007405580000000001,"median":0.00734207,"min":0.0037107299999999998,"recorded_attempt_count":17,"run_count":8,"total":0.05924464000000001}},"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":24,"cost_basis_counts":{"provider_reported":54},"evidence_basis":"Provider-reported","failed_cell_count":21,"max":0.010999479999999999,"mean":0.004008075000000001,"median":0.00280168,"min":0.00126116,"recorded_attempt_count":54,"run_count":24,"total":0.09619380000000001},"codegen_latency_ms":{"attempt_count":54,"max_ms":509048,"mean_ms":136775.45833333334,"min_ms":42240,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":17,"max_ms":509048,"mean_ms":269734.875,"min_ms":169447,"run_count":8},"medium":{"attempt_count":18,"max_ms":98606,"mean_ms":61749.125,"min_ms":42240,"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":54,"output_max":45556,"output_mean":12967.0,"output_min":2790,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":17,"output_max":45556,"output_mean":27869.5,"output_min":14641,"run_count":8},"medium":{"attempt_count":18,"output_max":6691,"output_mean":4472.75,"output_min":2790,"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":{"highest":20.32563417683313,"medium":10.934934183457305},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["stop"],"indexed_attempts":54,"output_token_observations":54,"provider_post_attempt_observations":54,"provider_post_attempts":54,"reasoning_token_observations":54,"reconciliation_get_attempt_observations":54,"reconciliation_get_attempts":257,"total_output_tokens":311208,"total_reasoning_output_tokens":196736,"total_visible_output_tokens":114472,"visible_token_observations":54},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"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":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","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":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06"],"model_code_failure_rate":0.75,"model_code_failures":6,"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":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"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}},"id":"ibm-granite/granite-4.2-8b","is_recent_addition":false,"last_measured_at":"2026-09-10T11:06:08Z","match_totals_all":{"draws":206,"losses":167,"wins":7},"match_totals_tracks":{"highest":{"draws":101,"losses":30,"wins":1},"medium":{"draws":105,"losses":137,"wins":6}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":21.86986836691461,"mean":9.90893025148373,"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"],"overall_official_rank":63,"overall_ranking_status":"partial","per_game":{"GB2-03":20.32563417683313},"per_game_match_totals_all":{"GB2-03":{"draws":101,"losses":30,"wins":1},"GB2-07":{"draws":0,"losses":118,"wins":6},"GB2-08":{"draws":105,"losses":19,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":101,"losses":30,"wins":1}},"medium":{"GB2-07":{"draws":0,"losses":118,"wins":6},"GB2-08":{"draws":105,"losses":19,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1328.441766750424},"medium":{"GB2-07":899.8395013993829,"GB2-08":1318.9419863684932}},"per_game_tracks":{"highest":{"GB2-03":20.32563417683313},"medium":{"GB2-07":0.0,"GB2-08":21.86986836691461}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":12.085694390016217,"medium":7.732166112951243},"reasoning_agg":{"highest":{"max":20.32563417683313,"mean":12.085694390016217,"min":20.32563417683313},"medium":{"max":21.86986836691461,"mean":7.732166112951243,"min":0.0}},"reasoning_labels":{"highest":"Full","medium":"Low","none":"Setting not tested"},"reasoning_settings":{"balanced":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":21.86986836691461,"reasoning_variance":4.3535282770649735},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":20.32563417683313,"expected_score":0.0,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-12.085694390016217},"medium":{"ceiling_score":21.86986836691461,"expected_score":8.592833213648284,"reliability_score":99.0286404500042,"uncertainty_avg":0.9713595499957961,"uncertainty_penalty":0.8606671006970403}}}],"public_release_id":"gb2-20260910-ebce011c03ff","results_cut_id":"gb2-20260910-ebce011c03ff","schema_version":2,"snapshot_id":"20260910_111653","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-09-10 11:16 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":20,"wins":20},"claude-fable-5":{"draws":12,"losses":25,"wins":9},"claude-fable-5-1":{"draws":2,"losses":43,"wins":3},"claude-opus-4-5":{"draws":13,"losses":23,"wins":10},"claude-opus-5":{"draws":1,"losses":1,"wins":2},"claude-sonnet-5":{"draws":25,"losses":43,"wins":18},"deepseek/deepseek-v4-flash":{"draws":35,"losses":34,"wins":23},"deepseek/deepseek-v4-pro":{"draws":25,"losses":31,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":29,"wins":21},"google/gemini-3.5-flash":{"draws":29,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":62,"losses":50,"wins":56},"google/gemini-3.6-flash":{"draws":38,"losses":52,"wins":34},"google/gemini-3.8-flash":{"draws":18,"losses":20,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":19,"losses":13,"wins":16},"gpt-5.6-luna":{"draws":30,"losses":21,"wins":33},"gpt-5.6-sol":{"draws":4,"losses":38,"wins":14},"gpt-5.6-terra":{"draws":18,"losses":36,"wins":16},"gpt-6-astra":{"draws":2,"losses":23,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":26,"losses":23,"wins":21},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":11},"meituan/longcat-2.0":{"draws":19,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":36,"losses":24,"wins":28},"meta/muse-spark-1.2":{"draws":17,"losses":21,"wins":18},"meta/muse-spark-1.3":{"draws":18,"losses":31,"wins":11},"moonshotai/kimi-k3":{"draws":15,"losses":23,"wins":16},"o3":{"draws":19,"losses":41,"wins":22},"openai/gpt-oss-120b":{"draws":21,"losses":27,"wins":28},"poolside/laguna-s-2.1":{"draws":19,"losses":11,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":26,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":14},"qwen/qwen3.8-flash":{"draws":20,"losses":17,"wins":13},"qwen/qwen3.8-max":{"draws":26,"losses":16,"wins":26},"stealth/ox-alpha":{"draws":57,"losses":97,"wins":54},"stepfun/step-3.7-flash":{"draws":2,"losses":12,"wins":4},"tencent/hy4-preview":{"draws":23,"losses":31,"wins":8},"thinkingmachines/inkling":{"draws":24,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":33,"losses":23,"wins":42},"x-ai/grok-4.5":{"draws":16,"losses":25,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":10},"z-ai/glm-5.2":{"draws":37,"losses":23,"wins":24},"z-ai/glm-5.3":{"draws":13,"losses":19,"wins":10},"z-ai/glm-5.3-flash":{"draws":25,"losses":25,"wins":12}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":25},"claude-fable-5":{"draws":8,"losses":34,"wins":34},"claude-fable-5-1":{"draws":2,"losses":113,"wins":25},"claude-opus-4-5":{"draws":10,"losses":9,"wins":29},"claude-opus-5":{"draws":2,"losses":0,"wins":4},"claude-sonnet-5":{"draws":19,"losses":15,"wins":36},"deepseek/deepseek-v4-flash":{"draws":19,"losses":7,"wins":34},"deepseek/deepseek-v4-pro":{"draws":18,"losses":26,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":17,"wins":36},"google/gemini-3.5-flash":{"draws":23,"losses":20,"wins":51},"google/gemini-3.5-flash-lite":{"draws":29,"losses":23,"wins":30},"google/gemini-3.6-flash":{"draws":24,"losses":43,"wins":53},"google/gemini-3.8-flash":{"draws":17,"losses":40,"wins":53},"gpt-5.4":{"draws":24,"losses":38,"wins":36},"gpt-5.6-luna":{"draws":22,"losses":14,"wins":24},"gpt-5.6-sol":{"draws":15,"losses":47,"wins":46},"gpt-5.6-terra":{"draws":23,"losses":20,"wins":43},"gpt-6-astra":{"draws":7,"losses":94,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":2,"wins":8},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":12},"meta/muse-glimmer-30b":{"draws":20,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":33},"meta/muse-spark-1.3":{"draws":16,"losses":27,"wins":39},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":45},"o3":{"draws":5,"losses":13,"wins":40},"openai/gpt-oss-120b":{"draws":14,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":23,"wins":35},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":19},"qwen/qwen3.8-flash":{"draws":19,"losses":8,"wins":23},"qwen/qwen3.8-max":{"draws":14,"losses":25,"wins":33},"stealth/ox-alpha":{"draws":78,"losses":67,"wins":141},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":17,"losses":23,"wins":42},"thinkingmachines/inkling":{"draws":9,"losses":0,"wins":15},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":22},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":29},"x-ai/grok-4.6":{"draws":28,"losses":37,"wins":47},"z-ai/glm-5.2":{"draws":25,"losses":17,"wins":30},"z-ai/glm-5.3":{"draws":14,"losses":59,"wins":39},"z-ai/glm-5.3-flash":{"draws":14,"losses":32,"wins":32}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":43},"claude-fable-5":{"draws":2,"losses":25,"wins":113},"claude-fable-5-1":{"draws":8,"losses":62,"wins":62},"claude-opus-4-5":{"draws":2,"losses":3,"wins":45},"claude-opus-5":{"draws":1,"losses":1,"wins":4},"claude-sonnet-5":{"draws":4,"losses":3,"wins":63},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":33},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":3,"wins":75},"google/gemini-3.5-flash":{"draws":9,"losses":6,"wins":83},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":37},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":117},"google/gemini-3.8-flash":{"draws":14,"losses":14,"wins":102},"gpt-5.4":{"draws":6,"losses":17,"wins":75},"gpt-5.6-luna":{"draws":7,"losses":4,"wins":33},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":103},"gpt-5.6-terra":{"draws":7,"losses":3,"wins":60},"gpt-6-astra":{"draws":15,"losses":94,"wins":53},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":17},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":24},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":13},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":68},"meta/muse-spark-1.3":{"draws":4,"losses":7,"wins":93},"moonshotai/kimi-k3":{"draws":10,"losses":4,"wins":90},"o3":{"draws":0,"losses":5,"wins":47},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":20},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":7,"wins":72},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":46},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":49},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":75},"stealth/ox-alpha":{"draws":41,"losses":23,"wins":266},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":3,"losses":13,"wins":72},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":16},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":28},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":58},"x-ai/grok-4.6":{"draws":6,"losses":21,"wins":97},"z-ai/glm-5.2":{"draws":9,"losses":2,"wins":53},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":84},"z-ai/glm-5.3-flash":{"draws":13,"losses":13,"wins":86}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":23},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":2,"losses":45,"wins":3},"claude-opus-4-5":{"draws":35,"losses":34,"wins":39},"claude-opus-4-8":{"draws":8,"losses":29,"wins":17},"claude-opus-5":{"draws":23,"losses":130,"wins":19},"claude-sonnet-5":{"draws":55,"losses":32,"wins":75},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":20,"wins":35},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":18,"wins":16},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":13,"losses":34,"wins":17},"google/gemini-3.5-flash-lite":{"draws":124,"losses":79,"wins":155},"google/gemini-3.6-flash":{"draws":91,"losses":150,"wins":109},"google/gemini-3.8-flash":{"draws":17,"losses":30,"wins":15},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":13},"gpt-4.1":{"draws":8,"losses":6,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":9,"wins":11},"gpt-5.4":{"draws":38,"losses":70,"wins":30},"gpt-5.4-mini":{"draws":17,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":24},"gpt-5.5":{"draws":18,"losses":23,"wins":11},"gpt-5.6-luna":{"draws":53,"losses":40,"wins":55},"gpt-5.6-sol":{"draws":24,"losses":92,"wins":34},"gpt-5.6-terra":{"draws":19,"losses":14,"wins":27},"gpt-6-astra":{"draws":6,"losses":43,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":24,"losses":15,"wins":27},"meituan/longcat-2.0":{"draws":36,"losses":29,"wins":58},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":27,"losses":50,"wins":31},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":81,"losses":77,"wins":58},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":7,"wins":20},"o3":{"draws":36,"losses":66,"wins":152},"openai/gpt-oss-120b":{"draws":13,"losses":4,"wins":25},"poolside/laguna-s-2.1":{"draws":58,"losses":8,"wins":60},"qwen/qwen3.7-max":{"draws":5,"losses":9,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":17,"wins":19},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":14},"qwen/qwen3.8-flash":{"draws":9,"losses":7,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":32,"wins":15},"stealth/ox-alpha":{"draws":63,"losses":73,"wins":61},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":41},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":21,"wins":16},"thinkingmachines/inkling":{"draws":35,"losses":17,"wins":80},"thinkingmachines/inkling-small":{"draws":23,"losses":12,"wins":26},"x-ai/grok-4.5":{"draws":60,"losses":82,"wins":50},"x-ai/grok-4.6":{"draws":19,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":9},"z-ai/glm-5.2":{"draws":20,"losses":27,"wins":39},"z-ai/glm-5.3":{"draws":13,"losses":24,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":16}},"claude-opus-4-8":{"claude-opus-4-5":{"draws":17,"losses":25,"wins":52},"claude-opus-4-8":{"draws":8,"losses":10,"wins":10},"claude-opus-5":{"draws":21,"losses":66,"wins":31},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":27},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":19,"losses":27,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":16},"gpt-4.1":{"draws":4,"losses":3,"wins":11},"gpt-5":{"draws":11,"losses":13,"wins":26},"gpt-5.4-mini":{"draws":18,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":36},"gpt-5.5":{"draws":19,"losses":35,"wins":22},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":17},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":13,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":31},"o3":{"draws":4,"losses":6,"wins":34},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":21},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":17},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":15,"losses":20,"wins":19},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":12,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":23,"losses":16,"wins":25}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":1},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":1,"losses":4,"wins":1},"claude-opus-4-5":{"draws":35,"losses":31,"wins":172},"claude-opus-4-8":{"draws":21,"losses":31,"wins":66},"claude-opus-5":{"draws":48,"losses":172,"wins":172},"claude-sonnet-5":{"draws":2,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":22},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":94},"google/gemini-3.6-flash":{"draws":18,"losses":33,"wins":111},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":20},"gpt-4.1":{"draws":10,"losses":2,"wins":41},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":5,"wins":51},"gpt-5.4":{"draws":0,"losses":0,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":32},"gpt-5.4-nano":{"draws":14,"losses":12,"wins":54},"gpt-5.5":{"draws":21,"losses":33,"wins":94},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":12},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":4},"gpt-6-astra":{"draws":0,"losses":5,"wins":1},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":22},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":50},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":29},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":62},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":43},"o3":{"draws":2,"losses":6,"wins":80},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":72},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":55},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":4,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":28},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":48},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":56},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":18,"losses":23,"wins":87},"x-ai/grok-4.6":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":1,"wins":35},"z-ai/glm-5.2":{"draws":13,"losses":9,"wins":60},"z-ai/glm-5.3":{"draws":1,"losses":2,"wins":1}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":18,"wins":43},"claude-fable-5":{"draws":19,"losses":36,"wins":15},"claude-fable-5-1":{"draws":4,"losses":63,"wins":3},"claude-opus-4-5":{"draws":55,"losses":75,"wins":32},"claude-opus-5":{"draws":2,"losses":4,"wins":6},"claude-sonnet-5":{"draws":42,"losses":53,"wins":53},"deepseek/deepseek-v4-flash":{"draws":28,"losses":18,"wins":34},"deepseek/deepseek-v4-pro":{"draws":30,"losses":32,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":27,"wins":20},"google/gemini-3.5-flash":{"draws":24,"losses":25,"wins":19},"google/gemini-3.5-flash-lite":{"draws":113,"losses":87,"wins":206},"google/gemini-3.6-flash":{"draws":93,"losses":137,"wins":116},"google/gemini-3.8-flash":{"draws":27,"losses":29,"wins":28},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":5},"gpt-5.4":{"draws":72,"losses":98,"wins":38},"gpt-5.6-luna":{"draws":76,"losses":58,"wins":90},"gpt-5.6-sol":{"draws":42,"losses":171,"wins":37},"gpt-5.6-terra":{"draws":32,"losses":24,"wins":26},"gpt-6-astra":{"draws":2,"losses":56,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":21,"losses":5,"wins":34},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":36},"meituan/longcat-2.0":{"draws":33,"losses":13,"wins":70},"meta/muse-glimmer-30b":{"draws":28,"losses":13,"wins":33},"meta/muse-spark-1.2":{"draws":47,"losses":56,"wins":67},"meta/muse-spark-1.3":{"draws":23,"losses":27,"wins":14},"moonshotai/kimi-k3":{"draws":78,"losses":92,"wins":46},"o3":{"draws":18,"losses":93,"wins":111},"openai/gpt-oss-120b":{"draws":30,"losses":11,"wins":43},"poolside/laguna-s-2.1":{"draws":43,"losses":9,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":29,"wins":22},"qwen/qwen3.8-27b":{"draws":14,"losses":11,"wins":17},"qwen/qwen3.8-flash":{"draws":18,"losses":13,"wins":19},"qwen/qwen3.8-max":{"draws":19,"losses":33,"wins":31},"stealth/ox-alpha":{"draws":71,"losses":118,"wins":90},"stepfun/step-3.7-flash":{"draws":6,"losses":17,"wins":17},"tencent/hy4-preview":{"draws":32,"losses":37,"wins":19},"thinkingmachines/inkling":{"draws":47,"losses":16,"wins":75},"thinkingmachines/inkling-small":{"draws":25,"losses":18,"wins":45},"x-ai/grok-4.5":{"draws":51,"losses":72,"wins":31},"x-ai/grok-4.6":{"draws":17,"losses":28,"wins":27},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":31},"z-ai/glm-5.3":{"draws":11,"losses":49,"wins":12},"z-ai/glm-5.3-flash":{"draws":20,"losses":41,"wins":21}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":9,"losses":22,"wins":3},"claude-opus-4-8":{"draws":7,"losses":15,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":8,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":13,"wins":13},"google/gemini-3.5-flash-lite":{"draws":19,"losses":0,"wins":11},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":27,"wins":11},"gpt-5.5":{"draws":14,"losses":11,"wins":3},"inclusionai/ling-3.0-flash":{"draws":18,"losses":10,"wins":6},"meituan/longcat-2.0":{"draws":22,"losses":18,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":15,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":13,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":13},"o3":{"draws":12,"losses":6,"wins":4},"poolside/laguna-s-2.1":{"draws":21,"losses":2,"wins":15},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":16},"x-ai/grok-4.5":{"draws":5,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":27,"losses":24,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":9,"wins":5}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":23,"wins":34},"claude-fable-5":{"draws":19,"losses":34,"wins":7},"claude-fable-5-1":{"draws":2,"losses":33,"wins":1},"claude-opus-4-5":{"draws":22,"losses":37,"wins":21},"claude-opus-4-8":{"draws":8,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":22,"wins":1},"claude-sonnet-5":{"draws":28,"losses":34,"wins":18},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":20,"losses":36,"wins":36},"deepseek/deepseek-v4-pro":{"draws":32,"losses":31,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":28,"wins":21},"google/gemini-3.1-flash-lite":{"draws":9,"losses":19,"wins":18},"google/gemini-3.5-flash":{"draws":30,"losses":31,"wins":19},"google/gemini-3.5-flash-lite":{"draws":60,"losses":47,"wins":63},"google/gemini-3.6-flash":{"draws":46,"losses":64,"wins":34},"google/gemini-3.8-flash":{"draws":20,"losses":26,"wins":12},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":8},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":7,"losses":6,"wins":1},"gpt-5.4":{"draws":34,"losses":27,"wins":13},"gpt-5.4-mini":{"draws":10,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":47,"losses":24,"wins":31},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":10},"gpt-5.6-terra":{"draws":29,"losses":22,"wins":19},"gpt-6-astra":{"draws":1,"losses":29,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":28,"losses":5,"wins":33},"inclusionai/ling-3.0-flash":{"draws":21,"losses":15,"wins":18},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":32},"meta/muse-glimmer-30b":{"draws":50,"losses":17,"wins":29},"meta/muse-spark-1.2":{"draws":16,"losses":15,"wins":13},"meta/muse-spark-1.3":{"draws":6,"losses":30,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":19,"wins":19},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":17,"losses":36,"wins":45},"openai/gpt-oss-120b":{"draws":41,"losses":25,"wins":26},"poolside/laguna-s-2.1":{"draws":40,"losses":19,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":31,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":16,"wins":17},"qwen/qwen3.8-flash":{"draws":20,"losses":17,"wins":13},"qwen/qwen3.8-max":{"draws":27,"losses":24,"wins":19},"stealth/ox-alpha":{"draws":83,"losses":71,"wins":54},"stepfun/step-3.7-flash":{"draws":7,"losses":18,"wins":13},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":20,"losses":28,"wins":22},"thinkingmachines/inkling":{"draws":28,"losses":30,"wins":24},"thinkingmachines/inkling-small":{"draws":39,"losses":18,"wins":45},"x-ai/grok-4.5":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":24,"losses":22,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":35,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":48,"wins":27},"z-ai/glm-5.3":{"draws":18,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":24,"losses":16,"wins":12}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":20,"wins":31},"claude-fable-5":{"draws":18,"losses":20,"wins":26},"claude-fable-5-1":{"draws":0,"losses":61,"wins":3},"claude-opus-4-5":{"draws":15,"losses":16,"wins":13},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":30,"losses":28,"wins":32},"deepseek/deepseek-v4-flash":{"draws":32,"losses":17,"wins":31},"deepseek/deepseek-v4-pro":{"draws":22,"losses":23,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":28,"wins":23},"google/gemini-3.5-flash":{"draws":19,"losses":19,"wins":28},"google/gemini-3.5-flash-lite":{"draws":52,"losses":48,"wins":62},"google/gemini-3.6-flash":{"draws":35,"losses":36,"wins":45},"google/gemini-3.8-flash":{"draws":22,"losses":28,"wins":16},"gpt-4.1-nano":{"draws":1,"losses":4,"wins":1},"gpt-5.4":{"draws":26,"losses":21,"wins":17},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":32},"gpt-5.6-sol":{"draws":7,"losses":28,"wins":21},"gpt-5.6-terra":{"draws":26,"losses":21,"wins":31},"gpt-6-astra":{"draws":1,"losses":50,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":12,"losses":6,"wins":24},"meta/muse-glimmer-30b":{"draws":31,"losses":19,"wins":20},"meta/muse-spark-1.2":{"draws":9,"losses":19,"wins":24},"meta/muse-spark-1.3":{"draws":11,"losses":33,"wins":22},"moonshotai/kimi-k3":{"draws":22,"losses":23,"wins":17},"o3":{"draws":14,"losses":25,"wins":35},"openai/gpt-oss-120b":{"draws":34,"losses":18,"wins":20},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":26,"wins":19},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":17},"qwen/qwen3.8-flash":{"draws":18,"losses":20,"wins":20},"qwen/qwen3.8-max":{"draws":22,"losses":28,"wins":20},"stealth/ox-alpha":{"draws":62,"losses":75,"wins":71},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":9},"tencent/hy4-preview":{"draws":29,"losses":26,"wins":24},"thinkingmachines/inkling":{"draws":25,"losses":7,"wins":20},"thinkingmachines/inkling-small":{"draws":47,"losses":14,"wins":35},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":20},"x-ai/grok-4.6":{"draws":19,"losses":35,"wins":20},"z-ai/glm-5.2":{"draws":30,"losses":20,"wins":20},"z-ai/glm-5.3":{"draws":14,"losses":31,"wins":15},"z-ai/glm-5.3-flash":{"draws":20,"losses":23,"wins":25}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":21,"wins":29},"claude-fable-5":{"draws":17,"losses":36,"wins":17},"claude-fable-5-1":{"draws":4,"losses":75,"wins":3},"claude-opus-4-5":{"draws":14,"losses":16,"wins":18},"claude-sonnet-5":{"draws":29,"losses":20,"wins":27},"deepseek/deepseek-v4-flash":{"draws":33,"losses":21,"wins":28},"deepseek/deepseek-v4-pro":{"draws":29,"losses":23,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":28,"losses":30,"wins":24},"google/gemini-3.5-flash-lite":{"draws":60,"losses":30,"wins":56},"google/gemini-3.6-flash":{"draws":35,"losses":57,"wins":30},"google/gemini-3.8-flash":{"draws":18,"losses":34,"wins":18},"gpt-4.1-nano":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":25,"losses":25,"wins":18},"gpt-5.6-luna":{"draws":29,"losses":23,"wins":28},"gpt-5.6-sol":{"draws":12,"losses":42,"wins":16},"gpt-5.6-terra":{"draws":27,"losses":21,"wins":22},"gpt-6-astra":{"draws":4,"losses":62,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":9,"wins":20},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":17,"losses":6,"wins":23},"meta/muse-glimmer-30b":{"draws":35,"losses":15,"wins":32},"meta/muse-spark-1.2":{"draws":23,"losses":14,"wins":23},"meta/muse-spark-1.3":{"draws":16,"losses":24,"wins":22},"moonshotai/kimi-k3":{"draws":26,"losses":18,"wins":22},"o3":{"draws":18,"losses":23,"wins":41},"openai/gpt-oss-120b":{"draws":31,"losses":14,"wins":15},"poolside/laguna-s-2.1":{"draws":21,"losses":12,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":26,"wins":25},"qwen/qwen3.8-27b":{"draws":17,"losses":16,"wins":11},"qwen/qwen3.8-flash":{"draws":23,"losses":17,"wins":14},"qwen/qwen3.8-max":{"draws":29,"losses":27,"wins":26},"stealth/ox-alpha":{"draws":73,"losses":92,"wins":83},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":7},"tencent/hy4-preview":{"draws":23,"losses":38,"wins":27},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":17},"thinkingmachines/inkling-small":{"draws":29,"losses":17,"wins":38},"x-ai/grok-4.5":{"draws":11,"losses":13,"wins":18},"x-ai/grok-4.6":{"draws":22,"losses":25,"wins":27},"z-ai/glm-5.2":{"draws":29,"losses":13,"wins":30},"z-ai/glm-5.3":{"draws":13,"losses":37,"wins":22},"z-ai/glm-5.3-flash":{"draws":23,"losses":36,"wins":23}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":9,"losses":27,"wins":4},"claude-opus-5":{"draws":4,"losses":27,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":18,"wins":19},"google/gemini-3.1-flash-lite":{"draws":0,"losses":12,"wins":12},"google/gemini-3.5-flash-lite":{"draws":12,"losses":10,"wins":12},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":16,"wins":14},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-5":{"draws":14,"losses":18,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":21,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":29,"wins":19},"gpt-5.5":{"draws":11,"losses":22,"wins":3},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":24,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":15,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":24,"wins":13},"o3":{"draws":10,"losses":24,"wins":2},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":19,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":24,"wins":11},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.5":{"draws":35,"losses":42,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":19,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":21,"wins":8}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":14,"wins":25},"claude-fable-5":{"draws":23,"losses":51,"wins":20},"claude-fable-5-1":{"draws":9,"losses":83,"wins":6},"claude-opus-4-5":{"draws":13,"losses":17,"wins":34},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":24,"losses":19,"wins":25},"deepseek/deepseek-v4-flash":{"draws":30,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":19,"losses":28,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":24,"wins":30},"google/gemini-3.5-flash":{"draws":16,"losses":18,"wins":18},"google/gemini-3.5-flash-lite":{"draws":51,"losses":39,"wins":36},"google/gemini-3.6-flash":{"draws":43,"losses":48,"wins":43},"google/gemini-3.8-flash":{"draws":20,"losses":41,"wins":37},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":11,"losses":42,"wins":29},"gpt-5.6-luna":{"draws":35,"losses":24,"wins":23},"gpt-5.6-sol":{"draws":10,"losses":46,"wins":30},"gpt-5.6-terra":{"draws":30,"losses":26,"wins":20},"gpt-6-astra":{"draws":13,"losses":69,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":21,"losses":4,"wins":19},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":20},"meta/muse-glimmer-30b":{"draws":28,"losses":16,"wins":24},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":21},"meta/muse-spark-1.3":{"draws":20,"losses":38,"wins":22},"moonshotai/kimi-k3":{"draws":31,"losses":14,"wins":31},"o3":{"draws":11,"losses":19,"wins":38},"openai/gpt-oss-120b":{"draws":28,"losses":19,"wins":15},"poolside/laguna-s-2.1":{"draws":22,"losses":9,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":34,"wins":29},"qwen/qwen3.8-27b":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":18,"losses":15,"wins":23},"qwen/qwen3.8-max":{"draws":28,"losses":21,"wins":25},"stealth/ox-alpha":{"draws":71,"losses":95,"wins":83},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy4-preview":{"draws":20,"losses":48,"wins":20},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":12},"thinkingmachines/inkling-small":{"draws":22,"losses":16,"wins":24},"x-ai/grok-4.5":{"draws":16,"losses":22,"wins":16},"x-ai/grok-4.6":{"draws":25,"losses":43,"wins":20},"z-ai/glm-5.2":{"draws":26,"losses":25,"wins":25},"z-ai/glm-5.3":{"draws":16,"losses":44,"wins":20},"z-ai/glm-5.3-flash":{"draws":30,"losses":27,"wins":27}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":62,"losses":56,"wins":50},"claude-fable-5":{"draws":29,"losses":30,"wins":23},"claude-fable-5-1":{"draws":4,"losses":37,"wins":1},"claude-opus-4-5":{"draws":125,"losses":155,"wins":80},"claude-opus-4-8":{"draws":13,"losses":24,"wins":9},"claude-opus-5":{"draws":17,"losses":94,"wins":9},"claude-sonnet-5":{"draws":113,"losses":206,"wins":87},"cohere/north-mini-code":{"draws":19,"losses":11,"wins":0},"deepseek/deepseek-v4-flash":{"draws":60,"losses":63,"wins":47},"deepseek/deepseek-v4-pro":{"draws":52,"losses":62,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":60,"losses":56,"wins":30},"google/gemini-3.1-flash-lite":{"draws":12,"losses":12,"wins":10},"google/gemini-3.5-flash":{"draws":51,"losses":36,"wins":39},"google/gemini-3.5-flash-lite":{"draws":304,"losses":292,"wins":292},"google/gemini-3.6-flash":{"draws":292,"losses":396,"wins":167},"google/gemini-3.8-flash":{"draws":25,"losses":48,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":15,"wins":4},"gpt-4.1":{"draws":6,"losses":6,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":14,"wins":11},"gpt-5":{"draws":19,"losses":10,"wins":7},"gpt-5.4":{"draws":111,"losses":190,"wins":57},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":7},"gpt-5.4-nano":{"draws":19,"losses":12,"wins":19},"gpt-5.5":{"draws":30,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":141,"losses":160,"wins":127},"gpt-5.6-sol":{"draws":47,"losses":250,"wins":31},"gpt-5.6-terra":{"draws":45,"losses":54,"wins":39},"gpt-6-astra":{"draws":1,"losses":48,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":15,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":57,"losses":27,"wins":44},"inclusionai/ling-3.0-flash":{"draws":79,"losses":38,"wins":91},"meituan/longcat-2.0":{"draws":89,"losses":124,"wins":132},"meta/muse-glimmer-30b":{"draws":71,"losses":34,"wins":63},"meta/muse-spark-1.2":{"draws":73,"losses":127,"wins":60},"meta/muse-spark-1.3":{"draws":30,"losses":51,"wins":29},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":155,"losses":201,"wins":90},"nex-agi/nex-n2-pro":{"draws":13,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":8},"o3":{"draws":94,"losses":313,"wins":191},"openai/gpt-oss-120b":{"draws":61,"losses":46,"wins":53},"poolside/laguna-s-2.1":{"draws":163,"losses":113,"wins":96},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":61,"wins":25},"qwen/qwen3.8-27b":{"draws":17,"losses":35,"wins":18},"qwen/qwen3.8-flash":{"draws":42,"losses":34,"wins":18},"qwen/qwen3.8-max":{"draws":59,"losses":47,"wins":39},"stealth/ox-alpha":{"draws":112,"losses":149,"wins":98},"stepfun/step-3.7-flash":{"draws":29,"losses":56,"wins":47},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"tencent/hy4-preview":{"draws":53,"losses":51,"wins":30},"thinkingmachines/inkling":{"draws":149,"losses":105,"wins":158},"thinkingmachines/inkling-small":{"draws":68,"losses":61,"wins":71},"x-ai/grok-4.5":{"draws":102,"losses":203,"wins":85},"x-ai/grok-4.6":{"draws":43,"losses":50,"wins":23},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":17,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":11},"z-ai/glm-5.2":{"draws":67,"losses":49,"wins":42},"z-ai/glm-5.3":{"draws":25,"losses":37,"wins":10},"z-ai/glm-5.3-flash":{"draws":45,"losses":43,"wins":28}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":34,"wins":52},"claude-fable-5":{"draws":24,"losses":53,"wins":43},"claude-fable-5-1":{"draws":9,"losses":117,"wins":14},"claude-opus-4-5":{"draws":92,"losses":109,"wins":151},"claude-opus-4-8":{"draws":19,"losses":16,"wins":27},"claude-opus-5":{"draws":18,"losses":111,"wins":33},"claude-sonnet-5":{"draws":93,"losses":116,"wins":137},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":46,"losses":34,"wins":64},"deepseek/deepseek-v4-pro":{"draws":35,"losses":45,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":30,"wins":57},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":43,"losses":43,"wins":48},"google/gemini-3.5-flash-lite":{"draws":292,"losses":167,"wins":396},"google/gemini-3.6-flash":{"draws":152,"losses":260,"wins":260},"google/gemini-3.8-flash":{"draws":21,"losses":59,"wins":56},"google/gemma-4-31b-it":{"draws":10,"losses":9,"wins":7},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":13,"losses":9,"wins":4},"gpt-5":{"draws":5,"losses":12,"wins":21},"gpt-5.4":{"draws":88,"losses":157,"wins":117},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":23},"gpt-5.4-nano":{"draws":18,"losses":11,"wins":19},"gpt-5.5":{"draws":25,"losses":23,"wins":26},"gpt-5.6-luna":{"draws":111,"losses":89,"wins":164},"gpt-5.6-sol":{"draws":44,"losses":201,"wins":107},"gpt-5.6-terra":{"draws":38,"losses":40,"wins":38},"gpt-6-astra":{"draws":17,"losses":96,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":36,"losses":11,"wins":37},"inclusionai/ling-3.0-flash":{"draws":99,"losses":35,"wins":82},"meituan/longcat-2.0":{"draws":90,"losses":53,"wins":172},"meta/muse-glimmer-30b":{"draws":52,"losses":14,"wins":38},"meta/muse-spark-1.2":{"draws":47,"losses":120,"wins":99},"meta/muse-spark-1.3":{"draws":16,"losses":57,"wins":47},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":122,"losses":144,"wins":174},"nex-agi/nex-n2-pro":{"draws":15,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":21},"o3":{"draws":90,"losses":173,"wins":265},"openai/gpt-oss-120b":{"draws":46,"losses":23,"wins":33},"poolside/laguna-s-2.1":{"draws":139,"losses":53,"wins":128},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":45,"wins":44},"qwen/qwen3.8-27b":{"draws":17,"losses":14,"wins":29},"qwen/qwen3.8-flash":{"draws":43,"losses":13,"wins":34},"qwen/qwen3.8-max":{"draws":47,"losses":46,"wins":50},"stealth/ox-alpha":{"draws":104,"losses":151,"wins":147},"stepfun/step-3.7-flash":{"draws":16,"losses":13,"wins":62},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":18},"tencent/hy4-preview":{"draws":35,"losses":56,"wins":45},"thinkingmachines/inkling":{"draws":144,"losses":52,"wins":172},"thinkingmachines/inkling-small":{"draws":53,"losses":36,"wins":45},"x-ai/grok-4.5":{"draws":76,"losses":155,"wins":161},"x-ai/grok-4.6":{"draws":30,"losses":43,"wins":49},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":13},"z-ai/glm-5.2":{"draws":54,"losses":36,"wins":52},"z-ai/glm-5.3":{"draws":22,"losses":74,"wins":32},"z-ai/glm-5.3-flash":{"draws":38,"losses":41,"wins":31}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":20},"claude-fable-5":{"draws":17,"losses":53,"wins":40},"claude-fable-5-1":{"draws":14,"losses":102,"wins":14},"claude-opus-4-5":{"draws":17,"losses":15,"wins":30},"claude-opus-5":{"draws":1,"losses":1,"wins":2},"claude-sonnet-5":{"draws":27,"losses":28,"wins":29},"deepseek/deepseek-v4-flash":{"draws":20,"losses":12,"wins":26},"deepseek/deepseek-v4-pro":{"draws":22,"losses":16,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":18,"wins":34},"google/gemini-3.5-flash":{"draws":20,"losses":37,"wins":41},"google/gemini-3.5-flash-lite":{"draws":25,"losses":7,"wins":48},"google/gemini-3.6-flash":{"draws":21,"losses":56,"wins":59},"google/gemini-3.8-flash":{"draws":20,"losses":24,"wins":24},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":23,"losses":43,"wins":30},"gpt-5.6-luna":{"draws":22,"losses":19,"wins":25},"gpt-5.6-sol":{"draws":15,"losses":53,"wins":42},"gpt-5.6-terra":{"draws":27,"losses":24,"wins":31},"gpt-6-astra":{"draws":14,"losses":98,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":10},"meta/muse-glimmer-30b":{"draws":21,"losses":11,"wins":8},"meta/muse-spark-1.2":{"draws":9,"losses":22,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":40,"wins":28},"moonshotai/kimi-k3":{"draws":29,"losses":22,"wins":37},"o3":{"draws":7,"losses":24,"wins":35},"openai/gpt-oss-120b":{"draws":11,"losses":5,"wins":20},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":31,"wins":41},"qwen/qwen3.8-27b":{"draws":9,"losses":16,"wins":27},"qwen/qwen3.8-flash":{"draws":16,"losses":15,"wins":25},"qwen/qwen3.8-max":{"draws":25,"losses":27,"wins":32},"stealth/ox-alpha":{"draws":72,"losses":106,"wins":122},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":19,"losses":36,"wins":31},"thinkingmachines/inkling":{"draws":14,"losses":4,"wins":12},"thinkingmachines/inkling-small":{"draws":20,"losses":7,"wins":17},"x-ai/grok-4.5":{"draws":10,"losses":25,"wins":13},"x-ai/grok-4.6":{"draws":27,"losses":38,"wins":31},"z-ai/glm-5.2":{"draws":21,"losses":20,"wins":27},"z-ai/glm-5.3":{"draws":14,"losses":60,"wins":22},"z-ai/glm-5.3-flash":{"draws":21,"losses":28,"wins":37}},"google/gemma-4-31b-it":{"claude-opus-4-5":{"draws":11,"losses":13,"wins":14},"claude-opus-4-8":{"draws":10,"losses":16,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":0},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":7,"losses":8,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":14,"wins":16},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":15},"google/gemini-3.6-flash":{"draws":10,"losses":7,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":5,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":8,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":10},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":13},"gpt-5.5":{"draws":7,"losses":11,"wins":2},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":19},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":13},"o3":{"draws":8,"losses":7,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":3,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":1,"losses":7,"wins":12},"stepfun/step-3.7-flash":{"draws":3,"losses":13,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":26,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":3}},"gpt-4.1":{"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":5,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":4},"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":5,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":3,"losses":11,"wins":14},"google/gemini-3.6-flash":{"draws":13,"losses":4,"wins":9},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":3},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":0},"o3":{"draws":0,"losses":6,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":1,"losses":4,"wins":1},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":12},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":2,"wins":1}},"gpt-5":{"claude-opus-4-5":{"draws":25,"losses":21,"wins":20},"claude-opus-4-8":{"draws":11,"losses":26,"wins":13},"claude-opus-5":{"draws":10,"losses":51,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":6},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":18},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":21,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":8},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":13},"gpt-5.5":{"draws":11,"losses":21,"wins":10},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":15},"o3":{"draws":6,"losses":16,"wins":20},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":9},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":8,"losses":18,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":31,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":19}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":16,"wins":13},"claude-fable-5":{"draws":24,"losses":36,"wins":38},"claude-fable-5-1":{"draws":6,"losses":75,"wins":17},"claude-opus-4-5":{"draws":38,"losses":30,"wins":70},"claude-opus-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":72,"losses":38,"wins":98},"deepseek/deepseek-v4-flash":{"draws":34,"losses":13,"wins":27},"deepseek/deepseek-v4-pro":{"draws":26,"losses":17,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":18,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":29,"wins":42},"google/gemini-3.5-flash-lite":{"draws":111,"losses":57,"wins":190},"google/gemini-3.6-flash":{"draws":88,"losses":117,"wins":157},"google/gemini-3.8-flash":{"draws":23,"losses":30,"wins":43},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":52,"losses":76,"wins":76},"gpt-5.6-luna":{"draws":90,"losses":33,"wins":122},"gpt-5.6-sol":{"draws":50,"losses":105,"wins":79},"gpt-5.6-terra":{"draws":34,"losses":15,"wins":35},"gpt-6-astra":{"draws":8,"losses":64,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":23,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":9,"losses":12,"wins":29},"meituan/longcat-2.0":{"draws":30,"losses":15,"wins":58},"meta/muse-glimmer-30b":{"draws":21,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":34,"losses":53,"wins":81},"meta/muse-spark-1.3":{"draws":20,"losses":29,"wins":29},"moonshotai/kimi-k3":{"draws":55,"losses":48,"wins":107},"o3":{"draws":20,"losses":48,"wins":146},"openai/gpt-oss-120b":{"draws":27,"losses":10,"wins":15},"poolside/laguna-s-2.1":{"draws":47,"losses":6,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":32,"wins":26},"qwen/qwen3.8-27b":{"draws":13,"losses":9,"wins":20},"qwen/qwen3.8-flash":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-max":{"draws":34,"losses":28,"wins":30},"stealth/ox-alpha":{"draws":96,"losses":74,"wins":101},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":24},"tencent/hy4-preview":{"draws":25,"losses":27,"wins":34},"thinkingmachines/inkling":{"draws":30,"losses":24,"wins":68},"thinkingmachines/inkling-small":{"draws":46,"losses":10,"wins":17},"x-ai/grok-4.5":{"draws":33,"losses":49,"wins":68},"x-ai/grok-4.6":{"draws":32,"losses":24,"wins":44},"z-ai/glm-5.2":{"draws":27,"losses":14,"wins":37},"z-ai/glm-5.3":{"draws":12,"losses":35,"wins":37},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":29}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":25,"losses":27,"wins":18},"claude-opus-4-8":{"draws":18,"losses":17,"wins":15},"claude-opus-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":12},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":21},"google/gemini-3.5-flash-lite":{"draws":17,"losses":7,"wins":16},"google/gemini-3.6-flash":{"draws":13,"losses":23,"wins":9},"google/gemma-4-31b-it":{"draws":5,"losses":10,"wins":11},"gpt-4.1":{"draws":14,"losses":3,"wins":9},"gpt-5":{"draws":7,"losses":6,"wins":9},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":14,"losses":29,"wins":15},"gpt-5.5":{"draws":19,"losses":10,"wins":5},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":17},"minimax/minimax-m3":{"draws":16,"losses":12,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":10,"wins":7},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":9},"o3":{"draws":3,"losses":4,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":14,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":27,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"z-ai/glm-5.2":{"draws":30,"losses":17,"wins":7}},"gpt-5.4-nano":{"claude-opus-4-5":{"draws":24,"losses":33,"wins":33},"claude-opus-4-8":{"draws":13,"losses":36,"wins":17},"claude-opus-5":{"draws":14,"losses":54,"wins":12},"cohere/north-mini-code":{"draws":14,"losses":11,"wins":27},"deepseek/deepseek-v4-flash":{"draws":8,"losses":20,"wins":8},"google/gemini-3.1-flash-lite":{"draws":10,"losses":19,"wins":29},"google/gemini-3.5-flash-lite":{"draws":19,"losses":19,"wins":12},"google/gemini-3.6-flash":{"draws":18,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":3,"losses":13,"wins":22},"gpt-4.1":{"draws":5,"losses":9,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":8,"losses":13,"wins":15},"gpt-5.4-mini":{"draws":14,"losses":15,"wins":29},"gpt-5.4-nano":{"draws":12,"losses":30,"wins":30},"gpt-5.5":{"draws":16,"losses":28,"wins":18},"inclusionai/ling-3.0-flash":{"draws":20,"losses":9,"wins":19},"meituan/longcat-2.0":{"draws":18,"losses":21,"wins":31},"minimax/minimax-m3":{"draws":14,"losses":18,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":19,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":16,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":15,"wins":17},"o3":{"draws":6,"losses":13,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":20,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":22,"wins":15},"qwen/qwen3.7-plus":{"draws":12,"losses":25,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":12,"losses":12,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":17,"wins":13},"x-ai/grok-4.5":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.5":{"draws":42,"losses":58,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":24,"wins":19},"z-ai/glm-5.2":{"draws":14,"losses":19,"wins":17}},"gpt-5.5":{"claude-opus-4-5":{"draws":31,"losses":24,"wins":33},"claude-opus-4-8":{"draws":19,"losses":22,"wins":35},"claude-opus-5":{"draws":21,"losses":94,"wins":33},"cohere/north-mini-code":{"draws":14,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":15,"losses":0,"wins":13},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":22},"google/gemini-3.5-flash-lite":{"draws":30,"losses":6,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":26,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":11},"gpt-4.1":{"draws":10,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":18,"wins":28},"gpt-5.5":{"draws":16,"losses":16,"wins":16},"inclusionai/ling-3.0-flash":{"draws":27,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":12,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":5,"wins":23},"o3":{"draws":12,"losses":6,"wins":34},"poolside/laguna-s-2.1":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.7-max":{"draws":17,"losses":11,"wins":16},"qwen/qwen3.7-plus":{"draws":13,"losses":4,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":24,"losses":5,"wins":17},"thinkingmachines/inkling":{"draws":15,"losses":11,"wins":22},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":16},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":37,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":10},"z-ai/glm-5.2":{"draws":22,"losses":13,"wins":21}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":33,"wins":21},"claude-fable-5":{"draws":22,"losses":24,"wins":14},"claude-fable-5-1":{"draws":7,"losses":33,"wins":4},"claude-opus-4-5":{"draws":53,"losses":55,"wins":40},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":76,"losses":90,"wins":58},"deepseek/deepseek-v4-flash":{"draws":47,"losses":31,"wins":24},"deepseek/deepseek-v4-pro":{"draws":32,"losses":32,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":28,"wins":23},"google/gemini-3.5-flash":{"draws":35,"losses":23,"wins":24},"google/gemini-3.5-flash-lite":{"draws":141,"losses":127,"wins":160},"google/gemini-3.6-flash":{"draws":111,"losses":164,"wins":89},"google/gemini-3.8-flash":{"draws":22,"losses":25,"wins":19},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":90,"losses":122,"wins":33},"gpt-5.6-luna":{"draws":76,"losses":41,"wins":41},"gpt-5.6-sol":{"draws":33,"losses":130,"wins":37},"gpt-5.6-terra":{"draws":25,"losses":22,"wins":29},"gpt-6-astra":{"draws":5,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":6},"inception/mercury-2.5-preview":{"draws":29,"losses":17,"wins":22},"inclusionai/ling-3.0-flash":{"draws":20,"losses":19,"wins":17},"meituan/longcat-2.0":{"draws":36,"losses":35,"wins":51},"meta/muse-glimmer-30b":{"draws":47,"losses":28,"wins":23},"meta/muse-spark-1.2":{"draws":42,"losses":80,"wins":44},"meta/muse-spark-1.3":{"draws":18,"losses":28,"wins":18},"moonshotai/kimi-k3":{"draws":69,"losses":85,"wins":48},"o3":{"draws":34,"losses":95,"wins":89},"openai/gpt-oss-120b":{"draws":44,"losses":23,"wins":23},"poolside/laguna-s-2.1":{"draws":52,"losses":29,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":27,"wins":20},"qwen/qwen3.8-27b":{"draws":12,"losses":18,"wins":14},"qwen/qwen3.8-flash":{"draws":21,"losses":19,"wins":22},"qwen/qwen3.8-max":{"draws":35,"losses":35,"wins":18},"stealth/ox-alpha":{"draws":80,"losses":79,"wins":64},"stepfun/step-3.7-flash":{"draws":11,"losses":18,"wins":15},"tencent/hy4-preview":{"draws":29,"losses":27,"wins":18},"thinkingmachines/inkling":{"draws":54,"losses":32,"wins":60},"thinkingmachines/inkling-small":{"draws":45,"losses":34,"wins":29},"x-ai/grok-4.5":{"draws":43,"losses":57,"wins":52},"x-ai/grok-4.6":{"draws":22,"losses":25,"wins":15},"z-ai/glm-5.2":{"draws":36,"losses":32,"wins":16},"z-ai/glm-5.3":{"draws":13,"losses":28,"wins":13},"z-ai/glm-5.3-flash":{"draws":26,"losses":25,"wins":21}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":14,"wins":38},"claude-fable-5":{"draws":15,"losses":46,"wins":47},"claude-fable-5-1":{"draws":12,"losses":103,"wins":23},"claude-opus-4-5":{"draws":24,"losses":34,"wins":92},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":42,"losses":37,"wins":171},"deepseek/deepseek-v4-flash":{"draws":6,"losses":10,"wins":26},"deepseek/deepseek-v4-pro":{"draws":7,"losses":21,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":42},"google/gemini-3.5-flash":{"draws":10,"losses":30,"wins":46},"google/gemini-3.5-flash-lite":{"draws":47,"losses":31,"wins":250},"google/gemini-3.6-flash":{"draws":44,"losses":107,"wins":201},"google/gemini-3.8-flash":{"draws":15,"losses":42,"wins":53},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":50,"losses":79,"wins":105},"gpt-5.6-luna":{"draws":33,"losses":37,"wins":130},"gpt-5.6-sol":{"draws":28,"losses":84,"wins":84},"gpt-5.6-terra":{"draws":26,"losses":20,"wins":39},"gpt-6-astra":{"draws":13,"losses":92,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":34},"meituan/longcat-2.0":{"draws":21,"losses":13,"wins":78},"meta/muse-glimmer-30b":{"draws":4,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":19,"losses":37,"wins":124},"meta/muse-spark-1.3":{"draws":15,"losses":33,"wins":44},"moonshotai/kimi-k3":{"draws":44,"losses":43,"wins":127},"o3":{"draws":7,"losses":40,"wins":157},"openai/gpt-oss-120b":{"draws":13,"losses":4,"wins":23},"poolside/laguna-s-2.1":{"draws":25,"losses":1,"wins":76},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":25,"wins":40},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":26},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":31},"qwen/qwen3.8-max":{"draws":17,"losses":19,"wins":43},"stealth/ox-alpha":{"draws":41,"losses":85,"wins":165},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":22},"tencent/hy4-preview":{"draws":13,"losses":34,"wins":35},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":90},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":35},"x-ai/grok-4.5":{"draws":22,"losses":57,"wins":87},"x-ai/grok-4.6":{"draws":18,"losses":41,"wins":45},"z-ai/glm-5.2":{"draws":9,"losses":16,"wins":43},"z-ai/glm-5.3":{"draws":16,"losses":48,"wins":48},"z-ai/glm-5.3-flash":{"draws":16,"losses":37,"wins":35}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":16,"wins":36},"claude-fable-5":{"draws":23,"losses":43,"wins":20},"claude-fable-5-1":{"draws":7,"losses":60,"wins":3},"claude-opus-4-5":{"draws":19,"losses":27,"wins":14},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":32,"losses":26,"wins":24},"deepseek/deepseek-v4-flash":{"draws":29,"losses":19,"wins":22},"deepseek/deepseek-v4-pro":{"draws":26,"losses":31,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":22,"wins":21},"google/gemini-3.5-flash":{"draws":30,"losses":20,"wins":26},"google/gemini-3.5-flash-lite":{"draws":45,"losses":39,"wins":54},"google/gemini-3.6-flash":{"draws":38,"losses":38,"wins":40},"google/gemini-3.8-flash":{"draws":27,"losses":31,"wins":24},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5.4":{"draws":34,"losses":35,"wins":15},"gpt-5.6-luna":{"draws":25,"losses":29,"wins":22},"gpt-5.6-sol":{"draws":26,"losses":39,"wins":20},"gpt-5.6-terra":{"draws":20,"losses":20,"wins":20},"gpt-6-astra":{"draws":4,"losses":58,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":27,"losses":5,"wins":22},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":12},"meituan/longcat-2.0":{"draws":13,"losses":14,"wins":15},"meta/muse-glimmer-30b":{"draws":28,"losses":13,"wins":29},"meta/muse-spark-1.2":{"draws":22,"losses":24,"wins":20},"meta/muse-spark-1.3":{"draws":19,"losses":36,"wins":23},"moonshotai/kimi-k3":{"draws":28,"losses":34,"wins":24},"o3":{"draws":7,"losses":44,"wins":39},"openai/gpt-oss-120b":{"draws":35,"losses":11,"wins":34},"poolside/laguna-s-2.1":{"draws":21,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":40,"wins":22},"qwen/qwen3.8-27b":{"draws":12,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":18,"losses":12,"wins":12},"qwen/qwen3.8-max":{"draws":40,"losses":24,"wins":24},"stealth/ox-alpha":{"draws":81,"losses":82,"wins":77},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":20,"losses":26,"wins":22},"thinkingmachines/inkling":{"draws":14,"losses":8,"wins":22},"thinkingmachines/inkling-small":{"draws":29,"losses":18,"wins":35},"x-ai/grok-4.5":{"draws":17,"losses":36,"wins":17},"x-ai/grok-4.6":{"draws":34,"losses":47,"wins":21},"z-ai/glm-5.2":{"draws":43,"losses":11,"wins":32},"z-ai/glm-5.3":{"draws":26,"losses":38,"wins":10},"z-ai/glm-5.3-flash":{"draws":18,"losses":29,"wins":23}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":23},"claude-fable-5":{"draws":7,"losses":27,"wins":94},"claude-fable-5-1":{"draws":15,"losses":53,"wins":94},"claude-opus-4-5":{"draws":6,"losses":3,"wins":43},"claude-opus-5":{"draws":0,"losses":1,"wins":5},"claude-sonnet-5":{"draws":2,"losses":6,"wins":56},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":29},"deepseek/deepseek-v4-pro":{"draws":1,"losses":9,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":0,"wins":62},"google/gemini-3.5-flash":{"draws":13,"losses":4,"wins":69},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":48},"google/gemini-3.6-flash":{"draws":17,"losses":13,"wins":96},"google/gemini-3.8-flash":{"draws":14,"losses":8,"wins":98},"gpt-5.4":{"draws":8,"losses":16,"wins":64},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":33},"gpt-5.6-sol":{"draws":13,"losses":15,"wins":92},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":58},"gpt-6-astra":{"draws":8,"losses":44,"wins":44},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":20},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":1,"wins":62},"meta/muse-spark-1.3":{"draws":12,"losses":10,"wins":70},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":72},"o3":{"draws":1,"losses":1,"wins":52},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":73},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":44},"qwen/qwen3.8-flash":{"draws":9,"losses":2,"wins":39},"qwen/qwen3.8-max":{"draws":11,"losses":2,"wins":67},"stealth/ox-alpha":{"draws":46,"losses":21,"wins":216},"tencent/hy4-preview":{"draws":10,"losses":8,"wins":64},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":17},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":18},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":44},"x-ai/grok-4.6":{"draws":7,"losses":14,"wins":89},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":47},"z-ai/glm-5.3":{"draws":13,"losses":12,"wins":81},"z-ai/glm-5.3-flash":{"draws":16,"losses":6,"wins":68}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":7,"wins":0},"claude-fable-5":{"draws":4,"losses":0,"wins":0},"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":4,"losses":4,"wins":0},"deepseek/deepseek-v4-flash":{"draws":9,"losses":7,"wins":0},"deepseek/deepseek-v4-pro":{"draws":6,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":0},"google/gemini-3.5-flash-lite":{"draws":15,"losses":5,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":0},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":7,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":5,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":1},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"o3":{"draws":6,"losses":10,"wins":0},"openai/gpt-oss-120b":{"draws":10,"losses":8,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":5,"wins":0},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-max":{"draws":5,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":22,"losses":11,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":3,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":5,"wins":0},"thinkingmachines/inkling-small":{"draws":8,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":5,"wins":1},"z-ai/glm-5.3":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":21,"wins":23},"claude-fable-5":{"draws":18,"losses":8,"wins":2},"claude-fable-5-1":{"draws":1,"losses":17,"wins":0},"claude-opus-4-5":{"draws":14,"losses":15,"wins":3},"claude-sonnet-5":{"draws":21,"losses":34,"wins":5},"deepseek/deepseek-v4-flash":{"draws":28,"losses":33,"wins":5},"deepseek/deepseek-v4-pro":{"draws":29,"losses":16,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":20,"wins":9},"google/gemini-3.5-flash":{"draws":21,"losses":19,"wins":4},"google/gemini-3.5-flash-lite":{"draws":57,"losses":44,"wins":27},"google/gemini-3.6-flash":{"draws":36,"losses":37,"wins":11},"google/gemini-3.8-flash":{"draws":17,"losses":17,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":23,"losses":9,"wins":0},"gpt-5.6-luna":{"draws":29,"losses":22,"wins":17},"gpt-5.6-sol":{"draws":14,"losses":19,"wins":1},"gpt-5.6-terra":{"draws":27,"losses":22,"wins":5},"gpt-6-astra":{"draws":2,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":16,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":5},"meituan/longcat-2.0":{"draws":14,"losses":18,"wins":9},"meta/muse-glimmer-30b":{"draws":32,"losses":23,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":14,"losses":19,"wins":3},"moonshotai/kimi-k3":{"draws":23,"losses":21,"wins":6},"o3":{"draws":16,"losses":40,"wins":12},"openai/gpt-oss-120b":{"draws":31,"losses":26,"wins":17},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":22,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":19,"wins":3},"qwen/qwen3.8-flash":{"draws":22,"losses":12,"wins":6},"qwen/qwen3.8-max":{"draws":27,"losses":12,"wins":7},"stealth/ox-alpha":{"draws":48,"losses":54,"wins":27},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":22,"losses":21,"wins":7},"thinkingmachines/inkling":{"draws":26,"losses":14,"wins":8},"thinkingmachines/inkling-small":{"draws":34,"losses":30,"wins":22},"x-ai/grok-4.5":{"draws":17,"losses":17,"wins":2},"x-ai/grok-4.6":{"draws":14,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":28,"losses":26,"wins":8},"z-ai/glm-5.3":{"draws":19,"losses":5,"wins":2},"z-ai/glm-5.3-flash":{"draws":22,"losses":20,"wins":8}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":4},"claude-fable-5":{"draws":4,"losses":1,"wins":1},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":28,"losses":29,"wins":17},"claude-opus-4-8":{"draws":18,"losses":4,"wins":0},"claude-opus-5":{"draws":12,"losses":22,"wins":2},"claude-sonnet-5":{"draws":17,"losses":36,"wins":7},"cohere/north-mini-code":{"draws":18,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":15},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":5,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":13,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":79,"losses":91,"wins":38},"google/gemini-3.6-flash":{"draws":99,"losses":82,"wins":35},"google/gemini-3.8-flash":{"draws":2,"losses":7,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":19,"wins":5},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":8,"wins":1},"gpt-5":{"draws":6,"losses":6,"wins":8},"gpt-5.4":{"draws":9,"losses":29,"wins":12},"gpt-5.4-mini":{"draws":18,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":20,"losses":19,"wins":9},"gpt-5.5":{"draws":27,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":20,"losses":17,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":34,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":20,"losses":20,"wins":20},"meituan/longcat-2.0":{"draws":52,"losses":51,"wins":37},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":5},"meta/muse-spark-1.2":{"draws":15,"losses":12,"wins":11},"meta/muse-spark-1.3":{"draws":1,"losses":10,"wins":1},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":32,"losses":50,"wins":14},"nex-agi/nex-n2-pro":{"draws":20,"losses":12,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":5},"o3":{"draws":11,"losses":72,"wins":29},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":57,"losses":39,"wins":16},"qwen/qwen3.7-max":{"draws":21,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":12,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":10,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-max":{"draws":13,"losses":8,"wins":6},"stealth/ox-alpha":{"draws":14,"losses":22,"wins":12},"stepfun/step-3.7-flash":{"draws":4,"losses":22,"wins":10},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":45,"losses":42,"wins":37},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":8},"x-ai/grok-4.5":{"draws":30,"losses":67,"wins":13},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":30,"losses":24,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":8},"z-ai/glm-5.2":{"draws":23,"losses":8,"wins":11},"z-ai/glm-5.3":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":1}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":17,"wins":11},"claude-fable-5":{"draws":10,"losses":12,"wins":7},"claude-fable-5-1":{"draws":1,"losses":24,"wins":1},"claude-opus-4-5":{"draws":43,"losses":64,"wins":34},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":14,"losses":50,"wins":10},"claude-sonnet-5":{"draws":33,"losses":70,"wins":13},"cohere/north-mini-code":{"draws":22,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":20,"losses":32,"wins":14},"deepseek/deepseek-v4-pro":{"draws":12,"losses":24,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":23,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":16,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":5},"google/gemini-3.5-flash-lite":{"draws":89,"losses":132,"wins":124},"google/gemini-3.6-flash":{"draws":90,"losses":172,"wins":53},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":8},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":13},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":8,"losses":16,"wins":6},"gpt-5.4":{"draws":30,"losses":58,"wins":15},"gpt-5.4-mini":{"draws":21,"losses":17,"wins":10},"gpt-5.4-nano":{"draws":18,"losses":31,"wins":21},"gpt-5.5":{"draws":16,"losses":12,"wins":12},"gpt-5.6-luna":{"draws":36,"losses":51,"wins":35},"gpt-5.6-sol":{"draws":21,"losses":78,"wins":13},"gpt-5.6-terra":{"draws":13,"losses":15,"wins":14},"gpt-6-astra":{"draws":2,"losses":20,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":9,"wins":18},"inclusionai/ling-3.0-flash":{"draws":52,"losses":37,"wins":51},"meituan/longcat-2.0":{"draws":34,"losses":27,"wins":27},"meta/muse-glimmer-30b":{"draws":10,"losses":18,"wins":8},"meta/muse-spark-1.2":{"draws":21,"losses":31,"wins":28},"meta/muse-spark-1.3":{"draws":12,"losses":15,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":18,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":54,"losses":91,"wins":19},"nex-agi/nex-n2-pro":{"draws":11,"losses":13,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":18,"wins":9},"o3":{"draws":23,"losses":126,"wins":61},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":15},"poolside/laguna-s-2.1":{"draws":68,"losses":46,"wins":48},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":35,"losses":60,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":34,"wins":27},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":43,"losses":68,"wins":55},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":24},"x-ai/grok-4.5":{"draws":44,"losses":108,"wins":30},"x-ai/grok-4.6":{"draws":12,"losses":13,"wins":7},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":29,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":18,"wins":14},"z-ai/glm-5.2":{"draws":32,"losses":29,"wins":25},"z-ai/glm-5.3":{"draws":12,"losses":13,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":28,"wins":24},"claude-fable-5":{"draws":20,"losses":16,"wins":6},"claude-fable-5-1":{"draws":3,"losses":13,"wins":0},"claude-opus-4-5":{"draws":18,"losses":21,"wins":7},"claude-sonnet-5":{"draws":28,"losses":33,"wins":13},"deepseek/deepseek-v4-flash":{"draws":50,"losses":29,"wins":17},"deepseek/deepseek-v4-pro":{"draws":31,"losses":20,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":32,"wins":15},"google/gemini-3.5-flash":{"draws":28,"losses":24,"wins":16},"google/gemini-3.5-flash-lite":{"draws":71,"losses":63,"wins":34},"google/gemini-3.6-flash":{"draws":52,"losses":38,"wins":14},"google/gemini-3.8-flash":{"draws":21,"losses":8,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":21,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":47,"losses":23,"wins":28},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":6},"gpt-5.6-terra":{"draws":28,"losses":29,"wins":13},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":32,"losses":15,"wins":23},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":9},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":18},"meta/muse-glimmer-30b":{"draws":34,"losses":13,"wins":13},"meta/muse-spark-1.2":{"draws":8,"losses":20,"wins":12},"meta/muse-spark-1.3":{"draws":20,"losses":16,"wins":8},"moonshotai/kimi-k3":{"draws":21,"losses":12,"wins":11},"o3":{"draws":26,"losses":41,"wins":17},"openai/gpt-oss-120b":{"draws":45,"losses":29,"wins":22},"poolside/laguna-s-2.1":{"draws":30,"losses":18,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":26,"wins":8},"qwen/qwen3.8-27b":{"draws":16,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":14},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":20},"stealth/ox-alpha":{"draws":70,"losses":82,"wins":38},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":31,"losses":29,"wins":8},"thinkingmachines/inkling":{"draws":28,"losses":10,"wins":20},"thinkingmachines/inkling-small":{"draws":43,"losses":15,"wins":36},"x-ai/grok-4.5":{"draws":10,"losses":17,"wins":9},"x-ai/grok-4.6":{"draws":19,"losses":18,"wins":7},"z-ai/glm-5.2":{"draws":43,"losses":21,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":11,"wins":7},"z-ai/glm-5.3-flash":{"draws":29,"losses":20,"wins":11}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":18,"wins":21},"claude-fable-5":{"draws":14,"losses":33,"wins":15},"claude-fable-5-1":{"draws":5,"losses":68,"wins":7},"claude-opus-4-5":{"draws":27,"losses":31,"wins":50},"claude-opus-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":47,"losses":67,"wins":56},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":15},"deepseek/deepseek-v4-pro":{"draws":9,"losses":24,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":23,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":21,"wins":14},"google/gemini-3.5-flash-lite":{"draws":73,"losses":60,"wins":127},"google/gemini-3.6-flash":{"draws":47,"losses":99,"wins":120},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":22},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5.4":{"draws":34,"losses":81,"wins":53},"gpt-5.6-luna":{"draws":42,"losses":44,"wins":80},"gpt-5.6-sol":{"draws":19,"losses":124,"wins":37},"gpt-5.6-terra":{"draws":22,"losses":20,"wins":24},"gpt-6-astra":{"draws":5,"losses":62,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":16,"losses":6,"wins":22},"inclusionai/ling-3.0-flash":{"draws":15,"losses":11,"wins":12},"meituan/longcat-2.0":{"draws":21,"losses":28,"wins":31},"meta/muse-glimmer-30b":{"draws":8,"losses":12,"wins":20},"meta/muse-spark-1.2":{"draws":16,"losses":32,"wins":32},"meta/muse-spark-1.3":{"draws":14,"losses":25,"wins":17},"moonshotai/kimi-k3":{"draws":34,"losses":63,"wins":55},"o3":{"draws":8,"losses":80,"wins":56},"openai/gpt-oss-120b":{"draws":22,"losses":7,"wins":23},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":27,"wins":15},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":17,"losses":15,"wins":14},"qwen/qwen3.8-max":{"draws":19,"losses":23,"wins":15},"stealth/ox-alpha":{"draws":54,"losses":104,"wins":61},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":17},"tencent/hy4-preview":{"draws":12,"losses":28,"wins":16},"thinkingmachines/inkling":{"draws":32,"losses":12,"wins":54},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":32},"x-ai/grok-4.5":{"draws":25,"losses":61,"wins":26},"x-ai/grok-4.6":{"draws":13,"losses":37,"wins":18},"z-ai/glm-5.2":{"draws":9,"losses":16,"wins":25},"z-ai/glm-5.3":{"draws":8,"losses":33,"wins":13},"z-ai/glm-5.3-flash":{"draws":8,"losses":23,"wins":19}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":11,"wins":31},"claude-fable-5":{"draws":16,"losses":39,"wins":27},"claude-fable-5-1":{"draws":4,"losses":93,"wins":7},"claude-opus-4-5":{"draws":12,"losses":16,"wins":28},"claude-opus-5":{"draws":3,"losses":0,"wins":1},"claude-sonnet-5":{"draws":23,"losses":14,"wins":27},"deepseek/deepseek-v4-flash":{"draws":6,"losses":14,"wins":30},"deepseek/deepseek-v4-pro":{"draws":11,"losses":22,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":22,"wins":24},"google/gemini-3.5-flash":{"draws":20,"losses":22,"wins":38},"google/gemini-3.5-flash-lite":{"draws":30,"losses":29,"wins":51},"google/gemini-3.6-flash":{"draws":16,"losses":47,"wins":57},"google/gemini-3.8-flash":{"draws":10,"losses":28,"wins":40},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":20,"losses":29,"wins":29},"gpt-5.6-luna":{"draws":18,"losses":18,"wins":28},"gpt-5.6-sol":{"draws":15,"losses":44,"wins":33},"gpt-5.6-terra":{"draws":19,"losses":23,"wins":36},"gpt-6-astra":{"draws":12,"losses":70,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":5,"wins":15},"meta/muse-glimmer-30b":{"draws":20,"losses":8,"wins":16},"meta/muse-spark-1.2":{"draws":14,"losses":17,"wins":25},"meta/muse-spark-1.3":{"draws":4,"losses":16,"wins":16},"moonshotai/kimi-k3":{"draws":20,"losses":23,"wins":31},"o3":{"draws":6,"losses":23,"wins":25},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":26},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":31,"wins":29},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":17},"qwen/qwen3.8-flash":{"draws":22,"losses":14,"wins":22},"qwen/qwen3.8-max":{"draws":21,"losses":19,"wins":42},"stealth/ox-alpha":{"draws":62,"losses":96,"wins":93},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":4},"tencent/hy4-preview":{"draws":18,"losses":33,"wins":25},"thinkingmachines/inkling":{"draws":13,"losses":6,"wins":13},"thinkingmachines/inkling-small":{"draws":24,"losses":8,"wins":24},"x-ai/grok-4.5":{"draws":5,"losses":21,"wins":24},"x-ai/grok-4.6":{"draws":21,"losses":30,"wins":29},"z-ai/glm-5.2":{"draws":20,"losses":16,"wins":22},"z-ai/glm-5.3":{"draws":12,"losses":45,"wins":23},"z-ai/glm-5.3-flash":{"draws":22,"losses":36,"wins":22}},"minimax/minimax-m3":{"claude-opus-4-5":{"draws":11,"losses":28,"wins":7},"claude-opus-4-8":{"draws":11,"losses":19,"wins":4},"claude-opus-5":{"draws":3,"losses":33,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":12,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":13,"wins":10},"google/gemini-3.5-flash-lite":{"draws":9,"losses":11,"wins":6},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":7,"losses":11,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":14,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":30,"wins":18},"gpt-5.5":{"draws":9,"losses":21,"wins":10},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":16,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":9},"o3":{"draws":5,"losses":12,"wins":3},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":9},"qwen/qwen3.7-max":{"draws":13,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":26,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":14,"losses":10,"wins":6}},"moonshotai/kimi-k2.7-code":{"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":16,"wins":23},"claude-fable-5":{"draws":10,"losses":45,"wins":13},"claude-fable-5-1":{"draws":10,"losses":90,"wins":4},"claude-opus-4-5":{"draws":81,"losses":58,"wins":77},"claude-opus-4-8":{"draws":8,"losses":9,"wins":13},"claude-opus-5":{"draws":15,"losses":62,"wins":15},"claude-sonnet-5":{"draws":78,"losses":46,"wins":92},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":12,"losses":19,"wins":19},"deepseek/deepseek-v4-pro":{"draws":22,"losses":17,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":22,"wins":18},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":31,"losses":31,"wins":14},"google/gemini-3.5-flash-lite":{"draws":155,"losses":90,"wins":201},"google/gemini-3.6-flash":{"draws":122,"losses":174,"wins":144},"google/gemini-3.8-flash":{"draws":29,"losses":37,"wins":22},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":6,"losses":3,"wins":5},"gpt-5.4":{"draws":55,"losses":107,"wins":48},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":6,"wins":19},"gpt-5.5":{"draws":15,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":69,"losses":48,"wins":85},"gpt-5.6-sol":{"draws":44,"losses":127,"wins":43},"gpt-5.6-terra":{"draws":28,"losses":24,"wins":34},"gpt-6-astra":{"draws":11,"losses":72,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":23,"losses":6,"wins":21},"inclusionai/ling-3.0-flash":{"draws":32,"losses":14,"wins":50},"meituan/longcat-2.0":{"draws":54,"losses":19,"wins":91},"meta/muse-glimmer-30b":{"draws":21,"losses":11,"wins":12},"meta/muse-spark-1.2":{"draws":34,"losses":55,"wins":63},"meta/muse-spark-1.3":{"draws":20,"losses":31,"wins":23},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":80,"losses":52,"wins":52},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":4},"o3":{"draws":28,"losses":116,"wins":108},"openai/gpt-oss-120b":{"draws":24,"losses":11,"wins":21},"poolside/laguna-s-2.1":{"draws":70,"losses":14,"wins":72},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":28,"wins":31},"qwen/qwen3.8-27b":{"draws":10,"losses":16,"wins":16},"qwen/qwen3.8-flash":{"draws":21,"losses":13,"wins":16},"qwen/qwen3.8-max":{"draws":22,"losses":27,"wins":24},"stealth/ox-alpha":{"draws":72,"losses":115,"wins":82},"stepfun/step-3.7-flash":{"draws":12,"losses":8,"wins":34},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":11},"tencent/hy4-preview":{"draws":29,"losses":23,"wins":32},"thinkingmachines/inkling":{"draws":75,"losses":23,"wins":90},"thinkingmachines/inkling-small":{"draws":32,"losses":14,"wins":22},"x-ai/grok-4.5":{"draws":77,"losses":89,"wins":68},"x-ai/grok-4.6":{"draws":31,"losses":32,"wins":17},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":5},"z-ai/glm-5.2":{"draws":34,"losses":14,"wins":24},"z-ai/glm-5.3":{"draws":22,"losses":46,"wins":20},"z-ai/glm-5.3-flash":{"draws":27,"losses":34,"wins":11}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":9,"losses":20,"wins":7},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":0,"losses":15,"wins":1},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":13},"deepseek/deepseek-v4-flash":{"draws":8,"losses":9,"wins":13},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":15},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":8},"google/gemini-3.6-flash":{"draws":15,"losses":11,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":4,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":16},"gpt-5.5":{"draws":8,"losses":15,"wins":3},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":13,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":16,"wins":9},"o3":{"draws":2,"losses":11,"wins":3},"poolside/laguna-s-2.1":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":7},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":29,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":14,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":35,"losses":29,"wins":16},"claude-opus-4-8":{"draws":14,"losses":31,"wins":11},"claude-opus-5":{"draws":11,"losses":43,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":12,"wins":10},"google/gemini-3.1-flash-lite":{"draws":16,"losses":13,"wins":24},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":11},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":13,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-5":{"draws":17,"losses":15,"wins":6},"gpt-5.4-mini":{"draws":18,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":17,"wins":15},"gpt-5.5":{"draws":22,"losses":23,"wins":5},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":18},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":3},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":7},"o3":{"draws":18,"losses":30,"wins":10},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":18,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":24},"x-ai/grok-4.5":{"draws":10,"losses":15,"wins":1},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":46,"losses":23,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":3},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":11}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":22,"wins":41},"claude-fable-5":{"draws":5,"losses":40,"wins":13},"claude-fable-5-1":{"draws":0,"losses":47,"wins":5},"claude-opus-4-5":{"draws":40,"losses":161,"wins":69},"claude-opus-4-8":{"draws":4,"losses":34,"wins":6},"claude-opus-5":{"draws":2,"losses":80,"wins":6},"claude-sonnet-5":{"draws":18,"losses":111,"wins":93},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":45,"wins":36},"deepseek/deepseek-v4-pro":{"draws":14,"losses":35,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":41,"wins":23},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":11,"losses":38,"wins":19},"google/gemini-3.5-flash-lite":{"draws":94,"losses":191,"wins":313},"google/gemini-3.6-flash":{"draws":90,"losses":265,"wins":173},"google/gemini-3.8-flash":{"draws":7,"losses":35,"wins":24},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":7},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":12,"wins":6},"gpt-5":{"draws":6,"losses":20,"wins":16},"gpt-5.4":{"draws":20,"losses":146,"wins":48},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":13},"gpt-5.5":{"draws":12,"losses":34,"wins":6},"gpt-5.6-luna":{"draws":34,"losses":89,"wins":95},"gpt-5.6-sol":{"draws":7,"losses":157,"wins":40},"gpt-5.6-terra":{"draws":7,"losses":39,"wins":44},"gpt-6-astra":{"draws":1,"losses":52,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":16,"losses":12,"wins":40},"inclusionai/ling-3.0-flash":{"draws":11,"losses":29,"wins":72},"meituan/longcat-2.0":{"draws":23,"losses":61,"wins":126},"meta/muse-glimmer-30b":{"draws":26,"losses":17,"wins":41},"meta/muse-spark-1.2":{"draws":8,"losses":56,"wins":80},"meta/muse-spark-1.3":{"draws":6,"losses":25,"wins":23},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":28,"losses":108,"wins":116},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":30},"o3":{"draws":34,"losses":175,"wins":175},"openai/gpt-oss-120b":{"draws":15,"losses":23,"wins":44},"poolside/laguna-s-2.1":{"draws":46,"losses":45,"wins":61},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":37,"wins":31},"qwen/qwen3.8-27b":{"draws":11,"losses":30,"wins":17},"qwen/qwen3.8-flash":{"draws":17,"losses":20,"wins":21},"qwen/qwen3.8-max":{"draws":20,"losses":45,"wins":31},"stealth/ox-alpha":{"draws":28,"losses":94,"wins":104},"stepfun/step-3.7-flash":{"draws":21,"losses":35,"wins":70},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":39,"wins":24},"thinkingmachines/inkling":{"draws":55,"losses":50,"wins":114},"thinkingmachines/inkling-small":{"draws":32,"losses":32,"wins":43},"x-ai/grok-4.5":{"draws":18,"losses":125,"wins":65},"x-ai/grok-4.6":{"draws":13,"losses":34,"wins":25},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":25,"losses":34,"wins":53},"z-ai/glm-5.3":{"draws":6,"losses":39,"wins":17},"z-ai/glm-5.3-flash":{"draws":17,"losses":24,"wins":27}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":28,"wins":27},"claude-fable-5":{"draws":14,"losses":8,"wins":8},"claude-fable-5-1":{"draws":2,"losses":20,"wins":0},"claude-opus-4-5":{"draws":13,"losses":25,"wins":4},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":30,"losses":43,"wins":11},"deepseek/deepseek-v4-flash":{"draws":41,"losses":26,"wins":25},"deepseek/deepseek-v4-pro":{"draws":34,"losses":20,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":15,"wins":14},"google/gemini-3.5-flash":{"draws":28,"losses":15,"wins":19},"google/gemini-3.5-flash-lite":{"draws":61,"losses":53,"wins":46},"google/gemini-3.6-flash":{"draws":46,"losses":33,"wins":23},"google/gemini-3.8-flash":{"draws":11,"losses":20,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":27,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":44,"losses":23,"wins":23},"gpt-5.6-sol":{"draws":13,"losses":23,"wins":4},"gpt-5.6-terra":{"draws":35,"losses":34,"wins":11},"gpt-6-astra":{"draws":2,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":31,"losses":17,"wins":26},"inclusionai/ling-3.0-flash":{"draws":6,"losses":6,"wins":16},"meituan/longcat-2.0":{"draws":16,"losses":15,"wins":7},"meta/muse-glimmer-30b":{"draws":45,"losses":22,"wins":29},"meta/muse-spark-1.2":{"draws":22,"losses":23,"wins":7},"meta/muse-spark-1.3":{"draws":16,"losses":26,"wins":10},"moonshotai/kimi-k3":{"draws":24,"losses":21,"wins":11},"o3":{"draws":15,"losses":44,"wins":23},"openai/gpt-oss-120b":{"draws":28,"losses":18,"wins":18},"poolside/laguna-s-2.1":{"draws":33,"losses":10,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":31,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":13},"qwen/qwen3.8-flash":{"draws":22,"losses":17,"wins":15},"qwen/qwen3.8-max":{"draws":28,"losses":24,"wins":6},"stealth/ox-alpha":{"draws":60,"losses":87,"wins":36},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":27,"losses":20,"wins":11},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":19},"thinkingmachines/inkling-small":{"draws":52,"losses":20,"wins":38},"x-ai/grok-4.5":{"draws":20,"losses":20,"wins":6},"x-ai/grok-4.6":{"draws":19,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":22,"wins":25},"z-ai/glm-5.3":{"draws":23,"losses":9,"wins":4},"z-ai/glm-5.3-flash":{"draws":21,"losses":24,"wins":7}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":16,"wins":11},"claude-fable-5":{"draws":10,"losses":5,"wins":7},"claude-fable-5-1":{"draws":2,"losses":8,"wins":0},"claude-opus-4-5":{"draws":61,"losses":66,"wins":9},"claude-opus-4-8":{"draws":12,"losses":23,"wins":5},"claude-opus-5":{"draws":8,"losses":72,"wins":8},"claude-sonnet-5":{"draws":43,"losses":60,"wins":9},"cohere/north-mini-code":{"draws":21,"losses":15,"wins":2},"deepseek/deepseek-v4-flash":{"draws":40,"losses":17,"wins":19},"deepseek/deepseek-v4-pro":{"draws":19,"losses":15,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":9,"wins":12},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":22,"losses":11,"wins":9},"google/gemini-3.5-flash-lite":{"draws":163,"losses":96,"wins":113},"google/gemini-3.6-flash":{"draws":139,"losses":128,"wins":53},"google/gemini-3.8-flash":{"draws":6,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":11,"losses":6,"wins":9},"gpt-5.4":{"draws":47,"losses":43,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":15,"wins":7},"gpt-5.4-nano":{"draws":18,"losses":14,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":14},"gpt-5.6-luna":{"draws":52,"losses":39,"wins":29},"gpt-5.6-sol":{"draws":25,"losses":76,"wins":1},"gpt-5.6-terra":{"draws":21,"losses":16,"wins":3},"gpt-6-astra":{"draws":3,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":57,"losses":16,"wins":39},"meituan/longcat-2.0":{"draws":68,"losses":48,"wins":46},"meta/muse-glimmer-30b":{"draws":30,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":26,"losses":45,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":10,"wins":7},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":70,"losses":72,"wins":14},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":9},"o3":{"draws":46,"losses":61,"wins":45},"openai/gpt-oss-120b":{"draws":33,"losses":11,"wins":10},"poolside/laguna-s-2.1":{"draws":62,"losses":35,"wins":35},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":15,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":4},"qwen/qwen3.8-27b":{"draws":4,"losses":11,"wins":5},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":18,"losses":7,"wins":10},"stealth/ox-alpha":{"draws":46,"losses":38,"wins":20},"stepfun/step-3.7-flash":{"draws":10,"losses":24,"wins":10},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":20,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":67,"losses":45,"wins":62},"thinkingmachines/inkling-small":{"draws":28,"losses":8,"wins":25},"x-ai/grok-4.5":{"draws":55,"losses":92,"wins":29},"x-ai/grok-4.6":{"draws":15,"losses":17,"wins":2},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":19,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":47,"losses":17,"wins":22},"z-ai/glm-5.3":{"draws":15,"losses":5,"wins":4},"z-ai/glm-5.3-flash":{"draws":19,"losses":10,"wins":5}},"qwen/qwen3.7-max":{"claude-opus-4-5":{"draws":22,"losses":28,"wins":14},"claude-opus-4-8":{"draws":12,"losses":17,"wins":11},"claude-opus-5":{"draws":12,"losses":55,"wins":7},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":10},"google/gemini-3.5-flash-lite":{"draws":7,"losses":7,"wins":4},"google/gemini-3.6-flash":{"draws":6,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":14},"gpt-4.1":{"draws":7,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":17,"losses":15,"wins":22},"gpt-5.5":{"draws":17,"losses":16,"wins":11},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":18,"losses":4,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":7,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":10},"o3":{"draws":10,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":8},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":17},"z-ai/glm-5.2":{"draws":14,"losses":17,"wins":9}},"qwen/qwen3.7-plus":{"claude-opus-4-5":{"draws":23,"losses":18,"wins":11},"claude-opus-4-8":{"draws":12,"losses":20,"wins":6},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":11},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash-lite":{"draws":12,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":12,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":12,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":25},"gpt-5.5":{"draws":13,"losses":13,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":11,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":11,"wins":13},"o3":{"draws":3,"losses":6,"wins":5},"poolside/laguna-s-2.1":{"draws":15,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":8,"wins":13},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":25,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":3},"z-ai/glm-5.2":{"draws":13,"losses":15,"wins":6}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":20,"wins":26},"claude-fable-5":{"draws":22,"losses":35,"wins":23},"claude-fable-5-1":{"draws":13,"losses":72,"wins":7},"claude-opus-4-5":{"draws":24,"losses":19,"wins":17},"claude-opus-5":{"draws":1,"losses":2,"wins":1},"claude-sonnet-5":{"draws":37,"losses":22,"wins":29},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":31},"deepseek/deepseek-v4-pro":{"draws":23,"losses":19,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":25,"wins":26},"google/gemini-3.5-flash":{"draws":23,"losses":29,"wins":34},"google/gemini-3.5-flash-lite":{"draws":50,"losses":25,"wins":61},"google/gemini-3.6-flash":{"draws":41,"losses":44,"wins":45},"google/gemini-3.8-flash":{"draws":20,"losses":41,"wins":31},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.4":{"draws":18,"losses":26,"wins":32},"gpt-5.6-luna":{"draws":31,"losses":20,"wins":27},"gpt-5.6-sol":{"draws":19,"losses":40,"wins":25},"gpt-5.6-terra":{"draws":32,"losses":22,"wins":40},"gpt-6-astra":{"draws":7,"losses":73,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":19,"losses":7,"wins":22},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":12},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":23},"meta/muse-glimmer-30b":{"draws":24,"losses":8,"wins":26},"meta/muse-spark-1.2":{"draws":16,"losses":15,"wins":27},"meta/muse-spark-1.3":{"draws":26,"losses":29,"wins":31},"moonshotai/kimi-k3":{"draws":33,"losses":31,"wins":28},"o3":{"draws":12,"losses":31,"wins":37},"openai/gpt-oss-120b":{"draws":33,"losses":6,"wins":31},"poolside/laguna-s-2.1":{"draws":15,"losses":4,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-27b":{"draws":15,"losses":13,"wins":17},"qwen/qwen3.8-flash":{"draws":22,"losses":17,"wins":25},"qwen/qwen3.8-max":{"draws":32,"losses":25,"wins":27},"stealth/ox-alpha":{"draws":73,"losses":99,"wins":92},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":23,"losses":31,"wins":20},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":20},"thinkingmachines/inkling-small":{"draws":35,"losses":10,"wins":39},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":15},"x-ai/grok-4.6":{"draws":25,"losses":30,"wins":27},"z-ai/glm-5.2":{"draws":32,"losses":18,"wins":24},"z-ai/glm-5.3":{"draws":21,"losses":41,"wins":16},"z-ai/glm-5.3-flash":{"draws":18,"losses":26,"wins":22}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":19},"claude-fable-5":{"draws":8,"losses":19,"wins":13},"claude-fable-5-1":{"draws":3,"losses":46,"wins":1},"claude-opus-4-5":{"draws":8,"losses":14,"wins":12},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":14,"losses":17,"wins":11},"deepseek/deepseek-v4-flash":{"draws":9,"losses":17,"wins":16},"deepseek/deepseek-v4-pro":{"draws":9,"losses":17,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":11,"wins":16},"google/gemini-3.5-flash":{"draws":15,"losses":13,"wins":14},"google/gemini-3.5-flash-lite":{"draws":17,"losses":18,"wins":35},"google/gemini-3.6-flash":{"draws":17,"losses":29,"wins":14},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":13,"losses":20,"wins":9},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":26,"wins":14},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":9},"gpt-6-astra":{"draws":0,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":10},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":10},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":6,"losses":10,"wins":12},"meta/muse-spark-1.3":{"draws":6,"losses":17,"wins":15},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":16},"o3":{"draws":11,"losses":17,"wins":30},"openai/gpt-oss-120b":{"draws":8,"losses":13,"wins":17},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":13},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":12},"qwen/qwen3.8-max":{"draws":12,"losses":16,"wins":14},"stealth/ox-alpha":{"draws":36,"losses":59,"wins":48},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":11,"losses":7,"wins":10},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":32},"x-ai/grok-4.5":{"draws":1,"losses":14,"wins":11},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":13},"z-ai/glm-5.2":{"draws":15,"losses":15,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":9},"z-ai/glm-5.3-flash":{"draws":15,"losses":21,"wins":18}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":13,"wins":17},"claude-fable-5":{"draws":19,"losses":23,"wins":8},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-opus-4-5":{"draws":9,"losses":10,"wins":7},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":18,"losses":19,"wins":13},"deepseek/deepseek-v4-flash":{"draws":20,"losses":13,"wins":17},"deepseek/deepseek-v4-pro":{"draws":18,"losses":20,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":14,"wins":17},"google/gemini-3.5-flash":{"draws":18,"losses":23,"wins":15},"google/gemini-3.5-flash-lite":{"draws":42,"losses":18,"wins":34},"google/gemini-3.6-flash":{"draws":43,"losses":34,"wins":13},"google/gemini-3.8-flash":{"draws":16,"losses":25,"wins":15},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5.4":{"draws":17,"losses":18,"wins":13},"gpt-5.6-luna":{"draws":21,"losses":22,"wins":19},"gpt-5.6-sol":{"draws":13,"losses":31,"wins":9},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":12},"gpt-6-astra":{"draws":9,"losses":39,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":22,"losses":6,"wins":12},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":12,"losses":5,"wins":9},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":11},"meta/muse-spark-1.2":{"draws":17,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":22,"losses":22,"wins":14},"moonshotai/kimi-k3":{"draws":21,"losses":16,"wins":13},"o3":{"draws":17,"losses":21,"wins":20},"openai/gpt-oss-120b":{"draws":22,"losses":15,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":25,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":3,"wins":3},"qwen/qwen3.8-max":{"draws":30,"losses":16,"wins":16},"stealth/ox-alpha":{"draws":50,"losses":60,"wins":53},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":21},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":15},"thinkingmachines/inkling-small":{"draws":37,"losses":9,"wins":22},"x-ai/grok-4.5":{"draws":9,"losses":13,"wins":6},"x-ai/grok-4.6":{"draws":23,"losses":23,"wins":14},"z-ai/glm-5.2":{"draws":26,"losses":11,"wins":11},"z-ai/glm-5.3":{"draws":12,"losses":33,"wins":11},"z-ai/glm-5.3-flash":{"draws":21,"losses":13,"wins":20}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":26,"wins":16},"claude-fable-5":{"draws":14,"losses":33,"wins":25},"claude-fable-5-1":{"draws":6,"losses":75,"wins":5},"claude-opus-4-5":{"draws":16,"losses":15,"wins":32},"claude-opus-5":{"draws":1,"losses":2,"wins":1},"claude-sonnet-5":{"draws":19,"losses":31,"wins":33},"deepseek/deepseek-v4-flash":{"draws":27,"losses":19,"wins":24},"deepseek/deepseek-v4-pro":{"draws":22,"losses":20,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":26,"wins":27},"google/gemini-3.5-flash":{"draws":28,"losses":25,"wins":21},"google/gemini-3.5-flash-lite":{"draws":59,"losses":39,"wins":47},"google/gemini-3.6-flash":{"draws":47,"losses":50,"wins":46},"google/gemini-3.8-flash":{"draws":25,"losses":32,"wins":27},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":34,"losses":30,"wins":28},"gpt-5.6-luna":{"draws":35,"losses":18,"wins":35},"gpt-5.6-sol":{"draws":17,"losses":43,"wins":19},"gpt-5.6-terra":{"draws":40,"losses":24,"wins":24},"gpt-6-astra":{"draws":11,"losses":67,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":27,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":13,"losses":6,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":8,"wins":19},"meta/muse-glimmer-30b":{"draws":16,"losses":20,"wins":22},"meta/muse-spark-1.2":{"draws":19,"losses":15,"wins":23},"meta/muse-spark-1.3":{"draws":21,"losses":42,"wins":19},"moonshotai/kimi-k3":{"draws":22,"losses":24,"wins":27},"o3":{"draws":20,"losses":31,"wins":45},"openai/gpt-oss-120b":{"draws":28,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":27,"wins":25},"qwen/qwen3.8-27b":{"draws":12,"losses":14,"wins":16},"qwen/qwen3.8-flash":{"draws":30,"losses":16,"wins":16},"qwen/qwen3.8-max":{"draws":48,"losses":48,"wins":48},"stealth/ox-alpha":{"draws":77,"losses":98,"wins":79},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":23,"losses":37,"wins":26},"thinkingmachines/inkling":{"draws":13,"losses":10,"wins":15},"thinkingmachines/inkling-small":{"draws":82,"losses":57,"wins":78},"x-ai/grok-4.5":{"draws":23,"losses":29,"wins":24},"x-ai/grok-4.6":{"draws":23,"losses":36,"wins":23},"z-ai/glm-5.2":{"draws":31,"losses":20,"wins":23},"z-ai/glm-5.3":{"draws":17,"losses":42,"wins":17},"z-ai/glm-5.3-flash":{"draws":25,"losses":21,"wins":26}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":54,"wins":97},"claude-fable-5":{"draws":78,"losses":141,"wins":67},"claude-fable-5-1":{"draws":41,"losses":266,"wins":23},"claude-opus-4-5":{"draws":63,"losses":61,"wins":73},"claude-opus-5":{"draws":4,"losses":5,"wins":3},"claude-sonnet-5":{"draws":71,"losses":90,"wins":118},"deepseek/deepseek-v4-flash":{"draws":83,"losses":54,"wins":71},"deepseek/deepseek-v4-pro":{"draws":62,"losses":71,"wins":75},"deepseek/deepseek-v4-pro-0813":{"draws":73,"losses":83,"wins":92},"google/gemini-3.5-flash":{"draws":71,"losses":83,"wins":95},"google/gemini-3.5-flash-lite":{"draws":112,"losses":98,"wins":149},"google/gemini-3.6-flash":{"draws":104,"losses":147,"wins":151},"google/gemini-3.8-flash":{"draws":72,"losses":122,"wins":106},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5.4":{"draws":96,"losses":101,"wins":74},"gpt-5.6-luna":{"draws":80,"losses":64,"wins":79},"gpt-5.6-sol":{"draws":41,"losses":165,"wins":85},"gpt-5.6-terra":{"draws":81,"losses":77,"wins":82},"gpt-6-astra":{"draws":46,"losses":216,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":22,"losses":1,"wins":11},"inception/mercury-2.5-preview":{"draws":48,"losses":27,"wins":54},"inclusionai/ling-3.0-flash":{"draws":14,"losses":12,"wins":22},"meituan/longcat-2.0":{"draws":35,"losses":21,"wins":60},"meta/muse-glimmer-30b":{"draws":70,"losses":38,"wins":82},"meta/muse-spark-1.2":{"draws":54,"losses":61,"wins":104},"meta/muse-spark-1.3":{"draws":62,"losses":93,"wins":96},"moonshotai/kimi-k3":{"draws":72,"losses":82,"wins":115},"o3":{"draws":28,"losses":104,"wins":94},"openai/gpt-oss-120b":{"draws":60,"losses":36,"wins":87},"poolside/laguna-s-2.1":{"draws":46,"losses":20,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":73,"losses":92,"wins":99},"qwen/qwen3.8-27b":{"draws":36,"losses":48,"wins":59},"qwen/qwen3.8-flash":{"draws":50,"losses":53,"wins":60},"qwen/qwen3.8-max":{"draws":77,"losses":79,"wins":98},"stealth/ox-alpha":{"draws":312,"losses":540,"wins":540},"stepfun/step-3.7-flash":{"draws":5,"losses":12,"wins":13},"tencent/hy4-preview":{"draws":74,"losses":101,"wins":77},"thinkingmachines/inkling":{"draws":40,"losses":28,"wins":77},"thinkingmachines/inkling-small":{"draws":91,"losses":45,"wins":97},"x-ai/grok-4.5":{"draws":43,"losses":82,"wins":51},"x-ai/grok-4.6":{"draws":79,"losses":113,"wins":90},"z-ai/glm-5.2":{"draws":78,"losses":52,"wins":108},"z-ai/glm-5.3":{"draws":61,"losses":116,"wins":70},"z-ai/glm-5.3-flash":{"draws":72,"losses":99,"wins":110}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":4,"wins":12},"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":18,"losses":52,"wins":18},"claude-opus-4-8":{"draws":7,"losses":21,"wins":8},"claude-opus-5":{"draws":5,"losses":28,"wins":1},"claude-sonnet-5":{"draws":6,"losses":17,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":7,"losses":13,"wins":18},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":29,"losses":47,"wins":56},"google/gemini-3.6-flash":{"draws":16,"losses":62,"wins":13},"google/gemini-3.8-flash":{"draws":2,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":13},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":8,"losses":14,"wins":0},"gpt-5.4":{"draws":6,"losses":24,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":10},"gpt-5.5":{"draws":6,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":18},"gpt-5.6-sol":{"draws":1,"losses":22,"wins":7},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":10,"wins":22},"meituan/longcat-2.0":{"draws":9,"losses":27,"wins":34},"meta/muse-glimmer-30b":{"draws":6,"losses":8,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":17,"wins":5},"meta/muse-spark-1.3":{"draws":3,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":34,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":10},"o3":{"draws":21,"losses":70,"wins":35},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":10,"wins":24},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.8-max":{"draws":1,"losses":8,"wins":3},"stealth/ox-alpha":{"draws":5,"losses":13,"wins":12},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":4,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":24,"wins":38},"thinkingmachines/inkling-small":{"draws":4,"losses":5,"wins":11},"x-ai/grok-4.5":{"draws":7,"losses":31,"wins":10},"x-ai/grok-4.6":{"draws":1,"losses":4,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":8},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":4,"wins":4}},"tencent/hy3-preview":{"claude-opus-4-5":{"draws":17,"losses":19,"wins":8},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":48,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":10,"losses":7,"wins":9},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":10},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":11,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":7},"gpt-4.1":{"draws":11,"losses":6,"wins":3},"gpt-5":{"draws":5,"losses":9,"wins":8},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":2,"wins":12},"gpt-5.5":{"draws":24,"losses":17,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":11,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":14},"o3":{"draws":10,"losses":12,"wins":14},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":11,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":20,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":16,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":19,"losses":8,"wins":9}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":8,"wins":31},"claude-fable-5":{"draws":17,"losses":42,"wins":23},"claude-fable-5-1":{"draws":3,"losses":72,"wins":13},"claude-opus-4-5":{"draws":19,"losses":16,"wins":21},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":32,"losses":19,"wins":37},"deepseek/deepseek-v4-flash":{"draws":20,"losses":22,"wins":28},"deepseek/deepseek-v4-pro":{"draws":29,"losses":24,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":27,"wins":38},"google/gemini-3.5-flash":{"draws":20,"losses":20,"wins":48},"google/gemini-3.5-flash-lite":{"draws":53,"losses":30,"wins":51},"google/gemini-3.6-flash":{"draws":35,"losses":45,"wins":56},"google/gemini-3.8-flash":{"draws":19,"losses":31,"wins":36},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5.4":{"draws":25,"losses":34,"wins":27},"gpt-5.6-luna":{"draws":29,"losses":18,"wins":27},"gpt-5.6-sol":{"draws":13,"losses":35,"wins":34},"gpt-5.6-terra":{"draws":20,"losses":22,"wins":26},"gpt-6-astra":{"draws":10,"losses":64,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":22,"losses":7,"wins":21},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":21},"meta/muse-glimmer-30b":{"draws":31,"losses":8,"wins":29},"meta/muse-spark-1.2":{"draws":12,"losses":16,"wins":28},"meta/muse-spark-1.3":{"draws":18,"losses":25,"wins":33},"moonshotai/kimi-k3":{"draws":29,"losses":32,"wins":23},"o3":{"draws":15,"losses":24,"wins":39},"openai/gpt-oss-120b":{"draws":27,"losses":11,"wins":20},"poolside/laguna-s-2.1":{"draws":20,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":20,"wins":31},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":22},"qwen/qwen3.8-flash":{"draws":14,"losses":21,"wins":21},"qwen/qwen3.8-max":{"draws":23,"losses":26,"wins":37},"stealth/ox-alpha":{"draws":74,"losses":77,"wins":101},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":15,"wins":15},"thinkingmachines/inkling":{"draws":17,"losses":7,"wins":18},"thinkingmachines/inkling-small":{"draws":30,"losses":13,"wins":29},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":22},"x-ai/grok-4.6":{"draws":22,"losses":29,"wins":27},"z-ai/glm-5.2":{"draws":28,"losses":17,"wins":33},"z-ai/glm-5.3":{"draws":13,"losses":55,"wins":16},"z-ai/glm-5.3-flash":{"draws":22,"losses":32,"wins":24}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":28,"wins":16},"claude-fable-5":{"draws":9,"losses":15,"wins":0},"claude-fable-5-1":{"draws":4,"losses":16,"wins":0},"claude-opus-4-5":{"draws":48,"losses":91,"wins":21},"claude-opus-4-8":{"draws":8,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":56,"wins":11},"claude-sonnet-5":{"draws":47,"losses":75,"wins":16},"cohere/north-mini-code":{"draws":9,"losses":16,"wins":11},"deepseek/deepseek-v4-flash":{"draws":28,"losses":24,"wins":30},"deepseek/deepseek-v4-pro":{"draws":25,"losses":20,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":17,"wins":15},"google/gemini-3.1-flash-lite":{"draws":11,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":21,"losses":12,"wins":11},"google/gemini-3.5-flash-lite":{"draws":149,"losses":158,"wins":105},"google/gemini-3.6-flash":{"draws":144,"losses":172,"wins":52},"google/gemini-3.8-flash":{"draws":14,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":14,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":12,"wins":0},"gpt-5":{"draws":12,"losses":13,"wins":5},"gpt-5.4":{"draws":30,"losses":68,"wins":24},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":17},"gpt-5.5":{"draws":15,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":54,"losses":60,"wins":32},"gpt-5.6-sol":{"draws":18,"losses":90,"wins":10},"gpt-5.6-terra":{"draws":14,"losses":22,"wins":8},"gpt-6-astra":{"draws":3,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":26,"losses":8,"wins":14},"inclusionai/ling-3.0-flash":{"draws":45,"losses":37,"wins":42},"meituan/longcat-2.0":{"draws":43,"losses":55,"wins":68},"meta/muse-glimmer-30b":{"draws":28,"losses":20,"wins":10},"meta/muse-spark-1.2":{"draws":32,"losses":54,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":13,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":14,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":75,"losses":90,"wins":23},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":24,"wins":15},"o3":{"draws":55,"losses":114,"wins":50},"openai/gpt-oss-120b":{"draws":24,"losses":19,"wins":15},"poolside/laguna-s-2.1":{"draws":67,"losses":62,"wins":45},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":13,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":20,"wins":8},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":7},"qwen/qwen3.8-flash":{"draws":19,"losses":15,"wins":10},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":10},"stealth/ox-alpha":{"draws":40,"losses":77,"wins":28},"stepfun/step-3.7-flash":{"draws":18,"losses":38,"wins":24},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":17,"losses":18,"wins":7},"thinkingmachines/inkling":{"draws":28,"losses":34,"wins":34},"thinkingmachines/inkling-small":{"draws":28,"losses":14,"wins":24},"x-ai/grok-4.5":{"draws":50,"losses":75,"wins":25},"x-ai/grok-4.6":{"draws":14,"losses":7,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":42,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":31,"losses":26,"wins":25},"z-ai/glm-5.3":{"draws":11,"losses":18,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":18,"wins":11}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":42,"wins":23},"claude-fable-5":{"draws":13,"losses":22,"wins":11},"claude-fable-5-1":{"draws":5,"losses":28,"wins":1},"claude-opus-4-5":{"draws":23,"losses":26,"wins":12},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":25,"losses":45,"wins":18},"deepseek/deepseek-v4-flash":{"draws":39,"losses":45,"wins":18},"deepseek/deepseek-v4-pro":{"draws":47,"losses":35,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":38,"wins":17},"google/gemini-3.5-flash":{"draws":22,"losses":24,"wins":16},"google/gemini-3.5-flash-lite":{"draws":68,"losses":71,"wins":61},"google/gemini-3.6-flash":{"draws":53,"losses":45,"wins":36},"google/gemini-3.8-flash":{"draws":20,"losses":17,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":46,"losses":17,"wins":10},"gpt-5.6-luna":{"draws":45,"losses":29,"wins":34},"gpt-5.6-sol":{"draws":10,"losses":35,"wins":10},"gpt-5.6-terra":{"draws":29,"losses":35,"wins":18},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":34,"losses":22,"wins":30},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":13,"losses":24,"wins":14},"meta/muse-glimmer-30b":{"draws":43,"losses":36,"wins":15},"meta/muse-spark-1.2":{"draws":20,"losses":32,"wins":14},"meta/muse-spark-1.3":{"draws":24,"losses":24,"wins":8},"moonshotai/kimi-k3":{"draws":32,"losses":22,"wins":14},"o3":{"draws":32,"losses":43,"wins":32},"openai/gpt-oss-120b":{"draws":52,"losses":38,"wins":20},"poolside/laguna-s-2.1":{"draws":28,"losses":25,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":39,"wins":10},"qwen/qwen3.8-27b":{"draws":11,"losses":32,"wins":7},"qwen/qwen3.8-flash":{"draws":37,"losses":22,"wins":9},"qwen/qwen3.8-max":{"draws":82,"losses":78,"wins":57},"stealth/ox-alpha":{"draws":91,"losses":97,"wins":45},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":30,"losses":29,"wins":13},"thinkingmachines/inkling":{"draws":28,"losses":24,"wins":14},"thinkingmachines/inkling-small":{"draws":64,"losses":52,"wins":52},"x-ai/grok-4.5":{"draws":17,"losses":29,"wins":13},"x-ai/grok-4.6":{"draws":30,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":38,"losses":28,"wins":28},"z-ai/glm-5.3":{"draws":12,"losses":15,"wins":11},"z-ai/glm-5.3-flash":{"draws":32,"losses":25,"wins":19}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":9,"wins":25},"claude-fable-5":{"draws":9,"losses":29,"wins":26},"claude-fable-5-1":{"draws":0,"losses":58,"wins":8},"claude-opus-4-5":{"draws":64,"losses":53,"wins":87},"claude-opus-4-8":{"draws":15,"losses":19,"wins":20},"claude-opus-5":{"draws":18,"losses":87,"wins":23},"claude-sonnet-5":{"draws":51,"losses":31,"wins":72},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":16,"losses":16,"wins":22},"google/gemini-3.5-flash-lite":{"draws":102,"losses":85,"wins":203},"google/gemini-3.6-flash":{"draws":76,"losses":161,"wins":155},"google/gemini-3.8-flash":{"draws":10,"losses":13,"wins":25},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":10},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":6,"wins":18},"gpt-5.4":{"draws":33,"losses":68,"wins":49},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":14},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":23},"gpt-5.5":{"draws":14,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":43,"losses":52,"wins":57},"gpt-5.6-sol":{"draws":22,"losses":87,"wins":57},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":36},"gpt-6-astra":{"draws":1,"losses":44,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":17,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":30,"losses":13,"wins":67},"meituan/longcat-2.0":{"draws":44,"losses":30,"wins":108},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":25,"losses":26,"wins":61},"meta/muse-spark-1.3":{"draws":5,"losses":24,"wins":21},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":77,"losses":68,"wins":89},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":15},"o3":{"draws":18,"losses":65,"wins":125},"openai/gpt-oss-120b":{"draws":20,"losses":6,"wins":20},"poolside/laguna-s-2.1":{"draws":55,"losses":29,"wins":92},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":1,"losses":11,"wins":14},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.8-max":{"draws":23,"losses":24,"wins":29},"stealth/ox-alpha":{"draws":43,"losses":51,"wins":82},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":31},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":20},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":20},"thinkingmachines/inkling":{"draws":50,"losses":25,"wins":75},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":29},"x-ai/grok-4.5":{"draws":38,"losses":41,"wins":41},"x-ai/grok-4.6":{"draws":18,"losses":24,"wins":22},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":10},"z-ai/glm-5.2":{"draws":24,"losses":11,"wins":29},"z-ai/glm-5.3":{"draws":14,"losses":33,"wins":17},"z-ai/glm-5.3-flash":{"draws":12,"losses":20,"wins":14}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":10,"wins":27},"claude-fable-5":{"draws":28,"losses":47,"wins":37},"claude-fable-5-1":{"draws":6,"losses":97,"wins":21},"claude-opus-4-5":{"draws":19,"losses":10,"wins":27},"claude-opus-5":{"draws":0,"losses":0,"wins":4},"claude-sonnet-5":{"draws":17,"losses":27,"wins":28},"deepseek/deepseek-v4-flash":{"draws":24,"losses":10,"wins":22},"deepseek/deepseek-v4-pro":{"draws":19,"losses":20,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":27,"wins":25},"google/gemini-3.5-flash":{"draws":25,"losses":20,"wins":43},"google/gemini-3.5-flash-lite":{"draws":43,"losses":23,"wins":50},"google/gemini-3.6-flash":{"draws":30,"losses":49,"wins":43},"google/gemini-3.8-flash":{"draws":27,"losses":31,"wins":38},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":32,"losses":44,"wins":24},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":25},"gpt-5.6-sol":{"draws":18,"losses":45,"wins":41},"gpt-5.6-terra":{"draws":34,"losses":21,"wins":47},"gpt-6-astra":{"draws":7,"losses":89,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":14,"losses":10,"wins":12},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":13},"meta/muse-glimmer-30b":{"draws":19,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":18,"wins":37},"meta/muse-spark-1.3":{"draws":21,"losses":29,"wins":30},"moonshotai/kimi-k3":{"draws":31,"losses":17,"wins":32},"o3":{"draws":13,"losses":25,"wins":34},"openai/gpt-oss-120b":{"draws":19,"losses":11,"wins":16},"poolside/laguna-s-2.1":{"draws":15,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":27,"wins":30},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":17},"qwen/qwen3.8-flash":{"draws":23,"losses":14,"wins":23},"qwen/qwen3.8-max":{"draws":23,"losses":23,"wins":36},"stealth/ox-alpha":{"draws":79,"losses":90,"wins":113},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":22,"losses":27,"wins":29},"thinkingmachines/inkling":{"draws":14,"losses":3,"wins":7},"thinkingmachines/inkling-small":{"draws":30,"losses":12,"wins":14},"x-ai/grok-4.5":{"draws":18,"losses":22,"wins":24},"x-ai/grok-4.6":{"draws":20,"losses":20,"wins":20},"z-ai/glm-5.2":{"draws":28,"losses":16,"wins":30},"z-ai/glm-5.3":{"draws":17,"losses":52,"wins":31},"z-ai/glm-5.3-flash":{"draws":16,"losses":38,"wins":28}},"x-ai/grok-build-0.1":{"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":6,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":62,"losses":55,"wins":33},"claude-opus-4-8":{"draws":38,"losses":46,"wins":12},"claude-opus-5":{"draws":9,"losses":50,"wins":3},"cohere/north-mini-code":{"draws":27,"losses":15,"wins":24},"deepseek/deepseek-v4-flash":{"draws":26,"losses":13,"wins":35},"google/gemini-3.1-flash-lite":{"draws":35,"losses":25,"wins":42},"google/gemini-3.5-flash-lite":{"draws":11,"losses":12,"wins":17},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":11},"google/gemma-4-31b-it":{"draws":17,"losses":27,"wins":26},"gpt-4.1":{"draws":13,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":31,"losses":23,"wins":18},"gpt-5.4-mini":{"draws":39,"losses":28,"wins":27},"gpt-5.4-nano":{"draws":42,"losses":60,"wins":58},"gpt-5.5":{"draws":37,"losses":33,"wins":10},"inclusionai/ling-3.0-flash":{"draws":30,"losses":16,"wins":24},"meituan/longcat-2.0":{"draws":23,"losses":32,"wins":29},"minimax/minimax-m3":{"draws":28,"losses":30,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":22,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":9},"nex-agi/nex-n2-pro":{"draws":18,"losses":19,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":31,"wins":23},"o3":{"draws":12,"losses":24,"wins":4},"poolside/laguna-s-2.1":{"draws":23,"losses":24,"wins":19},"qwen/qwen3.7-max":{"draws":28,"losses":31,"wins":19},"qwen/qwen3.7-plus":{"draws":23,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":28,"losses":15,"wins":15},"tencent/hy3-preview":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":42},"x-ai/grok-4.5":{"draws":16,"losses":23,"wins":5},"x-ai/grok-build-0.1":{"draws":24,"losses":18,"wins":10},"xiaomi/mimo-v2.5":{"draws":76,"losses":56,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":30,"wins":22},"z-ai/glm-5.2":{"draws":32,"losses":46,"wins":26}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":7,"losses":21,"wins":18},"claude-opus-4-8":{"draws":9,"losses":16,"wins":7},"claude-opus-5":{"draws":8,"losses":35,"wins":1},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":12},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":2,"losses":11,"wins":5},"gpt-5":{"draws":5,"losses":8,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":24},"gpt-5.5":{"draws":8,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":8,"wins":11},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":18},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":10},"o3":{"draws":4,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":6,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":30},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":10}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":24,"wins":23},"claude-fable-5":{"draws":25,"losses":30,"wins":17},"claude-fable-5-1":{"draws":9,"losses":53,"wins":2},"claude-opus-4-5":{"draws":36,"losses":66,"wins":52},"claude-opus-4-8":{"draws":23,"losses":25,"wins":16},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-sonnet-5":{"draws":33,"losses":31,"wins":28},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":43,"losses":27,"wins":48},"deepseek/deepseek-v4-pro":{"draws":30,"losses":20,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":30,"wins":13},"google/gemini-3.1-flash-lite":{"draws":11,"losses":8,"wins":21},"google/gemini-3.5-flash":{"draws":26,"losses":25,"wins":25},"google/gemini-3.5-flash-lite":{"draws":67,"losses":42,"wins":49},"google/gemini-3.6-flash":{"draws":54,"losses":52,"wins":36},"google/gemini-3.8-flash":{"draws":21,"losses":27,"wins":20},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":3},"gpt-4.1":{"draws":12,"losses":8,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":14,"losses":19,"wins":17},"gpt-5.4":{"draws":27,"losses":37,"wins":14},"gpt-5.4-mini":{"draws":30,"losses":7,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":19},"gpt-5.5":{"draws":22,"losses":21,"wins":13},"gpt-5.6-luna":{"draws":36,"losses":16,"wins":32},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":16},"gpt-5.6-terra":{"draws":43,"losses":32,"wins":11},"gpt-6-astra":{"draws":8,"losses":47,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":1,"wins":5},"inception/mercury-2.5-preview":{"draws":28,"losses":8,"wins":26},"inclusionai/ling-3.0-flash":{"draws":23,"losses":11,"wins":8},"meituan/longcat-2.0":{"draws":32,"losses":25,"wins":29},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":25,"wins":16},"meta/muse-spark-1.3":{"draws":20,"losses":22,"wins":16},"minimax/minimax-m3":{"draws":14,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":10},"moonshotai/kimi-k3":{"draws":34,"losses":24,"wins":14},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":11},"o3":{"draws":25,"losses":53,"wins":34},"openai/gpt-oss-120b":{"draws":37,"losses":25,"wins":22},"poolside/laguna-s-2.1":{"draws":47,"losses":22,"wins":17},"qwen/qwen3.7-max":{"draws":14,"losses":9,"wins":17},"qwen/qwen3.7-plus":{"draws":13,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":24,"wins":18},"qwen/qwen3.8-27b":{"draws":15,"losses":18,"wins":15},"qwen/qwen3.8-flash":{"draws":26,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":31,"losses":23,"wins":20},"stealth/ox-alpha":{"draws":78,"losses":108,"wins":52},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":9},"tencent/hy3-preview":{"draws":19,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":28,"losses":33,"wins":17},"thinkingmachines/inkling":{"draws":31,"losses":25,"wins":26},"thinkingmachines/inkling-small":{"draws":38,"losses":28,"wins":28},"x-ai/grok-4.5":{"draws":24,"losses":29,"wins":11},"x-ai/grok-4.6":{"draws":28,"losses":30,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":26,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":12},"z-ai/glm-5.2":{"draws":52,"losses":42,"wins":42},"z-ai/glm-5.3":{"draws":19,"losses":30,"wins":15},"z-ai/glm-5.3-flash":{"draws":36,"losses":38,"wins":14}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":19},"claude-fable-5":{"draws":14,"losses":39,"wins":59},"claude-fable-5-1":{"draws":8,"losses":84,"wins":28},"claude-opus-4-5":{"draws":13,"losses":9,"wins":24},"claude-opus-5":{"draws":1,"losses":1,"wins":2},"claude-sonnet-5":{"draws":11,"losses":12,"wins":49},"deepseek/deepseek-v4-flash":{"draws":18,"losses":2,"wins":30},"deepseek/deepseek-v4-pro":{"draws":14,"losses":15,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":37},"google/gemini-3.5-flash":{"draws":16,"losses":20,"wins":44},"google/gemini-3.5-flash-lite":{"draws":25,"losses":10,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":32,"wins":74},"google/gemini-3.8-flash":{"draws":14,"losses":22,"wins":60},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":12,"losses":37,"wins":35},"gpt-5.6-luna":{"draws":13,"losses":13,"wins":28},"gpt-5.6-sol":{"draws":16,"losses":48,"wins":48},"gpt-5.6-terra":{"draws":26,"losses":10,"wins":38},"gpt-6-astra":{"draws":13,"losses":81,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":19,"losses":2,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":5,"wins":13},"meta/muse-glimmer-30b":{"draws":6,"losses":7,"wins":11},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":33},"meta/muse-spark-1.3":{"draws":12,"losses":23,"wins":45},"moonshotai/kimi-k3":{"draws":22,"losses":20,"wins":46},"o3":{"draws":6,"losses":17,"wins":39},"openai/gpt-oss-120b":{"draws":23,"losses":4,"wins":9},"poolside/laguna-s-2.1":{"draws":15,"losses":4,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":16,"wins":41},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":23},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":33},"qwen/qwen3.8-max":{"draws":17,"losses":17,"wins":42},"stealth/ox-alpha":{"draws":61,"losses":70,"wins":116},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":55},"thinkingmachines/inkling":{"draws":11,"losses":1,"wins":18},"thinkingmachines/inkling-small":{"draws":12,"losses":11,"wins":15},"x-ai/grok-4.5":{"draws":14,"losses":17,"wins":33},"x-ai/grok-4.6":{"draws":17,"losses":31,"wins":52},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":30},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":27},"z-ai/glm-5.3-flash":{"draws":15,"losses":17,"wins":46}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":12,"wins":25},"claude-fable-5":{"draws":14,"losses":32,"wins":32},"claude-fable-5-1":{"draws":13,"losses":86,"wins":13},"claude-opus-4-5":{"draws":12,"losses":16,"wins":26},"claude-sonnet-5":{"draws":20,"losses":21,"wins":41},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":16},"deepseek/deepseek-v4-pro":{"draws":20,"losses":25,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":23,"wins":36},"google/gemini-3.5-flash":{"draws":30,"losses":27,"wins":27},"google/gemini-3.5-flash-lite":{"draws":45,"losses":28,"wins":43},"google/gemini-3.6-flash":{"draws":38,"losses":31,"wins":41},"google/gemini-3.8-flash":{"draws":21,"losses":37,"wins":28},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":14,"losses":29,"wins":23},"gpt-5.6-luna":{"draws":26,"losses":21,"wins":25},"gpt-5.6-sol":{"draws":16,"losses":35,"wins":37},"gpt-5.6-terra":{"draws":18,"losses":23,"wins":29},"gpt-6-astra":{"draws":16,"losses":68,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":8,"wins":20},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":21},"meta/muse-glimmer-30b":{"draws":29,"losses":11,"wins":20},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":23},"meta/muse-spark-1.3":{"draws":22,"losses":22,"wins":36},"moonshotai/kimi-k3":{"draws":27,"losses":11,"wins":34},"o3":{"draws":17,"losses":27,"wins":24},"openai/gpt-oss-120b":{"draws":21,"losses":7,"wins":24},"poolside/laguna-s-2.1":{"draws":19,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":22,"wins":26},"qwen/qwen3.8-27b":{"draws":15,"losses":18,"wins":21},"qwen/qwen3.8-flash":{"draws":21,"losses":20,"wins":13},"qwen/qwen3.8-max":{"draws":25,"losses":26,"wins":21},"stealth/ox-alpha":{"draws":72,"losses":110,"wins":99},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":4},"tencent/hy4-preview":{"draws":22,"losses":24,"wins":32},"thinkingmachines/inkling":{"draws":19,"losses":11,"wins":18},"thinkingmachines/inkling-small":{"draws":32,"losses":19,"wins":25},"x-ai/grok-4.5":{"draws":12,"losses":14,"wins":20},"x-ai/grok-4.6":{"draws":16,"losses":28,"wins":38},"z-ai/glm-5.2":{"draws":36,"losses":14,"wins":38},"z-ai/glm-5.3":{"draws":15,"losses":46,"wins":17},"z-ai/glm-5.3-flash":{"draws":24,"losses":20,"wins":20}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":7},"claude-fable-5":{"draws":5,"losses":15,"wins":4},"claude-fable-5-1":{"draws":0,"losses":19,"wins":1},"claude-opus-4-5":{"draws":5,"losses":9,"wins":4},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":7,"losses":16,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":12,"wins":11},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":8},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":5},"google/gemini-3.5-flash-lite":{"draws":30,"losses":15,"wins":21},"google/gemini-3.6-flash":{"draws":15,"losses":17,"wins":14},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":8,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":6,"wins":10},"gpt-5.6-sol":{"draws":1,"losses":10,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":13,"wins":8},"gpt-6-astra":{"draws":0,"losses":11,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":4},"meta/muse-glimmer-30b":{"draws":13,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":7,"losses":6,"wins":7},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":5},"o3":{"draws":6,"losses":11,"wins":9},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":7,"wins":8},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":4,"wins":3},"qwen/qwen3.8-max":{"draws":12,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":25,"losses":32,"wins":17},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":8,"wins":5},"thinkingmachines/inkling":{"draws":9,"losses":4,"wins":11},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":17},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":5},"x-ai/grok-4.6":{"draws":7,"losses":14,"wins":1},"z-ai/glm-5.2":{"draws":16,"losses":10,"wins":12},"z-ai/glm-5.3":{"draws":5,"losses":6,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":4}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":9},"claude-fable-5":{"draws":2,"losses":12,"wins":12},"claude-fable-5-1":{"draws":1,"losses":41,"wins":12},"claude-opus-4-5":{"draws":2,"losses":2,"wins":10},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":5,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":0,"losses":7,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":22},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":11},"google/gemini-3.6-flash":{"draws":10,"losses":10,"wins":18},"google/gemini-3.8-flash":{"draws":6,"losses":16,"wins":20},"gpt-5.4":{"draws":4,"losses":13,"wins":9},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":10},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":23},"gpt-5.6-terra":{"draws":6,"losses":5,"wins":13},"gpt-6-astra":{"draws":2,"losses":37,"wins":9},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":6},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":15},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":17},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":19},"o3":{"draws":2,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":8,"wins":15},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":8},"qwen/qwen3.8-flash":{"draws":8,"losses":1,"wins":11},"qwen/qwen3.8-max":{"draws":6,"losses":8,"wins":10},"stealth/ox-alpha":{"draws":20,"losses":20,"wins":54},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":5,"losses":7,"wins":16},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":12},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":18},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":13},"z-ai/glm-5.3":{"draws":7,"losses":15,"wins":18},"z-ai/glm-5.3-flash":{"draws":4,"losses":8,"wins":22}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":21},"claude-fable-5":{"draws":0,"losses":4,"wins":52},"claude-fable-5-1":{"draws":3,"losses":12,"wins":41},"claude-opus-4-5":{"draws":1,"losses":2,"wins":19},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":0,"losses":0,"wins":28},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":30},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":36},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":13},"google/gemini-3.6-flash":{"draws":5,"losses":3,"wins":54},"google/gemini-3.8-flash":{"draws":4,"losses":4,"wins":44},"gpt-5.4":{"draws":0,"losses":3,"wins":35},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":16},"gpt-5.6-sol":{"draws":1,"losses":7,"wins":52},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":24},"gpt-6-astra":{"draws":4,"losses":26,"wins":36},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":10},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":8},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":28},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":42},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"o3":{"draws":0,"losses":0,"wins":18},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":32},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":22},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":21},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":35},"stealth/ox-alpha":{"draws":11,"losses":6,"wins":125},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":35},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":11},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":14},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":23},"x-ai/grok-4.6":{"draws":1,"losses":5,"wins":42},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":25},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":40},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":42}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":10},"claude-fable-5":{"draws":6,"losses":17,"wins":7},"claude-fable-5-1":{"draws":1,"losses":20,"wins":3},"claude-opus-4-5":{"draws":10,"losses":20,"wins":10},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":7,"losses":70,"wins":3},"claude-sonnet-5":{"draws":37,"losses":14,"wins":29},"deepseek/deepseek-v4-flash":{"draws":7,"losses":8,"wins":17},"deepseek/deepseek-v4-pro":{"draws":12,"losses":5,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":7,"losses":19,"wins":8},"google/gemini-3.5-flash-lite":{"draws":72,"losses":41,"wins":65},"google/gemini-3.6-flash":{"draws":49,"losses":78,"wins":51},"google/gemini-3.8-flash":{"draws":12,"losses":14,"wins":6},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":5,"wins":4},"gpt-5.4":{"draws":27,"losses":36,"wins":15},"gpt-5.5":{"draws":2,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":29,"losses":18,"wins":29},"gpt-5.6-sol":{"draws":11,"losses":47,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":12},"gpt-6-astra":{"draws":1,"losses":27,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":4},"inclusionai/ling-3.0-flash":{"draws":8,"losses":12,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":16,"wins":24},"meta/muse-glimmer-30b":{"draws":14,"losses":3,"wins":11},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":17},"meta/muse-spark-1.3":{"draws":7,"losses":10,"wins":7},"moonshotai/kimi-k3":{"draws":35,"losses":40,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":8},"o3":{"draws":23,"losses":23,"wins":76},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":11},"poolside/laguna-s-2.1":{"draws":31,"losses":2,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":7,"wins":8},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":11,"losses":18,"wins":9},"stealth/ox-alpha":{"draws":38,"losses":40,"wins":28},"stepfun/step-3.7-flash":{"draws":8,"losses":1,"wins":23},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":12,"losses":10,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":2,"wins":37},"thinkingmachines/inkling-small":{"draws":18,"losses":9,"wins":11},"x-ai/grok-4.5":{"draws":29,"losses":38,"wins":19},"x-ai/grok-4.6":{"draws":12,"losses":14,"wins":6},"z-ai/glm-5.2":{"draws":11,"losses":10,"wins":13},"z-ai/glm-5.3":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.3-flash":{"draws":5,"losses":15,"wins":6}},"claude-opus-4-8":{"claude-opus-4-5":{"draws":3,"losses":8,"wins":25},"claude-opus-4-8":{"draws":0,"losses":3,"wins":5},"claude-opus-5":{"draws":14,"losses":33,"wins":23},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":5,"wins":16},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":8},"gpt-5.5":{"draws":4,"losses":14,"wins":10},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":18},"o3":{"draws":0,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":7,"losses":4,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":6,"wins":11}},"claude-opus-5":{"claude-opus-4-5":{"draws":3,"losses":6,"wins":53},"claude-opus-4-8":{"draws":2,"losses":12,"wins":16},"claude-opus-5":{"draws":14,"losses":51,"wins":81},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":13},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":34},"google/gemini-3.6-flash":{"draws":4,"losses":8,"wins":34},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":0,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":3},"gpt-5.5":{"draws":0,"losses":7,"wins":23},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":15},"o3":{"draws":0,"losses":3,"wins":41},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":19},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":23},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":2,"wins":12},"claude-fable-5":{"draws":6,"losses":19,"wins":9},"claude-fable-5-1":{"draws":1,"losses":39,"wins":2},"claude-opus-4-5":{"draws":22,"losses":21,"wins":15},"claude-opus-5":{"draws":0,"losses":0,"wins":4},"claude-sonnet-5":{"draws":14,"losses":7,"wins":31},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":10,"wins":4},"google/gemini-3.5-flash":{"draws":6,"losses":12,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":17,"wins":74},"google/gemini-3.6-flash":{"draws":21,"losses":42,"wins":51},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":21,"losses":33,"wins":20},"gpt-5.6-luna":{"draws":23,"losses":18,"wins":29},"gpt-5.6-sol":{"draws":13,"losses":62,"wins":15},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":15},"gpt-6-astra":{"draws":1,"losses":32,"wins":5},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":27},"meta/muse-glimmer-30b":{"draws":6,"losses":3,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":9,"wins":35},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":8},"moonshotai/kimi-k3":{"draws":22,"losses":26,"wins":20},"o3":{"draws":1,"losses":28,"wins":41},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":9},"poolside/laguna-s-2.1":{"draws":11,"losses":0,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":8},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.8-max":{"draws":3,"losses":10,"wins":15},"stealth/ox-alpha":{"draws":28,"losses":44,"wins":35},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":5,"losses":12,"wins":11},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":19},"thinkingmachines/inkling-small":{"draws":5,"losses":6,"wins":3},"x-ai/grok-4.5":{"draws":21,"losses":24,"wins":11},"x-ai/grok-4.6":{"draws":4,"losses":15,"wins":13},"z-ai/glm-5.2":{"draws":6,"losses":9,"wins":7},"z-ai/glm-5.3":{"draws":3,"losses":20,"wins":7},"z-ai/glm-5.3-flash":{"draws":4,"losses":21,"wins":5}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":4,"wins":5},"claude-fable-5":{"draws":6,"losses":5,"wins":5},"claude-fable-5-1":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":3,"losses":10,"wins":7},"claude-sonnet-5":{"draws":6,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":9,"wins":11},"deepseek/deepseek-v4-pro":{"draws":14,"losses":10,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":7},"google/gemini-3.5-flash-lite":{"draws":21,"losses":20,"wins":11},"google/gemini-3.6-flash":{"draws":15,"losses":15,"wins":8},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":13,"losses":5,"wins":8},"gpt-5.6-luna":{"draws":20,"losses":3,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":5,"wins":7},"gpt-6-astra":{"draws":1,"losses":8,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":7},"meta/muse-glimmer-30b":{"draws":22,"losses":4,"wins":6},"meta/muse-spark-1.2":{"draws":7,"losses":4,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":2,"wins":7},"o3":{"draws":8,"losses":8,"wins":8},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":2},"poolside/laguna-s-2.1":{"draws":9,"losses":4,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":5,"wins":6},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":6},"qwen/qwen3.8-max":{"draws":10,"losses":5,"wins":3},"stealth/ox-alpha":{"draws":29,"losses":16,"wins":13},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy4-preview":{"draws":7,"losses":7,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":6,"wins":4},"thinkingmachines/inkling-small":{"draws":15,"losses":6,"wins":7},"x-ai/grok-4.5":{"draws":5,"losses":7,"wins":2},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":7,"wins":4},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":2,"wins":2}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":13},"claude-fable-5":{"draws":4,"losses":12,"wins":8},"claude-fable-5-1":{"draws":0,"losses":33,"wins":1},"claude-opus-4-5":{"draws":9,"losses":4,"wins":1},"claude-sonnet-5":{"draws":13,"losses":13,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":6,"wins":12},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":9,"wins":9},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":14},"google/gemini-3.5-flash-lite":{"draws":21,"losses":15,"wins":22},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":12,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":16,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":13,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":10},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":4},"gpt-6-astra":{"draws":1,"losses":27,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":3,"wins":6},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":9},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":13,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":8},"o3":{"draws":6,"losses":3,"wins":11},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":5},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.8-27b":{"draws":2,"losses":11,"wins":5},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":7},"stealth/ox-alpha":{"draws":20,"losses":33,"wins":19},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":11,"losses":10,"wins":8},"thinkingmachines/inkling":{"draws":9,"losses":1,"wins":10},"thinkingmachines/inkling-small":{"draws":18,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.6":{"draws":8,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.3":{"draws":6,"losses":10,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":9,"wins":11}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":3,"wins":14},"claude-fable-5":{"draws":8,"losses":14,"wins":8},"claude-fable-5-1":{"draws":2,"losses":33,"wins":1},"claude-opus-4-5":{"draws":5,"losses":3,"wins":10},"claude-sonnet-5":{"draws":11,"losses":5,"wins":12},"deepseek/deepseek-v4-flash":{"draws":10,"losses":2,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":13,"losses":7,"wins":12},"google/gemini-3.5-flash-lite":{"draws":22,"losses":6,"wins":20},"google/gemini-3.6-flash":{"draws":11,"losses":24,"wins":17},"google/gemini-3.8-flash":{"draws":4,"losses":11,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":10,"losses":6,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":9},"gpt-5.6-terra":{"draws":11,"losses":1,"wins":10},"gpt-6-astra":{"draws":2,"losses":26,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":10},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":2,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k3":{"draws":12,"losses":1,"wins":9},"o3":{"draws":5,"losses":3,"wins":16},"openai/gpt-oss-120b":{"draws":15,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":8,"wins":13},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":8,"losses":7,"wins":15},"stealth/ox-alpha":{"draws":24,"losses":27,"wins":41},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":7,"losses":15,"wins":16},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":8},"thinkingmachines/inkling-small":{"draws":9,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.6":{"draws":7,"losses":9,"wins":12},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":17,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":17,"wins":7}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":6,"losses":14,"wins":2},"claude-opus-4-8":{"draws":3,"losses":13,"wins":2},"claude-opus-5":{"draws":2,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":3},"gpt-5.5":{"draws":4,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":3},"o3":{"draws":4,"losses":16,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":3,"wins":8},"claude-fable-5":{"draws":5,"losses":20,"wins":11},"claude-fable-5-1":{"draws":3,"losses":37,"wins":6},"claude-opus-4-5":{"draws":3,"losses":2,"wins":17},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":5,"losses":5,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":12,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":12},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":12},"google/gemini-3.5-flash-lite":{"draws":9,"losses":5,"wins":10},"google/gemini-3.6-flash":{"draws":9,"losses":15,"wins":24},"google/gemini-3.8-flash":{"draws":5,"losses":14,"wins":21},"gpt-5.4":{"draws":3,"losses":15,"wins":12},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":17},"gpt-5.6-terra":{"draws":14,"losses":11,"wins":9},"gpt-6-astra":{"draws":8,"losses":32,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":10},"meta/muse-glimmer-30b":{"draws":3,"losses":3,"wins":8},"meta/muse-spark-1.2":{"draws":4,"losses":5,"wins":11},"meta/muse-spark-1.3":{"draws":5,"losses":15,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":12},"o3":{"draws":0,"losses":5,"wins":15},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":15},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-max":{"draws":13,"losses":9,"wins":8},"stealth/ox-alpha":{"draws":27,"losses":30,"wins":31},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":4,"losses":17,"wins":9},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":8,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":12},"z-ai/glm-5.3":{"draws":3,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":6,"wins":15}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":18,"wins":18},"claude-fable-5":{"draws":8,"losses":10,"wins":10},"claude-fable-5-1":{"draws":3,"losses":13,"wins":0},"claude-opus-4-5":{"draws":30,"losses":46,"wins":34},"claude-opus-4-8":{"draws":0,"losses":12,"wins":2},"claude-opus-5":{"draws":3,"losses":32,"wins":1},"claude-sonnet-5":{"draws":30,"losses":53,"wins":31},"deepseek/deepseek-v4-flash":{"draws":16,"losses":20,"wins":18},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":18,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":17,"losses":18,"wins":13},"google/gemini-3.5-flash-lite":{"draws":79,"losses":96,"wins":107},"google/gemini-3.6-flash":{"draws":66,"losses":139,"wins":61},"google/gemini-3.8-flash":{"draws":1,"losses":12,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":6,"wins":2},"gpt-5.4":{"draws":26,"losses":63,"wins":31},"gpt-5.5":{"draws":6,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":36,"losses":45,"wins":51},"gpt-5.6-sol":{"draws":17,"losses":76,"wins":9},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":16},"gpt-6-astra":{"draws":1,"losses":6,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":20},"inclusionai/ling-3.0-flash":{"draws":13,"losses":14,"wins":23},"meituan/longcat-2.0":{"draws":23,"losses":30,"wins":44},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":25},"meta/muse-spark-1.2":{"draws":20,"losses":32,"wins":26},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":8},"moonshotai/kimi-k3":{"draws":39,"losses":63,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":6},"o3":{"draws":15,"losses":110,"wins":79},"openai/gpt-oss-120b":{"draws":18,"losses":12,"wins":24},"poolside/laguna-s-2.1":{"draws":45,"losses":25,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":20,"losses":15,"wins":11},"stealth/ox-alpha":{"draws":28,"losses":46,"wins":42},"stepfun/step-3.7-flash":{"draws":8,"losses":21,"wins":17},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":15,"losses":18,"wins":11},"thinkingmachines/inkling":{"draws":44,"losses":28,"wins":54},"thinkingmachines/inkling-small":{"draws":18,"losses":28,"wins":19},"x-ai/grok-4.5":{"draws":26,"losses":54,"wins":32},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":9},"z-ai/glm-5.2":{"draws":14,"losses":11,"wins":19},"z-ai/glm-5.3":{"draws":9,"losses":12,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":17,"wins":7}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":7,"wins":9},"claude-fable-5":{"draws":4,"losses":22,"wins":22},"claude-fable-5-1":{"draws":4,"losses":47,"wins":9},"claude-opus-4-5":{"draws":16,"losses":31,"wins":59},"claude-opus-4-8":{"draws":2,"losses":10,"wins":10},"claude-opus-5":{"draws":12,"losses":39,"wins":11},"claude-sonnet-5":{"draws":14,"losses":27,"wins":63},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":21},"deepseek/deepseek-v4-pro":{"draws":5,"losses":14,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":4,"wins":23},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":18,"wins":20},"google/gemini-3.5-flash-lite":{"draws":60,"losses":27,"wins":145},"google/gemini-3.6-flash":{"draws":34,"losses":73,"wins":115},"google/gemini-3.8-flash":{"draws":5,"losses":15,"wins":32},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":7,"wins":12},"gpt-5.4":{"draws":14,"losses":55,"wins":51},"gpt-5.5":{"draws":4,"losses":12,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":32,"wins":55},"gpt-5.6-sol":{"draws":8,"losses":50,"wins":58},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":14},"gpt-6-astra":{"draws":5,"losses":39,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":7},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":17},"meituan/longcat-2.0":{"draws":17,"losses":8,"wins":56},"meta/muse-glimmer-30b":{"draws":12,"losses":1,"wins":11},"meta/muse-spark-1.2":{"draws":9,"losses":28,"wins":45},"meta/muse-spark-1.3":{"draws":1,"losses":21,"wins":22},"moonshotai/kimi-k3":{"draws":23,"losses":19,"wins":92},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":11},"o3":{"draws":25,"losses":34,"wins":111},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":8},"poolside/laguna-s-2.1":{"draws":24,"losses":2,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":24},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":4,"wins":13},"qwen/qwen3.8-max":{"draws":12,"losses":15,"wins":20},"stealth/ox-alpha":{"draws":22,"losses":41,"wins":57},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":28},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":12},"tencent/hy4-preview":{"draws":10,"losses":15,"wins":19},"thinkingmachines/inkling":{"draws":30,"losses":15,"wins":51},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":11,"losses":38,"wins":63},"x-ai/grok-4.6":{"draws":2,"losses":16,"wins":28},"z-ai/glm-5.2":{"draws":12,"losses":7,"wins":19},"z-ai/glm-5.3":{"draws":4,"losses":29,"wins":19},"z-ai/glm-5.3-flash":{"draws":13,"losses":15,"wins":12}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":7},"claude-fable-5":{"draws":4,"losses":20,"wins":16},"claude-fable-5-1":{"draws":7,"losses":40,"wins":7},"claude-opus-4-5":{"draws":4,"losses":6,"wins":6},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":4,"losses":10,"wins":10},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":9,"wins":12},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":19},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":17},"google/gemini-3.6-flash":{"draws":3,"losses":16,"wins":21},"google/gemini-3.8-flash":{"draws":5,"losses":10,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":19,"wins":21},"gpt-5.6-terra":{"draws":10,"losses":9,"wins":9},"gpt-6-astra":{"draws":6,"losses":38,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"meta/muse-glimmer-30b":{"draws":0,"losses":4,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":6,"wins":13},"meta/muse-spark-1.3":{"draws":2,"losses":18,"wins":8},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":17},"o3":{"draws":0,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":12,"wins":15},"qwen/qwen3.8-27b":{"draws":2,"losses":8,"wins":8},"qwen/qwen3.8-flash":{"draws":3,"losses":7,"wins":10},"qwen/qwen3.8-max":{"draws":7,"losses":7,"wins":12},"stealth/ox-alpha":{"draws":17,"losses":35,"wins":47},"tencent/hy4-preview":{"draws":3,"losses":13,"wins":12},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":4},"thinkingmachines/inkling-small":{"draws":1,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":12,"wins":6},"x-ai/grok-4.6":{"draws":4,"losses":16,"wins":18},"z-ai/glm-5.2":{"draws":4,"losses":8,"wins":8},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":9},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":14}},"gpt-5":{"claude-opus-4-5":{"draws":19,"losses":9,"wins":10},"claude-opus-4-8":{"draws":4,"losses":15,"wins":5},"claude-opus-5":{"draws":3,"losses":37,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":8},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":12,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":7},"gpt-5.5":{"draws":8,"losses":12,"wins":4},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":0,"wins":10},"o3":{"draws":3,"losses":12,"wins":15},"poolside/laguna-s-2.1":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":5,"losses":6,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":11,"wins":13}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":4,"wins":5},"claude-fable-5":{"draws":8,"losses":13,"wins":17},"claude-fable-5-1":{"draws":3,"losses":28,"wins":9},"claude-opus-4-5":{"draws":6,"losses":7,"wins":27},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":9,"losses":12,"wins":43},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":12},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":21},"google/gemini-3.5-flash-lite":{"draws":13,"losses":11,"wins":74},"google/gemini-3.6-flash":{"draws":17,"losses":23,"wins":72},"google/gemini-3.8-flash":{"draws":2,"losses":9,"wins":21},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":12,"losses":4,"wins":45},"gpt-5.6-luna":{"draws":10,"losses":2,"wins":53},"gpt-5.6-sol":{"draws":20,"losses":26,"wins":38},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":17},"gpt-6-astra":{"draws":2,"losses":28,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":26},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":4,"losses":12,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":9,"wins":13},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":44},"o3":{"draws":0,"losses":7,"wins":59},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":10,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":7},"qwen/qwen3.8-max":{"draws":5,"losses":9,"wins":12},"stealth/ox-alpha":{"draws":30,"losses":16,"wins":39},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":18},"thinkingmachines/inkling":{"draws":3,"losses":8,"wins":23},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":7,"losses":6,"wins":31},"x-ai/grok-4.6":{"draws":6,"losses":7,"wins":23},"z-ai/glm-5.2":{"draws":5,"losses":5,"wins":14},"z-ai/glm-5.3":{"draws":0,"losses":13,"wins":17},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":13}},"gpt-5.5":{"claude-opus-4-5":{"draws":6,"losses":5,"wins":17},"claude-opus-4-8":{"draws":2,"losses":3,"wins":19},"claude-opus-5":{"draws":1,"losses":38,"wins":27},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":5,"losses":3,"wins":14},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":10},"gpt-5.5":{"draws":6,"losses":5,"wins":7},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":11},"o3":{"draws":1,"losses":2,"wins":27},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":11},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":12}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":5,"wins":6},"claude-fable-5":{"draws":9,"losses":12,"wins":13},"claude-fable-5-1":{"draws":2,"losses":20,"wins":4},"claude-opus-4-5":{"draws":20,"losses":11,"wins":21},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":20,"losses":15,"wins":31},"deepseek/deepseek-v4-flash":{"draws":18,"losses":3,"wins":9},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":5,"wins":12},"google/gemini-3.5-flash":{"draws":13,"losses":9,"wins":14},"google/gemini-3.5-flash-lite":{"draws":55,"losses":17,"wins":60},"google/gemini-3.6-flash":{"draws":36,"losses":38,"wins":52},"google/gemini-3.8-flash":{"draws":9,"losses":7,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":35,"losses":40,"wins":14},"gpt-5.6-luna":{"draws":26,"losses":6,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":36,"wins":24},"gpt-5.6-terra":{"draws":7,"losses":4,"wins":11},"gpt-6-astra":{"draws":3,"losses":21,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":22},"meta/muse-glimmer-30b":{"draws":16,"losses":1,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":24,"wins":24},"meta/muse-spark-1.3":{"draws":6,"losses":8,"wins":8},"moonshotai/kimi-k3":{"draws":21,"losses":16,"wins":27},"o3":{"draws":12,"losses":13,"wins":39},"openai/gpt-oss-120b":{"draws":19,"losses":4,"wins":5},"poolside/laguna-s-2.1":{"draws":17,"losses":4,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":3,"wins":13},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":5},"stealth/ox-alpha":{"draws":25,"losses":23,"wins":31},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":5,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":2,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":34},"x-ai/grok-4.6":{"draws":9,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":11,"losses":10,"wins":5},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":9},"z-ai/glm-5.3-flash":{"draws":9,"losses":8,"wins":9}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":3,"wins":11},"claude-fable-5":{"draws":2,"losses":14,"wins":26},"claude-fable-5-1":{"draws":5,"losses":33,"wins":16},"claude-opus-4-5":{"draws":2,"losses":12,"wins":32},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":0,"losses":6,"wins":68},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":18},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":91},"google/gemini-3.6-flash":{"draws":7,"losses":24,"wins":89},"google/gemini-3.8-flash":{"draws":4,"losses":9,"wins":25},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":6,"losses":20,"wins":50},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":51},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":54},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":14},"gpt-6-astra":{"draws":6,"losses":34,"wins":8},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":3},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":25},"meta/muse-glimmer-30b":{"draws":1,"losses":1,"wins":6},"meta/muse-spark-1.2":{"draws":2,"losses":4,"wins":52},"meta/muse-spark-1.3":{"draws":4,"losses":8,"wins":22},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":59},"o3":{"draws":0,"losses":13,"wins":51},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":17},"qwen/qwen3.8-27b":{"draws":0,"losses":5,"wins":9},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":13},"qwen/qwen3.8-max":{"draws":2,"losses":1,"wins":25},"stealth/ox-alpha":{"draws":10,"losses":15,"wins":72},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy4-preview":{"draws":3,"losses":12,"wins":13},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":31},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":4,"wins":42},"x-ai/grok-4.6":{"draws":3,"losses":13,"wins":20},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":15},"z-ai/glm-5.3":{"draws":4,"losses":14,"wins":22},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":19}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":9},"claude-fable-5":{"draws":11,"losses":12,"wins":11},"claude-fable-5-1":{"draws":3,"losses":22,"wins":1},"claude-opus-4-5":{"draws":4,"losses":8,"wins":6},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":6,"losses":8,"wins":10},"deepseek/deepseek-v4-flash":{"draws":7,"losses":8,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":11,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":5,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":9,"wins":13},"google/gemini-3.5-flash-lite":{"draws":11,"losses":11,"wins":26},"google/gemini-3.6-flash":{"draws":15,"losses":15,"wins":14},"google/gemini-3.8-flash":{"draws":9,"losses":13,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":10,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":7,"wins":11},"gpt-5.6-sol":{"draws":8,"losses":15,"wins":9},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":8},"gpt-6-astra":{"draws":2,"losses":22,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":5},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":11},"meta/muse-spark-1.2":{"draws":7,"losses":12,"wins":5},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":5,"wins":12},"o3":{"draws":0,"losses":13,"wins":15},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":16},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":6},"qwen/qwen3.8-flash":{"draws":6,"losses":3,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":10,"wins":8},"stealth/ox-alpha":{"draws":25,"losses":27,"wins":32},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":7,"losses":5,"wins":12},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":12},"thinkingmachines/inkling-small":{"draws":10,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":10,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":18,"wins":6},"z-ai/glm-5.2":{"draws":16,"losses":2,"wins":12},"z-ai/glm-5.3":{"draws":13,"losses":11,"wins":4},"z-ai/glm-5.3-flash":{"draws":7,"losses":10,"wins":13}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":8},"claude-fable-5":{"draws":1,"losses":8,"wins":35},"claude-fable-5-1":{"draws":5,"losses":11,"wins":38},"claude-opus-4-5":{"draws":1,"losses":1,"wins":14},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":0,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":30},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":14},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":37},"google/gemini-3.8-flash":{"draws":4,"losses":1,"wins":33},"gpt-5.4":{"draws":2,"losses":5,"wins":23},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":35},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":21},"gpt-6-astra":{"draws":0,"losses":8,"wins":24},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":24},"meta/muse-spark-1.3":{"draws":1,"losses":1,"wins":32},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":28},"o3":{"draws":0,"losses":1,"wins":15},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":15},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":25},"stealth/ox-alpha":{"draws":4,"losses":4,"wins":86},"tencent/hy4-preview":{"draws":0,"losses":3,"wins":25},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":0,"wins":18},"x-ai/grok-4.6":{"draws":0,"losses":1,"wins":35},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":21},"z-ai/glm-5.3":{"draws":3,"losses":0,"wins":33},"z-ai/glm-5.3-flash":{"draws":4,"losses":0,"wins":26}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":0},"claude-fable-5":{"draws":4,"losses":0,"wins":0},"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":1,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":0},"o3":{"draws":2,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":16,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":0,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":7,"wins":7},"claude-fable-5":{"draws":5,"losses":5,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":8,"losses":4,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":0},"deepseek/deepseek-v4-flash":{"draws":9,"losses":13,"wins":2},"deepseek/deepseek-v4-pro":{"draws":11,"losses":5,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":2},"google/gemini-3.5-flash":{"draws":10,"losses":8,"wins":0},"google/gemini-3.5-flash-lite":{"draws":24,"losses":19,"wins":3},"google/gemini-3.6-flash":{"draws":16,"losses":13,"wins":1},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":9,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":0},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":1},"gpt-6-astra":{"draws":2,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":3},"meta/muse-glimmer-30b":{"draws":12,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":6,"losses":10,"wins":0},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":3},"o3":{"draws":7,"losses":19,"wins":2},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":5,"wins":3},"qwen/qwen3.8-27b":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"losses":3,"wins":2},"qwen/qwen3.8-max":{"draws":13,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":16,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":3,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":10,"losses":6,"wins":0},"thinkingmachines/inkling-small":{"draws":11,"losses":14,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3":{"draws":6,"losses":3,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":7,"wins":1}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":5,"wins":11},"claude-fable-5":{"draws":8,"losses":7,"wins":1},"claude-fable-5-1":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":8,"losses":10,"wins":2},"claude-sonnet-5":{"draws":13,"losses":7,"wins":8},"deepseek/deepseek-v4-flash":{"draws":16,"losses":7,"wins":7},"deepseek/deepseek-v4-pro":{"draws":10,"losses":6,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":10,"wins":5},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":7},"google/gemini-3.5-flash-lite":{"draws":21,"losses":16,"wins":7},"google/gemini-3.6-flash":{"draws":20,"losses":10,"wins":8},"google/gemini-3.8-flash":{"draws":9,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":9,"losses":5,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":9,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":7},"meta/muse-glimmer-30b":{"draws":13,"losses":2,"wins":5},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":6,"wins":5},"o3":{"draws":10,"losses":10,"wins":6},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":2,"wins":6},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":25,"losses":29,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":10,"wins":5},"thinkingmachines/inkling":{"draws":11,"losses":1,"wins":4},"thinkingmachines/inkling-small":{"draws":16,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.6":{"draws":6,"losses":11,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":10,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":8,"wins":5}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":3},"claude-fable-5":{"draws":2,"losses":2,"wins":2},"claude-fable-5-1":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":3,"losses":5,"wins":8},"claude-sonnet-5":{"draws":2,"losses":12,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":9,"wins":15},"google/gemini-3.6-flash":{"draws":7,"losses":9,"wins":18},"google/gemini-3.8-flash":{"draws":1,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":1,"losses":16,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":7,"wins":13},"gpt-5.6-sol":{"draws":0,"losses":20,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":2},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":1},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":7},"meta/muse-spark-1.3":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":9},"o3":{"draws":1,"losses":9,"wins":4},"poolside/laguna-s-2.1":{"draws":1,"losses":5,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":1},"stealth/ox-alpha":{"draws":4,"losses":15,"wins":13},"tencent/hy4-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.6":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.3":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.3-flash":{"draws":0,"losses":1,"wins":3}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":5},"claude-fable-5":{"draws":5,"losses":13,"wins":10},"claude-fable-5-1":{"draws":2,"losses":36,"wins":2},"claude-opus-4-5":{"draws":1,"losses":1,"wins":10},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":8,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":14},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":12},"google/gemini-3.6-flash":{"draws":1,"losses":8,"wins":21},"google/gemini-3.8-flash":{"draws":2,"losses":8,"wins":18},"gpt-5.4":{"draws":3,"losses":6,"wins":11},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":17},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":10},"gpt-6-astra":{"draws":4,"losses":27,"wins":5},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":10},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":10},"o3":{"draws":0,"losses":1,"wins":9},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":8,"wins":8},"qwen/qwen3.8-27b":{"draws":0,"losses":3,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":9},"qwen/qwen3.8-max":{"draws":3,"losses":4,"wins":13},"stealth/ox-alpha":{"draws":10,"losses":25,"wins":32},"tencent/hy4-preview":{"draws":3,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":9},"x-ai/grok-4.6":{"draws":8,"losses":10,"wins":12},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":4},"z-ai/glm-5.3":{"draws":7,"losses":14,"wins":9},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":6}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":0},"claude-fable-5":{"draws":3,"losses":16,"wins":5},"claude-fable-5-1":{"draws":5,"losses":30,"wins":1},"claude-opus-4-5":{"draws":24,"losses":6,"wins":20},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":5,"losses":20,"wins":1},"claude-sonnet-5":{"draws":18,"losses":8,"wins":22},"deepseek/deepseek-v4-flash":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":2},"google/gemini-3.5-flash-lite":{"draws":32,"losses":14,"wins":48},"google/gemini-3.6-flash":{"draws":18,"losses":34,"wins":36},"google/gemini-3.8-flash":{"draws":6,"losses":8,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":1,"wins":5},"gpt-5.4":{"draws":20,"losses":14,"wins":16},"gpt-5.5":{"draws":3,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":16},"gpt-5.6-sol":{"draws":17,"losses":29,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":11},"gpt-6-astra":{"draws":5,"losses":24,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":17},"meituan/longcat-2.0":{"draws":10,"losses":1,"wins":21},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":4,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":10,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":20,"losses":4,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":3},"o3":{"draws":0,"losses":18,"wins":32},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":3,"wins":5},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":4,"wins":3},"stealth/ox-alpha":{"draws":14,"losses":36,"wins":20},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":5,"losses":3,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":5,"wins":16},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":22,"losses":22,"wins":16},"x-ai/grok-4.6":{"draws":9,"losses":7,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":12,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":15,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":25,"losses":18,"wins":5},"claude-opus-4-8":{"draws":8,"losses":18,"wins":4},"claude-opus-5":{"draws":1,"losses":13,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":12,"losses":1,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":12},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":4},"gpt-5.5":{"draws":7,"losses":13,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":3},"o3":{"draws":12,"losses":25,"wins":7},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":21},"x-ai/grok-4.5":{"draws":7,"losses":9,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":21,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":5,"losses":6,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":19,"wins":37},"claude-fable-5":{"draws":5,"losses":38,"wins":13},"claude-fable-5-1":{"draws":0,"losses":47,"wins":5},"claude-opus-4-5":{"draws":25,"losses":128,"wins":53},"claude-opus-4-8":{"draws":0,"losses":25,"wins":3},"claude-opus-5":{"draws":0,"losses":53,"wins":3},"claude-sonnet-5":{"draws":12,"losses":78,"wins":88},"deepseek/deepseek-v4-flash":{"draws":10,"losses":33,"wins":29},"deepseek/deepseek-v4-pro":{"draws":9,"losses":29,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":35,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":7,"losses":33,"wins":16},"google/gemini-3.5-flash-lite":{"draws":63,"losses":127,"wins":280},"google/gemini-3.6-flash":{"draws":54,"losses":213,"wins":151},"google/gemini-3.8-flash":{"draws":5,"losses":33,"wins":24},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":6},"gpt-5":{"draws":3,"losses":13,"wins":12},"gpt-5.4":{"draws":14,"losses":127,"wins":41},"gpt-5.5":{"draws":1,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":26,"losses":67,"wins":83},"gpt-5.6-sol":{"draws":7,"losses":127,"wins":36},"gpt-5.6-terra":{"draws":6,"losses":30,"wins":42},"gpt-6-astra":{"draws":1,"losses":50,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":35},"inclusionai/ling-3.0-flash":{"draws":0,"losses":16,"wins":52},"meituan/longcat-2.0":{"draws":9,"losses":40,"wins":95},"meta/muse-glimmer-30b":{"draws":16,"losses":9,"wins":39},"meta/muse-spark-1.2":{"draws":8,"losses":37,"wins":77},"meta/muse-spark-1.3":{"draws":4,"losses":21,"wins":21},"moonshotai/kimi-k3":{"draws":21,"losses":80,"wins":107},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":25},"o3":{"draws":21,"losses":137,"wins":162},"openai/gpt-oss-120b":{"draws":11,"losses":15,"wins":38},"poolside/laguna-s-2.1":{"draws":22,"losses":29,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":30,"wins":28},"qwen/qwen3.8-27b":{"draws":7,"losses":25,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":16,"wins":18},"qwen/qwen3.8-max":{"draws":14,"losses":40,"wins":30},"stealth/ox-alpha":{"draws":21,"losses":82,"wins":95},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":65},"tencent/hy3-preview":{"draws":3,"losses":13,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":36,"wins":22},"thinkingmachines/inkling":{"draws":29,"losses":34,"wins":98},"thinkingmachines/inkling-small":{"draws":20,"losses":26,"wins":37},"x-ai/grok-4.5":{"draws":9,"losses":97,"wins":58},"x-ai/grok-4.6":{"draws":10,"losses":32,"wins":24},"z-ai/glm-5.2":{"draws":13,"losses":19,"wins":42},"z-ai/glm-5.3":{"draws":5,"losses":35,"wins":16},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":25}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":8},"claude-fable-5":{"draws":9,"losses":4,"wins":5},"claude-fable-5-1":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":2,"losses":4,"wins":4},"claude-sonnet-5":{"draws":7,"losses":14,"wins":1},"deepseek/deepseek-v4-flash":{"draws":15,"losses":8,"wins":5},"deepseek/deepseek-v4-pro":{"draws":14,"losses":1,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":6,"wins":4},"google/gemini-3.5-flash":{"draws":12,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":24,"losses":11,"wins":11},"google/gemini-3.6-flash":{"draws":16,"losses":17,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":10,"wins":3},"gpt-5.4":{"draws":10,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":15,"losses":1,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":6},"gpt-6-astra":{"draws":2,"losses":10,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":8},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":3},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":6},"meta/muse-spark-1.2":{"draws":7,"losses":6,"wins":5},"meta/muse-spark-1.3":{"draws":5,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":6},"o3":{"draws":3,"losses":15,"wins":8},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":7},"poolside/laguna-s-2.1":{"draws":12,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":11,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":7},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":2},"stealth/ox-alpha":{"draws":19,"losses":25,"wins":21},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":3},"thinkingmachines/inkling-small":{"draws":18,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":8,"losses":8,"wins":2},"x-ai/grok-4.6":{"draws":5,"losses":7,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":9,"wins":9},"z-ai/glm-5.3":{"draws":11,"losses":5,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":7,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":6},"claude-fable-5":{"draws":7,"losses":10,"wins":17},"claude-fable-5-1":{"draws":6,"losses":40,"wins":6},"claude-opus-4-5":{"draws":5,"losses":3,"wins":6},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":9,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":4,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":15},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":18},"google/gemini-3.6-flash":{"draws":14,"losses":13,"wins":19},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":17},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":3,"losses":8,"wins":17},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":8},"gpt-5.6-sol":{"draws":9,"losses":13,"wins":16},"gpt-5.6-terra":{"draws":7,"losses":4,"wins":15},"gpt-6-astra":{"draws":1,"losses":36,"wins":5},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":5},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":6},"meta/muse-spark-1.2":{"draws":8,"losses":1,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":6,"wins":16},"moonshotai/kimi-k3":{"draws":15,"losses":8,"wins":9},"o3":{"draws":0,"losses":7,"wins":13},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":3,"wins":9},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.8-max":{"draws":10,"losses":6,"wins":14},"stealth/ox-alpha":{"draws":31,"losses":34,"wins":39},"tencent/hy4-preview":{"draws":8,"losses":12,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":1},"thinkingmachines/inkling-small":{"draws":7,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":13},"z-ai/glm-5.2":{"draws":5,"losses":7,"wins":10},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":11,"wins":14}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":10},"claude-fable-5":{"draws":3,"losses":15,"wins":10},"claude-fable-5-1":{"draws":1,"losses":26,"wins":1},"claude-opus-4-5":{"draws":2,"losses":3,"wins":9},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":9,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":7,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":8,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":8},"google/gemini-3.5-flash-lite":{"draws":1,"losses":3,"wins":14},"google/gemini-3.6-flash":{"draws":3,"losses":9,"wins":12},"google/gemini-3.8-flash":{"draws":4,"losses":10,"wins":12},"gpt-5.4":{"draws":5,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":18,"wins":10},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":7},"gpt-6-astra":{"draws":0,"losses":26,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":7},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":9},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":9},"meta/muse-spark-1.3":{"draws":2,"losses":8,"wins":12},"moonshotai/kimi-k3":{"draws":2,"losses":11,"wins":9},"o3":{"draws":1,"losses":6,"wins":17},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":8,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":6,"losses":7,"wins":5},"stealth/ox-alpha":{"draws":13,"losses":25,"wins":30},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":3,"losses":9,"wins":11},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":3},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":14},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":4},"x-ai/grok-4.6":{"draws":5,"losses":10,"wins":11},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":10},"z-ai/glm-5.3":{"draws":4,"losses":16,"wins":6},"z-ai/glm-5.3-flash":{"draws":3,"losses":8,"wins":15}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":9,"wins":7},"claude-fable-5":{"draws":6,"losses":14,"wins":4},"claude-fable-5-1":{"draws":2,"losses":32,"wins":2},"claude-opus-4-5":{"draws":5,"losses":4,"wins":13},"claude-sonnet-5":{"draws":3,"losses":8,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":10,"wins":11},"google/gemini-3.5-flash":{"draws":5,"losses":11,"wins":6},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":21},"google/gemini-3.6-flash":{"draws":9,"losses":18,"wins":19},"google/gemini-3.8-flash":{"draws":10,"losses":15,"wins":3},"gpt-5.4":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":16,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":9,"wins":8},"gpt-6-astra":{"draws":5,"losses":27,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":9},"meta/muse-glimmer-30b":{"draws":2,"losses":7,"wins":7},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":16,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":9},"o3":{"draws":7,"losses":13,"wins":15},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":10,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":10},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":7},"qwen/qwen3.8-max":{"draws":12,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":25,"losses":38,"wins":33},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":14,"wins":11},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":6},"thinkingmachines/inkling-small":{"draws":27,"losses":13,"wins":32},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":9},"x-ai/grok-4.6":{"draws":9,"losses":8,"wins":9},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":6},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":8,"wins":17}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":11,"wins":37},"claude-fable-5":{"draws":17,"losses":59,"wins":30},"claude-fable-5-1":{"draws":22,"losses":110,"wins":18},"claude-opus-4-5":{"draws":12,"losses":12,"wins":35},"claude-opus-5":{"draws":2,"losses":1,"wins":3},"claude-sonnet-5":{"draws":12,"losses":26,"wins":43},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":27},"deepseek/deepseek-v4-pro":{"draws":2,"losses":21,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":19,"wins":36},"google/gemini-3.5-flash":{"draws":11,"losses":28,"wins":42},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"wins":36},"google/gemini-3.6-flash":{"draws":19,"losses":46,"wins":66},"google/gemini-3.8-flash":{"draws":15,"losses":42,"wins":55},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":12,"losses":31,"wins":36},"gpt-5.6-luna":{"draws":5,"losses":10,"wins":22},"gpt-5.6-sol":{"draws":14,"losses":56,"wins":49},"gpt-5.6-terra":{"draws":14,"losses":23,"wins":29},"gpt-6-astra":{"draws":26,"losses":91,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":9,"wins":15},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":20},"meta/muse-spark-1.2":{"draws":11,"losses":11,"wins":45},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":45},"moonshotai/kimi-k3":{"draws":16,"losses":21,"wins":50},"o3":{"draws":0,"losses":26,"wins":36},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":18},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":28,"wins":42},"qwen/qwen3.8-27b":{"draws":8,"losses":7,"wins":26},"qwen/qwen3.8-flash":{"draws":11,"losses":18,"wins":28},"qwen/qwen3.8-max":{"draws":15,"losses":30,"wins":47},"stealth/ox-alpha":{"draws":75,"losses":106,"wins":253},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":10,"losses":33,"wins":35},"thinkingmachines/inkling":{"draws":5,"losses":3,"wins":17},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":28},"x-ai/grok-4.5":{"draws":5,"losses":32,"wins":15},"x-ai/grok-4.6":{"draws":15,"losses":46,"wins":43},"z-ai/glm-5.2":{"draws":11,"losses":16,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":51,"wins":41},"z-ai/glm-5.3-flash":{"draws":14,"losses":32,"wins":53}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":3,"losses":15,"wins":4},"claude-opus-4-8":{"draws":2,"losses":10,"wins":4},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":15},"google/gemini-3.5-flash-lite":{"draws":2,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":6},"gpt-5.5":{"draws":0,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":9},"o3":{"draws":5,"losses":19,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":17},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":3,"wins":3}},"tencent/hy3-preview":{"claude-opus-4-5":{"draws":11,"losses":12,"wins":5},"claude-opus-4-8":{"draws":3,"losses":10,"wins":7},"claude-opus-5":{"draws":3,"losses":35,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":9,"wins":8},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":2},"gpt-5.5":{"draws":12,"losses":11,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":12},"o3":{"draws":5,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":8,"wins":8},"z-ai/glm-5.2":{"draws":7,"losses":3,"wins":6}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":0,"wins":4},"claude-fable-5":{"draws":10,"losses":14,"wins":12},"claude-fable-5-1":{"draws":2,"losses":37,"wins":9},"claude-opus-4-5":{"draws":6,"losses":4,"wins":4},"claude-sonnet-5":{"draws":13,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":21},"google/gemini-3.5-flash-lite":{"draws":16,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":13,"losses":17,"wins":18},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":16},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":9,"losses":13,"wins":10},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":14,"wins":15},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":6},"gpt-6-astra":{"draws":6,"losses":32,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":5},"meta/muse-glimmer-30b":{"draws":11,"losses":0,"wins":5},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":13},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":12},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":13},"o3":{"draws":6,"losses":6,"wins":12},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":5,"wins":12},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":5},"qwen/qwen3.8-max":{"draws":7,"losses":9,"wins":14},"stealth/ox-alpha":{"draws":29,"losses":19,"wins":48},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":3,"losses":4,"wins":7},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":6,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":13,"wins":11},"z-ai/glm-5.2":{"draws":11,"losses":2,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":21,"wins":8},"z-ai/glm-5.3-flash":{"draws":12,"losses":16,"wins":8}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":11},"claude-fable-5":{"draws":8,"losses":12,"wins":0},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":16,"losses":48,"wins":8},"claude-opus-4-8":{"draws":2,"losses":8,"wins":0},"claude-opus-5":{"draws":1,"losses":17,"wins":2},"claude-sonnet-5":{"draws":26,"losses":52,"wins":12},"deepseek/deepseek-v4-flash":{"draws":15,"losses":13,"wins":8},"deepseek/deepseek-v4-pro":{"draws":18,"losses":16,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":12,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":13,"losses":7,"wins":8},"google/gemini-3.5-flash-lite":{"draws":80,"losses":90,"wins":70},"google/gemini-3.6-flash":{"draws":60,"losses":109,"wins":27},"google/gemini-3.8-flash":{"draws":9,"losses":6,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4":{"draws":19,"losses":43,"wins":14},"gpt-5.5":{"draws":1,"losses":8,"wins":1},"gpt-5.6-luna":{"draws":39,"losses":37,"wins":20},"gpt-5.6-sol":{"draws":16,"losses":54,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":12,"wins":4},"gpt-6-astra":{"draws":1,"losses":13,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":18,"losses":9,"wins":7},"meituan/longcat-2.0":{"draws":18,"losses":19,"wins":33},"meta/muse-glimmer-30b":{"draws":16,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":23,"losses":33,"wins":4},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":46,"losses":45,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":3},"o3":{"draws":28,"losses":81,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":14},"poolside/laguna-s-2.1":{"draws":33,"losses":30,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":5},"qwen/qwen3.8-27b":{"draws":7,"losses":9,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":11,"wins":6},"qwen/qwen3.8-max":{"draws":5,"losses":9,"wins":6},"stealth/ox-alpha":{"draws":32,"losses":55,"wins":17},"stepfun/step-3.7-flash":{"draws":11,"losses":14,"wins":15},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":23,"wins":10},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":21},"x-ai/grok-4.5":{"draws":23,"losses":44,"wins":11},"x-ai/grok-4.6":{"draws":9,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":8,"wins":11},"z-ai/glm-5.3":{"draws":7,"losses":10,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":15,"wins":7}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":13,"wins":8},"claude-fable-5":{"draws":2,"losses":8,"wins":4},"claude-fable-5-1":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":10,"losses":8,"wins":10},"claude-sonnet-5":{"draws":5,"losses":6,"wins":9},"deepseek/deepseek-v4-flash":{"draws":9,"losses":17,"wins":10},"deepseek/deepseek-v4-pro":{"draws":18,"losses":9,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":4},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":8},"google/gemini-3.5-flash-lite":{"draws":19,"losses":15,"wins":33},"google/gemini-3.6-flash":{"draws":19,"losses":10,"wins":10},"google/gemini-3.8-flash":{"draws":5,"losses":10,"wins":1},"gpt-5.4":{"draws":9,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":5,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":8},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":5},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":6},"meta/muse-glimmer-30b":{"draws":12,"losses":10,"wins":8},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":7,"wins":6},"o3":{"draws":12,"losses":11,"wins":11},"openai/gpt-oss-120b":{"draws":17,"losses":10,"wins":9},"poolside/laguna-s-2.1":{"draws":9,"losses":8,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":11,"wins":6},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.8-flash":{"draws":15,"losses":4,"wins":5},"qwen/qwen3.8-max":{"draws":25,"losses":18,"wins":26},"stealth/ox-alpha":{"draws":25,"losses":35,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":8,"wins":5},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":8},"thinkingmachines/inkling-small":{"draws":20,"losses":9,"wins":23},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.6":{"draws":12,"losses":6,"wins":4},"z-ai/glm-5.2":{"draws":11,"losses":8,"wins":11},"z-ai/glm-5.3":{"draws":5,"losses":3,"wins":4},"z-ai/glm-5.3-flash":{"draws":13,"losses":3,"wins":6}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":1,"wins":15},"claude-fable-5":{"draws":3,"losses":11,"wins":18},"claude-fable-5-1":{"draws":0,"losses":31,"wins":5},"claude-opus-4-5":{"draws":26,"losses":14,"wins":42},"claude-opus-4-8":{"draws":6,"losses":7,"wins":3},"claude-opus-5":{"draws":7,"losses":30,"wins":9},"claude-sonnet-5":{"draws":13,"losses":19,"wins":42},"deepseek/deepseek-v4-flash":{"draws":4,"losses":6,"wins":14},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":16},"google/gemini-3.5-flash-lite":{"draws":24,"losses":49,"wins":95},"google/gemini-3.6-flash":{"draws":21,"losses":64,"wins":87},"google/gemini-3.8-flash":{"draws":3,"losses":5,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":3,"wins":9},"gpt-5.4":{"draws":17,"losses":29,"wins":34},"gpt-5.5":{"draws":3,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":24,"wins":33},"gpt-5.6-sol":{"draws":12,"losses":37,"wins":35},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":24},"gpt-6-astra":{"draws":0,"losses":24,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":26},"meituan/longcat-2.0":{"draws":21,"losses":7,"wins":46},"meta/muse-glimmer-30b":{"draws":3,"losses":5,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":39},"meta/muse-spark-1.3":{"draws":1,"losses":9,"wins":16},"moonshotai/kimi-k3":{"draws":26,"losses":25,"wins":57},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":8},"o3":{"draws":9,"losses":19,"wins":74},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":8,"wins":17},"qwen/qwen3.8-27b":{"draws":0,"losses":3,"wins":9},"qwen/qwen3.8-flash":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":6,"losses":12,"wins":16},"stealth/ox-alpha":{"draws":22,"losses":19,"wins":49},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":19},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":13},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":28},"thinkingmachines/inkling-small":{"draws":4,"losses":7,"wins":15},"x-ai/grok-4.5":{"draws":19,"losses":10,"wins":27},"x-ai/grok-4.6":{"draws":5,"losses":12,"wins":17},"z-ai/glm-5.2":{"draws":7,"losses":5,"wins":16},"z-ai/glm-5.3":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":8}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":4,"wins":5},"claude-fable-5":{"draws":12,"losses":16,"wins":14},"claude-fable-5-1":{"draws":2,"losses":35,"wins":11},"claude-opus-4-5":{"draws":5,"losses":5,"wins":6},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":11,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":10,"losses":5,"wins":17},"google/gemini-3.5-flash-lite":{"draws":9,"losses":7,"wins":20},"google/gemini-3.6-flash":{"draws":7,"losses":20,"wins":11},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":18},"gpt-5.4":{"draws":11,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":20},"gpt-5.6-terra":{"draws":8,"losses":5,"wins":23},"gpt-6-astra":{"draws":5,"losses":29,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":1,"losses":5,"wins":6},"meta/muse-spark-1.2":{"draws":4,"losses":10,"wins":12},"meta/muse-spark-1.3":{"draws":5,"losses":12,"wins":13},"moonshotai/kimi-k3":{"draws":10,"losses":5,"wins":13},"o3":{"draws":3,"losses":10,"wins":9},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":10,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-max":{"draws":4,"losses":7,"wins":17},"stealth/ox-alpha":{"draws":33,"losses":31,"wins":42},"tencent/hy4-preview":{"draws":11,"losses":10,"wins":11},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":3},"thinkingmachines/inkling-small":{"draws":10,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":10},"x-ai/grok-4.6":{"draws":10,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":13},"z-ai/glm-5.3":{"draws":9,"losses":17,"wins":14},"z-ai/glm-5.3-flash":{"draws":4,"losses":15,"wins":11}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":12,"losses":5,"wins":3},"claude-opus-4-8":{"draws":7,"losses":2,"wins":1},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":3},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":2},"o3":{"draws":1,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":4}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":8},"claude-fable-5":{"draws":7,"losses":12,"wins":5},"claude-fable-5-1":{"draws":3,"losses":25,"wins":0},"claude-opus-4-5":{"draws":4,"losses":12,"wins":6},"claude-sonnet-5":{"draws":7,"losses":14,"wins":17},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":2},"google/gemini-3.5-flash":{"draws":7,"losses":13,"wins":6},"google/gemini-3.5-flash-lite":{"draws":16,"losses":9,"wins":17},"google/gemini-3.6-flash":{"draws":12,"losses":19,"wins":7},"google/gemini-3.8-flash":{"draws":7,"losses":14,"wins":5},"gpt-5.4":{"draws":7,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":21,"wins":2},"gpt-5.6-terra":{"draws":17,"losses":12,"wins":1},"gpt-6-astra":{"draws":4,"losses":22,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":2},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":8},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":10,"wins":5},"o3":{"draws":7,"losses":17,"wins":10},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":14},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":8,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-flash":{"draws":6,"losses":3,"wins":3},"qwen/qwen3.8-max":{"draws":9,"losses":9,"wins":4},"stealth/ox-alpha":{"draws":24,"losses":38,"wins":20},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":11,"wins":5},"thinkingmachines/inkling":{"draws":5,"losses":8,"wins":3},"thinkingmachines/inkling-small":{"draws":10,"losses":8,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":2},"x-ai/grok-4.6":{"draws":11,"losses":7,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":8,"wins":8},"z-ai/glm-5.3":{"draws":7,"losses":9,"wins":8},"z-ai/glm-5.3-flash":{"draws":13,"losses":14,"wins":5}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":9},"claude-fable-5":{"draws":4,"losses":5,"wins":27},"claude-fable-5-1":{"draws":4,"losses":30,"wins":12},"claude-opus-4-5":{"draws":3,"losses":0,"wins":9},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":13},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":24},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":34},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":27},"gpt-5.4":{"draws":0,"losses":5,"wins":21},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":27},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":16},"gpt-6-astra":{"draws":4,"losses":30,"wins":8},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":18},"meta/muse-spark-1.3":{"draws":4,"losses":1,"wins":23},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":24},"o3":{"draws":0,"losses":0,"wins":14},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":3,"wins":17},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":18},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":23},"stealth/ox-alpha":{"draws":17,"losses":8,"wins":51},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":19},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":2,"wins":13},"x-ai/grok-4.6":{"draws":5,"losses":4,"wins":29},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":12},"z-ai/glm-5.3":{"draws":4,"losses":1,"wins":17},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":21}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":6,"wins":4},"claude-fable-5":{"draws":5,"losses":11,"wins":16},"claude-fable-5-1":{"draws":5,"losses":33,"wins":6},"claude-opus-4-5":{"draws":3,"losses":2,"wins":7},"claude-sonnet-5":{"draws":2,"losses":6,"wins":12},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":8,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":13},"google/gemini-3.5-flash":{"draws":10,"losses":9,"wins":7},"google/gemini-3.5-flash-lite":{"draws":10,"losses":7,"wins":15},"google/gemini-3.6-flash":{"draws":9,"losses":12,"wins":15},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":10},"gpt-5.4":{"draws":1,"losses":11,"wins":8},"gpt-5.6-luna":{"draws":5,"losses":4,"wins":11},"gpt-5.6-sol":{"draws":6,"losses":11,"wins":15},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":13},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":3,"wins":6},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":6},"meta/muse-spark-1.2":{"draws":1,"losses":8,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":16},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":16},"o3":{"draws":5,"losses":13,"wins":6},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":6,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":7,"wins":11},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":3,"wins":5},"qwen/qwen3.8-max":{"draws":7,"losses":8,"wins":7},"stealth/ox-alpha":{"draws":23,"losses":32,"wins":41},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":7,"losses":3,"wins":14},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":3},"thinkingmachines/inkling-small":{"draws":9,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.6":{"draws":2,"losses":12,"wins":14},"z-ai/glm-5.2":{"draws":10,"losses":6,"wins":12},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":8},"z-ai/glm-5.3-flash":{"draws":8,"losses":10,"wins":4}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":9},"claude-fable-5":{"draws":3,"losses":6,"wins":5},"claude-fable-5-1":{"draws":1,"losses":15,"wins":2},"claude-opus-4-5":{"draws":3,"losses":10,"wins":5},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":12,"losses":12,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":10,"wins":8},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":7},"google/gemini-3.5-flash-lite":{"draws":16,"losses":10,"wins":22},"google/gemini-3.6-flash":{"draws":10,"losses":20,"wins":16},"google/gemini-3.8-flash":{"draws":6,"losses":8,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":4,"losses":1,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":14},"gpt-5.6-sol":{"draws":1,"losses":13,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":7},"gpt-6-astra":{"draws":2,"losses":5,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":10,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":9},"meta/muse-glimmer-30b":{"draws":6,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":8},"meta/muse-spark-1.3":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":3,"losses":9,"wins":6},"o3":{"draws":4,"losses":11,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-27b":{"draws":1,"losses":4,"wins":5},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":6,"wins":12},"stealth/ox-alpha":{"draws":19,"losses":33,"wins":24},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":9},"thinkingmachines/inkling-small":{"draws":5,"losses":4,"wins":13},"x-ai/grok-4.5":{"draws":6,"losses":7,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":9,"wins":7},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":5}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":4,"wins":3},"claude-fable-5":{"draws":4,"losses":8,"wins":14},"claude-fable-5-1":{"draws":0,"losses":37,"wins":9},"claude-opus-4-5":{"draws":3,"losses":2,"wins":11},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":4,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":5,"losses":10,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":9,"wins":9},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":18},"google/gemini-3.5-flash-lite":{"draws":7,"losses":10,"wins":5},"google/gemini-3.6-flash":{"draws":4,"losses":15,"wins":15},"google/gemini-3.8-flash":{"draws":4,"losses":9,"wins":19},"gpt-5.4":{"draws":7,"losses":12,"wins":13},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":13},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":14},"gpt-6-astra":{"draws":4,"losses":31,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":5},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":4},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":8},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":12},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":19},"o3":{"draws":1,"losses":4,"wins":13},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.8-flash":{"draws":5,"losses":3,"wins":4},"qwen/qwen3.8-max":{"draws":2,"losses":8,"wins":14},"stealth/ox-alpha":{"draws":29,"losses":18,"wins":45},"tencent/hy4-preview":{"draws":5,"losses":5,"wins":14},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling-small":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":6},"x-ai/grok-4.6":{"draws":8,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":9,"losses":6,"wins":11},"z-ai/glm-5.3":{"draws":3,"losses":21,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":8,"wins":9}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":10},"claude-fable-5":{"draws":2,"losses":9,"wins":31},"claude-fable-5-1":{"draws":2,"losses":23,"wins":13},"claude-opus-4-5":{"draws":0,"losses":1,"wins":11},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":2,"losses":1,"wins":19},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":11},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":25},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":16},"google/gemini-3.6-flash":{"draws":2,"losses":8,"wins":30},"google/gemini-3.8-flash":{"draws":6,"losses":4,"wins":28},"gpt-5.4":{"draws":4,"losses":6,"wins":20},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":28},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":16},"gpt-6-astra":{"draws":4,"losses":35,"wins":9},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":3},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":17},"meta/muse-spark-1.3":{"draws":2,"losses":2,"wins":26},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":23},"o3":{"draws":0,"losses":2,"wins":14},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":13},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-max":{"draws":1,"losses":2,"wins":21},"stealth/ox-alpha":{"draws":12,"losses":11,"wins":71},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":0,"losses":7,"wins":19},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":18},"x-ai/grok-4.6":{"draws":2,"losses":10,"wins":28},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":14},"z-ai/glm-5.3":{"draws":4,"losses":8,"wins":26},"z-ai/glm-5.3-flash":{"draws":3,"losses":5,"wins":22}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":13},"claude-fable-5":{"draws":4,"losses":12,"wins":2},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-opus-4-5":{"draws":12,"losses":10,"wins":20},"claude-opus-4-8":{"draws":4,"losses":6,"wins":6},"claude-opus-5":{"draws":6,"losses":22,"wins":10},"claude-sonnet-5":{"draws":18,"losses":18,"wins":46},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":15},"deepseek/deepseek-v4-pro":{"draws":3,"losses":8,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":10,"wins":8},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":15,"wins":9},"google/gemini-3.5-flash-lite":{"draws":41,"losses":33,"wins":90},"google/gemini-3.6-flash":{"draws":35,"losses":64,"wins":51},"google/gemini-3.8-flash":{"draws":5,"losses":16,"wins":9},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":3},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":4,"wins":7},"gpt-5.4":{"draws":11,"losses":34,"wins":15},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":12},"gpt-5.5":{"draws":6,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":24,"losses":22,"wins":26},"gpt-5.6-sol":{"draws":13,"losses":45,"wins":14},"gpt-5.6-terra":{"draws":8,"losses":7,"wins":15},"gpt-6-astra":{"draws":5,"losses":16,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":15},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":28},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":25,"wins":14},"meta/muse-spark-1.3":{"draws":5,"losses":18,"wins":9},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":39,"losses":31,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":4},"o3":{"draws":11,"losses":40,"wins":73},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":18,"losses":3,"wins":29},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":10,"wins":11},"qwen/qwen3.8-27b":{"draws":1,"losses":8,"wins":5},"qwen/qwen3.8-flash":{"draws":5,"losses":3,"wins":8},"qwen/qwen3.8-max":{"draws":5,"losses":14,"wins":6},"stealth/ox-alpha":{"draws":25,"losses":33,"wins":33},"stepfun/step-3.7-flash":{"draws":4,"losses":12,"wins":12},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"tencent/hy4-preview":{"draws":7,"losses":11,"wins":8},"thinkingmachines/inkling":{"draws":9,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":5,"losses":3,"wins":15},"x-ai/grok-4.5":{"draws":26,"losses":38,"wins":26},"x-ai/grok-4.6":{"draws":7,"losses":13,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":5,"losses":6,"wins":11},"z-ai/glm-5.3":{"draws":6,"losses":6,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":11,"wins":10}},"claude-opus-4-8":{"claude-opus-4-5":{"draws":6,"losses":11,"wins":13},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":3,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":5,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":14},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":4,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":10}},"claude-opus-5":{"claude-opus-4-5":{"draws":15,"losses":6,"wins":73},"claude-opus-4-8":{"draws":8,"losses":9,"wins":25},"claude-opus-5":{"draws":15,"losses":59,"wins":54},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":19},"google/gemini-3.6-flash":{"draws":3,"losses":11,"wins":36},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":1,"wins":19},"gpt-5":{"draws":3,"losses":2,"wins":17},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":19},"gpt-5.5":{"draws":7,"losses":16,"wins":35},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k3":{"draws":5,"losses":1,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":16},"o3":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":31},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":24},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":13},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":32}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":2,"wins":21},"claude-fable-5":{"draws":6,"losses":9,"wins":5},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":14,"losses":26,"wins":10},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":16,"losses":21,"wins":11},"deepseek/deepseek-v4-flash":{"draws":12,"losses":5,"wins":19},"deepseek/deepseek-v4-pro":{"draws":14,"losses":11,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":10,"wins":6},"google/gemini-3.5-flash":{"draws":8,"losses":4,"wins":8},"google/gemini-3.5-flash-lite":{"draws":47,"losses":32,"wins":67},"google/gemini-3.6-flash":{"draws":41,"losses":47,"wins":30},"google/gemini-3.8-flash":{"draws":8,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":27,"losses":35,"wins":10},"gpt-5.6-luna":{"draws":27,"losses":17,"wins":34},"gpt-5.6-sol":{"draws":13,"losses":52,"wins":13},"gpt-5.6-terra":{"draws":11,"losses":5,"wins":4},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":15},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":14,"losses":5,"wins":23},"meta/muse-glimmer-30b":{"draws":15,"losses":3,"wins":14},"meta/muse-spark-1.2":{"draws":16,"losses":22,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":28,"losses":30,"wins":14},"o3":{"draws":12,"losses":32,"wins":34},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":19,"losses":3,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":6,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":2,"wins":7},"qwen/qwen3.8-max":{"draws":10,"losses":9,"wins":10},"stealth/ox-alpha":{"draws":24,"losses":41,"wins":31},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":20,"losses":5,"wins":27},"thinkingmachines/inkling-small":{"draws":9,"losses":4,"wins":21},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":13},"x-ai/grok-4.6":{"draws":7,"losses":7,"wins":8},"z-ai/glm-5.2":{"draws":16,"losses":10,"wins":14},"z-ai/glm-5.3":{"draws":4,"losses":16,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":11,"wins":7}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":4,"losses":11,"wins":3},"claude-opus-4-8":{"draws":5,"losses":5,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":7},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":13,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":5},"gpt-5.5":{"draws":7,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":8,"wins":9},"o3":{"draws":4,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":2,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":11,"wins":15},"claude-fable-5":{"draws":8,"losses":16,"wins":2},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-opus-4-5":{"draws":15,"losses":19,"wins":10},"claude-opus-4-8":{"draws":8,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":22,"wins":1},"claude-sonnet-5":{"draws":14,"losses":13,"wins":11},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":11,"losses":14,"wins":17},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":19,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":15,"wins":5},"google/gemini-3.5-flash-lite":{"draws":22,"losses":6,"wins":28},"google/gemini-3.6-flash":{"draws":20,"losses":22,"wins":18},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":8},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":6,"wins":1},"gpt-5.4":{"draws":13,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":20},"gpt-5.5":{"draws":15,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":16,"losses":10,"wins":10},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":3},"gpt-5.6-terra":{"draws":16,"losses":10,"wins":8},"gpt-6-astra":{"draws":0,"losses":15,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":13},"inclusionai/ling-3.0-flash":{"draws":14,"losses":10,"wins":12},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":18},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":8,"wins":8},"meta/muse-spark-1.3":{"draws":3,"losses":9,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":4,"losses":12,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":14},"poolside/laguna-s-2.1":{"draws":21,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":17,"wins":5},"qwen/qwen3.8-27b":{"draws":1,"losses":5,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":5,"wins":3},"qwen/qwen3.8-max":{"draws":10,"losses":11,"wins":9},"stealth/ox-alpha":{"draws":32,"losses":32,"wins":20},"stepfun/step-3.7-flash":{"draws":4,"losses":14,"wins":8},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":9},"thinkingmachines/inkling":{"draws":12,"losses":17,"wins":11},"thinkingmachines/inkling-small":{"draws":11,"losses":4,"wins":21},"x-ai/grok-4.5":{"draws":6,"losses":11,"wins":5},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":35,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":22,"losses":29,"wins":15},"z-ai/glm-5.3":{"draws":9,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":9,"wins":5}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":5,"wins":12},"claude-fable-5":{"draws":8,"losses":5,"wins":15},"claude-fable-5-1":{"draws":0,"losses":20,"wins":2},"claude-opus-4-5":{"draws":3,"losses":5,"wins":8},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":9,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":8,"wins":7},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":11,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":8},"google/gemini-3.5-flash-lite":{"draws":8,"losses":18,"wins":18},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":23},"google/gemini-3.8-flash":{"draws":5,"losses":9,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":10,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":11},"gpt-5.6-sol":{"draws":0,"losses":15,"wins":9},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":21},"gpt-6-astra":{"draws":0,"losses":13,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":5},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":10},"meta/muse-glimmer-30b":{"draws":8,"losses":4,"wins":6},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":13},"meta/muse-spark-1.3":{"draws":1,"losses":12,"wins":13},"moonshotai/kimi-k3":{"draws":6,"losses":12,"wins":6},"o3":{"draws":1,"losses":14,"wins":13},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":10},"poolside/laguna-s-2.1":{"draws":3,"losses":2,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":12,"wins":6},"qwen/qwen3.8-27b":{"draws":0,"losses":5,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":24,"losses":25,"wins":35},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":9,"wins":13},"thinkingmachines/inkling":{"draws":5,"losses":3,"wins":4},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":10,"wins":10},"x-ai/grok-4.6":{"draws":4,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":10},"z-ai/glm-5.3":{"draws":2,"losses":14,"wins":8},"z-ai/glm-5.3-flash":{"draws":2,"losses":7,"wins":11}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":11,"wins":12},"claude-fable-5":{"draws":4,"losses":17,"wins":7},"claude-fable-5-1":{"draws":1,"losses":27,"wins":2},"claude-opus-4-5":{"draws":6,"losses":6,"wins":6},"claude-sonnet-5":{"draws":12,"losses":7,"wins":15},"deepseek/deepseek-v4-flash":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":2},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":9},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":28},"google/gemini-3.6-flash":{"draws":15,"losses":20,"wins":7},"google/gemini-3.8-flash":{"draws":10,"losses":11,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":8,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":9},"gpt-5.6-sol":{"draws":7,"losses":19,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":13,"wins":9},"gpt-6-astra":{"draws":2,"losses":24,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":9},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":15},"meta/muse-spark-1.2":{"draws":11,"losses":7,"wins":8},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":9},"moonshotai/kimi-k3":{"draws":10,"losses":15,"wins":7},"o3":{"draws":5,"losses":13,"wins":12},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":8,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":7,"wins":9},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-flash":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-max":{"draws":18,"losses":11,"wins":7},"stealth/ox-alpha":{"draws":26,"losses":44,"wins":26},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":9},"thinkingmachines/inkling":{"draws":5,"losses":5,"wins":4},"thinkingmachines/inkling-small":{"draws":9,"losses":6,"wins":21},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":9},"x-ai/grok-4.6":{"draws":9,"losses":11,"wins":12},"z-ai/glm-5.2":{"draws":12,"losses":3,"wins":13},"z-ai/glm-5.3":{"draws":8,"losses":10,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":16,"wins":10}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":6,"losses":20,"wins":0},"claude-opus-4-8":{"draws":6,"losses":10,"wins":2},"claude-opus-5":{"draws":1,"losses":8,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":13,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":9},"gpt-5.5":{"draws":3,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":6,"losses":6,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":1},"xiaomi/mimo-v2.5":{"draws":17,"losses":17,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":4}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":7},"claude-fable-5":{"draws":10,"losses":19,"wins":7},"claude-fable-5-1":{"draws":6,"losses":38,"wins":0},"claude-opus-4-5":{"draws":5,"losses":7,"wins":10},"claude-sonnet-5":{"draws":9,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":7},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":8,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":5},"google/gemini-3.5-flash-lite":{"draws":15,"losses":7,"wins":10},"google/gemini-3.6-flash":{"draws":15,"losses":18,"wins":13},"google/gemini-3.8-flash":{"draws":9,"losses":18,"wins":15},"gpt-5.4":{"draws":3,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":10},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":8},"gpt-6-astra":{"draws":5,"losses":31,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":3,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":6},"meta/muse-spark-1.2":{"draws":5,"losses":3,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":9},"moonshotai/kimi-k3":{"draws":11,"losses":5,"wins":14},"o3":{"draws":3,"losses":5,"wins":10},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":7,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":5},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.8-max":{"draws":4,"losses":7,"wins":7},"stealth/ox-alpha":{"draws":26,"losses":31,"wins":36},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling-small":{"draws":5,"losses":6,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":7},"x-ai/grok-4.6":{"draws":8,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":10,"losses":11,"wins":9},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":11},"z-ai/glm-5.3-flash":{"draws":15,"losses":14,"wins":9}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":20,"wins":17},"claude-fable-5":{"draws":8,"losses":3,"wins":5},"claude-opus-4-5":{"draws":44,"losses":67,"wins":7},"claude-opus-4-8":{"draws":11,"losses":7,"wins":0},"claude-opus-5":{"draws":6,"losses":18,"wins":2},"claude-sonnet-5":{"draws":34,"losses":79,"wins":21},"cohere/north-mini-code":{"draws":12,"losses":10,"wins":0},"deepseek/deepseek-v4-flash":{"draws":23,"losses":25,"wins":12},"deepseek/deepseek-v4-pro":{"draws":17,"losses":17,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":17,"wins":9},"google/gemini-3.1-flash-lite":{"draws":7,"losses":8,"wins":5},"google/gemini-3.5-flash":{"draws":15,"losses":5,"wins":12},"google/gemini-3.5-flash-lite":{"draws":105,"losses":97,"wins":90},"google/gemini-3.6-flash":{"draws":109,"losses":121,"wins":39},"google/gemini-3.8-flash":{"draws":9,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":11,"wins":1},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":6},"gpt-5":{"draws":9,"losses":4,"wins":5},"gpt-5.4":{"draws":41,"losses":57,"wins":10},"gpt-5.4-mini":{"draws":11,"losses":13,"wins":2},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":10},"gpt-5.5":{"draws":13,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":48,"losses":66,"wins":26},"gpt-5.6-sol":{"draws":17,"losses":76,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":17,"wins":5},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":19,"losses":15,"wins":14},"inclusionai/ling-3.0-flash":{"draws":18,"losses":19,"wins":21},"meituan/longcat-2.0":{"draws":29,"losses":58,"wins":23},"meta/muse-glimmer-30b":{"draws":29,"losses":11,"wins":20},"meta/muse-spark-1.2":{"draws":21,"losses":56,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":12,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":52,"losses":64,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":2},"o3":{"draws":45,"losses":137,"wins":32},"openai/gpt-oss-120b":{"draws":25,"losses":22,"wins":15},"poolside/laguna-s-2.1":{"draws":56,"losses":46,"wins":22},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":24,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":12,"wins":2},"qwen/qwen3.8-max":{"draws":19,"losses":14,"wins":12},"stealth/ox-alpha":{"draws":42,"losses":52,"wins":18},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":38,"losses":32,"wins":48},"thinkingmachines/inkling-small":{"draws":27,"losses":18,"wins":30},"x-ai/grok-4.5":{"draws":40,"losses":71,"wins":9},"x-ai/grok-4.6":{"draws":19,"losses":16,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":15,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":31,"losses":20,"wins":13},"z-ai/glm-5.3":{"draws":11,"losses":3,"wins":2},"z-ai/glm-5.3-flash":{"draws":15,"losses":15,"wins":10}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":5,"wins":18},"claude-fable-5":{"draws":6,"losses":19,"wins":15},"claude-fable-5-1":{"draws":2,"losses":35,"wins":5},"claude-opus-4-5":{"draws":22,"losses":24,"wins":56},"claude-opus-4-8":{"draws":10,"losses":4,"wins":14},"claude-opus-5":{"draws":3,"losses":31,"wins":14},"claude-sonnet-5":{"draws":25,"losses":22,"wins":35},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":22},"deepseek/deepseek-v4-pro":{"draws":8,"losses":11,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":20},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":16},"google/gemini-3.5-flash-lite":{"draws":63,"losses":33,"wins":131},"google/gemini-3.6-flash":{"draws":41,"losses":55,"wins":94},"google/gemini-3.8-flash":{"draws":4,"losses":20,"wins":16},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":6},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":9},"gpt-5.4":{"draws":25,"losses":42,"wins":37},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":14},"gpt-5.5":{"draws":9,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":21,"losses":16,"wins":55},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":35},"gpt-5.6-terra":{"draws":12,"losses":9,"wins":13},"gpt-6-astra":{"draws":7,"losses":28,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":5,"losses":4,"wins":3},"inclusionai/ling-3.0-flash":{"draws":20,"losses":3,"wins":25},"meituan/longcat-2.0":{"draws":28,"losses":9,"wins":49},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":31},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":28,"losses":37,"wins":61},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":10},"o3":{"draws":20,"losses":25,"wins":101},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":25,"losses":12,"wins":39},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":14,"wins":10},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":9},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":11,"losses":6,"wins":15},"stealth/ox-alpha":{"draws":31,"losses":41,"wins":44},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":19},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":10,"losses":11,"wins":15},"thinkingmachines/inkling":{"draws":27,"losses":13,"wins":40},"thinkingmachines/inkling-small":{"draws":9,"losses":6,"wins":12},"x-ai/grok-4.5":{"draws":27,"losses":38,"wins":49},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":15},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":4,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":16,"losses":11,"wins":13},"z-ai/glm-5.3":{"draws":7,"losses":20,"wins":9},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":8}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":0,"wins":5},"claude-fable-5":{"draws":6,"losses":12,"wins":18},"claude-fable-5-1":{"draws":3,"losses":25,"wins":6},"claude-opus-4-5":{"draws":7,"losses":2,"wins":13},"claude-sonnet-5":{"draws":12,"losses":10,"wins":6},"deepseek/deepseek-v4-flash":{"draws":12,"losses":5,"wins":9},"deepseek/deepseek-v4-pro":{"draws":12,"losses":6,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":10,"losses":12,"wins":12},"google/gemini-3.5-flash-lite":{"draws":15,"losses":2,"wins":15},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":18},"google/gemini-3.8-flash":{"draws":6,"losses":6,"wins":10},"gpt-5.4":{"draws":12,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":17,"wins":9},"gpt-5.6-terra":{"draws":8,"losses":7,"wins":9},"gpt-6-astra":{"draws":2,"losses":28,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":2},"meta/muse-glimmer-30b":{"draws":14,"losses":2,"wins":2},"meta/muse-spark-1.2":{"draws":5,"losses":8,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":10,"wins":8},"moonshotai/kimi-k3":{"draws":13,"losses":4,"wins":9},"o3":{"draws":6,"losses":9,"wins":15},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":11,"wins":16},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":9},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":12},"stealth/ox-alpha":{"draws":25,"losses":29,"wins":46},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":9,"wins":14},"thinkingmachines/inkling":{"draws":10,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":12,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-4.6":{"draws":12,"losses":13,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":3,"wins":10},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":8,"wins":15}},"google/gemma-4-31b-it":{"claude-opus-4-5":{"draws":4,"losses":5,"wins":11},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":1,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":10,"wins":5},"gpt-5.5":{"draws":2,"losses":7,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":4,"losses":6,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"gpt-5":{"claude-opus-4-5":{"draws":6,"losses":12,"wins":10},"claude-opus-4-8":{"draws":7,"losses":11,"wins":8},"claude-opus-5":{"draws":7,"losses":14,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":9,"wins":5},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":6},"gpt-5.5":{"draws":3,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":5},"o3":{"draws":3,"losses":4,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":6}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":5,"wins":5},"claude-fable-5":{"draws":10,"losses":7,"wins":11},"claude-fable-5-1":{"draws":0,"losses":26,"wins":6},"claude-opus-4-5":{"draws":17,"losses":6,"wins":23},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":36,"losses":12,"wins":28},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":10},"deepseek/deepseek-v4-pro":{"draws":10,"losses":5,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":7,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":12},"google/gemini-3.5-flash-lite":{"draws":48,"losses":21,"wins":61},"google/gemini-3.6-flash":{"draws":40,"losses":42,"wins":46},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":22,"losses":16,"wins":29},"gpt-5.6-luna":{"draws":36,"losses":12,"wins":38},"gpt-5.6-sol":{"draws":14,"losses":44,"wins":24},"gpt-5.6-terra":{"draws":15,"losses":3,"wins":10},"gpt-6-astra":{"draws":6,"losses":15,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":3,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":20},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":7},"meta/muse-spark-1.2":{"draws":21,"losses":11,"wins":30},"meta/muse-spark-1.3":{"draws":12,"losses":7,"wins":11},"moonshotai/kimi-k3":{"draws":19,"losses":17,"wins":36},"o3":{"draws":10,"losses":15,"wins":51},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":6},"poolside/laguna-s-2.1":{"draws":16,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":12,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":7},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":9,"wins":11},"stealth/ox-alpha":{"draws":32,"losses":22,"wins":38},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":7,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":22},"thinkingmachines/inkling-small":{"draws":25,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":19,"wins":23},"x-ai/grok-4.6":{"draws":14,"losses":5,"wins":13},"z-ai/glm-5.2":{"draws":9,"losses":4,"wins":11},"z-ai/glm-5.3":{"draws":10,"losses":9,"wins":13},"z-ai/glm-5.3-flash":{"draws":4,"losses":7,"wins":7}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":11,"losses":16,"wins":13},"claude-opus-4-8":{"draws":8,"losses":8,"wins":12},"claude-opus-5":{"draws":6,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":13},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":6},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":7,"losses":2,"wins":5},"gpt-5":{"draws":3,"losses":4,"wins":9},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":14},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":6,"wins":5},"o3":{"draws":2,"losses":3,"wins":7},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":14},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":9},"xiaomi/mimo-v2.5":{"draws":17,"losses":7,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":10,"wins":5}},"gpt-5.4-nano":{"claude-opus-4-5":{"draws":14,"losses":17,"wins":21},"claude-opus-4-8":{"draws":6,"losses":20,"wins":8},"claude-opus-5":{"draws":3,"losses":22,"wins":11},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":13},"deepseek/deepseek-v4-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":18},"google/gemini-3.5-flash-lite":{"draws":2,"losses":10,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":8,"wins":9},"gpt-4.1":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":4,"losses":10,"wins":14},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":18},"gpt-5.4-nano":{"draws":2,"losses":13,"wins":21},"gpt-5.5":{"draws":7,"losses":17,"wins":10},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":19},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":9},"o3":{"draws":3,"losses":11,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":17,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":11},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":13},"xiaomi/mimo-v2.5":{"draws":24,"losses":27,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"z-ai/glm-5.2":{"draws":5,"losses":10,"wins":13}},"gpt-5.5":{"claude-opus-4-5":{"draws":11,"losses":9,"wins":10},"claude-opus-4-8":{"draws":8,"losses":10,"wins":12},"claude-opus-5":{"draws":10,"losses":28,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":10},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":7,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":6,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":5,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"o3":{"draws":4,"losses":3,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":11,"wins":8},"claude-fable-5":{"draws":6,"losses":11,"wins":1},"claude-fable-5-1":{"draws":5,"losses":11,"wins":0},"claude-opus-4-5":{"draws":19,"losses":20,"wins":15},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":34,"losses":31,"wins":19},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":12,"losses":11,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":14,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":50,"losses":31,"wins":61},"google/gemini-3.6-flash":{"draws":37,"losses":57,"wins":28},"google/gemini-3.8-flash":{"draws":10,"losses":13,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":28,"losses":37,"wins":13},"gpt-5.6-luna":{"draws":24,"losses":11,"wins":18},"gpt-5.6-sol":{"draws":16,"losses":47,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":12},"gpt-6-astra":{"draws":2,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":6,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":17},"meta/muse-glimmer-30b":{"draws":17,"losses":6,"wins":15},"meta/muse-spark-1.2":{"draws":15,"losses":26,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":10,"wins":7},"moonshotai/kimi-k3":{"draws":23,"losses":35,"wins":14},"o3":{"draws":16,"losses":26,"wins":34},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":10},"poolside/laguna-s-2.1":{"draws":18,"losses":4,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":12,"wins":7},"qwen/qwen3.8-27b":{"draws":6,"losses":6,"wins":8},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":9},"stealth/ox-alpha":{"draws":27,"losses":21,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":10,"losses":12,"wins":4},"thinkingmachines/inkling":{"draws":22,"losses":10,"wins":22},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":16},"x-ai/grok-4.5":{"draws":16,"losses":18,"wins":14},"x-ai/grok-4.6":{"draws":8,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":6,"wins":10},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":10,"wins":7}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":8,"wins":12},"claude-fable-5":{"draws":8,"losses":13,"wins":13},"claude-fable-5-1":{"draws":5,"losses":39,"wins":4},"claude-opus-4-5":{"draws":10,"losses":10,"wins":28},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":11,"losses":16,"wins":57},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":8,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":15},"google/gemini-3.5-flash-lite":{"draws":8,"losses":14,"wins":82},"google/gemini-3.6-flash":{"draws":13,"losses":41,"wins":54},"google/gemini-3.8-flash":{"draws":5,"losses":16,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":14,"losses":23,"wins":35},"gpt-5.6-luna":{"draws":6,"losses":12,"wins":46},"gpt-5.6-sol":{"draws":14,"losses":42,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":13},"gpt-6-astra":{"draws":6,"losses":33,"wins":3},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":8},"inclusionai/ling-3.0-flash":{"draws":1,"losses":4,"wins":9},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":22},"meta/muse-glimmer-30b":{"draws":0,"losses":1,"wins":7},"meta/muse-spark-1.2":{"draws":5,"losses":13,"wins":42},"meta/muse-spark-1.3":{"draws":9,"losses":10,"wins":11},"moonshotai/kimi-k3":{"draws":20,"losses":19,"wins":33},"o3":{"draws":7,"losses":11,"wins":50},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":7,"wins":12},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":9},"qwen/qwen3.8-max":{"draws":9,"losses":11,"wins":8},"stealth/ox-alpha":{"draws":15,"losses":31,"wins":55},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":7},"tencent/hy4-preview":{"draws":3,"losses":10,"wins":11},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":29},"thinkingmachines/inkling-small":{"draws":1,"losses":7,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":27},"x-ai/grok-4.6":{"draws":5,"losses":16,"wins":13},"z-ai/glm-5.2":{"draws":2,"losses":4,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":12,"wins":15},"z-ai/glm-5.3-flash":{"draws":8,"losses":15,"wins":9}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":5,"wins":10},"claude-fable-5":{"draws":4,"losses":16,"wins":8},"claude-fable-5-1":{"draws":2,"losses":24,"wins":2},"claude-opus-4-5":{"draws":9,"losses":7,"wins":8},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":10,"losses":9,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":5},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":13,"wins":7},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":13},"google/gemini-3.5-flash-lite":{"draws":14,"losses":12,"wins":12},"google/gemini-3.6-flash":{"draws":9,"losses":17,"wins":14},"google/gemini-3.8-flash":{"draws":6,"losses":9,"wins":11},"gpt-5.4":{"draws":14,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":12,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":16,"wins":8},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":0,"losses":24,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":10},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":6},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":13,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":16,"wins":9},"o3":{"draws":3,"losses":16,"wins":15},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":4},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":15,"wins":7},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":8},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":2},"qwen/qwen3.8-max":{"draws":12,"losses":11,"wins":7},"stealth/ox-alpha":{"draws":26,"losses":31,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":1},"tencent/hy4-preview":{"draws":5,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":17,"wins":7},"x-ai/grok-4.6":{"draws":11,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":11},"z-ai/glm-5.3":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.3-flash":{"draws":3,"losses":11,"wins":6}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":8},"claude-fable-5":{"draws":3,"losses":8,"wins":31},"claude-fable-5-1":{"draws":4,"losses":18,"wins":32},"claude-opus-4-5":{"draws":3,"losses":0,"wins":15},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":1,"losses":0,"wins":19},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":19},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":15},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":32},"google/gemini-3.8-flash":{"draws":5,"losses":2,"wins":35},"gpt-5.4":{"draws":2,"losses":5,"wins":25},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":26},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":19},"gpt-6-astra":{"draws":4,"losses":21,"wins":7},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":7},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":3,"losses":0,"wins":21},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":20},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":20},"o3":{"draws":0,"losses":0,"wins":16},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":24},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":14},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":16},"qwen/qwen3.8-max":{"draws":4,"losses":0,"wins":22},"stealth/ox-alpha":{"draws":22,"losses":7,"wins":66},"tencent/hy4-preview":{"draws":3,"losses":2,"wins":21},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":3,"wins":15},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":27},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":14},"z-ai/glm-5.3":{"draws":4,"losses":7,"wins":25},"z-ai/glm-5.3-flash":{"draws":7,"losses":2,"wins":21}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":4,"wins":0},"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":4,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":6,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":11,"wins":0},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":2,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":4,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":1},"meta/muse-glimmer-30b":{"draws":6,"losses":6,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":5,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"o3":{"draws":4,"losses":10,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":0},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":5,"wins":0},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-max":{"draws":3,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":6,"losses":8,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":5,"wins":0},"thinkingmachines/inkling-small":{"draws":2,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":7},"claude-fable-5":{"draws":6,"losses":0,"wins":0},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":3,"losses":9,"wins":0},"claude-sonnet-5":{"draws":8,"losses":12,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":12,"wins":1},"deepseek/deepseek-v4-pro":{"draws":13,"losses":7,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":2},"google/gemini-3.5-flash-lite":{"draws":19,"losses":16,"wins":7},"google/gemini-3.6-flash":{"draws":13,"losses":13,"wins":2},"google/gemini-3.8-flash":{"draws":10,"losses":5,"wins":1},"gpt-5.4":{"draws":8,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":11,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":3},"meta/muse-glimmer-30b":{"draws":16,"losses":9,"wins":3},"meta/muse-spark-1.2":{"draws":3,"losses":7,"wins":2},"meta/muse-spark-1.3":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":0},"o3":{"draws":7,"losses":15,"wins":4},"openai/gpt-oss-120b":{"draws":7,"losses":12,"wins":3},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":8,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":8,"losses":5,"wins":1},"stealth/ox-alpha":{"draws":15,"losses":19,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":10,"losses":6,"wins":4},"thinkingmachines/inkling-small":{"draws":10,"losses":11,"wins":7},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":12,"wins":3},"z-ai/glm-5.3":{"draws":7,"losses":0,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":7,"wins":3}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":4},"claude-fable-5":{"draws":4,"losses":1,"wins":1},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":14,"losses":23,"wins":15},"claude-opus-4-8":{"draws":4,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":5,"wins":1},"claude-sonnet-5":{"draws":17,"losses":36,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":10},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":5,"wins":4},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":5,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":46,"losses":76,"wins":34},"google/gemini-3.6-flash":{"draws":52,"losses":62,"wins":26},"google/gemini-3.8-flash":{"draws":2,"losses":7,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":9,"losses":29,"wins":12},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":2},"gpt-5.5":{"draws":1,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":20,"losses":17,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":34,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":4,"losses":7,"wins":9},"meituan/longcat-2.0":{"draws":17,"losses":29,"wins":24},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":5},"meta/muse-spark-1.2":{"draws":15,"losses":12,"wins":11},"meta/muse-spark-1.3":{"draws":1,"losses":10,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":44,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":6,"losses":67,"wins":27},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":18,"losses":18,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":12,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":10,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-max":{"draws":13,"losses":8,"wins":6},"stealth/ox-alpha":{"draws":14,"losses":22,"wins":12},"stepfun/step-3.7-flash":{"draws":0,"losses":12,"wins":8},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":22,"losses":19,"wins":21},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":8},"x-ai/grok-4.5":{"draws":20,"losses":43,"wins":7},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":5,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":5,"losses":6,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":1}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":17,"wins":11},"claude-fable-5":{"draws":10,"losses":12,"wins":7},"claude-fable-5-1":{"draws":1,"losses":24,"wins":1},"claude-opus-4-5":{"draws":27,"losses":52,"wins":26},"claude-opus-4-8":{"draws":4,"losses":4,"wins":2},"claude-opus-5":{"draws":7,"losses":19,"wins":4},"claude-sonnet-5":{"draws":33,"losses":70,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":12,"losses":22,"wins":6},"deepseek/deepseek-v4-pro":{"draws":12,"losses":24,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":23,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":5},"google/gemini-3.5-flash-lite":{"draws":69,"losses":105,"wins":115},"google/gemini-3.6-flash":{"draws":64,"losses":147,"wins":36},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":8},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-5":{"draws":1,"losses":7,"wins":0},"gpt-5.4":{"draws":30,"losses":58,"wins":15},"gpt-5.4-mini":{"draws":5,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":5},"gpt-5.5":{"draws":3,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":36,"losses":51,"wins":35},"gpt-5.6-sol":{"draws":21,"losses":78,"wins":13},"gpt-5.6-terra":{"draws":13,"losses":15,"wins":14},"gpt-6-astra":{"draws":2,"losses":20,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":9,"wins":18},"inclusionai/ling-3.0-flash":{"draws":19,"losses":18,"wins":27},"meituan/longcat-2.0":{"draws":24,"losses":18,"wins":16},"meta/muse-glimmer-30b":{"draws":10,"losses":18,"wins":8},"meta/muse-spark-1.2":{"draws":21,"losses":31,"wins":28},"meta/muse-spark-1.3":{"draws":12,"losses":15,"wins":5},"minimax/minimax-m3":{"draws":1,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":39,"losses":80,"wins":13},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":3},"o3":{"draws":16,"losses":122,"wins":48},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":15},"poolside/laguna-s-2.1":{"draws":35,"losses":21,"wins":36},"qwen/qwen3.7-max":{"draws":1,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":35,"losses":60,"wins":21},"stepfun/step-3.7-flash":{"draws":6,"losses":23,"wins":19},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":27,"losses":41,"wins":38},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":24},"x-ai/grok-4.5":{"draws":30,"losses":79,"wins":21},"x-ai/grok-4.6":{"draws":12,"losses":13,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":3},"xiaomi/mimo-v2.5":{"draws":5,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":14,"losses":12,"wins":16},"z-ai/glm-5.3":{"draws":12,"losses":13,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":11},"claude-fable-5":{"draws":6,"losses":2,"wins":2},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":7,"losses":2,"wins":5},"claude-sonnet-5":{"draws":11,"losses":12,"wins":3},"deepseek/deepseek-v4-flash":{"draws":22,"losses":12,"wins":4},"deepseek/deepseek-v4-pro":{"draws":12,"losses":8,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":5},"google/gemini-3.5-flash":{"draws":12,"losses":10,"wins":4},"google/gemini-3.5-flash-lite":{"draws":34,"losses":27,"wins":13},"google/gemini-3.6-flash":{"draws":18,"losses":15,"wins":5},"google/gemini-3.8-flash":{"draws":7,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":6,"losses":5,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":12,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":9,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":7},"meta/muse-glimmer-30b":{"draws":11,"losses":3,"wins":6},"meta/muse-spark-1.2":{"draws":1,"losses":9,"wins":6},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":3},"o3":{"draws":9,"losses":20,"wins":5},"openai/gpt-oss-120b":{"draws":19,"losses":12,"wins":7},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":0},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":2},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":6,"losses":10,"wins":6},"stealth/ox-alpha":{"draws":27,"losses":27,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":11,"wins":3},"thinkingmachines/inkling":{"draws":13,"losses":4,"wins":9},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":3,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":7,"wins":7},"z-ai/glm-5.3":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":5,"wins":5}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":7},"claude-fable-5":{"draws":6,"losses":20,"wins":8},"claude-fable-5-1":{"draws":1,"losses":34,"wins":5},"claude-opus-4-5":{"draws":11,"losses":10,"wins":25},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":22,"losses":22,"wins":24},"deepseek/deepseek-v4-flash":{"draws":11,"losses":3,"wins":4},"deepseek/deepseek-v4-pro":{"draws":3,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":8,"wins":5},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":9},"google/gemini-3.5-flash-lite":{"draws":27,"losses":16,"wins":61},"google/gemini-3.6-flash":{"draws":14,"losses":27,"wins":65},"google/gemini-3.8-flash":{"draws":3,"losses":10,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":18,"losses":29,"wins":23},"gpt-5.6-luna":{"draws":23,"losses":9,"wins":36},"gpt-5.6-sol":{"draws":8,"losses":47,"wins":25},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":9},"gpt-6-astra":{"draws":4,"losses":31,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":14},"meta/muse-glimmer-30b":{"draws":1,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":8,"losses":6,"wins":20},"meta/muse-spark-1.3":{"draws":8,"losses":7,"wins":11},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":25},"o3":{"draws":3,"losses":24,"wins":23},"openai/gpt-oss-120b":{"draws":12,"losses":2,"wins":8},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":5},"stealth/ox-alpha":{"draws":26,"losses":38,"wins":21},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":12,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":2,"wins":22},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":14},"x-ai/grok-4.5":{"draws":11,"losses":23,"wins":14},"x-ai/grok-4.6":{"draws":5,"losses":18,"wins":11},"z-ai/glm-5.2":{"draws":2,"losses":9,"wins":11},"z-ai/glm-5.3":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.3-flash":{"draws":2,"losses":11,"wins":9}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":3,"wins":11},"claude-fable-5":{"draws":7,"losses":20,"wins":15},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-opus-4-5":{"draws":4,"losses":5,"wins":13},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":3,"losses":5,"wins":10},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":0,"losses":8,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":7,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":19},"google/gemini-3.5-flash-lite":{"draws":0,"losses":7,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":22,"wins":20},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":22},"gpt-5.4":{"draws":4,"losses":15,"wins":13},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":9},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":16},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":4},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":5},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":12},"meta/muse-spark-1.3":{"draws":2,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":16},"o3":{"draws":0,"losses":7,"wins":9},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":6},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-27b":{"draws":1,"losses":4,"wins":7},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":5},"qwen/qwen3.8-max":{"draws":3,"losses":11,"wins":18},"stealth/ox-alpha":{"draws":19,"losses":37,"wins":39},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":3,"losses":12,"wins":15},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling-small":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":10},"x-ai/grok-4.6":{"draws":5,"losses":18,"wins":13},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":23,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":15,"wins":10}},"minimax/minimax-m3":{"claude-opus-4-5":{"draws":5,"losses":13,"wins":2},"claude-opus-4-8":{"draws":10,"losses":8,"wins":2},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":3,"losses":13,"wins":6},"google/gemini-3.5-flash-lite":{"draws":6,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":5,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":4},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-5":{"draws":5,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":24,"wins":8},"gpt-5.5":{"draws":5,"losses":12,"wins":3},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":3},"o3":{"draws":4,"losses":7,"wins":1},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":17,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":7,"wins":1}},"moonshotai/kimi-k2.7-code":{"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":11},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":9}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":8,"wins":8},"claude-fable-5":{"draws":7,"losses":15,"wins":0},"claude-fable-5-1":{"draws":4,"losses":27,"wins":1},"claude-opus-4-5":{"draws":29,"losses":31,"wins":20},"claude-opus-4-8":{"draws":2,"losses":2,"wins":4},"claude-opus-5":{"draws":4,"losses":19,"wins":1},"claude-sonnet-5":{"draws":32,"losses":20,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":8,"wins":8},"deepseek/deepseek-v4-pro":{"draws":12,"losses":6,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":13,"losses":13,"wins":8},"google/gemini-3.5-flash-lite":{"draws":68,"losses":41,"wins":75},"google/gemini-3.6-flash":{"draws":56,"losses":73,"wins":45},"google/gemini-3.8-flash":{"draws":18,"losses":19,"wins":5},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4":{"draws":25,"losses":49,"wins":6},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":3},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":32,"losses":21,"wins":29},"gpt-5.6-sol":{"draws":14,"losses":47,"wins":15},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":10},"gpt-6-astra":{"draws":1,"losses":26,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":7,"losses":7,"wins":18},"meituan/longcat-2.0":{"draws":20,"losses":3,"wins":33},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":2},"meta/muse-spark-1.2":{"draws":16,"losses":19,"wins":21},"meta/muse-spark-1.3":{"draws":5,"losses":14,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":26,"losses":28,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":1},"o3":{"draws":16,"losses":53,"wins":41},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":4},"poolside/laguna-s-2.1":{"draws":25,"losses":1,"wins":24},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":14,"wins":10},"qwen/qwen3.8-27b":{"draws":5,"losses":5,"wins":6},"qwen/qwen3.8-flash":{"draws":9,"losses":1,"wins":10},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":7},"stealth/ox-alpha":{"draws":32,"losses":41,"wins":28},"stepfun/step-3.7-flash":{"draws":9,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":13,"losses":11,"wins":10},"thinkingmachines/inkling":{"draws":32,"losses":3,"wins":33},"thinkingmachines/inkling-small":{"draws":12,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":24,"losses":35,"wins":17},"x-ai/grok-4.6":{"draws":18,"losses":8,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":8,"wins":8},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":7,"wins":8}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-8":{"draws":3,"losses":9,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":12},"google/gemini-3.5-flash-lite":{"draws":1,"losses":6,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":7,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":0,"losses":11,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":2,"losses":14,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":9,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":12,"wins":4},"o3":{"draws":0,"losses":8,"wins":0},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":16,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":0}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":8,"losses":4,"wins":8},"claude-opus-4-8":{"draws":4,"losses":8,"wins":0},"claude-opus-5":{"draws":2,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":4,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":8},"gpt-5.5":{"draws":3,"losses":6,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":3,"losses":5,"wins":0},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":1}},"o3":{"claude-opus-4-5":{"draws":7,"losses":16,"wins":9},"claude-opus-4-8":{"draws":4,"losses":7,"wins":3},"claude-opus-5":{"draws":2,"losses":19,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":15},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":12},"gpt-5.5":{"draws":7,"losses":10,"wins":3},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":4,"losses":8,"wins":8}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":11},"claude-fable-5":{"draws":4,"losses":3,"wins":1},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":10,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":17,"losses":17,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":10},"deepseek/deepseek-v4-pro":{"draws":11,"losses":11,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":6,"wins":3},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":7},"google/gemini-3.5-flash-lite":{"draws":20,"losses":25,"wins":19},"google/gemini-3.6-flash":{"draws":14,"losses":8,"wins":8},"google/gemini-3.8-flash":{"draws":6,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":10,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":15,"losses":15,"wins":2},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":12,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":3},"meta/muse-glimmer-30b":{"draws":19,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":7,"wins":2},"o3":{"draws":6,"losses":20,"wins":8},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":5},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":11,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":21,"losses":37,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":7,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":6,"wins":8},"thinkingmachines/inkling-small":{"draws":20,"losses":9,"wins":15},"x-ai/grok-4.5":{"draws":7,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":7,"wins":10},"z-ai/glm-5.3":{"draws":6,"losses":2,"wins":2},"z-ai/glm-5.3-flash":{"draws":2,"losses":12,"wins":4}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":14,"wins":11},"claude-fable-5":{"draws":9,"losses":5,"wins":4},"claude-fable-5-1":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":43,"losses":54,"wins":3},"claude-opus-4-8":{"draws":8,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":31,"wins":3},"claude-sonnet-5":{"draws":40,"losses":55,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":0},"deepseek/deepseek-v4-flash":{"draws":26,"losses":13,"wins":7},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":20,"losses":10,"wins":8},"google/gemini-3.5-flash-lite":{"draws":145,"losses":76,"wins":87},"google/gemini-3.6-flash":{"draws":116,"losses":100,"wins":28},"google/gemini-3.8-flash":{"draws":6,"losses":10,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":37,"losses":41,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":6},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":46,"losses":37,"wins":25},"gpt-5.6-sol":{"draws":22,"losses":71,"wins":1},"gpt-5.6-terra":{"draws":18,"losses":14,"wins":2},"gpt-6-astra":{"draws":3,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":31,"losses":7,"wins":18},"meituan/longcat-2.0":{"draws":45,"losses":41,"wins":32},"meta/muse-glimmer-30b":{"draws":28,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":22,"losses":41,"wins":11},"meta/muse-spark-1.3":{"draws":13,"losses":7,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":53,"losses":61,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":0},"o3":{"draws":39,"losses":50,"wins":39},"openai/gpt-oss-120b":{"draws":33,"losses":11,"wins":10},"poolside/laguna-s-2.1":{"draws":40,"losses":21,"wins":17},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":0},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":16,"wins":4},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":4},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":4},"qwen/qwen3.8-max":{"draws":16,"losses":7,"wins":9},"stealth/ox-alpha":{"draws":39,"losses":33,"wins":14},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":7},"tencent/hy4-preview":{"draws":18,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":52,"losses":31,"wins":41},"thinkingmachines/inkling-small":{"draws":24,"losses":8,"wins":23},"x-ai/grok-4.5":{"draws":44,"losses":56,"wins":16},"x-ai/grok-4.6":{"draws":13,"losses":17,"wins":2},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":28,"losses":7,"wins":7},"z-ai/glm-5.3":{"draws":14,"losses":5,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":10,"wins":5}},"qwen/qwen3.7-max":{"claude-opus-4-5":{"draws":14,"losses":16,"wins":8},"claude-opus-4-8":{"draws":8,"losses":8,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":1,"losses":11,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":11},"gpt-5.5":{"draws":7,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":11,"losses":1,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":7},"o3":{"draws":7,"losses":2,"wins":5},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":8,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":11},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":6}},"qwen/qwen3.7-plus":{"claude-opus-4-5":{"draws":7,"losses":11,"wins":8},"claude-opus-4-8":{"draws":6,"losses":11,"wins":3},"claude-opus-5":{"draws":4,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":12},"claude-fable-5":{"draws":11,"losses":12,"wins":1},"claude-fable-5-1":{"draws":6,"losses":13,"wins":1},"claude-opus-4-5":{"draws":13,"losses":10,"wins":3},"claude-sonnet-5":{"draws":20,"losses":13,"wins":7},"deepseek/deepseek-v4-flash":{"draws":9,"losses":7,"wins":6},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":4},"google/gemini-3.5-flash":{"draws":9,"losses":12,"wins":7},"google/gemini-3.5-flash-lite":{"draws":19,"losses":10,"wins":25},"google/gemini-3.6-flash":{"draws":15,"losses":11,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":11,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":11,"losses":10,"wins":5},"gpt-5.6-luna":{"draws":16,"losses":6,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":17,"losses":10,"wins":11},"gpt-6-astra":{"draws":3,"losses":18,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":14},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":11},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":14},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":7},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":5},"o3":{"draws":7,"losses":15,"wins":12},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":13},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.8-27b":{"draws":7,"losses":5,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":4,"wins":7},"stealth/ox-alpha":{"draws":29,"losses":32,"wins":24},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":8,"wins":11},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":8,"wins":7},"z-ai/glm-5.2":{"draws":19,"losses":6,"wins":9},"z-ai/glm-5.3":{"draws":8,"losses":15,"wins":3},"z-ai/glm-5.3-flash":{"draws":8,"losses":10,"wins":4}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":9},"claude-fable-5":{"draws":2,"losses":4,"wins":2},"claude-fable-5-1":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":2,"losses":11,"wins":3},"claude-sonnet-5":{"draws":6,"losses":6,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":10,"wins":8},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":5,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":10,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":15,"wins":18},"google/gemini-3.6-flash":{"draws":8,"losses":16,"wins":2},"google/gemini-3.8-flash":{"draws":0,"losses":14,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":2},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":3},"meta/muse-glimmer-30b":{"draws":3,"losses":7,"wins":10},"meta/muse-spark-1.2":{"draws":3,"losses":6,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":7},"o3":{"draws":6,"losses":11,"wins":13},"openai/gpt-oss-120b":{"draws":0,"losses":11,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":9,"wins":8},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":8},"qwen/qwen3.8-max":{"draws":3,"losses":4,"wins":9},"stealth/ox-alpha":{"draws":12,"losses":31,"wins":16},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":0,"losses":12,"wins":0},"thinkingmachines/inkling":{"draws":6,"losses":4,"wins":6},"thinkingmachines/inkling-small":{"draws":5,"losses":7,"wins":16},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":5,"losses":8,"wins":7},"z-ai/glm-5.3":{"draws":1,"losses":5,"wins":2},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":2}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":8},"claude-fable-5":{"draws":10,"losses":14,"wins":8},"claude-fable-5-1":{"draws":0,"losses":39,"wins":1},"claude-opus-4-5":{"draws":3,"losses":3,"wins":4},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":6,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":10,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":8,"wins":12},"google/gemini-3.5-flash-lite":{"draws":16,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":17,"losses":17,"wins":12},"google/gemini-3.8-flash":{"draws":11,"losses":11,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":8,"losses":11,"wins":9},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":11},"gpt-5.6-sol":{"draws":11,"losses":18,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":7},"gpt-6-astra":{"draws":6,"losses":32,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":3,"wins":5},"meta/muse-glimmer-30b":{"draws":2,"losses":5,"wins":3},"meta/muse-spark-1.2":{"draws":8,"losses":6,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":13,"wins":12},"moonshotai/kimi-k3":{"draws":9,"losses":3,"wins":10},"o3":{"draws":9,"losses":5,"wins":12},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":0,"wins":3},"qwen/qwen3.8-max":{"draws":14,"losses":8,"wins":12},"stealth/ox-alpha":{"draws":24,"losses":27,"wins":36},"tencent/hy4-preview":{"draws":10,"losses":8,"wins":16},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":8},"thinkingmachines/inkling-small":{"draws":18,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3},"x-ai/grok-4.6":{"draws":12,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":2,"wins":8},"z-ai/glm-5.3":{"draws":5,"losses":21,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":19}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":6},"claude-fable-5":{"draws":2,"losses":14,"wins":6},"claude-fable-5-1":{"draws":4,"losses":26,"wins":0},"claude-opus-4-5":{"draws":4,"losses":6,"wins":15},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":7,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":9,"wins":9},"google/gemini-3.5-flash":{"draws":12,"losses":11,"wins":7},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":14},"google/gemini-3.6-flash":{"draws":19,"losses":14,"wins":12},"google/gemini-3.8-flash":{"draws":9,"losses":15,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":11,"losses":12,"wins":9},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":9},"gpt-6-astra":{"draws":6,"losses":23,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":4},"meta/muse-glimmer-30b":{"draws":5,"losses":5,"wins":8},"meta/muse-spark-1.2":{"draws":8,"losses":6,"wins":8},"meta/muse-spark-1.3":{"draws":8,"losses":16,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":10},"o3":{"draws":4,"losses":8,"wins":21},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.8-flash":{"draws":13,"losses":7,"wins":4},"qwen/qwen3.8-max":{"draws":18,"losses":11,"wins":22},"stealth/ox-alpha":{"draws":23,"losses":31,"wins":26},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy4-preview":{"draws":7,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":2,"losses":6,"wins":6},"thinkingmachines/inkling-small":{"draws":25,"losses":22,"wins":24},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":7},"x-ai/grok-4.6":{"draws":5,"losses":15,"wins":6},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":5},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":6,"wins":4}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":26,"wins":36},"claude-fable-5":{"draws":27,"losses":49,"wins":20},"claude-fable-5-1":{"draws":14,"losses":106,"wins":4},"claude-opus-4-5":{"draws":20,"losses":25,"wins":23},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":23,"losses":34,"wins":45},"deepseek/deepseek-v4-flash":{"draws":18,"losses":23,"wins":23},"deepseek/deepseek-v4-pro":{"draws":17,"losses":25,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":28,"wins":31},"google/gemini-3.5-flash":{"draws":26,"losses":27,"wins":29},"google/gemini-3.5-flash-lite":{"draws":30,"losses":31,"wins":66},"google/gemini-3.6-flash":{"draws":32,"losses":55,"wins":44},"google/gemini-3.8-flash":{"draws":27,"losses":47,"wins":36},"gpt-5.4":{"draws":30,"losses":33,"wins":25},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":28},"gpt-5.6-sol":{"draws":15,"losses":74,"wins":21},"gpt-5.6-terra":{"draws":28,"losses":24,"wins":34},"gpt-6-astra":{"draws":16,"losses":83,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":15,"losses":13,"wins":22},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":7},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":32},"meta/muse-spark-1.2":{"draws":18,"losses":29,"wins":39},"meta/muse-spark-1.3":{"draws":20,"losses":34,"wins":32},"moonshotai/kimi-k3":{"draws":27,"losses":43,"wins":38},"o3":{"draws":3,"losses":40,"wins":33},"openai/gpt-oss-120b":{"draws":11,"losses":17,"wins":36},"poolside/laguna-s-2.1":{"draws":15,"losses":8,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":35,"wins":32},"qwen/qwen3.8-27b":{"draws":7,"losses":21,"wins":16},"qwen/qwen3.8-flash":{"draws":17,"losses":17,"wins":22},"qwen/qwen3.8-max":{"draws":29,"losses":23,"wins":30},"stealth/ox-alpha":{"draws":101,"losses":210,"wins":159},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":23,"losses":41,"wins":24},"thinkingmachines/inkling":{"draws":7,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":22,"losses":25,"wins":32},"x-ai/grok-4.5":{"draws":11,"losses":30,"wins":15},"x-ai/grok-4.6":{"draws":21,"losses":42,"wins":31},"z-ai/glm-5.2":{"draws":16,"losses":16,"wins":34},"z-ai/glm-5.3":{"draws":26,"losses":42,"wins":18},"z-ai/glm-5.3-flash":{"draws":22,"losses":42,"wins":36}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":9,"losses":8,"wins":1},"claude-opus-4-8":{"draws":5,"losses":4,"wins":3},"claude-opus-5":{"draws":5,"losses":18,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":4,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":0},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":1},"o3":{"draws":2,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":1}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":9},"claude-fable-5":{"draws":3,"losses":18,"wins":11},"claude-fable-5-1":{"draws":0,"losses":24,"wins":4},"claude-opus-4-5":{"draws":4,"losses":1,"wins":13},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":6,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":7,"losses":9,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":9,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":15,"wins":12},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":15},"google/gemini-3.5-flash-lite":{"draws":10,"losses":15,"wins":17},"google/gemini-3.6-flash":{"draws":2,"losses":19,"wins":21},"google/gemini-3.8-flash":{"draws":2,"losses":9,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":13,"wins":13},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":16},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":12},"gpt-6-astra":{"draws":2,"losses":22,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":5,"losses":3,"wins":4},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":8},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":1,"wins":7},"meta/muse-spark-1.3":{"draws":3,"losses":9,"wins":14},"moonshotai/kimi-k3":{"draws":1,"losses":14,"wins":5},"o3":{"draws":2,"losses":3,"wins":17},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":12},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-flash":{"draws":2,"losses":6,"wins":8},"qwen/qwen3.8-max":{"draws":5,"losses":9,"wins":10},"stealth/ox-alpha":{"draws":19,"losses":26,"wins":33},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":8,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":7,"losses":5,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":8,"wins":12},"x-ai/grok-4.6":{"draws":5,"losses":11,"wins":10},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":21,"wins":5},"z-ai/glm-5.3-flash":{"draws":0,"losses":8,"wins":10}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":5},"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-fable-5-1":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":12,"losses":21,"wins":5},"claude-opus-4-8":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":2,"losses":10,"wins":2},"claude-sonnet-5":{"draws":21,"losses":23,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":8,"wins":11},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":56,"losses":51,"wins":25},"google/gemini-3.6-flash":{"draws":59,"losses":39,"wins":16},"google/gemini-3.8-flash":{"draws":5,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":11,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":5},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":23,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":4},"gpt-6-astra":{"draws":2,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":6,"losses":9,"wins":9},"meituan/longcat-2.0":{"draws":10,"losses":19,"wins":17},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":0},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":3,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":29,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":5,"wins":1},"o3":{"draws":22,"losses":28,"wins":11},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":1},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":11},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":5,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-flash":{"draws":10,"losses":4,"wins":4},"qwen/qwen3.8-max":{"draws":8,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":8,"losses":22,"wins":11},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":9,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":14},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":11,"losses":11,"wins":6},"x-ai/grok-4.6":{"draws":5,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":9,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":4,"wins":5},"z-ai/glm-5.3":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":3,"wins":4}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":8,"losses":8,"wins":4},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":6,"losses":11,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":9,"losses":18,"wins":5},"deepseek/deepseek-v4-flash":{"draws":14,"losses":13,"wins":7},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":7},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":5},"google/gemini-3.5-flash-lite":{"draws":24,"losses":33,"wins":14},"google/gemini-3.6-flash":{"draws":18,"losses":20,"wins":14},"google/gemini-3.8-flash":{"draws":9,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":20,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":14,"losses":11,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":10,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":12,"wins":8},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":9,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":9,"wins":5},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":1},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":11,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":6,"wins":5},"o3":{"draws":8,"losses":18,"wins":12},"openai/gpt-oss-120b":{"draws":16,"losses":15,"wins":3},"poolside/laguna-s-2.1":{"draws":7,"losses":10,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":14,"wins":2},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":28,"losses":36,"wins":13},"stealth/ox-alpha":{"draws":35,"losses":35,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":11,"wins":3},"thinkingmachines/inkling-small":{"draws":19,"losses":20,"wins":17},"x-ai/grok-4.5":{"draws":3,"losses":15,"wins":4},"x-ai/grok-4.6":{"draws":9,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":13,"losses":11,"wins":10},"z-ai/glm-5.3":{"draws":1,"losses":11,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":15,"wins":8}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":9,"losses":10,"wins":13},"claude-opus-4-8":{"draws":4,"losses":10,"wins":12},"claude-opus-5":{"draws":6,"losses":39,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":5,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":3,"wins":9},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":11},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":12},"gpt-5.5":{"draws":6,"losses":9,"wins":9},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":3,"losses":6,"wins":27},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":7},"o3":{"draws":2,"losses":5,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":5,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":4}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":13},"claude-fable-5":{"draws":7,"losses":17,"wins":18},"claude-fable-5-1":{"draws":4,"losses":41,"wins":9},"claude-opus-4-5":{"draws":7,"losses":3,"wins":12},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":3,"losses":7,"wins":10},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":5},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":12},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":20},"google/gemini-3.5-flash-lite":{"draws":4,"losses":3,"wins":15},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":24},"google/gemini-3.8-flash":{"draws":10,"losses":12,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":9,"losses":10,"wins":9},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":17,"wins":14},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":13},"gpt-6-astra":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":4},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":8},"meta/muse-spark-1.2":{"draws":3,"losses":2,"wins":13},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":14},"moonshotai/kimi-k3":{"draws":13,"losses":6,"wins":9},"o3":{"draws":2,"losses":0,"wins":16},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":7,"wins":13},"qwen/qwen3.8-27b":{"draws":2,"losses":1,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-max":{"draws":5,"losses":5,"wins":16},"stealth/ox-alpha":{"draws":14,"losses":25,"wins":59},"tencent/hy4-preview":{"draws":3,"losses":8,"wins":11},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":9},"x-ai/grok-4.6":{"draws":3,"losses":7,"wins":8},"z-ai/glm-5.2":{"draws":9,"losses":5,"wins":10},"z-ai/glm-5.3":{"draws":6,"losses":18,"wins":12},"z-ai/glm-5.3-flash":{"draws":8,"losses":10,"wins":10}},"x-ai/grok-build-0.1":{"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":6,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":9},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":31,"losses":25,"wins":12},"claude-opus-4-8":{"draws":18,"losses":19,"wins":5},"claude-opus-5":{"draws":2,"losses":17,"wins":1},"cohere/north-mini-code":{"draws":10,"losses":10,"wins":10},"deepseek/deepseek-v4-flash":{"draws":12,"losses":3,"wins":15},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":22},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":9},"gpt-4.1":{"draws":3,"losses":3,"wins":4},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4-mini":{"draws":19,"losses":20,"wins":5},"gpt-5.4-nano":{"draws":19,"losses":28,"wins":25},"gpt-5.5":{"draws":20,"losses":16,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":14},"minimax/minimax-m3":{"draws":19,"losses":11,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":17,"wins":9},"o3":{"draws":8,"losses":20,"wins":0},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":22},"x-ai/grok-4.5":{"draws":11,"losses":17,"wins":2},"x-ai/grok-build-0.1":{"draws":14,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":41,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":6,"losses":20,"wins":8}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":2,"losses":12,"wins":8},"claude-opus-4-8":{"draws":3,"losses":12,"wins":1},"claude-opus-5":{"draws":5,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":5},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":7},"gpt-4.1":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":13},"gpt-5.5":{"draws":1,"losses":8,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":6},"o3":{"draws":3,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":17},"z-ai/glm-5.2":{"draws":2,"losses":5,"wins":3}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":4,"wins":8},"claude-fable-5":{"draws":10,"losses":13,"wins":9},"claude-fable-5-1":{"draws":6,"losses":26,"wins":2},"claude-opus-4-5":{"draws":9,"losses":16,"wins":23},"claude-opus-4-8":{"draws":12,"losses":10,"wins":4},"claude-opus-5":{"draws":1,"losses":17,"wins":0},"claude-sonnet-5":{"draws":10,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":17,"losses":6,"wins":13},"deepseek/deepseek-v4-pro":{"draws":14,"losses":5,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":7},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":11,"losses":7,"wins":10},"google/gemini-3.5-flash-lite":{"draws":28,"losses":8,"wins":10},"google/gemini-3.6-flash":{"draws":15,"losses":20,"wins":15},"google/gemini-3.8-flash":{"draws":7,"losses":11,"wins":12},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":6,"wins":5},"gpt-5.4":{"draws":9,"losses":11,"wins":8},"gpt-5.4-mini":{"draws":12,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":4},"gpt-5.5":{"draws":10,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":3,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":10},"gpt-5.6-terra":{"draws":11,"losses":4,"wins":5},"gpt-6-astra":{"draws":4,"losses":23,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":7},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":6},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":5},"meta/muse-spark-1.3":{"draws":10,"losses":5,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":5,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":4},"o3":{"draws":9,"losses":14,"wins":9},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":17,"losses":5,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":8,"losses":9,"wins":9},"stealth/ox-alpha":{"draws":31,"losses":37,"wins":20},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":7},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":6},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":7},"x-ai/grok-4.5":{"draws":7,"losses":4,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":15,"wins":8},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":22,"losses":12,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":7},"z-ai/glm-5.3-flash":{"draws":14,"losses":12,"wins":8}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":6},"claude-fable-5":{"draws":6,"losses":13,"wins":21},"claude-fable-5-1":{"draws":4,"losses":36,"wins":14},"claude-opus-4-5":{"draws":3,"losses":4,"wins":9},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":2,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-pro":{"draws":1,"losses":7,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":15},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":17},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":28},"google/gemini-3.8-flash":{"draws":6,"losses":11,"wins":25},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":5,"losses":12,"wins":11},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":19,"wins":14},"gpt-5.6-terra":{"draws":10,"losses":2,"wins":10},"gpt-6-astra":{"draws":9,"losses":36,"wins":3},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"meta/muse-glimmer-30b":{"draws":1,"losses":2,"wins":7},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":12},"meta/muse-spark-1.3":{"draws":5,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":15},"o3":{"draws":2,"losses":4,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":3,"wins":13},"qwen/qwen3.8-max":{"draws":7,"losses":7,"wins":16},"stealth/ox-alpha":{"draws":15,"losses":33,"wins":47},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":1,"losses":9,"wins":18},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":9},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":8},"x-ai/grok-4.6":{"draws":5,"losses":14,"wins":17},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":6},"z-ai/glm-5.3":{"draws":5,"losses":9,"wins":10},"z-ai/glm-5.3-flash":{"draws":6,"losses":6,"wins":16}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":3,"wins":7},"claude-fable-5":{"draws":5,"losses":12,"wins":11},"claude-fable-5-1":{"draws":6,"losses":33,"wins":5},"claude-opus-4-5":{"draws":7,"losses":4,"wins":13},"claude-sonnet-5":{"draws":7,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-pro":{"draws":5,"losses":10,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":9,"losses":10,"wins":15},"google/gemini-3.5-flash-lite":{"draws":13,"losses":1,"wins":14},"google/gemini-3.6-flash":{"draws":12,"losses":11,"wins":15},"google/gemini-3.8-flash":{"draws":8,"losses":15,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":7,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":11,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":12,"wins":9},"gpt-6-astra":{"draws":7,"losses":25,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":5},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":5},"meta/muse-spark-1.2":{"draws":3,"losses":7,"wins":6},"meta/muse-spark-1.3":{"draws":8,"losses":8,"wins":14},"moonshotai/kimi-k3":{"draws":11,"losses":4,"wins":9},"o3":{"draws":6,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-27b":{"draws":2,"losses":7,"wins":9},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":9,"wins":7},"stealth/ox-alpha":{"draws":17,"losses":40,"wins":36},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":4,"losses":12,"wins":12},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":10},"thinkingmachines/inkling-small":{"draws":10,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.6":{"draws":8,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":11,"losses":6,"wins":13},"z-ai/glm-5.3":{"draws":7,"losses":18,"wins":7},"z-ai/glm-5.3-flash":{"draws":8,"losses":2,"wins":12}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":9,"wins":4},"claude-fable-5":{"draws":4,"losses":4,"wins":0},"claude-fable-5-1":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":5,"losses":4,"wins":1},"claude-sonnet-5":{"draws":6,"losses":15,"wins":3},"deepseek/deepseek-v4-flash":{"draws":10,"losses":12,"wins":4},"deepseek/deepseek-v4-pro":{"draws":9,"losses":14,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":3},"google/gemini-3.5-flash":{"draws":8,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":16,"losses":25,"wins":13},"google/gemini-3.6-flash":{"draws":13,"losses":15,"wins":4},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":7,"losses":3,"wins":6},"gpt-5.6-luna":{"draws":4,"losses":11,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":15,"wins":1},"gpt-6-astra":{"draws":0,"losses":7,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":10},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":4},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":5},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":3},"meta/muse-spark-1.3":{"draws":4,"losses":11,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":5},"o3":{"draws":9,"losses":19,"wins":6},"openai/gpt-oss-120b":{"draws":9,"losses":13,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":10,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":2},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":13,"losses":32,"wins":13},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":5,"losses":10,"wins":1},"thinkingmachines/inkling":{"draws":9,"losses":9,"wins":8},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":12},"x-ai/grok-4.5":{"draws":2,"losses":7,"wins":1},"x-ai/grok-4.6":{"draws":3,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":15,"losses":4,"wins":5},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":7,"wins":3}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":2,"wins":13},"claude-fable-5":{"draws":2,"losses":14,"wins":8},"claude-fable-5-1":{"draws":1,"losses":35,"wins":4},"claude-opus-4-5":{"draws":5,"losses":5,"wins":8},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":10,"losses":6,"wins":12},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":16},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":12,"losses":9,"wins":11},"google/gemini-3.5-flash-lite":{"draws":17,"losses":11,"wins":14},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":20},"google/gemini-3.8-flash":{"draws":7,"losses":15,"wins":14},"gpt-5.4":{"draws":13,"losses":13,"wins":14},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":17,"wins":10},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":16},"gpt-6-astra":{"draws":1,"losses":26,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":3},"meta/muse-glimmer-30b":{"draws":13,"losses":1,"wins":6},"meta/muse-spark-1.2":{"draws":8,"losses":6,"wins":10},"meta/muse-spark-1.3":{"draws":4,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":7},"o3":{"draws":2,"losses":4,"wins":20},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":4},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.8-max":{"draws":6,"losses":9,"wins":9},"stealth/ox-alpha":{"draws":29,"losses":29,"wins":42},"tencent/hy4-preview":{"draws":7,"losses":11,"wins":12},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":7},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":11},"x-ai/grok-4.6":{"draws":10,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":6},"z-ai/glm-5.3":{"draws":4,"losses":23,"wins":9},"z-ai/glm-5.3-flash":{"draws":3,"losses":16,"wins":1}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":12},"claude-fable-5":{"draws":0,"losses":12,"wins":30},"claude-fable-5-1":{"draws":3,"losses":27,"wins":8},"claude-opus-4-5":{"draws":1,"losses":0,"wins":15},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":2,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":22},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":33},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":30},"gpt-5.4":{"draws":2,"losses":8,"wins":20},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":8},"gpt-5.6-sol":{"draws":8,"losses":7,"wins":23},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":20},"gpt-6-astra":{"draws":7,"losses":33,"wins":8},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":6},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":1,"losses":0,"wins":23},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":25},"moonshotai/kimi-k3":{"draws":6,"losses":0,"wins":24},"o3":{"draws":0,"losses":3,"wins":15},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":2,"wins":19},"qwen/qwen3.8-27b":{"draws":2,"losses":1,"wins":11},"qwen/qwen3.8-flash":{"draws":3,"losses":1,"wins":12},"qwen/qwen3.8-max":{"draws":5,"losses":2,"wins":19},"stealth/ox-alpha":{"draws":18,"losses":6,"wins":70},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":18},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":1},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":0,"losses":3,"wins":17},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":27},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":14},"z-ai/glm-5.3":{"draws":2,"losses":14,"wins":18},"z-ai/glm-5.3-flash":{"draws":10,"losses":2,"wins":22}},"claude-opus-4-5":{"claude-opus-4-5":{"draws":13,"losses":4,"wins":9},"claude-opus-4-8":{"draws":3,"losses":12,"wins":9},"claude-opus-5":{"draws":10,"losses":38,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":10},"gpt-4.1":{"draws":5,"losses":5,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":12},"gpt-5.5":{"draws":10,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":8},"o3":{"draws":2,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":6,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":4,"losses":11,"wins":15}},"claude-opus-4-8":{"claude-opus-4-5":{"draws":8,"losses":6,"wins":14},"claude-opus-4-8":{"draws":4,"losses":1,"wins":3},"claude-opus-5":{"draws":4,"losses":19,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":9},"gpt-4.1":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":12},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":14},"gpt-5.5":{"draws":5,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":6},"o3":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":11,"losses":7,"wins":4}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":1},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":1,"losses":4,"wins":1},"claude-opus-4-5":{"draws":17,"losses":19,"wins":46},"claude-opus-4-8":{"draws":11,"losses":10,"wins":25},"claude-opus-5":{"draws":19,"losses":62,"wins":37},"claude-sonnet-5":{"draws":2,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":10},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":41},"google/gemini-3.6-flash":{"draws":11,"losses":14,"wins":41},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":16},"gpt-4.1":{"draws":7,"losses":1,"wins":15},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":1,"wins":18},"gpt-5.4":{"draws":0,"losses":0,"wins":10},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":32},"gpt-5.5":{"draws":14,"losses":10,"wins":36},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":12},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":4},"gpt-6-astra":{"draws":0,"losses":5,"wins":1},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":1,"wins":27},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":12},"o3":{"draws":2,"losses":3,"wins":25},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":22},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":4,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":7,"wins":13},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":11,"losses":8,"wins":35},"x-ai/grok-4.6":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":18},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":26},"z-ai/glm-5.3":{"draws":1,"losses":2,"wins":1}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":14,"wins":10},"claude-fable-5":{"draws":7,"losses":8,"wins":1},"claude-fable-5-1":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":19,"losses":28,"wins":7},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":12,"losses":25,"wins":11},"deepseek/deepseek-v4-flash":{"draws":6,"losses":9,"wins":9},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":7,"wins":10},"google/gemini-3.5-flash":{"draws":10,"losses":9,"wins":5},"google/gemini-3.5-flash-lite":{"draws":43,"losses":38,"wins":65},"google/gemini-3.6-flash":{"draws":31,"losses":48,"wins":35},"google/gemini-3.8-flash":{"draws":10,"losses":9,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":24,"losses":30,"wins":8},"gpt-5.6-luna":{"draws":26,"losses":23,"wins":27},"gpt-5.6-sol":{"draws":16,"losses":57,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":10,"wins":7},"gpt-6-astra":{"draws":1,"losses":12,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":20},"meta/muse-glimmer-30b":{"draws":7,"losses":7,"wins":12},"meta/muse-spark-1.2":{"draws":19,"losses":25,"wins":14},"meta/muse-spark-1.3":{"draws":10,"losses":9,"wins":3},"moonshotai/kimi-k3":{"draws":28,"losses":36,"wins":12},"o3":{"draws":5,"losses":33,"wins":36},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":16},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":13,"wins":8},"qwen/qwen3.8-27b":{"draws":3,"losses":2,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":14,"wins":6},"stealth/ox-alpha":{"draws":19,"losses":33,"wins":24},"stepfun/step-3.7-flash":{"draws":0,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":15,"losses":6,"wins":29},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":21},"x-ai/grok-4.5":{"draws":20,"losses":27,"wins":7},"x-ai/grok-4.6":{"draws":6,"losses":6,"wins":6},"z-ai/glm-5.2":{"draws":11,"losses":9,"wins":10},"z-ai/glm-5.3":{"draws":4,"losses":13,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":9,"wins":9}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":5,"losses":11,"wins":0},"claude-opus-4-8":{"draws":2,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":2},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":14,"wins":6},"gpt-5.5":{"draws":7,"losses":4,"wins":1},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":11,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":8,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":13,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":10,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":15,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":4,"wins":2}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":14},"claude-fable-5":{"draws":5,"losses":13,"wins":0},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":4,"losses":8,"wins":4},"claude-sonnet-5":{"draws":8,"losses":13,"wins":5},"deepseek/deepseek-v4-flash":{"draws":5,"losses":13,"wins":8},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":10,"wins":6},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":21,"wins":24},"google/gemini-3.6-flash":{"draws":11,"losses":27,"wins":8},"google/gemini-3.8-flash":{"draws":5,"losses":9,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":8,"losses":12,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":11,"wins":12},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":14},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":7},"meta/muse-glimmer-30b":{"draws":17,"losses":9,"wins":8},"meta/muse-spark-1.2":{"draws":3,"losses":3,"wins":2},"meta/muse-spark-1.3":{"draws":1,"losses":11,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":5},"o3":{"draws":5,"losses":16,"wins":15},"openai/gpt-oss-120b":{"draws":11,"losses":11,"wins":10},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":9,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":3},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":7,"losses":8,"wins":7},"stealth/ox-alpha":{"draws":22,"losses":23,"wins":21},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":6,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":7,"wins":9},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":17},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.6":{"draws":4,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":12,"wins":8},"z-ai/glm-5.3":{"draws":5,"losses":7,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":5,"wins":5}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":7,"wins":6},"claude-fable-5":{"draws":6,"losses":3,"wins":3},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":3,"losses":7,"wins":4},"claude-sonnet-5":{"draws":8,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":3,"wins":12},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":8,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":15,"wins":22},"google/gemini-3.6-flash":{"draws":18,"losses":10,"wins":6},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":6,"losses":3,"wins":7},"gpt-5.6-luna":{"draws":8,"losses":11,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":2,"wins":6},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":8},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":5},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":3},"o3":{"draws":7,"losses":8,"wins":11},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":5},"poolside/laguna-s-2.1":{"draws":11,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":5,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":6},"qwen/qwen3.8-max":{"draws":5,"losses":9,"wins":4},"stealth/ox-alpha":{"draws":18,"losses":17,"wins":17},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":7,"wins":3},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":8},"x-ai/grok-4.5":{"draws":5,"losses":4,"wins":5},"x-ai/grok-4.6":{"draws":7,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":5,"wins":6},"z-ai/glm-5.3":{"draws":6,"losses":7,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":7,"wins":3}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":7,"wins":3},"claude-fable-5":{"draws":5,"losses":5,"wins":2},"claude-fable-5-1":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":3,"losses":7,"wins":2},"claude-sonnet-5":{"draws":6,"losses":8,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":7,"wins":9},"deepseek/deepseek-v4-pro":{"draws":13,"losses":3,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":5,"losses":16,"wins":3},"google/gemini-3.5-flash-lite":{"draws":19,"losses":17,"wins":8},"google/gemini-3.6-flash":{"draws":9,"losses":13,"wins":6},"google/gemini-3.8-flash":{"draws":4,"losses":12,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":7,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":7,"wins":3},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":4},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":10},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":3,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":6},"o3":{"draws":8,"losses":7,"wins":13},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":3},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":11,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":3,"wins":3},"qwen/qwen3.8-flash":{"draws":7,"losses":3,"wins":4},"qwen/qwen3.8-max":{"draws":3,"losses":9,"wins":4},"stealth/ox-alpha":{"draws":23,"losses":21,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":11,"losses":4,"wins":5},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":1,"wins":5},"x-ai/grok-4.6":{"draws":6,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":10},"z-ai/glm-5.3":{"draws":1,"losses":10,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":3,"wins":6}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":6,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":6},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":7},"gpt-5.5":{"draws":4,"losses":3,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":10,"wins":2},"o3":{"draws":0,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":21,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":12,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":9,"wins":10},"claude-fable-5":{"draws":8,"losses":12,"wins":2},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":5,"losses":8,"wins":7},"claude-sonnet-5":{"draws":9,"losses":12,"wins":5},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":10,"losses":11,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":12,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":27,"losses":27,"wins":16},"google/gemini-3.6-flash":{"draws":19,"losses":15,"wins":6},"google/gemini-3.8-flash":{"draws":6,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":5,"losses":10,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":9,"wins":3},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":11},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":8},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":2},"meta/muse-spark-1.3":{"draws":8,"losses":9,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":2,"wins":5},"o3":{"draws":8,"losses":9,"wins":13},"openai/gpt-oss-120b":{"draws":13,"losses":13,"wins":6},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":16,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":3},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":11,"losses":5,"wins":10},"stealth/ox-alpha":{"draws":18,"losses":34,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":11,"losses":14,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":8},"thinkingmachines/inkling-small":{"draws":15,"losses":7,"wins":16},"x-ai/grok-4.5":{"draws":6,"losses":8,"wins":2},"x-ai/grok-4.6":{"draws":8,"losses":11,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":7,"wins":4},"z-ai/glm-5.3":{"draws":5,"losses":5,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":7,"wins":3}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":18,"wins":15},"claude-fable-5":{"draws":13,"losses":17,"wins":8},"claude-fable-5-1":{"draws":1,"losses":24,"wins":1},"claude-opus-4-5":{"draws":51,"losses":42,"wins":39},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":44,"wins":6},"claude-sonnet-5":{"draws":49,"losses":74,"wins":35},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":17},"deepseek/deepseek-v4-pro":{"draws":19,"losses":25,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":21,"wins":11},"google/gemini-3.5-flash":{"draws":19,"losses":13,"wins":14},"google/gemini-3.5-flash-lite":{"draws":120,"losses":99,"wins":95},"google/gemini-3.6-flash":{"draws":117,"losses":136,"wins":67},"google/gemini-3.8-flash":{"draws":15,"losses":26,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":5,"wins":5},"gpt-5.4":{"draws":44,"losses":70,"wins":16},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":14,"losses":7,"wins":9},"gpt-5.5":{"draws":11,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":57,"losses":49,"wins":50},"gpt-5.6-sol":{"draws":13,"losses":98,"wins":17},"gpt-5.6-terra":{"draws":16,"losses":16,"wins":18},"gpt-6-astra":{"draws":0,"losses":38,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":48,"losses":5,"wins":47},"meituan/longcat-2.0":{"draws":37,"losses":36,"wins":65},"meta/muse-glimmer-30b":{"draws":29,"losses":9,"wins":18},"meta/muse-spark-1.2":{"draws":32,"losses":39,"wins":23},"meta/muse-spark-1.3":{"draws":11,"losses":18,"wins":15},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":64,"losses":74,"wins":36},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":1},"o3":{"draws":34,"losses":66,"wins":80},"openai/gpt-oss-120b":{"draws":18,"losses":12,"wins":14},"poolside/laguna-s-2.1":{"draws":62,"losses":42,"wins":40},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":5},"qwen/qwen3.8-flash":{"draws":14,"losses":12,"wins":10},"qwen/qwen3.8-max":{"draws":20,"losses":18,"wins":16},"stealth/ox-alpha":{"draws":42,"losses":51,"wins":38},"stepfun/step-3.7-flash":{"draws":6,"losses":11,"wins":17},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":19,"losses":16,"wins":11},"thinkingmachines/inkling":{"draws":67,"losses":45,"wins":56},"thinkingmachines/inkling-small":{"draws":23,"losses":15,"wins":22},"x-ai/grok-4.5":{"draws":36,"losses":78,"wins":44},"x-ai/grok-4.6":{"draws":16,"losses":21,"wins":11},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":22,"losses":18,"wins":10},"z-ai/glm-5.3":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":18,"losses":11,"wins":11}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":22,"wins":25},"claude-fable-5":{"draws":14,"losses":12,"wins":6},"claude-fable-5-1":{"draws":3,"losses":35,"wins":0},"claude-opus-4-5":{"draws":54,"losses":54,"wins":36},"claude-opus-4-8":{"draws":7,"losses":2,"wins":3},"claude-opus-5":{"draws":3,"losses":41,"wins":8},"claude-sonnet-5":{"draws":54,"losses":67,"wins":39},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":30,"losses":21,"wins":21},"deepseek/deepseek-v4-pro":{"draws":22,"losses":20,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":17,"wins":14},"google/gemini-3.5-flash":{"draws":23,"losses":15,"wins":12},"google/gemini-3.5-flash-lite":{"draws":169,"losses":107,"wins":120},"google/gemini-3.6-flash":{"draws":77,"losses":132,"wins":51},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":9,"wins":0},"gpt-5.4":{"draws":49,"losses":60,"wins":29},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":7,"wins":5},"gpt-5.5":{"draws":12,"losses":4,"wins":8},"gpt-5.6-luna":{"draws":71,"losses":41,"wins":54},"gpt-5.6-sol":{"draws":23,"losses":105,"wins":14},"gpt-5.6-terra":{"draws":18,"losses":21,"wins":11},"gpt-6-astra":{"draws":5,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":24,"losses":5,"wins":27},"inclusionai/ling-3.0-flash":{"draws":61,"losses":29,"wins":40},"meituan/longcat-2.0":{"draws":45,"losses":36,"wins":67},"meta/muse-glimmer-30b":{"draws":33,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":25,"losses":66,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":71,"losses":88,"wins":21},"nex-agi/nex-n2-pro":{"draws":12,"losses":3,"wins":7},"o3":{"draws":45,"losses":114,"wins":53},"openai/gpt-oss-120b":{"draws":28,"losses":16,"wins":18},"poolside/laguna-s-2.1":{"draws":90,"losses":39,"wins":49},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":21,"losses":3,"wins":10},"qwen/qwen3.8-max":{"draws":24,"losses":25,"wins":15},"stealth/ox-alpha":{"draws":51,"losses":69,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":11,"wins":15},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":15,"losses":30,"wins":11},"thinkingmachines/inkling":{"draws":87,"losses":24,"wins":81},"thinkingmachines/inkling-small":{"draws":34,"losses":25,"wins":20},"x-ai/grok-4.5":{"draws":38,"losses":79,"wins":49},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":26,"losses":18,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":25,"wins":4},"z-ai/glm-5.3-flash":{"draws":21,"losses":16,"wins":11}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":9,"wins":8},"claude-fable-5":{"draws":7,"losses":21,"wins":6},"claude-fable-5-1":{"draws":4,"losses":37,"wins":1},"claude-opus-4-5":{"draws":6,"losses":7,"wins":11},"claude-opus-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":11,"losses":8,"wins":13},"deepseek/deepseek-v4-flash":{"draws":7,"losses":5,"wins":12},"deepseek/deepseek-v4-pro":{"draws":6,"losses":5,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":8,"wins":7},"google/gemini-3.5-flash":{"draws":3,"losses":19,"wins":10},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":16},"google/gemini-3.6-flash":{"draws":8,"losses":22,"wins":20},"google/gemini-3.8-flash":{"draws":9,"losses":8,"wins":7},"gpt-5.4":{"draws":7,"losses":15,"wins":12},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":17,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":13},"gpt-6-astra":{"draws":6,"losses":32,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":9},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":5},"meta/muse-glimmer-30b":{"draws":7,"losses":5,"wins":6},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":9},"meta/muse-spark-1.3":{"draws":0,"losses":12,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":9,"wins":11},"o3":{"draws":1,"losses":9,"wins":12},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":8,"wins":10},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":10},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.8-max":{"draws":10,"losses":10,"wins":8},"stealth/ox-alpha":{"draws":30,"losses":42,"wins":29},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":7,"losses":14,"wins":5},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":4},"thinkingmachines/inkling-small":{"draws":7,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":9,"wins":9},"z-ai/glm-5.3":{"draws":3,"losses":20,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":8}},"google/gemma-4-31b-it":{"claude-opus-4-5":{"draws":7,"losses":8,"wins":3},"claude-opus-4-8":{"draws":6,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":3,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":9,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":5},"o3":{"draws":4,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.7-max":{"draws":1,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":22,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":3}},"gpt-4.1":{"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":5,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":8}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":4},"claude-opus-4-5":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":5,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":3,"losses":11,"wins":14},"google/gemini-3.6-flash":{"draws":13,"losses":4,"wins":9},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":3},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":0},"o3":{"draws":0,"losses":6,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":1,"losses":4,"wins":1},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":12},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":2,"wins":1}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":3},"claude-fable-5":{"draws":6,"losses":16,"wins":10},"claude-fable-5-1":{"draws":3,"losses":21,"wins":2},"claude-opus-4-5":{"draws":15,"losses":17,"wins":20},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":27,"losses":14,"wins":27},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":7},"deepseek/deepseek-v4-pro":{"draws":12,"losses":7,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":16,"wins":9},"google/gemini-3.5-flash-lite":{"draws":50,"losses":25,"wins":55},"google/gemini-3.6-flash":{"draws":31,"losses":52,"wins":39},"google/gemini-3.8-flash":{"draws":11,"losses":13,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":18,"losses":56,"wins":2},"gpt-5.6-luna":{"draws":44,"losses":19,"wins":31},"gpt-5.6-sol":{"draws":16,"losses":35,"wins":17},"gpt-5.6-terra":{"draws":16,"losses":8,"wins":8},"gpt-6-astra":{"draws":0,"losses":21,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":12},"meta/muse-glimmer-30b":{"draws":9,"losses":9,"wins":4},"meta/muse-spark-1.2":{"draws":9,"losses":30,"wins":15},"meta/muse-spark-1.3":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":28,"losses":21,"wins":27},"o3":{"draws":10,"losses":26,"wins":36},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":24,"losses":0,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":3},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":7},"stealth/ox-alpha":{"draws":34,"losses":36,"wins":24},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":6},"thinkingmachines/inkling":{"draws":17,"losses":6,"wins":23},"thinkingmachines/inkling-small":{"draws":17,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":12},"z-ai/glm-5.3":{"draws":2,"losses":13,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":10,"wins":9}},"gpt-5.4-mini":{"claude-opus-4-5":{"draws":14,"losses":11,"wins":5},"claude-opus-4-8":{"draws":10,"losses":9,"wins":3},"claude-opus-5":{"draws":4,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":7,"losses":7,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":13},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":11,"losses":10,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":8,"wins":3},"gpt-4.1":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":3},"gpt-5.5":{"draws":9,"losses":4,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":4},"o3":{"draws":1,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":15,"losses":7,"wins":2}},"gpt-5.4-nano":{"claude-opus-4-5":{"draws":10,"losses":16,"wins":12},"claude-opus-4-8":{"draws":7,"losses":16,"wins":9},"claude-opus-5":{"draws":11,"losses":32,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":6,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":11},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":8},"google/gemini-3.6-flash":{"draws":16,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":9},"gpt-5.5":{"draws":9,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":14},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":12,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":16,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":12,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":3,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":31,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":4}},"gpt-5.5":{"claude-opus-4-5":{"draws":14,"losses":10,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":4},"claude-opus-5":{"draws":10,"losses":28,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":15,"losses":4,"wins":3},"google/gemini-3.6-flash":{"draws":12,"losses":11,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":5},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":2,"wins":9},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"inclusionai/ling-3.0-flash":{"draws":22,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":1},"o3":{"draws":7,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":19,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":8,"wins":7}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":7},"claude-fable-5":{"draws":7,"losses":1,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":14,"losses":24,"wins":4},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":22,"losses":44,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":3},"deepseek/deepseek-v4-pro":{"draws":9,"losses":13,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":11,"wins":3},"google/gemini-3.5-flash":{"draws":8,"losses":8,"wins":4},"google/gemini-3.5-flash-lite":{"draws":36,"losses":79,"wins":39},"google/gemini-3.6-flash":{"draws":38,"losses":69,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":27,"losses":45,"wins":6},"gpt-5.6-luna":{"draws":26,"losses":24,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":47,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":6},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":13,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":10,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":20,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":21,"wins":3},"meta/muse-spark-1.2":{"draws":17,"losses":30,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":10,"wins":3},"moonshotai/kimi-k3":{"draws":25,"losses":34,"wins":7},"o3":{"draws":6,"losses":56,"wins":16},"openai/gpt-oss-120b":{"draws":17,"losses":13,"wins":8},"poolside/laguna-s-2.1":{"draws":17,"losses":21,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":3,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":4},"stealth/ox-alpha":{"draws":28,"losses":35,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":12,"wins":2},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":4},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":16},"thinkingmachines/inkling-small":{"draws":15,"losses":22,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":28,"wins":4},"x-ai/grok-4.6":{"draws":5,"losses":5,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":16,"wins":1},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":7,"wins":5}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":15},"claude-fable-5":{"draws":5,"losses":19,"wins":8},"claude-fable-5-1":{"draws":2,"losses":31,"wins":3},"claude-opus-4-5":{"draws":12,"losses":12,"wins":32},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":31,"losses":15,"wins":46},"deepseek/deepseek-v4-flash":{"draws":5,"losses":8,"wins":15},"deepseek/deepseek-v4-pro":{"draws":5,"losses":10,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":11,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":15,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":16,"wins":77},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":58},"google/gemini-3.8-flash":{"draws":6,"losses":17,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":30,"losses":36,"wins":20},"gpt-5.6-luna":{"draws":23,"losses":16,"wins":33},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":18},"gpt-5.6-terra":{"draws":15,"losses":10,"wins":12},"gpt-6-astra":{"draws":1,"losses":25,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":13},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":31},"meta/muse-glimmer-30b":{"draws":3,"losses":4,"wins":9},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":30},"meta/muse-spark-1.3":{"draws":2,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":19,"losses":18,"wins":35},"o3":{"draws":0,"losses":16,"wins":56},"openai/gpt-oss-120b":{"draws":11,"losses":0,"wins":15},"poolside/laguna-s-2.1":{"draws":17,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":11},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":10},"qwen/qwen3.8-flash":{"draws":9,"losses":2,"wins":9},"qwen/qwen3.8-max":{"draws":6,"losses":7,"wins":10},"stealth/ox-alpha":{"draws":16,"losses":39,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":11},"thinkingmachines/inkling":{"draws":10,"losses":6,"wins":30},"thinkingmachines/inkling-small":{"draws":9,"losses":2,"wins":16},"x-ai/grok-4.5":{"draws":10,"losses":32,"wins":18},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":12},"z-ai/glm-5.2":{"draws":4,"losses":10,"wins":10},"z-ai/glm-5.3":{"draws":5,"losses":22,"wins":11},"z-ai/glm-5.3-flash":{"draws":5,"losses":12,"wins":7}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":7,"wins":17},"claude-fable-5":{"draws":8,"losses":15,"wins":1},"claude-fable-5-1":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":6,"losses":12,"wins":0},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":16,"losses":9,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":10},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":14,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":20,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":14,"losses":6,"wins":12},"google/gemini-3.8-flash":{"draws":12,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":10,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":5},"gpt-6-astra":{"draws":2,"losses":12,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":8},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":4},"meta/muse-glimmer-30b":{"draws":12,"losses":2,"wins":14},"meta/muse-spark-1.2":{"draws":9,"losses":3,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":7},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":3},"o3":{"draws":4,"losses":15,"wins":9},"openai/gpt-oss-120b":{"draws":17,"losses":1,"wins":14},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":9,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":3,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"losses":0,"wins":3},"qwen/qwen3.8-max":{"draws":14,"losses":3,"wins":9},"stealth/ox-alpha":{"draws":30,"losses":24,"wins":16},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":8,"losses":7,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":7},"thinkingmachines/inkling-small":{"draws":8,"losses":8,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":9,"wins":2},"x-ai/grok-4.6":{"draws":11,"losses":13,"wins":4},"z-ai/glm-5.2":{"draws":15,"losses":4,"wins":9},"z-ai/glm-5.3":{"draws":6,"losses":8,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":4}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":4,"wins":7},"claude-fable-5":{"draws":3,"losses":11,"wins":28},"claude-fable-5-1":{"draws":6,"losses":24,"wins":24},"claude-opus-4-5":{"draws":2,"losses":2,"wins":14},"claude-opus-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":1,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":8},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":8,"losses":0,"wins":20},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":19},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":27},"google/gemini-3.8-flash":{"draws":5,"losses":5,"wins":30},"gpt-5.4":{"draws":4,"losses":6,"wins":16},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":4,"wins":31},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":18},"gpt-6-astra":{"draws":4,"losses":15,"wins":13},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":5},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":17},"meta/muse-spark-1.3":{"draws":6,"losses":6,"wins":18},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":24},"o3":{"draws":1,"losses":0,"wins":21},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":22},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":14},"qwen/qwen3.8-flash":{"draws":6,"losses":0,"wins":8},"qwen/qwen3.8-max":{"draws":6,"losses":2,"wins":20},"stealth/ox-alpha":{"draws":20,"losses":10,"wins":64},"tencent/hy4-preview":{"draws":7,"losses":3,"wins":18},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":5},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":11},"x-ai/grok-4.6":{"draws":4,"losses":7,"wins":27},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":12},"z-ai/glm-5.3":{"draws":6,"losses":5,"wins":23},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":21}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":9},"claude-fable-5":{"draws":7,"losses":3,"wins":2},"claude-fable-5-1":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":3,"losses":2,"wins":3},"claude-sonnet-5":{"draws":4,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":8,"wins":2},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":2},"google/gemini-3.5-flash":{"draws":6,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":14,"losses":9,"wins":17},"google/gemini-3.6-flash":{"draws":7,"losses":11,"wins":8},"google/gemini-3.8-flash":{"draws":4,"losses":5,"wins":1},"gpt-5.4":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":9,"losses":7,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":3},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":5,"wins":4},"meta/muse-spark-1.3":{"draws":3,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":3},"o3":{"draws":2,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":9,"wins":1},"qwen/qwen3.8-27b":{"draws":1,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":2},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":4},"stealth/ox-alpha":{"draws":17,"losses":18,"wins":14},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":6,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":4},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":4,"wins":2},"x-ai/grok-4.6":{"draws":8,"losses":4,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":5,"wins":3},"z-ai/glm-5.3":{"draws":6,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":6,"wins":4}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":14,"losses":6,"wins":2},"claude-opus-4-8":{"draws":14,"losses":4,"wins":0},"claude-opus-5":{"draws":8,"losses":17,"wins":1},"cohere/north-mini-code":{"draws":16,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":11,"wins":7},"google/gemini-3.5-flash-lite":{"draws":33,"losses":15,"wins":4},"google/gemini-3.6-flash":{"draws":47,"losses":20,"wins":9},"google/gemma-4-31b-it":{"draws":12,"losses":17,"wins":3},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":8},"gpt-5.4-mini":{"draws":18,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":14,"wins":7},"gpt-5.5":{"draws":26,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":11},"meituan/longcat-2.0":{"draws":35,"losses":22,"wins":13},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":5},"o3":{"draws":5,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":39,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":17,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":16},"x-ai/grok-4.5":{"draws":10,"losses":24,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":2,"wins":4}},"meituan/longcat-2.0":{"claude-opus-4-5":{"draws":16,"losses":12,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":7,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":18,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":8,"losses":10,"wins":8},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":17},"google/gemini-3.5-flash-lite":{"draws":20,"losses":27,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":25,"wins":17},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":7,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":16,"losses":22,"wins":16},"gpt-5.5":{"draws":13,"losses":4,"wins":9},"inclusionai/ling-3.0-flash":{"draws":33,"losses":19,"wins":24},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":11,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":11,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":14,"wins":6},"o3":{"draws":7,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":12},"qwen/qwen3.7-max":{"draws":17,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":11,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":27,"wins":17},"x-ai/grok-4.5":{"draws":14,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":24,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":17,"wins":9}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":11,"wins":2},"claude-fable-5":{"draws":6,"losses":7,"wins":3},"claude-fable-5-1":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":3,"losses":9,"wins":0},"claude-sonnet-5":{"draws":4,"losses":14,"wins":2},"deepseek/deepseek-v4-flash":{"draws":12,"losses":10,"wins":6},"deepseek/deepseek-v4-pro":{"draws":9,"losses":6,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":6,"wins":5},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":16,"losses":20,"wins":14},"google/gemini-3.6-flash":{"draws":14,"losses":13,"wins":1},"google/gemini-3.8-flash":{"draws":5,"losses":2,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":6,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":11,"losses":7,"wins":10},"gpt-5.6-sol":{"draws":0,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":8,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":4},"meta/muse-glimmer-30b":{"draws":10,"losses":8,"wins":2},"meta/muse-spark-1.2":{"draws":3,"losses":7,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":3,"wins":3},"o3":{"draws":7,"losses":11,"wins":6},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":9,"wins":2},"qwen/qwen3.8-27b":{"draws":8,"losses":5,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":5},"qwen/qwen3.8-max":{"draws":4,"losses":7,"wins":5},"stealth/ox-alpha":{"draws":18,"losses":26,"wins":12},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":12,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":7},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":11},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.6":{"draws":6,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":14,"losses":4,"wins":4},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":3},"z-ai/glm-5.3-flash":{"draws":10,"losses":7,"wins":1}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":6,"losses":11,"wins":5},"claude-fable-5-1":{"draws":4,"losses":30,"wins":0},"claude-opus-4-5":{"draws":13,"losses":16,"wins":17},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":23,"losses":33,"wins":24},"deepseek/deepseek-v4-flash":{"draws":5,"losses":10,"wins":7},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":12,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":42,"losses":35,"wins":51},"google/gemini-3.6-flash":{"draws":26,"losses":63,"wins":37},"google/gemini-3.8-flash":{"draws":5,"losses":12,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":15,"losses":36,"wins":23},"gpt-5.6-luna":{"draws":19,"losses":28,"wins":31},"gpt-5.6-sol":{"draws":11,"losses":57,"wins":10},"gpt-5.6-terra":{"draws":9,"losses":10,"wins":13},"gpt-6-astra":{"draws":1,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":17},"inclusionai/ling-3.0-flash":{"draws":9,"losses":6,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":19,"wins":16},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":9},"meta/muse-spark-1.2":{"draws":6,"losses":21,"wins":5},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":33,"wins":21},"o3":{"draws":4,"losses":47,"wins":29},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":15},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":14,"wins":6},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":9},"stealth/ox-alpha":{"draws":24,"losses":51,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":3,"losses":16,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":6,"wins":24},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":12},"x-ai/grok-4.5":{"draws":12,"losses":32,"wins":8},"x-ai/grok-4.6":{"draws":6,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":7,"losses":7,"wins":8},"z-ai/glm-5.3":{"draws":2,"losses":12,"wins":2},"z-ai/glm-5.3-flash":{"draws":6,"losses":11,"wins":7}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":6,"wins":15},"claude-fable-5":{"draws":4,"losses":6,"wins":2},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":7,"losses":10,"wins":5},"claude-sonnet-5":{"draws":12,"losses":7,"wins":11},"deepseek/deepseek-v4-flash":{"draws":6,"losses":11,"wins":11},"deepseek/deepseek-v4-pro":{"draws":9,"losses":9,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":5},"google/gemini-3.5-flash-lite":{"draws":27,"losses":19,"wins":30},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":13,"losses":8,"wins":5},"gpt-5.6-luna":{"draws":16,"losses":10,"wins":12},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":10},"gpt-6-astra":{"draws":2,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":1,"wins":9},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":9},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":5},"o3":{"draws":6,"losses":15,"wins":7},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":14},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":8,"wins":9},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-max":{"draws":15,"losses":4,"wins":11},"stealth/ox-alpha":{"draws":33,"losses":34,"wins":22},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":12,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":7,"losses":5,"wins":12},"thinkingmachines/inkling-small":{"draws":18,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":5},"x-ai/grok-4.6":{"draws":8,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":5,"wins":11},"z-ai/glm-5.3":{"draws":3,"losses":8,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":10,"wins":6}},"minimax/minimax-m3":{"claude-opus-4-5":{"draws":6,"losses":15,"wins":5},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":3,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":8},"gpt-4.1":{"draws":0,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":10},"gpt-5.5":{"draws":4,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":9,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":6},"o3":{"draws":1,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":9,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":5}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":8,"wins":15},"claude-fable-5":{"draws":0,"losses":14,"wins":8},"claude-fable-5-1":{"draws":1,"losses":33,"wins":2},"claude-opus-4-5":{"draws":28,"losses":21,"wins":37},"claude-opus-4-8":{"draws":4,"losses":3,"wins":7},"claude-opus-5":{"draws":6,"losses":23,"wins":13},"claude-sonnet-5":{"draws":28,"losses":18,"wins":42},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":10},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":7,"wins":6},"google/gemini-3.5-flash":{"draws":13,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":55,"losses":35,"wins":78},"google/gemini-3.6-flash":{"draws":48,"losses":67,"wins":63},"google/gemini-3.8-flash":{"draws":5,"losses":10,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":8},"gpt-4.1":{"draws":1,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":10,"losses":44,"wins":26},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":16},"gpt-5.5":{"draws":5,"losses":3,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":16,"wins":40},"gpt-5.6-sol":{"draws":13,"losses":51,"wins":20},"gpt-5.6-terra":{"draws":10,"losses":11,"wins":13},"gpt-6-astra":{"draws":5,"losses":22,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":22,"losses":5,"wins":15},"meituan/longcat-2.0":{"draws":24,"losses":15,"wins":37},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":17,"wins":27},"meta/muse-spark-1.3":{"draws":5,"losses":13,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":34,"losses":20,"wins":16},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"o3":{"draws":12,"losses":45,"wins":35},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":29,"losses":7,"wins":34},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":11,"wins":16},"qwen/qwen3.8-27b":{"draws":0,"losses":7,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":8,"losses":13,"wins":14},"stealth/ox-alpha":{"draws":26,"losses":38,"wins":34},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":9,"wins":12},"thinkingmachines/inkling":{"draws":26,"losses":15,"wins":41},"thinkingmachines/inkling-small":{"draws":12,"losses":10,"wins":11},"x-ai/grok-4.5":{"draws":31,"losses":32,"wins":35},"x-ai/grok-4.6":{"draws":4,"losses":17,"wins":9},"xiaomi/mimo-v2.5":{"draws":8,"losses":8,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":14,"losses":3,"wins":9},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":9},"z-ai/glm-5.3-flash":{"draws":10,"losses":12,"wins":2}},"nex-agi/nex-n2-pro":{"claude-opus-4-5":{"draws":7,"losses":9,"wins":6},"claude-opus-4-8":{"draws":11,"losses":12,"wins":3},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":12,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":15,"losses":8,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":8},"gpt-5.5":{"draws":8,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":5},"o3":{"draws":2,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":13,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":3,"wins":3}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":2,"losses":7,"wins":3},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":5},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":5,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":3},"gpt-5.5":{"draws":12,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":3,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":12,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":4},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":8,"losses":17,"wins":7},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":6,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":10,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":6,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":2},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":29,"losses":63,"wins":18},"google/gemini-3.6-flash":{"draws":32,"losses":42,"wins":18},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":0},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":0},"gpt-5.4":{"draws":6,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":1},"gpt-5.5":{"draws":4,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":8,"losses":22,"wins":12},"gpt-5.6-sol":{"draws":0,"losses":30,"wins":4},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":12,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":18},"meta/muse-glimmer-30b":{"draws":10,"losses":8,"wins":2},"meta/muse-spark-1.2":{"draws":0,"losses":19,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":23,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"o3":{"draws":13,"losses":38,"wins":13},"openai/gpt-oss-120b":{"draws":4,"losses":8,"wins":6},"poolside/laguna-s-2.1":{"draws":20,"losses":15,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":7,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"losses":4,"wins":3},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":1},"stealth/ox-alpha":{"draws":7,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":22,"losses":11,"wins":13},"thinkingmachines/inkling-small":{"draws":12,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":23,"wins":2},"x-ai/grok-4.6":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":8,"losses":7,"wins":3},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":3,"wins":2}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":10,"wins":8},"claude-fable-5":{"draws":1,"losses":1,"wins":2},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":5,"losses":11,"wins":0},"claude-sonnet-5":{"draws":6,"losses":12,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":10},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":7},"google/gemini-3.5-flash":{"draws":8,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":17,"losses":17,"wins":16},"google/gemini-3.6-flash":{"draws":16,"losses":8,"wins":6},"google/gemini-3.8-flash":{"draws":2,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":7,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":10,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":1},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":11},"meta/muse-spark-1.2":{"draws":6,"losses":8,"wins":0},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":3},"o3":{"draws":6,"losses":9,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":7,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.8-max":{"draws":3,"losses":6,"wins":3},"stealth/ox-alpha":{"draws":20,"losses":25,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":7,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":8},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":16},"x-ai/grok-4.5":{"draws":5,"losses":3,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":12,"losses":6,"wins":6},"z-ai/glm-5.3":{"draws":6,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":5,"wins":2}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":0},"claude-fable-5":{"draws":1,"losses":0,"wins":3},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":18,"losses":12,"wins":6},"claude-opus-4-8":{"draws":4,"losses":18,"wins":4},"claude-opus-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":3,"losses":5,"wins":0},"cohere/north-mini-code":{"draws":17,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":12},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":20,"wins":26},"google/gemini-3.6-flash":{"draws":23,"losses":28,"wins":25},"google/gemini-3.8-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":8},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":4,"wins":9},"gpt-5.4":{"draws":10,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":16,"losses":10,"wins":14},"gpt-5.5":{"draws":13,"losses":9,"wins":12},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":21},"meituan/longcat-2.0":{"draws":23,"losses":7,"wins":14},"meta/muse-glimmer-30b":{"draws":2,"losses":2,"wins":2},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":4},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":9},"o3":{"draws":7,"losses":11,"wins":6},"poolside/laguna-s-2.1":{"draws":22,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":1},"stealth/ox-alpha":{"draws":7,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":15,"losses":14,"wins":21},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":11,"losses":36,"wins":13},"x-ai/grok-4.6":{"draws":2,"losses":0,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":19,"losses":10,"wins":15},"z-ai/glm-5.3":{"draws":1,"losses":0,"wins":1}},"qwen/qwen3.7-max":{"claude-opus-4-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-8":{"draws":4,"losses":9,"wins":5},"claude-opus-5":{"draws":7,"losses":30,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":4,"wins":9},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":11},"gpt-5.5":{"draws":10,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":3},"o3":{"draws":3,"losses":4,"wins":1},"poolside/laguna-s-2.1":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":13,"losses":11,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":3}},"qwen/qwen3.7-plus":{"claude-opus-4-5":{"draws":16,"losses":7,"wins":3},"claude-opus-4-8":{"draws":6,"losses":9,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":8},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":7},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":10,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":9,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":8},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":6,"wins":6},"o3":{"draws":1,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":23,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":8},"claude-fable-5":{"draws":4,"losses":13,"wins":5},"claude-fable-5-1":{"draws":1,"losses":19,"wins":0},"claude-opus-4-5":{"draws":6,"losses":6,"wins":8},"claude-opus-5":{"draws":0,"losses":1,"wins":1},"claude-sonnet-5":{"draws":8,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":10,"losses":6,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":10,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":12},"google/gemini-3.5-flash-lite":{"draws":24,"losses":14,"wins":18},"google/gemini-3.6-flash":{"draws":12,"losses":20,"wins":12},"google/gemini-3.8-flash":{"draws":1,"losses":16,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":4,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":8,"losses":12,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":8,"wins":14},"gpt-6-astra":{"draws":3,"losses":19,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":7},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":6},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":11},"meta/muse-spark-1.3":{"draws":9,"losses":10,"wins":11},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":14},"o3":{"draws":5,"losses":9,"wins":12},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":8,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":6},"stealth/ox-alpha":{"draws":13,"losses":33,"wins":29},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":4,"losses":11,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":5,"wins":9},"thinkingmachines/inkling-small":{"draws":12,"losses":3,"wins":17},"x-ai/grok-4.5":{"draws":2,"losses":7,"wins":5},"x-ai/grok-4.6":{"draws":5,"losses":10,"wins":7},"z-ai/glm-5.2":{"draws":8,"losses":5,"wins":5},"z-ai/glm-5.3":{"draws":8,"losses":9,"wins":3},"z-ai/glm-5.3-flash":{"draws":3,"losses":5,"wins":4}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":0,"wins":0},"claude-fable-5":{"draws":3,"losses":0,"wins":1},"claude-fable-5-1":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":4,"losses":0,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":5,"losses":3,"wins":0},"gpt-5.4":{"draws":8,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":5,"wins":0},"stealth/ox-alpha":{"draws":11,"losses":3,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":0,"wins":1},"x-ai/grok-4.6":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":6,"losses":1,"wins":1},"z-ai/glm-5.3":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":4,"wins":1}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":9},"claude-fable-5":{"draws":9,"losses":9,"wins":0},"claude-fable-5-1":{"draws":4,"losses":10,"wins":0},"claude-opus-4-5":{"draws":6,"losses":7,"wins":3},"claude-sonnet-5":{"draws":12,"losses":14,"wins":2},"deepseek/deepseek-v4-flash":{"draws":10,"losses":11,"wins":11},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":11,"wins":4},"google/gemini-3.5-flash":{"draws":10,"losses":15,"wins":3},"google/gemini-3.5-flash-lite":{"draws":26,"losses":16,"wins":22},"google/gemini-3.6-flash":{"draws":26,"losses":17,"wins":1},"google/gemini-3.8-flash":{"draws":5,"losses":14,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":9,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":17,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":13,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":7,"wins":5},"gpt-6-astra":{"draws":3,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":6,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":4},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":8},"meta/muse-spark-1.2":{"draws":9,"losses":8,"wins":3},"meta/muse-spark-1.3":{"draws":9,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":3},"o3":{"draws":8,"losses":16,"wins":8},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":11},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":15,"wins":4},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":0},"qwen/qwen3.8-flash":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.8-max":{"draws":16,"losses":8,"wins":4},"stealth/ox-alpha":{"draws":26,"losses":33,"wins":17},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":7,"wins":7},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":14,"losses":9,"wins":3},"z-ai/glm-5.3":{"draws":7,"losses":12,"wins":3},"z-ai/glm-5.3-flash":{"draws":15,"losses":6,"wins":1}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":3},"claude-fable-5":{"draws":6,"losses":5,"wins":15},"claude-fable-5-1":{"draws":0,"losses":17,"wins":3},"claude-opus-4-5":{"draws":7,"losses":5,"wins":4},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":9,"losses":14,"wins":6},"deepseek/deepseek-v4-flash":{"draws":20,"losses":6,"wins":6},"deepseek/deepseek-v4-pro":{"draws":10,"losses":6,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":7,"wins":7},"google/gemini-3.5-flash":{"draws":11,"losses":3,"wins":8},"google/gemini-3.5-flash-lite":{"draws":28,"losses":17,"wins":12},"google/gemini-3.6-flash":{"draws":19,"losses":18,"wins":15},"google/gemini-3.8-flash":{"draws":6,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":13,"losses":9,"wins":12},"gpt-5.6-luna":{"draws":16,"losses":7,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":8,"wins":7},"gpt-6-astra":{"draws":0,"losses":17,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":9,"losses":4,"wins":6},"meta/muse-glimmer-30b":{"draws":9,"losses":8,"wins":7},"meta/muse-spark-1.2":{"draws":6,"losses":4,"wins":10},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":8},"o3":{"draws":9,"losses":10,"wins":9},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":9,"losses":6,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":9,"wins":5},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":3,"wins":5},"qwen/qwen3.8-max":{"draws":18,"losses":22,"wins":8},"stealth/ox-alpha":{"draws":29,"losses":29,"wins":20},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":9,"wins":8},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":3},"thinkingmachines/inkling-small":{"draws":30,"losses":22,"wins":22},"x-ai/grok-4.5":{"draws":12,"losses":10,"wins":8},"x-ai/grok-4.6":{"draws":9,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":14,"losses":4,"wins":12},"z-ai/glm-5.3":{"draws":4,"losses":12,"wins":6},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":5}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":17,"wins":24},"claude-fable-5":{"draws":34,"losses":33,"wins":17},"claude-fable-5-1":{"draws":5,"losses":50,"wins":1},"claude-opus-4-5":{"draws":31,"losses":24,"wins":15},"claude-sonnet-5":{"draws":36,"losses":30,"wins":30},"deepseek/deepseek-v4-flash":{"draws":60,"losses":27,"wins":21},"deepseek/deepseek-v4-pro":{"draws":43,"losses":25,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":36,"wins":25},"google/gemini-3.5-flash":{"draws":34,"losses":28,"wins":24},"google/gemini-3.5-flash-lite":{"draws":77,"losses":56,"wins":47},"google/gemini-3.6-flash":{"draws":53,"losses":46,"wins":41},"google/gemini-3.8-flash":{"draws":30,"losses":33,"wins":15},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":54,"losses":37,"wins":13},"gpt-5.6-luna":{"draws":55,"losses":34,"wins":29},"gpt-5.6-sol":{"draws":12,"losses":35,"wins":15},"gpt-5.6-terra":{"draws":39,"losses":30,"wins":19},"gpt-6-astra":{"draws":4,"losses":42,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":15,"losses":1,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":9,"wins":22},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":9},"meituan/longcat-2.0":{"draws":19,"losses":6,"wins":20},"meta/muse-glimmer-30b":{"draws":55,"losses":21,"wins":30},"meta/muse-spark-1.2":{"draws":25,"losses":21,"wins":20},"meta/muse-spark-1.3":{"draws":30,"losses":29,"wins":19},"moonshotai/kimi-k3":{"draws":29,"losses":18,"wins":27},"o3":{"draws":25,"losses":38,"wins":25},"openai/gpt-oss-120b":{"draws":47,"losses":18,"wins":33},"poolside/laguna-s-2.1":{"draws":27,"losses":9,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":29,"wins":25},"qwen/qwen3.8-27b":{"draws":21,"losses":20,"wins":17},"qwen/qwen3.8-flash":{"draws":22,"losses":18,"wins":10},"qwen/qwen3.8-max":{"draws":33,"losses":26,"wins":21},"stealth/ox-alpha":{"draws":136,"losses":224,"wins":128},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":6},"tencent/hy4-preview":{"draws":41,"losses":27,"wins":18},"thinkingmachines/inkling":{"draws":28,"losses":11,"wins":27},"thinkingmachines/inkling-small":{"draws":63,"losses":18,"wins":37},"x-ai/grok-4.5":{"draws":27,"losses":20,"wins":21},"x-ai/grok-4.6":{"draws":43,"losses":25,"wins":16},"z-ai/glm-5.2":{"draws":51,"losses":20,"wins":35},"z-ai/glm-5.3":{"draws":24,"losses":23,"wins":11},"z-ai/glm-5.3-flash":{"draws":36,"losses":25,"wins":21}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":4,"wins":12},"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":6,"losses":29,"wins":13},"claude-opus-4-8":{"draws":0,"losses":7,"wins":1},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":6,"losses":17,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":8,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":22,"losses":39,"wins":45},"google/gemini-3.6-flash":{"draws":12,"losses":47,"wins":13},"google/gemini-3.8-flash":{"draws":2,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":6,"losses":24,"wins":4},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":4},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":18},"gpt-5.6-sol":{"draws":1,"losses":22,"wins":7},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":20,"wins":22},"meta/muse-glimmer-30b":{"draws":6,"losses":8,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":17,"wins":5},"meta/muse-spark-1.3":{"draws":3,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":27,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":0},"o3":{"draws":14,"losses":49,"wins":23},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":8},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":17},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.8-max":{"draws":1,"losses":8,"wins":3},"stealth/ox-alpha":{"draws":5,"losses":13,"wins":12},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":3,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":16,"wins":18},"thinkingmachines/inkling-small":{"draws":4,"losses":5,"wins":11},"x-ai/grok-4.5":{"draws":3,"losses":20,"wins":9},"x-ai/grok-4.6":{"draws":1,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":4,"wins":4}},"tencent/hy3-preview":{"claude-opus-4-5":{"draws":6,"losses":7,"wins":3},"claude-opus-4-8":{"draws":8,"losses":7,"wins":3},"claude-opus-5":{"draws":8,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":10},"gpt-5.5":{"draws":12,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":5,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":3}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":4,"wins":18},"claude-fable-5":{"draws":4,"losses":10,"wins":0},"claude-fable-5-1":{"draws":1,"losses":11,"wins":0},"claude-opus-4-5":{"draws":9,"losses":11,"wins":4},"claude-sonnet-5":{"draws":13,"losses":11,"wins":12},"deepseek/deepseek-v4-flash":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-pro":{"draws":16,"losses":9,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":7,"wins":7},"google/gemini-3.5-flash":{"draws":10,"losses":6,"wins":12},"google/gemini-3.5-flash-lite":{"draws":27,"losses":13,"wins":24},"google/gemini-3.6-flash":{"draws":20,"losses":9,"wins":17},"google/gemini-3.8-flash":{"draws":8,"losses":11,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":12,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":11},"gpt-5.6-sol":{"draws":3,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":8},"gpt-6-astra":{"draws":2,"losses":10,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":14},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":8},"meta/muse-spark-1.3":{"draws":11,"losses":6,"wins":7},"moonshotai/kimi-k3":{"draws":20,"losses":9,"wins":5},"o3":{"draws":7,"losses":15,"wins":10},"openai/gpt-oss-120b":{"draws":10,"losses":8,"wins":12},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":7,"wins":7},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":8},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":11,"losses":8,"wins":13},"stealth/ox-alpha":{"draws":26,"losses":32,"wins":20},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":5,"losses":3,"wins":4},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":8},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":14},"x-ai/grok-4.5":{"draws":6,"losses":8,"wins":2},"x-ai/grok-4.6":{"draws":5,"losses":5,"wins":6},"z-ai/glm-5.2":{"draws":10,"losses":7,"wins":11},"z-ai/glm-5.3":{"draws":4,"losses":13,"wins":3},"z-ai/glm-5.3-flash":{"draws":10,"losses":8,"wins":6}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":20,"losses":22,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":6,"losses":29,"wins":7},"cohere/north-mini-code":{"draws":7,"losses":10,"wins":11},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":11},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":13},"google/gemini-3.5-flash-lite":{"draws":13,"losses":17,"wins":10},"google/gemini-3.6-flash":{"draws":25,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":8,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":12},"gpt-5.5":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":26},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":11},"o3":{"draws":5,"losses":5,"wins":6},"poolside/laguna-s-2.1":{"draws":16,"losses":21,"wins":17},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":14,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":33,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":9,"losses":14,"wins":9}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":6},"claude-fable-5":{"draws":3,"losses":6,"wins":3},"claude-fable-5-1":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":7,"losses":7,"wins":0},"claude-sonnet-5":{"draws":11,"losses":21,"wins":4},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":1},"deepseek/deepseek-v4-pro":{"draws":18,"losses":8,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":10,"wins":6},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":25,"losses":23,"wins":14},"google/gemini-3.6-flash":{"draws":16,"losses":15,"wins":12},"google/gemini-3.8-flash":{"draws":6,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":17,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":13,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":2},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":4,"losses":10,"wins":3},"meta/muse-glimmer-30b":{"draws":18,"losses":12,"wins":6},"meta/muse-spark-1.2":{"draws":4,"losses":9,"wins":5},"meta/muse-spark-1.3":{"draws":10,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":3},"o3":{"draws":12,"losses":14,"wins":9},"openai/gpt-oss-120b":{"draws":19,"losses":13,"wins":8},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":15,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":12,"wins":0},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":29,"losses":24,"wins":18},"stealth/ox-alpha":{"draws":31,"losses":27,"wins":11},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":9,"wins":3},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":3},"thinkingmachines/inkling-small":{"draws":25,"losses":23,"wins":12},"x-ai/grok-4.5":{"draws":10,"losses":7,"wins":2},"x-ai/grok-4.6":{"draws":9,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":14,"losses":9,"wins":7},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":7,"wins":5}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":10},"claude-fable-5":{"draws":6,"losses":18,"wins":8},"claude-fable-5-1":{"draws":0,"losses":27,"wins":3},"claude-opus-4-5":{"draws":29,"losses":29,"wins":32},"claude-opus-4-8":{"draws":5,"losses":2,"wins":5},"claude-opus-5":{"draws":5,"losses":18,"wins":7},"claude-sonnet-5":{"draws":38,"losses":12,"wins":30},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":7,"wins":7},"deepseek/deepseek-v4-pro":{"draws":6,"losses":15,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":12,"wins":5},"google/gemini-3.5-flash":{"draws":11,"losses":11,"wins":6},"google/gemini-3.5-flash-lite":{"draws":73,"losses":27,"wins":84},"google/gemini-3.6-flash":{"draws":45,"losses":79,"wins":48},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":16,"losses":39,"wins":15},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":11},"gpt-5.5":{"draws":5,"losses":0,"wins":5},"gpt-5.6-luna":{"draws":28,"losses":28,"wins":24},"gpt-5.6-sol":{"draws":10,"losses":50,"wins":22},"gpt-5.6-terra":{"draws":9,"losses":13,"wins":12},"gpt-6-astra":{"draws":1,"losses":20,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":8},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":21},"meituan/longcat-2.0":{"draws":20,"losses":17,"wins":35},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":9},"meta/muse-spark-1.2":{"draws":18,"losses":16,"wins":22},"meta/muse-spark-1.3":{"draws":4,"losses":15,"wins":5},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":41,"losses":32,"wins":21},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"o3":{"draws":7,"losses":41,"wins":46},"openai/gpt-oss-120b":{"draws":15,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":28,"losses":16,"wins":30},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-27b":{"draws":1,"losses":8,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":1,"wins":7},"qwen/qwen3.8-max":{"draws":17,"losses":12,"wins":13},"stealth/ox-alpha":{"draws":21,"losses":32,"wins":33},"stepfun/step-3.7-flash":{"draws":3,"losses":6,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":8},"thinkingmachines/inkling":{"draws":24,"losses":9,"wins":35},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":14},"x-ai/grok-4.5":{"draws":14,"losses":25,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":12,"wins":5},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":12,"losses":3,"wins":9},"z-ai/glm-5.3":{"draws":8,"losses":19,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":11,"wins":6}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":4,"wins":9},"claude-fable-5":{"draws":9,"losses":14,"wins":5},"claude-fable-5-1":{"draws":0,"losses":21,"wins":1},"claude-opus-4-5":{"draws":7,"losses":2,"wins":9},"claude-sonnet-5":{"draws":11,"losses":16,"wins":9},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":6},"deepseek/deepseek-v4-pro":{"draws":12,"losses":5,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":3},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":6},"google/gemini-3.5-flash-lite":{"draws":30,"losses":13,"wins":15},"google/gemini-3.6-flash":{"draws":16,"losses":16,"wins":8},"google/gemini-3.8-flash":{"draws":8,"losses":8,"wins":4},"gpt-5.4":{"draws":12,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":6,"wins":8},"gpt-5.6-sol":{"draws":5,"losses":14,"wins":7},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":11},"gpt-6-astra":{"draws":0,"losses":20,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":5,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":10,"losses":5,"wins":1},"meta/muse-glimmer-30b":{"draws":16,"losses":2,"wins":4},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":12},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":6,"wins":10},"o3":{"draws":8,"losses":15,"wins":9},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":4},"poolside/laguna-s-2.1":{"draws":14,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":10,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":14,"losses":11,"wins":3},"stealth/ox-alpha":{"draws":32,"losses":34,"wins":12},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":8,"losses":2,"wins":0},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":9,"wins":5},"x-ai/grok-4.6":{"draws":7,"losses":8,"wins":1},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":17,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":13,"wins":7}},"xiaomi/mimo-v2.5":{"claude-opus-4-5":{"draws":19,"losses":25,"wins":18},"claude-opus-4-8":{"draws":13,"losses":25,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":14},"deepseek/deepseek-v4-flash":{"draws":9,"losses":10,"wins":19},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":19},"google/gemini-3.5-flash-lite":{"draws":3,"losses":8,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":15,"wins":17},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":19},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":30},"gpt-5.5":{"draws":16,"losses":15,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":15,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":12},"o3":{"draws":3,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":9,"wins":18},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":29,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":13,"losses":21,"wins":14}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":5,"losses":9,"wins":10},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":3,"losses":26,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":10,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":11},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":1,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":15,"wins":13},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":7}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":12,"wins":7},"claude-fable-5":{"draws":8,"losses":5,"wins":3},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":23,"losses":38,"wins":23},"claude-opus-4-8":{"draws":11,"losses":15,"wins":12},"claude-opus-5":{"draws":12,"losses":43,"wins":9},"claude-sonnet-5":{"draws":16,"losses":12,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":19,"losses":11,"wins":28},"deepseek/deepseek-v4-pro":{"draws":12,"losses":10,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":16},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":9},"google/gemini-3.5-flash-lite":{"draws":23,"losses":25,"wins":22},"google/gemini-3.6-flash":{"draws":27,"losses":13,"wins":14},"google/gemini-3.8-flash":{"draws":7,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":0},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":9,"losses":13,"wins":12},"gpt-5.4":{"draws":11,"losses":8,"wins":3},"gpt-5.4-mini":{"draws":18,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":15},"gpt-5.5":{"draws":12,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":14},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":5},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":15},"inclusionai/ling-3.0-flash":{"draws":14,"losses":7,"wins":3},"meituan/longcat-2.0":{"draws":19,"losses":13,"wins":20},"meta/muse-glimmer-30b":{"draws":18,"losses":3,"wins":7},"meta/muse-spark-1.2":{"draws":1,"losses":8,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":7},"o3":{"draws":9,"losses":22,"wins":15},"openai/gpt-oss-120b":{"draws":10,"losses":14,"wins":6},"poolside/laguna-s-2.1":{"draws":22,"losses":16,"wins":8},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":7,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-flash":{"draws":12,"losses":4,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":5,"wins":7},"stealth/ox-alpha":{"draws":23,"losses":33,"wins":12},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":10,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":15,"losses":12,"wins":17},"thinkingmachines/inkling-small":{"draws":17,"losses":14,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":15,"wins":6},"x-ai/grok-4.6":{"draws":10,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":6},"z-ai/glm-5.2":{"draws":22,"losses":22,"wins":22},"z-ai/glm-5.3":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":12,"wins":1}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":7,"wins":4},"claude-fable-5":{"draws":4,"losses":21,"wins":11},"claude-fable-5-1":{"draws":0,"losses":18,"wins":2},"claude-opus-4-5":{"draws":7,"losses":5,"wins":6},"claude-sonnet-5":{"draws":9,"losses":6,"wins":13},"deepseek/deepseek-v4-flash":{"draws":15,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":12,"losses":8,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":5},"google/gemini-3.5-flash":{"draws":10,"losses":13,"wins":5},"google/gemini-3.5-flash-lite":{"draws":20,"losses":10,"wins":10},"google/gemini-3.6-flash":{"draws":12,"losses":20,"wins":12},"google/gemini-3.8-flash":{"draws":6,"losses":8,"wins":8},"gpt-5.4":{"draws":7,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":7},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":12},"gpt-6-astra":{"draws":0,"losses":15,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":4},"meta/muse-glimmer-30b":{"draws":5,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":3},"meta/muse-spark-1.3":{"draws":3,"losses":11,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":6,"wins":7},"o3":{"draws":4,"losses":13,"wins":9},"openai/gpt-oss-120b":{"draws":17,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":4,"wins":9},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-max":{"draws":6,"losses":9,"wins":3},"stealth/ox-alpha":{"draws":29,"losses":29,"wins":18},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":0},"tencent/hy4-preview":{"draws":10,"losses":4,"wins":18},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":1},"thinkingmachines/inkling-small":{"draws":12,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":12},"x-ai/grok-4.6":{"draws":7,"losses":13,"wins":6},"z-ai/glm-5.2":{"draws":11,"losses":7,"wins":12},"z-ai/glm-5.3":{"draws":1,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":10,"wins":9}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":14},"claude-fable-5":{"draws":4,"losses":9,"wins":5},"claude-fable-5-1":{"draws":2,"losses":20,"wins":2},"claude-opus-4-5":{"draws":2,"losses":10,"wins":6},"claude-sonnet-5":{"draws":11,"losses":11,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":5,"wins":3},"deepseek/deepseek-v4-pro":{"draws":11,"losses":7,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":10,"wins":11},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":5},"google/gemini-3.5-flash-lite":{"draws":22,"losses":20,"wins":14},"google/gemini-3.6-flash":{"draws":17,"losses":8,"wins":11},"google/gemini-3.8-flash":{"draws":7,"losses":10,"wins":9},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5.4":{"draws":6,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":7},"gpt-6-astra":{"draws":5,"losses":11,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":11},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":3,"wins":10},"meta/muse-glimmer-30b":{"draws":13,"losses":6,"wins":9},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":6},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":3,"wins":9},"o3":{"draws":6,"losses":9,"wins":11},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":9},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.8-max":{"draws":10,"losses":9,"wins":7},"stealth/ox-alpha":{"draws":32,"losses":38,"wins":22},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":11,"losses":9,"wins":6},"thinkingmachines/inkling":{"draws":9,"losses":6,"wins":5},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":6},"x-ai/grok-4.6":{"draws":6,"losses":5,"wins":9},"z-ai/glm-5.2":{"draws":15,"losses":2,"wins":13},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":4}}}}}