{"benchmark_line":"gamebench2","economics_chart":{"eligible_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"enabled":true},"game_order":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"games":[{"alias":"GB2-01","name":"Go","slug":"go"},{"alias":"GB2-02","name":"Chess","slug":"chess"},{"alias":"GB2-03","name":"Shogi","slug":"shogi"},{"alias":"GB2-04","name":"Xiangqi","slug":"xiangqi"},{"alias":"GB2-05","name":"Hex","slug":"hex"},{"alias":"GB2-06","name":"International Draughts","slug":"international-draughts"},{"alias":"GB2-07","name":"Game of the Amazons","slug":"game-of-the-amazons"},{"alias":"GB2-08","name":"Tumbleweed","slug":"tumbleweed"}],"generated_at":"2026-10-06T16:58:22Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:0835f9147f2986b4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.427439999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.27234},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.9134900000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.2723400000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.427439999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":0.6505529166666667,"median":0.40659249999999997,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":24},"run_count":24,"token_priced_attempt_count":24,"total":15.613270000000002},"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":79.39650648138176,"highest":93.11456867236295,"medium":76.5656656847458,"none":68.50928508703656},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:11:00Z","match_totals_all":{"draws":816,"losses":676,"wins":7864},"match_totals_tracks":{"highest":{"draws":90,"losses":130,"wins":2890},"medium":{"draws":286,"losses":227,"wins":2601},"none":{"draws":440,"losses":319,"wins":2373}},"model_slug":"gpt-6-astra","overall":{"max":100.0,"mean":79.39650648138178,"min":38.60476864555238},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":96.56137654691018,"GB2-02":100.0,"GB2-03":99.99999999999999,"GB2-04":95.07514409691512,"GB2-05":100.0,"GB2-06":84.11141385014908,"GB2-07":100.0,"GB2-08":69.1686148849292},"per_game_all":{"GB2-01":80.09548580974835,"GB2-02":63.52072668111452,"GB2-03":73.43649174164017,"GB2-04":80.56069194203947,"GB2-05":90.94702488005107,"GB2-06":81.65042589526274,"GB2-07":95.04700624339436,"GB2-08":69.91419865780351},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":110,"wins":948},"GB2-02":{"draws":360,"losses":48,"wins":826},"GB2-03":{"draws":228,"losses":48,"wins":826},"GB2-04":{"draws":107,"losses":71,"wins":902},"GB2-05":{"draws":0,"losses":40,"wins":1066},"GB2-06":{"draws":85,"losses":127,"wins":982},"GB2-07":{"draws":0,"losses":35,"wins":1169},"GB2-08":{"draws":0,"losses":197,"wins":1145}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":9,"wins":343},"GB2-02":{"draws":21,"losses":5,"wins":380},"GB2-03":{"draws":13,"losses":3,"wins":356},"GB2-04":{"draws":27,"losses":9,"wins":316},"GB2-05":{"draws":0,"losses":0,"wins":382},"GB2-06":{"draws":29,"losses":30,"wins":333},"GB2-07":{"draws":0,"losses":6,"wins":396},"GB2-08":{"draws":0,"losses":68,"wins":384}},"medium":{"GB2-01":{"draws":24,"losses":81,"wins":265},"GB2-02":{"draws":135,"losses":17,"wins":254},"GB2-03":{"draws":69,"losses":11,"wins":280},"GB2-04":{"draws":34,"losses":18,"wins":306},"GB2-05":{"draws":0,"losses":24,"wins":338},"GB2-06":{"draws":24,"losses":36,"wins":348},"GB2-07":{"draws":0,"losses":12,"wins":392},"GB2-08":{"draws":0,"losses":28,"wins":418}},"none":{"GB2-01":{"draws":12,"losses":20,"wins":340},"GB2-02":{"draws":204,"losses":26,"wins":192},"GB2-03":{"draws":146,"losses":34,"wins":190},"GB2-04":{"draws":46,"losses":44,"wins":280},"GB2-05":{"draws":0,"losses":16,"wins":346},"GB2-06":{"draws":32,"losses":61,"wins":301},"GB2-07":{"draws":0,"losses":17,"wins":381},"GB2-08":{"draws":0,"losses":101,"wins":343}}},"per_game_raw_elo_all":{"GB2-01":2088.8944522231054,"GB2-02":1866.3999911863111,"GB2-03":1985.264240713949,"GB2-04":1951.2407784325915,"GB2-05":2426.17562639732,"GB2-06":2126.2189922574107,"GB2-07":2423.539868472558,"GB2-08":2062.44624040042},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2353.027997950955,"GB2-02":2163.043726492965,"GB2-03":2298.8151673216544,"GB2-04":2062.863964895922,"GB2-05":2612.2889134205,"GB2-06":2177.6727911016533,"GB2-07":2519.0304840991257,"GB2-08":2051.1715553117538},"medium":{"GB2-01":1789.4213353910577,"GB2-02":1772.3689229633117,"GB2-03":1948.8078302982176,"GB2-04":1982.5182919813442,"GB2-05":2292.9711850575277,"GB2-06":2169.4304294915764,"GB2-07":2395.590578152841,"GB2-08":2251.006631260958},"none":{"GB2-01":2124.2340233273035,"GB2-02":1663.7873241026562,"GB2-03":1708.1697245219743,"GB2-04":1808.3400784205078,"GB2-05":2373.2667807139323,"GB2-06":2031.553756179002,"GB2-07":2355.998543165707,"GB2-08":1885.1605346285476}},"per_game_tracks":{"highest":{"GB2-01":96.56137654691018,"GB2-02":100.0,"GB2-03":99.99999999999999,"GB2-04":95.07514409691512,"GB2-05":100.0,"GB2-06":84.11141385014908,"GB2-07":100.0,"GB2-08":69.1686148849292},"medium":{"GB2-01":61.426552233418136,"GB2-02":51.95741139779117,"GB2-03":70.34796583732977,"GB2-04":84.62773202851814,"GB2-05":84.4676567886926,"GB2-06":83.71718926230825,"GB2-07":93.59730713373021,"GB2-08":82.38351079617817},"none":{"GB2-01":82.2985286489167,"GB2-02":38.60476864555238,"GB2-03":49.96150938759075,"GB2-04":61.97919970068515,"GB2-05":88.37341785146064,"GB2-06":77.12267457333088,"GB2-07":91.54371159645285,"GB2-08":58.190470292303154}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":93.11456867236295,"medium":76.5656656847458,"none":68.50928508703656},"reasoning_agg":{"highest":{"max":100.0,"mean":93.11456867236295,"min":69.1686148849292},"medium":{"max":93.59730713373021,"mean":76.5656656847458,"min":51.95741139779117},"none":{"max":91.54371159645285,"mean":68.50928508703656,"min":38.60476864555238}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":87.8102662983203,"reasoning_variance":24.60528358532639,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.413759816938523},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":92.38653997780992,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7280286945530321},"medium":{"ceiling_score":93.59730713373021,"expected_score":82.71209230772001,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.146426622974218},"none":{"ceiling_score":91.54371159645285,"expected_score":88.33216660943097,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":19.82288152239441}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:42ee50f4f60be049","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677192},"medium":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.0063079999999998},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.0527920000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.0063079999999998},"historical-provider-setting-baseline":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.052792},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677191999999998}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292000000006},"codegen_output_tokens":{"attempt_count":30,"output_max":149830,"output_mean":37334.40740740741,"output_min":2400,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":149830,"output_mean":94967.22222222222,"output_min":65515,"run_count":9},"medium":{"attempt_count":10,"output_max":31033,"output_mean":13777.666666666666,"output_min":6104,"run_count":9},"none":{"attempt_count":9,"output_max":3890,"output_mean":3258.3333333333335,"output_min":2400,"run_count":9}},"display_name":"Claude Opus 5.5","economics":{"all":77.6206569634728,"highest":90.7279024953924,"medium":82.86703716268381,"none":59.267031232342106},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[65536,128000],"finish_reason_observations":30,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[65536,128000],"total_output_tokens":1008029,"total_reasoning_output_tokens":820640,"total_visible_output_tokens":187389,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.1111111111111111},"baseline":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":9,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_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,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-10-06T16:11:02Z","match_totals_all":{"draws":478,"losses":579,"wins":5377},"match_totals_tracks":{"highest":{"draws":48,"losses":78,"wins":1770},"medium":{"draws":73,"losses":132,"wins":2149},"none":{"draws":357,"losses":369,"wins":1458}},"model_slug":"claude-opus-5-5","overall":{"max":100.0,"mean":77.62065696347277,"min":29.074139099563844},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":65.06595728586343,"GB2-02":95.10941676820096,"GB2-03":98.64709912670227,"GB2-04":94.93025166624834,"GB2-05":93.6635173163565,"GB2-06":100.0,"GB2-07":95.48879922050352,"GB2-08":82.91817857926416},"per_game_all":{"GB2-01":72.4416203078744,"GB2-02":79.0776921586728,"GB2-03":68.35388235667745,"GB2-04":70.94790892226652,"GB2-05":84.81423770158209,"GB2-06":85.81479225932132,"GB2-07":87.63603861243622,"GB2-08":71.87908338895144},"per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":67,"wins":525},"GB2-02":{"draws":90,"losses":42,"wins":682},"GB2-03":{"draws":156,"losses":57,"wins":395},"GB2-04":{"draws":158,"losses":49,"wins":609},"GB2-05":{"draws":0,"losses":50,"wins":618},"GB2-06":{"draws":34,"losses":59,"wins":655},"GB2-07":{"draws":0,"losses":42,"wins":684},"GB2-08":{"draws":14,"losses":213,"wins":1209}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":41,"wins":158},"GB2-02":{"draws":17,"losses":4,"wins":249},"GB2-03":{"draws":3,"losses":3,"wins":196},"GB2-04":{"draws":22,"losses":5,"wins":191},"GB2-05":{"draws":0,"losses":4,"wins":212},"GB2-06":{"draws":1,"losses":0,"wins":251},"GB2-07":{"draws":0,"losses":5,"wins":239},"GB2-08":{"draws":0,"losses":16,"wins":274}},"medium":{"GB2-01":{"draws":13,"losses":7,"wins":186},"GB2-02":{"draws":9,"losses":11,"wins":250},"GB2-03":{"draws":12,"losses":15,"wins":173},"GB2-04":{"draws":27,"losses":24,"wins":333},"GB2-05":{"draws":0,"losses":25,"wins":203},"GB2-06":{"draws":12,"losses":17,"wins":229},"GB2-07":{"draws":0,"losses":16,"wins":224},"GB2-08":{"draws":0,"losses":17,"wins":551}},"none":{"GB2-01":{"draws":8,"losses":19,"wins":181},"GB2-02":{"draws":64,"losses":27,"wins":183},"GB2-03":{"draws":141,"losses":39,"wins":26},"GB2-04":{"draws":109,"losses":20,"wins":85},"GB2-05":{"draws":0,"losses":21,"wins":203},"GB2-06":{"draws":21,"losses":42,"wins":175},"GB2-07":{"draws":0,"losses":21,"wins":221},"GB2-08":{"draws":14,"losses":180,"wins":384}}},"per_game_raw_elo_all":{"GB2-01":1966.1168469416982,"GB2-02":1992.906797091088,"GB2-03":1925.2700235819348,"GB2-04":1877.3138082653286,"GB2-05":2300.096280626963,"GB2-06":2213.2866549757746,"GB2-07":2280.6610569406535,"GB2-08":2092.159141063234},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1847.8019584734577,"GB2-02":2123.274269875037,"GB2-03":2282.8457660548856,"GB2-04":2061.7496717326067,"GB2-05":2482.0219454024764,"GB2-06":2509.867881309482,"GB2-07":2432.0573602031673,"GB2-08":2259.09185400945},"medium":{"GB2-01":2082.0457238095323,"GB2-02":2084.634684562334,"GB2-03":2031.3453837943648,"GB2-04":1930.1142340023166,"GB2-05":2174.6668848273926,"GB2-06":2184.176892901536,"GB2-07":2234.758126864417,"GB2-08":2356.585103939697},"none":{"GB2-01":1968.5028585421053,"GB2-02":1770.811436835893,"GB2-03":1461.6189208965543,"GB2-04":1640.0775190610625,"GB2-05":2243.6000116510204,"GB2-06":1945.8151907163053,"GB2-07":2175.1676837543755,"GB2-08":1660.8004652405566}},"per_game_tracks":{"highest":{"GB2-01":65.06595728586343,"GB2-02":95.10941676820096,"GB2-03":98.64709912670227,"GB2-04":94.93025166624834,"GB2-05":93.6635173163565,"GB2-06":100.0,"GB2-07":95.48879922050352,"GB2-08":82.91817857926416},"medium":{"GB2-01":79.66854112373491,"GB2-02":90.35777759370977,"GB2-03":77.34040884376623,"GB2-04":77.81359048358208,"GB2-05":78.71306557332714,"GB2-06":84.4224990673032,"GB2-07":85.25510385161512,"GB2-08":89.36531076443214},"none":{"GB2-01":72.59036251402483,"GB2-02":51.76588211410766,"GB2-03":29.074139099563844,"GB2-04":40.099884616969156,"GB2-05":82.0661302150626,"GB2-06":73.02187771066075,"GB2-07":82.16421276519004,"GB2-08":43.35376082315801}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":90.7279024953924,"medium":82.86703716268381,"none":59.267031232342106},"reasoning_agg":{"highest":{"max":100.0,"mean":90.7279024953924,"min":65.06595728586343},"medium":{"max":90.35777759370977,"mean":82.86703716268381,"min":77.34040884376623},"none":{"max":82.16421276519004,"mean":59.267031232342106,"min":29.074139099563844}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":85.35278975036212,"reasoning_variance":31.460871263050294,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.732132786889352},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":89.96784356204483,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7600589333475654},"medium":{"ceiling_score":90.35777759370977,"expected_score":89.75054436117279,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.883507198488971},"none":{"ceiling_score":82.16421276519004,"expected_score":76.33998132786873,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":17.072950095526622}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:e070032b2da3e46a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.739117931213684},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276067},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.339052010326091},"historical-provider-setting-intensive":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.73911793121369}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781585},"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":76.10876774550164,"highest":88.26506259627894,"medium":71.46747588300943,"none":68.59376475721655},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:50:31Z","match_totals_all":{"draws":680,"losses":914,"wins":8813},"match_totals_tracks":{"highest":{"draws":104,"losses":209,"wins":3861},"medium":{"draws":242,"losses":354,"wins":2528},"none":{"draws":334,"losses":351,"wins":2424}},"model_slug":"claude-fable-5-1","overall":{"max":99.5665396814597,"mean":76.10876774550164,"min":36.427824332608786},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.93967288747089,"GB2-02":89.18925472269825,"GB2-03":88.54050150873039,"GB2-04":74.21496393981138,"GB2-05":86.3523863653389,"GB2-06":99.5665396814597,"GB2-07":90.509036482198,"GB2-08":96.80814518252392},"per_game_all":{"GB2-01":71.66560249999489,"GB2-02":73.45065834197376,"GB2-03":76.96725172136514,"GB2-04":51.15113996978647,"GB2-05":82.96018902621388,"GB2-06":85.73133419163797,"GB2-07":86.71594654398962,"GB2-08":80.22801966905133},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":32,"wins":311},"GB2-02":{"draws":20,"losses":10,"wins":360},"GB2-03":{"draws":4,"losses":11,"wins":347},"GB2-04":{"draws":29,"losses":28,"wins":303},"GB2-05":{"draws":0,"losses":18,"wins":342},"GB2-06":{"draws":7,"losses":3,"wins":386},"GB2-07":{"draws":0,"losses":27,"wins":373},"GB2-08":{"draws":0,"losses":7,"wins":433}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":32,"wins":311},"GB2-02":{"draws":20,"losses":10,"wins":360},"GB2-03":{"draws":4,"losses":11,"wins":347},"GB2-04":{"draws":29,"losses":28,"wins":303},"GB2-05":{"draws":0,"losses":18,"wins":342},"GB2-06":{"draws":7,"losses":3,"wins":386},"GB2-07":{"draws":0,"losses":27,"wins":373},"GB2-08":{"draws":0,"losses":7,"wins":433}}},"per_game_raw_elo_all":{"GB2-01":1953.668547702073,"GB2-02":1947.1486396987832,"GB2-03":2026.9407034953194,"GB2-04":1725.0670401079888,"GB2-05":2261.9802923798093,"GB2-06":2211.5417319183566,"GB2-07":2262.9222584751974,"GB2-08":2218.411389044138},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2102.436272076996,"GB2-02":2075.132439651423,"GB2-03":2163.5492854415234,"GB2-04":1902.439048096504,"GB2-05":2331.7179188121027,"GB2-06":2500.805187608422,"GB2-07":2336.0506553853284,"GB2-08":2469.1353193334216},"medium":{"GB2-01":1778.0083745087065,"GB2-02":1984.6719466269772,"GB2-03":1993.0447315632985,"GB2-04":1611.8375920247493,"GB2-05":2192.397364393096,"GB2-06":2114.338754592938,"GB2-07":2341.8685563678,"GB2-08":2078.3774370071087},"none":{"GB2-01":1980.5609965205167,"GB2-02":1781.64153281795,"GB2-03":1924.228093481137,"GB2-04":1660.924480202713,"GB2-05":2261.82559393423,"GB2-06":2019.48125355371,"GB2-07":2110.8475636724634,"GB2-08":2107.7214107918835}},"per_game_tracks":{"highest":{"GB2-01":80.93967288747089,"GB2-02":89.18925472269825,"GB2-03":88.54050150873039,"GB2-04":74.21496393981138,"GB2-05":86.3523863653389,"GB2-06":99.5665396814597,"GB2-07":90.509036482198,"GB2-08":96.80814518252392},"medium":{"GB2-01":60.71507665632531,"GB2-02":78.06502502612773,"GB2-03":74.09564186811826,"GB2-04":36.427824332608786,"GB2-05":79.57551657261062,"GB2-06":81.08220503596412,"GB2-07":90.81080464081394,"GB2-08":70.96771293150664},"none":{"GB2-01":73.34205795618848,"GB2-02":53.09769527709532,"GB2-03":68.26561178724677,"GB2-04":42.81063163693924,"GB2-05":82.95266414069214,"GB2-06":76.54525785749006,"GB2-07":78.8279985089569,"GB2-08":72.90820089312348}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":88.26506259627894,"medium":71.46747588300943,"none":68.59376475721655},"reasoning_agg":{"highest":{"max":99.5665396814597,"mean":88.26506259627894,"min":74.21496393981138},"medium":{"max":90.81080464081394,"mean":71.46747588300943,"min":36.427824332608786},"none":{"max":82.95266414069214,"mean":68.59376475721655,"min":42.81063163693924}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":99.5665396814597,"expected_score":84.54358825018872,"reasoning_variance":19.67129783906239,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.434820504687082},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":99.5665396814597,"expected_score":87.30184683120882,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9632157650701174},"medium":{"ceiling_score":90.81080464081394,"expected_score":76.77369796408306,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.306222081073628},"none":{"ceiling_score":82.95266414069214,"expected_score":89.55521995527431,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":20.961455198057763}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:189df670ab8f6f27","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.2665285,"median":0.263151,"min":0.174431,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.132228},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6746989999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.388508}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.674699},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.38850799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.2665285,"median":0.263151,"min":0.174431,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.132228}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.133143125,"median":0.0768835,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":3.1954350000000002},"codegen_latency_ms":{"attempt_count":25,"max_ms":926657,"mean_ms":272565.25,"min_ms":42196,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":926657,"mean_ms":625149.0,"min_ms":331732,"run_count":8},"medium":{"attempt_count":9,"max_ms":198934,"mean_ms":135760.75,"min_ms":63072,"run_count":8},"none":{"attempt_count":8,"max_ms":73464,"mean_ms":56786.0,"min_ms":42196,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":33557,"output_mean":11287.458333333334,"output_min":2159,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":33557,"output_mean":24715.125,"output_min":14936,"run_count":8},"medium":{"attempt_count":9,"output_max":9484,"output_mean":6228.625,"output_min":3242,"run_count":8},"none":{"attempt_count":8,"output_max":3711,"output_mean":2918.625,"output_min":2159,"run_count":8}},"display_name":"GPT-6.1 Sol","economics":{"all":73.63917261746444,"highest":87.71262127527837,"medium":73.57730148908533,"none":59.627595088029665},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[128000],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[128000],"total_output_tokens":270899,"total_reasoning_output_tokens":149779,"total_visible_output_tokens":121120,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-10-06T15:47:09Z","match_totals_all":{"draws":476,"losses":622,"wins":4660},"match_totals_tracks":{"highest":{"draws":50,"losses":113,"wins":1761},"medium":{"draws":121,"losses":203,"wins":1602},"none":{"draws":305,"losses":306,"wins":1297}},"model_slug":"gpt-6-1-sol","overall":{"max":100.0,"mean":73.63917261746445,"min":30.762992573569026},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.51253280244982,"GB2-02":94.7731413030975,"GB2-03":99.1273585236765,"GB2-04":100.0,"GB2-05":93.91217768557095,"GB2-06":82.5999417759285,"GB2-07":91.73754484748298,"GB2-08":80.03827326402072},"per_game_all":{"GB2-01":53.3166064601376,"GB2-02":57.864291031313485,"GB2-03":85.77864660688822,"GB2-04":72.6845028581174,"GB2-05":86.5016044489119,"GB2-06":79.34340405384258,"GB2-07":90.46429165008276,"GB2-08":63.16003383042167},"per_game_match_totals_all":{"GB2-01":{"draws":25,"losses":206,"wins":389},"GB2-02":{"draws":266,"losses":45,"wins":515},"GB2-03":{"draws":18,"losses":42,"wins":570},"GB2-04":{"draws":107,"losses":43,"wins":482},"GB2-05":{"draws":0,"losses":39,"wins":645},"GB2-06":{"draws":58,"losses":70,"wins":624},"GB2-07":{"draws":0,"losses":30,"wins":718},"GB2-08":{"draws":2,"losses":147,"wins":717}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":56,"wins":152},"GB2-02":{"draws":15,"losses":6,"wins":251},"GB2-03":{"draws":2,"losses":4,"wins":202},"GB2-04":{"draws":16,"losses":4,"wins":206},"GB2-05":{"draws":0,"losses":4,"wins":226},"GB2-06":{"draws":17,"losses":12,"wins":217},"GB2-07":{"draws":0,"losses":7,"wins":243},"GB2-08":{"draws":0,"losses":20,"wins":264}},"medium":{"GB2-01":{"draws":3,"losses":61,"wins":144},"GB2-02":{"draws":85,"losses":21,"wins":168},"GB2-03":{"draws":2,"losses":7,"wins":203},"GB2-04":{"draws":16,"losses":17,"wins":173},"GB2-05":{"draws":0,"losses":13,"wins":221},"GB2-06":{"draws":15,"losses":11,"wins":228},"GB2-07":{"draws":0,"losses":13,"wins":237},"GB2-08":{"draws":0,"losses":60,"wins":228}},"none":{"GB2-01":{"draws":22,"losses":89,"wins":93},"GB2-02":{"draws":166,"losses":18,"wins":96},"GB2-03":{"draws":14,"losses":31,"wins":165},"GB2-04":{"draws":75,"losses":22,"wins":103},"GB2-05":{"draws":0,"losses":22,"wins":198},"GB2-06":{"draws":26,"losses":47,"wins":179},"GB2-07":{"draws":0,"losses":10,"wins":238},"GB2-08":{"draws":2,"losses":67,"wins":225}}},"per_game_raw_elo_all":{"GB2-01":1659.327630352517,"GB2-02":1820.4027426936984,"GB2-03":2130.9488414336756,"GB2-04":1890.6690590625456,"GB2-05":2334.7855808402323,"GB2-06":2077.9842832975332,"GB2-07":2335.188003063368,"GB2-08":1960.3100563307164},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1758.7180623666186,"GB2-02":2120.539730478151,"GB2-03":2288.514662552619,"GB2-04":2100.7384986991433,"GB2-05":2487.1339663738936,"GB2-06":2146.071262979088,"GB2-07":2359.7355267718503,"GB2-08":2215.542052235506},"medium":{"GB2-01":1721.650120030692,"GB2-02":1740.6492679219284,"GB2-03":2246.325902612548,"GB2-04":1894.206294495918,"GB2-05":2328.206232236825,"GB2-06":2169.657562219738,"GB2-07":2336.8228496928587,"GB2-08":1824.8707435503995},"none":{"GB2-01":1497.6147086602398,"GB2-02":1600.0192296810167,"GB2-03":1858.0059591358606,"GB2-04":1677.0623839925754,"GB2-05":2189.016543909978,"GB2-06":1918.2240246937738,"GB2-07":2309.005632725394,"GB2-08":1840.517373206244}},"per_game_tracks":{"highest":{"GB2-01":59.51253280244982,"GB2-02":94.7731413030975,"GB2-03":99.1273585236765,"GB2-04":100.0,"GB2-05":93.91217768557095,"GB2-06":82.5999417759285,"GB2-07":91.73754484748298,"GB2-08":80.03827326402072},"medium":{"GB2-01":57.20174457343909,"GB2-02":48.056739217273936,"GB2-03":95.55319758847327,"GB2-04":73.14445240878786,"GB2-05":86.18156991422177,"GB2-06":83.72805281214755,"GB2-07":90.54908935607453,"GB2-08":54.203566042264534},"none":{"GB2-01":43.2355420045239,"GB2-02":30.762992573569026,"GB2-03":62.65538370851485,"GB2-04":44.909056165564316,"GB2-05":79.41106574694298,"GB2-06":71.7022175734517,"GB2-07":89.10624074669074,"GB2-08":55.23826218497976}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":87.71262127527837,"medium":73.57730148908533,"none":59.627595088029665},"reasoning_agg":{"highest":{"max":100.0,"mean":87.71262127527837,"min":59.51253280244982},"medium":{"max":95.55319758847327,"mean":73.57730148908533,"min":48.056739217273936},"none":{"max":89.10624074669074,"mean":59.627595088029665,"min":30.762992573569026}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":80.22579432786549,"reasoning_variance":28.0850261872487,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.586621710401033},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":86.03828903453496,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6743322407434107},"medium":{"ceiling_score":95.55319758847327,"expected_score":79.30125668386337,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.723955194778043},"none":{"ceiling_score":89.10624074669074,"expected_score":75.3378372651981,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":15.710242177168439}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:bc9ed3a634eba3cc","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.074450000000002},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.138875},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.138875},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.074450000000002}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":60.03991629975173,"highest":72.42703190086469,"medium":58.12272599941219,"none":54.10581610819095},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:45:05Z","match_totals_all":{"draws":1956,"losses":2365,"wins":10471},"match_totals_tracks":{"highest":{"draws":270,"losses":577,"wins":3545},"medium":{"draws":677,"losses":789,"wins":3708},"none":{"draws":1009,"losses":999,"wins":3218}},"model_slug":"claude-opus-5","overall":{"max":92.94181174981662,"mean":59.10238321810939,"min":14.772328563486472},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.27233713148352,"GB2-02":53.83905065987624,"GB2-03":89.28438291519518,"GB2-04":63.458536290209835,"GB2-05":86.43921084980195,"GB2-07":92.94181174981662,"GB2-08":63.75389370966944},"per_game_all":{"GB2-01":58.50923153118712,"GB2-02":44.90146254196865,"GB2-03":61.760302771222825,"GB2-04":32.39238029362611,"GB2-05":82.77475001321194,"GB2-07":78.02689082256303,"GB2-08":61.914396124482465},"per_game_match_totals_all":{"GB2-01":{"draws":332,"losses":391,"wins":1102},"GB2-02":{"draws":772,"losses":183,"wins":1294},"GB2-03":{"draws":100,"losses":355,"wins":1240},"GB2-04":{"draws":666,"losses":531,"wins":890},"GB2-05":{"draws":0,"losses":170,"wins":1828},"GB2-06":{"draws":19,"losses":16,"wins":331},"GB2-07":{"draws":0,"losses":209,"wins":1471},"GB2-08":{"draws":67,"losses":510,"wins":2315}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":179,"wins":369},"GB2-02":{"draws":165,"losses":62,"wins":491},"GB2-03":{"draws":5,"losses":24,"wins":489},"GB2-04":{"draws":94,"losses":80,"wins":492},"GB2-05":{"draws":0,"losses":46,"wins":564},"GB2-07":{"draws":0,"losses":14,"wins":346},"GB2-08":{"draws":0,"losses":172,"wins":794}},"medium":{"GB2-01":{"draws":66,"losses":152,"wins":408},"GB2-02":{"draws":291,"losses":48,"wins":396},"GB2-03":{"draws":10,"losses":83,"wins":482},"GB2-04":{"draws":310,"losses":237,"wins":183},"GB2-05":{"draws":0,"losses":69,"wins":621},"GB2-07":{"draws":0,"losses":109,"wins":825},"GB2-08":{"draws":0,"losses":91,"wins":793}},"none":{"GB2-01":{"draws":260,"losses":60,"wins":325},"GB2-02":{"draws":316,"losses":73,"wins":407},"GB2-03":{"draws":85,"losses":248,"wins":269},"GB2-04":{"draws":262,"losses":214,"wins":215},"GB2-05":{"draws":0,"losses":55,"wins":643},"GB2-06":{"draws":19,"losses":16,"wins":331},"GB2-07":{"draws":0,"losses":86,"wins":300},"GB2-08":{"draws":67,"losses":247,"wins":728}}},"per_game_raw_elo_all":{"GB2-01":1742.6238512217708,"GB2-02":1714.9910523454698,"GB2-03":1847.4405829608786,"GB2-04":1580.8030674268375,"GB2-05":2258.167991584232,"GB2-07":2095.402709526443,"GB2-08":1941.4735776143261},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1722.7825132279936,"GB2-02":1787.6701186402443,"GB2-03":2172.3299292486104,"GB2-04":1819.716895279494,"GB2-05":2333.502877898304,"GB2-07":2382.953037944598,"GB2-08":1969.290379359341},"medium":{"GB2-01":1729.1583383159104,"GB2-02":1684.1489356781685,"GB2-03":1894.720228582391,"GB2-04":1445.296311899298,"GB2-05":2188.2913424106964,"GB2-07":2049.093541895954,"GB2-08":2102.1809789349454},"none":{"GB2-01":1775.9307021214083,"GB2-02":1673.1541027179965,"GB2-03":1475.271591051635,"GB2-04":1477.395995101721,"GB2-05":2252.7097544436956,"GB2-06":2214.160592165599,"GB2-07":1854.1615487387776,"GB2-08":1752.9493745486923}},"per_game_tracks":{"highest":{"GB2-01":57.27233713148352,"GB2-02":53.83905065987624,"GB2-03":89.28438291519518,"GB2-04":63.458536290209835,"GB2-05":86.43921084980195,"GB2-07":92.94181174981662,"GB2-08":63.75389370966944},"medium":{"GB2-01":57.66980137241361,"GB2-02":41.10870419338473,"GB2-03":65.76575499714043,"GB2-04":14.772328563486472,"GB2-05":79.37579029060693,"GB2-07":75.62488496426587,"GB2-08":72.54181761458727},"none":{"GB2-01":60.58555608966424,"GB2-02":39.75663277264499,"GB2-03":30.230770401332844,"GB2-04":18.94627602718203,"GB2-05":82.50924889922699,"GB2-06":85.85659187267923,"GB2-07":65.51397575360662,"GB2-08":49.44747704919067}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":68.76327145818792,"medium":56.21445287295079,"none":52.32942532318945},"reasoning_agg":{"highest":{"max":92.94181174981662,"mean":68.76327145818792,"min":53.83905065987624},"medium":{"max":79.37579029060693,"mean":56.21445287295079,"min":14.772328563486472},"none":{"max":85.85659187267923,"mean":52.32942532318945,"min":18.94627602718203}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":92.94181174981662,"expected_score":65.16279872938728,"reasoning_variance":16.43384613499847,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.060415511277888},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":92.94181174981662,"expected_score":69.96293232675386,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1996608685659425},"medium":{"ceiling_score":79.37579029060693,"expected_score":61.85277003784098,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.638317164890196},"none":{"ceiling_score":85.85659187267923,"expected_score":68.2136070956211,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":15.884181772431653}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:0c719c1b0f24bb51","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265164999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.345568}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265164999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.345568},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.10943510416666667,"median":0.0772785,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":2.6264425000000005},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":58.23022294604122,"highest":69.10720843157753,"medium":58.5936877052916,"none":46.989772701254545},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[65536],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[65536],"total_output_tokens":214370,"total_reasoning_output_tokens":129853,"total_visible_output_tokens":84517,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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-6-sol","is_recent_addition":false,"last_measured_at":"2026-10-06T15:08:25Z","match_totals_all":{"draws":751,"losses":1132,"wins":3776},"match_totals_tracks":{"highest":{"draws":130,"losses":283,"wins":1453},"medium":{"draws":280,"losses":333,"wins":1288},"none":{"draws":341,"losses":516,"wins":1035}},"model_slug":"gpt-6-sol","overall":{"max":88.61971124046333,"mean":58.23022294604123,"min":11.405628656720026},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":11.405628656720026,"GB2-02":55.7027225294803,"GB2-03":87.3588150500225,"GB2-04":68.87219378382888,"GB2-05":83.687073453008,"GB2-06":82.8911309238819,"GB2-07":88.61971124046333,"GB2-08":74.32039181521526},"per_game_all":{"GB2-01":30.941936409612325,"GB2-02":36.30767392170269,"GB2-03":63.052296459178386,"GB2-04":42.91275765379572,"GB2-05":76.03129610099951,"GB2-06":75.07543542849771,"GB2-07":75.90640440579516,"GB2-08":65.61398318874826},"per_game_match_totals_all":{"GB2-01":{"draws":55,"losses":361,"wins":162},"GB2-02":{"draws":362,"losses":99,"wins":353},"GB2-03":{"draws":38,"losses":104,"wins":454},"GB2-04":{"draws":205,"losses":117,"wins":309},"GB2-05":{"draws":0,"losses":94,"wins":592},"GB2-06":{"draws":78,"losses":104,"wins":566},"GB2-07":{"draws":0,"losses":135,"wins":595},"GB2-08":{"draws":13,"losses":118,"wins":745}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":168,"wins":15},"GB2-02":{"draws":77,"losses":11,"wins":178},"GB2-03":{"draws":2,"losses":11,"wins":183},"GB2-04":{"draws":29,"losses":21,"wins":160},"GB2-05":{"draws":0,"losses":15,"wins":209},"GB2-06":{"draws":15,"losses":18,"wins":213},"GB2-07":{"draws":0,"losses":12,"wins":232},"GB2-08":{"draws":2,"losses":27,"wins":263}},"medium":{"GB2-01":{"draws":42,"losses":103,"wins":43},"GB2-02":{"draws":118,"losses":29,"wins":127},"GB2-03":{"draws":18,"losses":55,"wins":127},"GB2-04":{"draws":64,"losses":31,"wins":124},"GB2-05":{"draws":0,"losses":23,"wins":209},"GB2-06":{"draws":32,"losses":32,"wins":190},"GB2-07":{"draws":0,"losses":18,"wins":224},"GB2-08":{"draws":6,"losses":42,"wins":244}},"none":{"GB2-01":{"draws":8,"losses":90,"wins":104},"GB2-02":{"draws":167,"losses":59,"wins":48},"GB2-03":{"draws":18,"losses":38,"wins":144},"GB2-04":{"draws":112,"losses":65,"wins":25},"GB2-05":{"draws":0,"losses":56,"wins":174},"GB2-06":{"draws":31,"losses":54,"wins":163},"GB2-07":{"draws":0,"losses":105,"wins":139},"GB2-08":{"draws":5,"losses":49,"wins":238}}},"per_game_raw_elo_all":{"GB2-01":1300.4098512130063,"GB2-02":1645.1077097013679,"GB2-03":1862.691046645482,"GB2-04":1661.7098788729963,"GB2-05":2119.534409047858,"GB2-06":1988.750527120057,"GB2-07":2054.5210603027003,"GB2-08":1997.4185708199805},"per_game_raw_elo_tracks":{"highest":{"GB2-01":987.0229643708697,"GB2-02":1802.8252062965291,"GB2-03":2149.600868670518,"GB2-04":1861.3505507155248,"GB2-05":2276.923761036705,"GB2-06":2152.1593821081033,"GB2-07":2299.625648749403,"GB2-08":2129.076499932674},"medium":{"GB2-01":1359.3852678448638,"GB2-02":1649.0856452696205,"GB2-03":1670.2962472171778,"GB2-04":1698.0239009110844,"GB2-05":2194.2482813936076,"GB2-06":1954.7730865747417,"GB2-07":2265.5053102777238,"GB2-08":1957.5996090363833},"none":{"GB2-01":1554.821321423285,"GB2-02":1483.4122775379544,"GB2-03":1768.1760240487502,"GB2-04":1425.7551849923796,"GB2-05":1887.4311847132608,"GB2-06":1859.319112677326,"GB2-07":1598.4322218809734,"GB2-08":1905.5796034908844}},"per_game_tracks":{"highest":{"GB2-01":11.405628656720026,"GB2-02":55.7027225294803,"GB2-03":87.3588150500225,"GB2-04":68.87219378382888,"GB2-05":83.687073453008,"GB2-06":82.8911309238819,"GB2-07":88.61971124046333,"GB2-08":74.32039181521526},"medium":{"GB2-01":34.61842045393482,"GB2-02":36.79685397699423,"GB2-03":46.75293195475327,"GB2-04":47.63469896476234,"GB2-05":79.66554940058725,"GB2-06":73.45032564461158,"GB2-07":86.84992661487883,"GB2-08":62.98079463181049},"none":{"GB2-01":46.80176011818213,"GB2-02":16.423445258633535,"GB2-03":55.04514237275939,"GB2-04":12.231380212795964,"GB2-05":64.74126544940329,"GB2-06":68.88484971699968,"GB2-07":52.24957536204329,"GB2-08":59.54076311921907}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":69.10720843157753,"medium":58.5936877052916,"none":46.989772701254545},"reasoning_agg":{"highest":{"max":88.61971124046333,"mean":69.10720843157753,"min":11.405628656720026},"medium":{"max":86.84992661487883,"mean":58.5936877052916,"min":34.61842045393482},"none":{"max":68.88484971699968,"mean":46.989772701254545,"min":12.231380212795964}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":88.61971124046333,"expected_score":61.5926302714794,"reasoning_variance":22.11743573032299,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.36240732543817},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":88.61971124046333,"expected_score":65.36292854777072,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.7442798838068114},"medium":{"ceiling_score":86.84992661487883,"expected_score":62.04134733874024,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.4476596334486374},"none":{"ceiling_score":68.88484971699968,"expected_score":57.37361492792726,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":10.383842226672712}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:6bfb8232452f9722","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.23556},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.1897539999999998},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.663736}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.1897539999999998},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.6637359999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.2355599999999995}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":1.2177,"mean":0.4203770833333333,"median":0.380795,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":10.089050000000002},"codegen_latency_ms":{"attempt_count":29,"max_ms":2516111,"mean_ms":895095.7083333334,"min_ms":107275,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2516111,"mean_ms":1632486.25,"min_ms":1212881,"run_count":8},"medium":{"attempt_count":9,"max_ms":1551665,"mean_ms":884117.375,"min_ms":472109,"run_count":8},"none":{"attempt_count":10,"max_ms":283828,"mean_ms":168683.5,"min_ms":107275,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":195136,"output_mean":67634.29166666667,"output_min":8421,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":195136,"output_mean":126135.375,"output_min":92484,"run_count":8},"medium":{"attempt_count":9,"output_max":95241,"output_mean":63372.625,"output_min":32426,"run_count":8},"none":{"attempt_count":10,"output_max":23276,"output_mean":13394.875,"output_min":8421,"run_count":8}},"display_name":"Grok 4.7","economics":{"all":57.199761650600294,"highest":69.10098825693217,"medium":67.55123857184601,"none":40.53965652899949},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[450000],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[450000],"total_output_tokens":1623223,"total_reasoning_output_tokens":1401661,"total_visible_output_tokens":221562,"visible_token_observations":29},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":450000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"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":["GB2-04"],"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}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-10-06T16:04:16Z","match_totals_all":{"draws":516,"losses":1082,"wins":3590},"match_totals_tracks":{"highest":{"draws":68,"losses":255,"wins":1375},"medium":{"draws":104,"losses":240,"wins":1358},"none":{"draws":344,"losses":587,"wins":857}},"model_slug":"x-ai-grok-4-7","overall":{"max":89.40749445644646,"mean":57.12478555912835,"min":12.296768253094946},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":46.497774429139064,"GB2-02":66.11177761816505,"GB2-03":71.80312170204402,"GB2-05":81.96207658579897,"GB2-06":83.94332368077653,"GB2-07":65.04177614937451,"GB2-08":68.34706763322703},"per_game_all":{"GB2-01":46.044758668151616,"GB2-02":45.082824425449736,"GB2-05":68.49786514766232,"GB2-07":59.79518637235312,"GB2-08":66.57817363938467},"per_game_match_totals_all":{"GB2-01":{"draws":84,"losses":242,"wins":278},"GB2-02":{"draws":276,"losses":93,"wins":451},"GB2-03":{"draws":40,"losses":66,"wins":314},"GB2-04":{"draws":68,"losses":105,"wins":239},"GB2-05":{"draws":0,"losses":170,"wins":512},"GB2-06":{"draws":48,"losses":59,"wins":539},"GB2-07":{"draws":0,"losses":227,"wins":511},"GB2-08":{"draws":0,"losses":120,"wins":746}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":89,"wins":112},"GB2-02":{"draws":30,"losses":23,"wins":225},"GB2-03":{"draws":29,"losses":11,"wins":168},"GB2-05":{"draws":0,"losses":19,"wins":205},"GB2-06":{"draws":8,"losses":19,"wins":223},"GB2-07":{"draws":0,"losses":54,"wins":192},"GB2-08":{"draws":0,"losses":40,"wins":250}},"medium":{"GB2-01":{"draws":15,"losses":42,"wins":143},"GB2-02":{"draws":62,"losses":25,"wins":193},"GB2-03":{"draws":11,"losses":55,"wins":146},"GB2-04":{"draws":16,"losses":7,"wins":187},"GB2-05":{"draws":0,"losses":17,"wins":229},"GB2-07":{"draws":0,"losses":67,"wins":189},"GB2-08":{"draws":0,"losses":27,"wins":271}},"none":{"GB2-01":{"draws":68,"losses":111,"wins":23},"GB2-02":{"draws":184,"losses":45,"wins":33},"GB2-04":{"draws":52,"losses":98,"wins":52},"GB2-05":{"draws":0,"losses":134,"wins":78},"GB2-06":{"draws":40,"losses":40,"wins":316},"GB2-07":{"draws":0,"losses":106,"wins":130},"GB2-08":{"draws":0,"losses":53,"wins":225}}},"per_game_raw_elo_all":{"GB2-01":1542.6780684217076,"GB2-02":1716.465858767401,"GB2-05":1964.66028438599,"GB2-07":1743.9068733868714,"GB2-08":2011.9990164948047},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1549.9450095869472,"GB2-02":1887.4700114583036,"GB2-03":1965.9842312954843,"GB2-05":2241.4608515724435,"GB2-06":2174.158398540155,"GB2-07":1845.0578362928231,"GB2-08":2038.7481538303987},"medium":{"GB2-01":1787.3516605566094,"GB2-02":1777.6510974830446,"GB2-03":1676.6053377430344,"GB2-04":2019.2769864914806,"GB2-05":2299.3190876024437,"GB2-07":1818.1181043989275,"GB2-08":2121.7873075024363},"none":{"GB2-01":1290.737535121567,"GB2-02":1484.276467360855,"GB2-04":1426.2580507800017,"GB2-05":1353.2009139830836,"GB2-06":2041.713862664902,"GB2-07":1568.544679468863,"GB2-08":1875.4615881515792}},"per_game_tracks":{"highest":{"GB2-01":46.497774429139064,"GB2-02":66.11177761816505,"GB2-03":71.80312170204402,"GB2-05":81.96207658579897,"GB2-06":83.94332368077653,"GB2-07":65.04177614937451,"GB2-08":68.34706763322703},"medium":{"GB2-01":61.29753022831246,"GB2-02":52.60697808364819,"GB2-03":47.28742751532934,"GB2-04":89.40749445644646,"GB2-05":84.77643325877787,"GB2-07":63.6444417307034,"GB2-08":73.83836472970432},"none":{"GB2-01":30.33897134700332,"GB2-02":16.529717574535965,"GB2-04":12.296768253094946,"GB2-05":38.755085598410126,"GB2-06":77.60862313774791,"GB2-07":50.69934123698144,"GB2-08":57.549088555222674}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.83227913093621,"medium":65.33341050185597,"none":39.20866704459286},"reasoning_agg":{"highest":{"max":83.94332368077653,"mean":66.83227913093621,"min":46.497774429139064},"medium":{"max":89.40749445644646,"mean":65.33341050185597,"min":47.28742751532934},"none":{"max":77.60862313774791,"mean":39.20866704459286,"min":12.296768253094946}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":89.40749445644646,"expected_score":59.63640452656098,"reasoning_variance":27.623612086343357,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.511618967432632},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.94332368077653,"expected_score":64.85133049738604,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.9809486335501703},"medium":{"ceiling_score":89.40749445644646,"expected_score":72.64267070667891,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.309260204822948},"none":{"ceiling_score":77.60862313774791,"expected_score":47.462893317333844,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.254226272740986}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:e0da15537cfdcfa1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.5256212,"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},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.25555516},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181688}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.2555551600000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181688000000007},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.5256212,"mean":0.38805244562499996,"median":0.41839404999999996,"min":0.063446985,"recorded_attempt_count":8,"run_count":8,"total":3.104419565}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"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":53.99904118767389,"highest":71.54529789552987,"medium":54.872241368061125,"none":34.44303593240559},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:30:56Z","match_totals_all":{"draws":2012,"losses":2180,"wins":5315},"match_totals_tracks":{"highest":{"draws":321,"losses":251,"wins":2214},"medium":{"draws":601,"losses":718,"wins":1981},"none":{"draws":1090,"losses":1211,"wins":1120}},"model_slug":"z-ai-glm-5-3","overall":{"max":91.70746717126478,"mean":53.620191731998865,"min":10.031434482843649},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":8,"overall_ranking_status":"partial","per_game":{"GB2-01":75.27949445723183,"GB2-02":31.439604852133826,"GB2-03":66.68941055622497,"GB2-05":81.60475857542293,"GB2-06":87.1958084548523,"GB2-07":91.70746717126478,"GB2-08":66.90054120157848},"per_game_all":{"GB2-01":57.50589642173704,"GB2-02":20.677046276162773,"GB2-03":48.178129054164266,"GB2-05":63.06439868062042,"GB2-06":75.88935569801653,"GB2-07":72.32373965545217,"GB2-08":40.35472252756403},"per_game_match_totals_all":{"GB2-01":{"draws":164,"losses":308,"wins":682},"GB2-02":{"draws":924,"losses":160,"wins":216},"GB2-03":{"draws":205,"losses":284,"wins":661},"GB2-04":{"draws":305,"losses":108,"wins":340},"GB2-05":{"draws":0,"losses":367,"wins":851},"GB2-06":{"draws":68,"losses":279,"wins":943},"GB2-07":{"draws":0,"losses":272,"wins":1012},"GB2-08":{"draws":346,"losses":402,"wins":610}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":24,"losses":33,"wins":281},"GB2-02":{"draws":245,"losses":34,"wins":137},"GB2-03":{"draws":22,"losses":45,"wins":299},"GB2-05":{"draws":0,"losses":35,"wins":355},"GB2-06":{"draws":29,"losses":21,"wins":356},"GB2-07":{"draws":0,"losses":15,"wins":411},"GB2-08":{"draws":1,"losses":68,"wins":375}},"medium":{"GB2-01":{"draws":74,"losses":172,"wins":188},"GB2-02":{"draws":293,"losses":47,"wins":70},"GB2-03":{"draws":40,"losses":69,"wins":252},"GB2-04":{"draws":60,"losses":29,"wins":284},"GB2-05":{"draws":0,"losses":150,"wins":248},"GB2-06":{"draws":21,"losses":16,"wins":375},"GB2-07":{"draws":0,"losses":119,"wins":331},"GB2-08":{"draws":113,"losses":116,"wins":233}},"none":{"GB2-01":{"draws":66,"losses":103,"wins":213},"GB2-02":{"draws":386,"losses":79,"wins":9},"GB2-03":{"draws":143,"losses":170,"wins":110},"GB2-04":{"draws":245,"losses":79,"wins":56},"GB2-05":{"draws":0,"losses":182,"wins":248},"GB2-06":{"draws":18,"losses":242,"wins":212},"GB2-07":{"draws":0,"losses":138,"wins":270},"GB2-08":{"draws":232,"losses":218,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1726.5290972699438,"GB2-02":1518.001894587448,"GB2-03":1687.119020277596,"GB2-05":1852.9577456390264,"GB2-06":2005.7677944089608,"GB2-07":1985.449529142865,"GB2-08":1615.4491397666695},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2011.6399087282964,"GB2-02":1605.5213347233312,"GB2-03":1905.6228945104192,"GB2-05":2234.115020114548,"GB2-06":2242.1606400696082,"GB2-07":2359.1556480237978,"GB2-08":2016.8738446211255},"medium":{"GB2-01":1516.7320980734187,"GB2-02":1517.0509016733429,"GB2-03":1749.7481346757243,"GB2-04":1841.002746423391,"GB2-05":1732.3624474294822,"GB2-06":2296.1128543611258,"GB2-07":1828.0232855280556,"GB2-08":1657.6789236867496},"none":{"GB2-01":1651.215285008116,"GB2-02":1431.43344736567,"GB2-03":1405.9860316466445,"GB2-04":1448.0707133627145,"GB2-05":1592.3957693730488,"GB2-06":1479.0298887961478,"GB2-07":1769.169653876742,"GB2-08":1171.794650992133}},"per_game_tracks":{"highest":{"GB2-01":75.27949445723183,"GB2-02":31.439604852133826,"GB2-03":66.68941055622497,"GB2-05":81.60475857542293,"GB2-06":87.1958084548523,"GB2-07":91.70746717126478,"GB2-08":66.90054120157848},"medium":{"GB2-01":44.4273059828166,"GB2-02":20.56009949351084,"GB2-03":53.48396251326895,"GB2-04":66.22635252797141,"GB2-05":57.19836809389585,"GB2-06":89.77629332658744,"GB2-07":64.15821263864768,"GB2-08":43.1473363677902},"none":{"GB2-01":52.81088882516269,"GB2-02":10.031434482843649,"GB2-03":24.36101409299887,"GB2-04":15.133086203319722,"GB2-05":50.39006937254247,"GB2-06":50.695965312609886,"GB2-07":61.10553915644404,"GB2-08":11.016290013323413}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":71.54529789552987,"medium":54.872241368061125,"none":34.44303593240559},"reasoning_agg":{"highest":{"max":91.70746717126478,"mean":71.54529789552987,"min":31.439604852133826},"medium":{"max":89.77629332658744,"mean":54.872241368061125,"min":20.56009949351084},"none":{"max":61.10553915644404,"mean":34.44303593240559,"min":10.031434482843649}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":91.70746717126478,"expected_score":55.57634597864323,"reasoning_variance":37.10226196312428,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.9561542466443669},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":91.70746717126478,"expected_score":68.22709952961948,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.3181983659103906},"medium":{"ceiling_score":89.77629332658744,"expected_score":58.55071593964435,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.678474571583223},"none":{"ceiling_score":61.10553915644404,"expected_score":39.90117610673617,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.45814017433058}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:3f29acdf21829d79","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.832505},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.8325049999999998},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.22798375},"codegen_output_tokens":{"attempt_count":25,"output_max":35149,"output_mean":11102.833333333334,"output_min":1851,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":35149,"output_mean":24638.75,"output_min":19522,"run_count":8},"medium":{"attempt_count":8,"output_max":6769,"output_mean":6021.5,"output_min":5176,"run_count":8},"none":{"attempt_count":8,"output_max":3391,"output_mean":2648.25,"output_min":1851,"run_count":8}},"display_name":"GPT-5.6 Sol","economics":{"all":50.959741219474616,"highest":64.1539302026223,"medium":48.979166235361305,"none":39.74612722044025},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:37:00Z","match_totals_all":{"draws":1876,"losses":3054,"wins":6916},"match_totals_tracks":{"highest":{"draws":284,"losses":611,"wins":2918},"medium":{"draws":604,"losses":1054,"wins":2126},"none":{"draws":988,"losses":1389,"wins":1872}},"model_slug":"gpt-5-6-sol","overall":{"max":80.20802440903616,"mean":50.959741219474616,"min":11.261489530966506},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.01867615347743,"GB2-02":45.80082854043182,"GB2-03":58.62906857747237,"GB2-04":66.55896579039396,"GB2-05":64.66759732862414,"GB2-06":80.16253644727853,"GB2-07":80.20802440903616,"GB2-08":58.18574437426405},"per_game_all":{"GB2-01":58.4530076711867,"GB2-02":29.57144340247798,"GB2-03":42.97473070313964,"GB2-04":43.96587954292563,"GB2-05":59.62204015653624,"GB2-06":60.48827936199593,"GB2-07":62.3587738505395,"GB2-08":50.24377506699534},"per_game_match_totals_all":{"GB2-01":{"draws":111,"losses":370,"wins":805},"GB2-02":{"draws":796,"losses":176,"wins":494},"GB2-03":{"draws":254,"losses":404,"wins":775},"GB2-04":{"draws":515,"losses":220,"wins":690},"GB2-05":{"draws":0,"losses":436,"wins":1024},"GB2-06":{"draws":56,"losses":550,"wins":961},"GB2-07":{"draws":0,"losses":489,"wins":1092},"GB2-08":{"draws":144,"losses":409,"wins":1075}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":129,"wins":299},"GB2-02":{"draws":156,"losses":33,"wins":271},"GB2-03":{"draws":8,"losses":89,"wins":358},"GB2-04":{"draws":74,"losses":37,"wins":367},"GB2-05":{"draws":0,"losses":103,"wins":369},"GB2-06":{"draws":36,"losses":58,"wins":400},"GB2-07":{"draws":0,"losses":40,"wins":440},"GB2-08":{"draws":0,"losses":122,"wins":414}},"medium":{"GB2-01":{"draws":99,"losses":132,"wins":193},"GB2-02":{"draws":241,"losses":58,"wins":187},"GB2-03":{"draws":58,"losses":150,"wins":247},"GB2-04":{"draws":109,"losses":43,"wins":279},"GB2-05":{"draws":0,"losses":93,"wins":355},"GB2-06":{"draws":8,"losses":264,"wins":218},"GB2-07":{"draws":0,"losses":143,"wins":365},"GB2-08":{"draws":89,"losses":171,"wins":282}},"none":{"GB2-01":{"draws":2,"losses":109,"wins":313},"GB2-02":{"draws":399,"losses":85,"wins":36},"GB2-03":{"draws":188,"losses":165,"wins":170},"GB2-04":{"draws":332,"losses":140,"wins":44},"GB2-05":{"draws":0,"losses":240,"wins":300},"GB2-06":{"draws":12,"losses":228,"wins":343},"GB2-07":{"draws":0,"losses":306,"wins":287},"GB2-08":{"draws":55,"losses":116,"wins":379}}},"per_game_raw_elo_all":{"GB2-01":1741.7219499682353,"GB2-02":1590.3297385054618,"GB2-03":1625.6990316750243,"GB2-04":1669.8088976816032,"GB2-05":1782.18889324068,"GB2-06":1683.765452948891,"GB2-07":1793.3312333869414,"GB2-08":1764.9909582232747},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1750.7959821186334,"GB2-02":1722.3045557384717,"GB2-03":1810.4800514931574,"GB2-04":1843.5607039553324,"GB2-05":1885.9166973844694,"GB2-06":2095.1105245353137,"GB2-07":2137.453598175016,"GB2-08":1885.0890695033875},"medium":{"GB2-01":1654.2556982069163,"GB2-02":1601.5754594649152,"GB2-03":1603.025244061024,"GB2-04":1747.5697344977552,"GB2-05":1908.6406606928617,"GB2-06":1321.8999874887447,"GB2-07":1783.8512126440414,"GB2-08":1639.2238873669937},"none":{"GB2-01":1820.114169579157,"GB2-02":1447.1092003129984,"GB2-03":1463.5917994708918,"GB2-04":1418.2962545917217,"GB2-05":1552.0093216447085,"GB2-06":1634.2858468226143,"GB2-07":1458.688889341767,"GB2-08":1770.6599177994422}},"per_game_tracks":{"highest":{"GB2-01":59.01867615347743,"GB2-02":45.80082854043182,"GB2-03":58.62906857747237,"GB2-04":66.55896579039396,"GB2-05":64.66759732862414,"GB2-06":80.16253644727853,"GB2-07":80.20802440903616,"GB2-08":58.18574437426405},"medium":{"GB2-01":53.000425945066624,"GB2-02":30.9543673604835,"GB2-03":41.05384547071822,"GB2-04":54.077183307416426,"GB2-05":65.77294277573284,"GB2-06":43.180586406563044,"GB2-07":61.86705554666241,"GB2-08":41.926923070247355},"none":{"GB2-01":63.33992091501602,"GB2-02":11.959134306518607,"GB2-03":29.241278061228353,"GB2-04":11.261489530966506,"GB2-05":48.42558036525173,"GB2-06":58.121715232146215,"GB2-07":45.00124159591994,"GB2-08":50.618657756474626}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":64.1539302026223,"medium":48.979166235361305,"none":39.74612722044025},"reasoning_agg":{"highest":{"max":80.20802440903616,"mean":64.1539302026223,"min":45.80082854043182},"medium":{"max":65.77294277573284,"mean":48.979166235361305,"min":30.9543673604835},"none":{"max":63.33992091501602,"mean":39.74612722044025,"min":11.261489530966506}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":80.20802440903616,"expected_score":52.231832330304925,"reasoning_variance":24.407802982182055,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.27209111083031},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.20802440903616,"expected_score":59.59199882155163,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.5619313810706785},"medium":{"ceiling_score":65.77294277573284,"expected_score":49.62231184909481,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6431456137335019},"none":{"ceiling_score":63.33992091501602,"expected_score":47.481186320268336,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.735059099828085}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:e89088b634363388","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.3088499999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.3088499999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":false,"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":49.838237248690604,"highest":58.250829737630205,"medium":48.5360077972312,"none":42.72787421121039},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:32:31Z","match_totals_all":{"draws":2077,"losses":2685,"wins":6154},"match_totals_tracks":{"highest":{"draws":646,"losses":899,"wins":2932},"medium":{"draws":623,"losses":849,"wins":1713},"none":{"draws":808,"losses":937,"wins":1509}},"model_slug":"claude-fable-5","overall":{"max":81.52136004125657,"mean":49.8382372486906,"min":6.794336253338498},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":71.13617526871371,"GB2-02":46.23744105560916,"GB2-03":60.143178071563575,"GB2-04":68.88135545939626,"GB2-05":48.58150790282046,"GB2-06":81.52136004125657,"GB2-07":58.694650481800984,"GB2-08":30.810969619880904},"per_game_all":{"GB2-01":61.29695355237376,"GB2-02":26.651105423879603,"GB2-03":28.41332468194175,"GB2-04":34.40068773720708,"GB2-05":55.27067825346918,"GB2-06":76.5157653436326,"GB2-07":57.786896471770376,"GB2-08":58.37048652525047},"per_game_match_totals_all":{"GB2-01":{"draws":81,"losses":300,"wins":881},"GB2-02":{"draws":710,"losses":151,"wins":441},"GB2-03":{"draws":367,"losses":420,"wins":487},"GB2-04":{"draws":551,"losses":252,"wins":549},"GB2-05":{"draws":0,"losses":555,"wins":871},"GB2-06":{"draws":77,"losses":233,"wins":1030},"GB2-07":{"draws":0,"losses":513,"wins":949},"GB2-08":{"draws":291,"losses":261,"wins":946}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":86,"wins":482},"GB2-02":{"draws":155,"losses":40,"wins":303},"GB2-03":{"draws":106,"losses":47,"wins":391},"GB2-04":{"draws":72,"losses":42,"wins":429},"GB2-05":{"draws":0,"losses":280,"wins":344},"GB2-06":{"draws":24,"losses":62,"wins":460},"GB2-07":{"draws":0,"losses":190,"wins":376},"GB2-08":{"draws":289,"losses":152,"wins":147}},"medium":{"GB2-01":{"draws":33,"losses":108,"wins":213},"GB2-02":{"draws":243,"losses":48,"wins":113},"GB2-03":{"draws":97,"losses":227,"wins":36},"GB2-04":{"draws":212,"losses":77,"wins":86},"GB2-05":{"draws":0,"losses":146,"wins":260},"GB2-06":{"draws":38,"losses":80,"wins":292},"GB2-07":{"draws":0,"losses":133,"wins":275},"GB2-08":{"draws":0,"losses":30,"wins":438}},"none":{"GB2-01":{"draws":48,"losses":106,"wins":186},"GB2-02":{"draws":312,"losses":63,"wins":25},"GB2-03":{"draws":164,"losses":146,"wins":60},"GB2-04":{"draws":267,"losses":133,"wins":34},"GB2-05":{"draws":0,"losses":129,"wins":267},"GB2-06":{"draws":15,"losses":91,"wins":278},"GB2-07":{"draws":0,"losses":190,"wins":298},"GB2-08":{"draws":2,"losses":79,"wins":361}}},"per_game_raw_elo_all":{"GB2-01":1787.3424099510478,"GB2-02":1566.582007602039,"GB2-03":1453.8187850505699,"GB2-04":1596.2479270645629,"GB2-05":1692.7325260158661,"GB2-06":2018.8646305131872,"GB2-07":1705.1883026825362,"GB2-08":1887.8827322020068},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1945.1758706865764,"GB2-02":1725.8550203064374,"GB2-03":1828.352330645457,"GB2-04":1861.421008450289,"GB2-05":1555.214918276737,"GB2-06":2123.5205115612707,"GB2-07":1722.6892311138922,"GB2-08":1471.1289271856651},"medium":{"GB2-01":1722.4751653118071,"GB2-02":1548.9110102586528,"GB2-03":1198.632091027332,"GB2-04":1524.763296747634,"GB2-05":1751.262097752443,"GB2-06":1986.329316309887,"GB2-07":1777.2620393571349,"GB2-08":2215.7861815669094},"none":{"GB2-01":1694.3761938547602,"GB2-02":1424.9799922410266,"GB2-03":1334.4719334789202,"GB2-04":1402.5594759957658,"GB2-05":1771.7205620184184,"GB2-06":1946.744063668404,"GB2-07":1615.6136375765823,"GB2-08":1976.7330878534456}},"per_game_tracks":{"highest":{"GB2-01":71.13617526871371,"GB2-02":46.23744105560916,"GB2-03":60.143178071563575,"GB2-04":68.88135545939626,"GB2-05":48.58150790282046,"GB2-06":81.52136004125657,"GB2-07":58.694650481800984,"GB2-08":30.810969619880904},"medium":{"GB2-01":57.2531772887143,"GB2-02":24.47804371657504,"GB2-03":6.794336253338498,"GB2-04":25.105484120305434,"GB2-05":58.117690227667985,"GB2-06":74.95963113855392,"GB2-07":61.52528233746171,"GB2-08":80.05441729523271},"none":{"GB2-01":55.501508099693226,"GB2-02":9.237831499454614,"GB2-03":18.302459720923174,"GB2-04":9.21522363191955,"GB2-05":59.11283662991907,"GB2-06":73.06630485108732,"GB2-07":53.14075659604845,"GB2-08":64.2460726606378}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":58.250829737630205,"medium":48.5360077972312,"none":42.72787421121039},"reasoning_agg":{"highest":{"max":81.52136004125657,"mean":58.250829737630205,"min":30.810969619880904},"medium":{"max":80.05441729523271,"mean":48.5360077972312,"min":6.794336253338498},"none":{"max":73.06630485108732,"mean":42.72787421121039,"min":9.21522363191955}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":81.52136004125657,"expected_score":51.35087685980412,"reasoning_variance":15.522955526419814,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.5126396111135207},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.52136004125657,"expected_score":52.819499083964246,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.43133065366596},"medium":{"ceiling_score":80.05441729523271,"expected_score":50.70176038867812,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1657525914469176},"none":{"ceiling_score":73.06630485108732,"expected_score":50.531371106769974,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.803496895559583}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:252b89bab369c62e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385362},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.4863780000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.327498}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.486378},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.32749799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385362}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199238000000001},"codegen_output_tokens":{"attempt_count":28,"output_max":70064,"output_mean":18803.166666666668,"output_min":1228,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":70064,"output_mean":51989.0,"output_min":25995,"run_count":8},"medium":{"attempt_count":11,"output_max":4348,"output_mean":2842.75,"output_min":1552,"run_count":8},"none":{"attempt_count":8,"output_max":2376,"output_mean":1577.75,"output_min":1228,"run_count":8}},"display_name":"Claude Sonnet 5.5","economics":{"all":49.377083976292575,"highest":83.60074820402825,"medium":36.398256484547765,"none":28.1322472403017},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":451276,"total_reasoning_output_tokens":352227,"total_visible_output_tokens":99049,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":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":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-10-06T16:49:11Z","match_totals_all":{"draws":1018,"losses":1766,"wins":2990},"match_totals_tracks":{"highest":{"draws":129,"losses":104,"wins":1681},"medium":{"draws":462,"losses":710,"wins":774},"none":{"draws":427,"losses":952,"wins":535}},"model_slug":"claude-sonnet-5-5","overall":{"max":99.99999999999999,"mean":49.37708397629257,"min":7.386810443293055},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.37926822878865,"GB2-02":96.64250928172733,"GB2-03":88.62213320492829,"GB2-04":62.32789545742312,"GB2-05":90.4101963892994,"GB2-06":81.20502750584174,"GB2-07":85.21895556421747,"GB2-08":99.99999999999999},"per_game_all":{"GB2-01":47.13874245767874,"GB2-02":38.964682537089885,"GB2-03":44.3714701303048,"GB2-04":28.835849148999554,"GB2-05":46.10094300080629,"GB2-06":60.14533366467392,"GB2-07":63.844961442228055,"GB2-08":65.61468942855934},"per_game_match_totals_all":{"GB2-01":{"draws":74,"losses":245,"wins":287},"GB2-02":{"draws":436,"losses":115,"wins":285},"GB2-03":{"draws":140,"losses":196,"wins":284},"GB2-04":{"draws":287,"losses":146,"wins":203},"GB2-05":{"draws":0,"losses":388,"wins":290},"GB2-06":{"draws":42,"losses":280,"wins":430},"GB2-07":{"draws":0,"losses":234,"wins":528},"GB2-08":{"draws":39,"losses":162,"wins":683}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":54,"losses":17,"wins":133},"GB2-02":{"draws":18,"losses":3,"wins":259},"GB2-03":{"draws":1,"losses":13,"wins":192},"GB2-04":{"draws":32,"losses":22,"wins":150},"GB2-05":{"draws":0,"losses":7,"wins":213},"GB2-06":{"draws":22,"losses":21,"wins":209},"GB2-07":{"draws":0,"losses":21,"wins":233},"GB2-08":{"draws":2,"losses":0,"wins":292}},"medium":{"GB2-01":{"draws":5,"losses":117,"wins":78},"GB2-02":{"draws":214,"losses":63,"wins":5},"GB2-03":{"draws":91,"losses":103,"wins":18},"GB2-04":{"draws":131,"losses":70,"wins":17},"GB2-05":{"draws":0,"losses":182,"wins":46},"GB2-06":{"draws":16,"losses":56,"wins":178},"GB2-07":{"draws":0,"losses":68,"wins":188},"GB2-08":{"draws":5,"losses":51,"wins":244}},"none":{"GB2-01":{"draws":15,"losses":111,"wins":76},"GB2-02":{"draws":204,"losses":49,"wins":21},"GB2-03":{"draws":48,"losses":80,"wins":74},"GB2-04":{"draws":124,"losses":54,"wins":36},"GB2-05":{"draws":0,"losses":199,"wins":31},"GB2-06":{"draws":4,"losses":203,"wins":43},"GB2-07":{"draws":0,"losses":145,"wins":107},"GB2-08":{"draws":32,"losses":111,"wins":147}}},"per_game_raw_elo_all":{"GB2-01":1560.2269409308908,"GB2-02":1666.7140874797976,"GB2-03":1642.1858954340432,"GB2-04":1553.451615585375,"GB2-05":1504.218855493921,"GB2-06":1676.5952191858735,"GB2-07":1821.983998773055,"GB2-08":1997.4292505474057},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1836.786604469661,"GB2-02":2135.741138000606,"GB2-03":2164.5128514635435,"GB2-04":1811.0217181446953,"GB2-05":2415.1393743743442,"GB2-06":2116.9066999768593,"GB2-07":2234.0612105372275,"GB2-08":2517.402407788217},"medium":{"GB2-01":1422.082116142922,"GB2-02":1409.9277790176134,"GB2-03":1305.7638891077786,"GB2-04":1401.9043239808052,"GB2-05":1109.5196399660072,"GB2-06":1891.2657629821301,"GB2-07":1780.018449183802,"GB2-08":1932.0162802016184},"none":{"GB2-01":1421.8121021800896,"GB2-02":1454.4733454211728,"GB2-03":1456.2809457308076,"GB2-04":1447.4288046306249,"GB2-05":987.9975521414108,"GB2-06":1021.6131945986313,"GB2-07":1451.8723365981355,"GB2-08":1542.8690636523818}},"per_game_tracks":{"highest":{"GB2-01":64.37926822878865,"GB2-02":96.64250928172733,"GB2-03":88.62213320492829,"GB2-04":62.32789545742312,"GB2-05":90.4101963892994,"GB2-06":81.20502750584174,"GB2-07":85.21895556421747,"GB2-08":99.99999999999999},"medium":{"GB2-01":38.52689580792839,"GB2-02":7.386810443293055,"GB2-03":15.870362383547809,"GB2-04":9.13003369175923,"GB2-05":26.901872181147283,"GB2-06":70.41282866831254,"GB2-07":61.6682542993927,"GB2-08":61.28899440100111},"none":{"GB2-01":38.51006333631918,"GB2-02":12.864727886249268,"GB2-03":28.621914802438305,"GB2-04":15.049618297816304,"GB2-05":20.990760431972177,"GB2-06":28.818144819867484,"GB2-07":44.647674463074,"GB2-08":35.55507388467693}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":83.60074820402825,"medium":36.398256484547765,"none":28.1322472403017},"reasoning_agg":{"highest":{"max":99.99999999999999,"mean":83.60074820402825,"min":62.32789545742312},"medium":{"max":70.41282866831254,"mean":36.398256484547765,"min":7.386810443293055},"none":{"max":44.647674463074,"mean":28.1322472403017,"min":12.864727886249268}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":99.99999999999999,"expected_score":50.183858456116916,"reasoning_variance":55.46850096372655,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8067744798243481},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":99.99999999999999,"expected_score":81.55575955956064,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.044988644467608},"medium":{"ceiling_score":70.41282866831254,"expected_score":36.68450868851723,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.28625220396946105},"none":{"ceiling_score":44.647674463074,"expected_score":32.31130712027287,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.17905987997117}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:d86b04520ffc94d1","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.095582115,"mean":0.064849963125,"median":0.0720292575,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":7},"recorded_attempt_count":8,"run_count":8,"total":0.5187997049999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.095582115,"mean":0.064849963125,"median":0.0720292575,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":7},"recorded_attempt_count":8,"run_count":8,"total":0.5187997049999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.095582115,"mean":0.0360195496875,"median":0.011032687499999999,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":17},"recorded_attempt_count":18,"run_count":16,"total":0.576312795},"codegen_latency_ms":{"attempt_count":17,"max_ms":1918656,"mean_ms":677935.3333333334,"min_ms":33029,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":7,"max_ms":1918656,"mean_ms":1391641.4285714286,"min_ms":1011751,"run_count":7},"none":{"attempt_count":10,"max_ms":84396,"mean_ms":53442.5,"min_ms":33029,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":106279,"output_mean":38910.375,"output_min":2214,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":8,"output_max":106279,"output_mean":74392.625,"output_min":26428,"run_count":8},"none":{"attempt_count":10,"output_max":6088,"output_mean":3428.125,"output_min":2214,"run_count":8}},"display_name":"MiMo-V2.6-Pro","economics":{"medium":59.13105478879896,"none":36.14738780606713},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":18,"effective_max_output_tokens":[131072],"finish_reason_observations":17,"finish_reasons":["stop"],"indexed_attempts":18,"output_token_observations":18,"provider_post_attempt_observations":18,"provider_post_attempts":18,"reasoning_token_observations":18,"reconciliation_get_attempt_observations":18,"requested_max_output_token_observations":18,"requested_max_output_tokens":[131072],"total_output_tokens":622566,"total_reasoning_output_tokens":557845,"total_visible_output_tokens":64721,"visible_token_observations":18},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":7,"first_pass_admitted":7,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-05"],"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}},"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":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-06T14:17:53Z","match_totals_all":{"draws":641,"losses":1084,"wins":1863},"match_totals_tracks":{"medium":{"draws":154,"losses":359,"wins":1177},"none":{"draws":487,"losses":725,"wins":686}},"model_slug":"xiaomi-mimo-v2-6-pro","overall":{"max":77.27451935547508,"mean":47.639221297433046,"min":7.516229017033757},"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":12,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":121,"wins":194},"GB2-02":{"draws":227,"losses":81,"wins":236},"GB2-03":{"draws":78,"losses":126,"wins":210},"GB2-04":{"draws":217,"losses":62,"wins":153},"GB2-05":{"draws":0,"losses":131,"wins":103},"GB2-06":{"draws":40,"losses":146,"wins":320},"GB2-07":{"draws":0,"losses":312,"wins":176},"GB2-08":{"draws":0,"losses":105,"wins":471}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":0,"losses":34,"wins":162},"GB2-02":{"draws":17,"losses":21,"wins":234},"GB2-03":{"draws":31,"losses":29,"wins":150},"GB2-04":{"draws":74,"losses":32,"wins":114},"GB2-06":{"draws":32,"losses":28,"wins":194},"GB2-07":{"draws":0,"losses":167,"wins":77},"GB2-08":{"draws":0,"losses":48,"wins":246}},"none":{"GB2-01":{"draws":79,"losses":87,"wins":32},"GB2-02":{"draws":210,"losses":60,"wins":2},"GB2-03":{"draws":47,"losses":97,"wins":60},"GB2-04":{"draws":143,"losses":30,"wins":39},"GB2-05":{"draws":0,"losses":131,"wins":103},"GB2-06":{"draws":8,"losses":118,"wins":126},"GB2-07":{"draws":0,"losses":145,"wins":99},"GB2-08":{"draws":0,"losses":57,"wins":225}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1896.208642476134,"GB2-02":1934.2528361492475,"GB2-03":1809.3361191269585,"GB2-04":1642.3648656888795,"GB2-06":2034.728493731245,"GB2-07":1311.1280484291472,"GB2-08":1918.8385289332537},"none":{"GB2-01":1381.2173809323565,"GB2-02":1410.9801905828576,"GB2-03":1417.9167350096686,"GB2-04":1515.694667630787,"GB2-05":1422.724087201083,"GB2-06":1538.5605595638265,"GB2-07":1406.6099554533928,"GB2-08":1888.4096410285367}},"per_game_tracks":{"medium":{"GB2-01":68.08359432072017,"GB2-02":71.86481820325022,"GB2-03":58.532156547311004,"GB2-04":40.3973101272324,"GB2-06":77.27451935547508,"GB2-07":37.34742222357588,"GB2-08":60.41756274402797},"none":{"GB2-01":35.97941830700726,"GB2-02":7.516229017033757,"GB2-03":25.371763258183904,"GB2-04":23.9262830277974,"GB2-05":42.13685144366145,"GB2-06":53.5432626355743,"GB2-07":42.29996427450713,"GB2-08":58.40533048477179}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":59.13105478879896,"none":36.14738780606713},"reasoning_agg":{"medium":{"max":77.27451935547508,"mean":59.13105478879896,"min":37.34742222357588},"none":{"max":58.40533048477179,"mean":36.14738780606713,"min":7.516229017033757}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":77.27451935547508,"reasoning_variance":22.983666982731833},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":77.27451935547508,"expected_score":61.76303555187427,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.6319807630753047},"none":{"ceiling_score":58.40533048477179,"expected_score":42.57538316153334,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.427995355466209}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:a55c8df06bcae068","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.8727580000000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.13107158333333335,"median":0.12371399999999999,"min":0.027072,"recorded_attempt_count":27,"run_count":24,"total":3.145718000000001},"codegen_latency_ms":{"attempt_count":27,"max_ms":669574,"mean_ms":286694.0416666667,"min_ms":31621,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":669574,"mean_ms":551119.125,"min_ms":414817,"run_count":8},"medium":{"attempt_count":10,"max_ms":376458,"mean_ms":270365.25,"min_ms":196147,"run_count":8},"none":{"attempt_count":8,"max_ms":49571,"mean_ms":38597.75,"min_ms":31621,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":43739,"output_mean":18621.333333333332,"output_min":1925,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":43739,"output_mean":35745.125,"output_min":27954,"run_count":8},"medium":{"attempt_count":10,"output_max":24183,"output_mean":17614.25,"output_min":12541,"run_count":8},"none":{"attempt_count":8,"output_max":3323,"output_mean":2504.625,"output_min":1925,"run_count":8}},"display_name":"Grok 4.6","economics":{"all":43.78947310608864,"highest":48.48132368064659,"medium":52.89500356140194,"none":29.99209207621738},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:09:39Z","match_totals_all":{"draws":2983,"losses":3094,"wins":5247},"match_totals_tracks":{"highest":{"draws":823,"losses":903,"wins":1685},"medium":{"draws":876,"losses":877,"wins":2686},"none":{"draws":1284,"losses":1314,"wins":876}},"model_slug":"x-ai-grok-4-6","overall":{"max":74.16809836224792,"mean":43.78947310608864,"min":9.701446950228679},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.140166212405106,"GB2-02":57.20536642017024,"GB2-03":29.945668978487785,"GB2-04":26.39635225381869,"GB2-05":74.16809836224792,"GB2-06":61.28427531174276,"GB2-07":65.24509056803718,"GB2-08":28.465571338263043},"per_game_all":{"GB2-01":49.48928846126637,"GB2-02":29.261748139467453,"GB2-03":31.51137622543156,"GB2-04":24.641215294776384,"GB2-05":63.63663294586515,"GB2-06":53.51820314786395,"GB2-07":60.399956928006816,"GB2-08":37.85736370603143},"per_game_match_totals_all":{"GB2-01":{"draws":424,"losses":392,"wins":574},"GB2-02":{"draws":733,"losses":171,"wins":423},"GB2-03":{"draws":534,"losses":364,"wins":470},"GB2-04":{"draws":713,"losses":291,"wins":399},"GB2-05":{"draws":0,"losses":380,"wins":1020},"GB2-06":{"draws":75,"losses":588,"wins":673},"GB2-07":{"draws":0,"losses":456,"wins":1008},"GB2-08":{"draws":504,"losses":452,"wins":680}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":224,"losses":99,"wins":101},"GB2-02":{"draws":57,"losses":38,"wins":302},"GB2-03":{"draws":101,"losses":170,"wins":173},"GB2-04":{"draws":203,"losses":95,"wins":142},"GB2-05":{"draws":0,"losses":59,"wins":331},"GB2-06":{"draws":35,"losses":161,"wins":206},"GB2-07":{"draws":0,"losses":102,"wins":298},"GB2-08":{"draws":203,"losses":179,"wins":132}},"medium":{"GB2-01":{"draws":152,"losses":159,"wins":267},"GB2-02":{"draws":338,"losses":65,"wins":109},"GB2-03":{"draws":116,"losses":139,"wins":295},"GB2-04":{"draws":236,"losses":77,"wins":222},"GB2-05":{"draws":0,"losses":94,"wins":478},"GB2-06":{"draws":34,"losses":106,"wins":408},"GB2-07":{"draws":0,"losses":141,"wins":425},"GB2-08":{"draws":0,"losses":96,"wins":482}},"none":{"GB2-01":{"draws":48,"losses":134,"wins":206},"GB2-02":{"draws":338,"losses":68,"wins":12},"GB2-03":{"draws":317,"losses":55,"wins":2},"GB2-04":{"draws":274,"losses":119,"wins":35},"GB2-05":{"draws":0,"losses":227,"wins":211},"GB2-06":{"draws":6,"losses":321,"wins":59},"GB2-07":{"draws":0,"losses":213,"wins":285},"GB2-08":{"draws":301,"losses":177,"wins":66}}},"per_game_raw_elo_all":{"GB2-01":1597.9326478516111,"GB2-02":1587.8113451475913,"GB2-03":1490.387634416841,"GB2-04":1521.1928439928097,"GB2-05":1864.7218782739772,"GB2-06":1538.0366212661083,"GB2-07":1755.5664706951,"GB2-08":1577.6841892801076},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1528.1672705190022,"GB2-02":1815.0444709916737,"GB2-03":1471.9063045676062,"GB2-04":1534.6906996443613,"GB2-05":2081.23033210755,"GB2-06":1700.4079624734843,"GB2-07":1848.9776108691517,"GB2-08":1435.6619173139286},"medium":{"GB2-01":1619.2545109906694,"GB2-02":1519.6395240004704,"GB2-03":1623.972224193879,"GB2-04":1608.7575978456557,"GB2-05":2005.0388090978438,"GB2-06":1968.6138825616922,"GB2-07":1840.181684516333,"GB2-08":1961.5829431136403},"none":{"GB2-01":1646.3761620451617,"GB2-02":1428.75004045063,"GB2-03":1375.2843744890379,"GB2-04":1420.1302344884123,"GB2-05":1507.896493616538,"GB2-06":945.0880187631487,"GB2-07":1577.5401166998154,"GB2-08":1335.8077074127546}},"per_game_tracks":{"highest":{"GB2-01":45.140166212405106,"GB2-02":57.20536642017024,"GB2-03":29.945668978487785,"GB2-04":26.39635225381869,"GB2-05":74.16809836224792,"GB2-06":61.28427531174276,"GB2-07":65.24509056803718,"GB2-08":28.465571338263043},"medium":{"GB2-01":50.81847770829292,"GB2-02":20.878431048003424,"GB2-03":42.82843847150036,"GB2-04":36.02733022769955,"GB2-05":70.46196876134535,"GB2-06":74.11231820832947,"GB2-07":64.78885549170836,"GB2-08":63.24420857433609},"none":{"GB2-01":52.509221463101085,"GB2-02":9.701446950228679,"GB2-03":21.76002122630653,"GB2-04":11.499963402810904,"GB2-05":46.27983171400216,"GB2-06":25.15801592351964,"GB2-07":51.165924724274916,"GB2-08":21.86231120549516}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.48132368064659,"medium":52.89500356140194,"none":29.99209207621738},"reasoning_agg":{"highest":{"max":74.16809836224792,"mean":48.48132368064659,"min":26.39635225381869},"medium":{"max":74.11231820832947,"mean":52.89500356140194,"min":20.878431048003424},"none":{"max":52.509221463101085,"mean":29.99209207621738,"min":9.701446950228679}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.16809836224792,"expected_score":43.63650546260056,"reasoning_variance":22.902911485184564,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.15296764348808267},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.16809836224792,"expected_score":41.48153058346851,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.9997930971780775},"medium":{"ceiling_score":74.11231820832947,"expected_score":55.55948581941614,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.6644822580141962},"none":{"ceiling_score":52.509221463101085,"expected_score":33.86849998491703,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.876407908699651}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:10f11e42e673e506","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.2669949999999996},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"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":46.640573571292805,"highest":57.42388892739695,"medium":41.71140222401212,"none":32.85092857848582},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:05:52Z","match_totals_all":{"draws":3067,"losses":3322,"wins":4927},"match_totals_tracks":{"highest":{"draws":506,"losses":731,"wins":2165},"medium":{"draws":1274,"losses":1112,"wins":1554},"none":{"draws":1287,"losses":1479,"wins":1208}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":43.36696355844419,"min":2.1897990952375683},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":86.9649414142018,"GB2-03":24.750314831183438,"GB2-04":28.751665097677872,"GB2-05":76.51945678898174,"GB2-06":76.01828340227591,"GB2-07":68.8211824401747,"GB2-08":40.14137851728319},"per_game_all":{"GB2-01":84.16754927350529,"GB2-03":21.830143939462165,"GB2-04":12.815916436798915,"GB2-05":62.57775002714725,"GB2-06":71.24481402985298,"GB2-07":46.52455368055728,"GB2-08":27.323287611725736},"per_game_match_totals_all":{"GB2-01":{"draws":49,"losses":103,"wins":1182},"GB2-02":{"draws":780,"losses":160,"wins":43},"GB2-03":{"draws":614,"losses":549,"wins":294},"GB2-04":{"draws":740,"losses":413,"wins":223},"GB2-05":{"draws":0,"losses":381,"wins":999},"GB2-06":{"draws":96,"losses":341,"wins":1015},"GB2-07":{"draws":0,"losses":808,"wins":780},"GB2-08":{"draws":788,"losses":567,"wins":391}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":22,"wins":408},"GB2-03":{"draws":163,"losses":212,"wins":146},"GB2-04":{"draws":239,"losses":67,"wins":139},"GB2-05":{"draws":0,"losses":59,"wins":423},"GB2-06":{"draws":38,"losses":78,"wins":364},"GB2-07":{"draws":0,"losses":90,"wins":396},"GB2-08":{"draws":58,"losses":203,"wins":289}},"medium":{"GB2-01":{"draws":5,"losses":4,"wins":431},"GB2-02":{"draws":403,"losses":73,"wins":33},"GB2-03":{"draws":239,"losses":161,"wins":96},"GB2-04":{"draws":220,"losses":171,"wins":39},"GB2-05":{"draws":0,"losses":130,"wins":316},"GB2-06":{"draws":30,"losses":92,"wins":358},"GB2-07":{"draws":0,"losses":326,"wins":200},"GB2-08":{"draws":377,"losses":155,"wins":81}},"none":{"GB2-01":{"draws":36,"losses":77,"wins":343},"GB2-02":{"draws":377,"losses":87,"wins":10},"GB2-03":{"draws":212,"losses":176,"wins":52},"GB2-04":{"draws":281,"losses":175,"wins":45},"GB2-05":{"draws":0,"losses":192,"wins":260},"GB2-06":{"draws":28,"losses":171,"wins":293},"GB2-07":{"draws":0,"losses":392,"wins":184},"GB2-08":{"draws":353,"losses":209,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":2154.21545904137,"GB2-03":1376.1120905223397,"GB2-04":1430.2505524530477,"GB2-05":1842.9531030410683,"GB2-06":1908.6607312708038,"GB2-07":1488.057391686316,"GB2-08":1418.3883529377},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2199.0891386198336,"GB2-03":1410.5812683149193,"GB2-04":1552.8041993441248,"GB2-05":2129.570136422792,"GB2-06":2008.4633867003572,"GB2-07":1917.9224210563546,"GB2-08":1612.2229610071765},"medium":{"GB2-01":2408.1878322766934,"GB2-02":1447.2662870722468,"GB2-03":1402.9303303395925,"GB2-04":1348.5305491940962,"GB2-05":1791.7964947954513,"GB2-06":1969.9940644211422,"GB2-07":1300.860856201879,"GB2-08":1373.2486791993292},"none":{"GB2-01":1855.3694062275833,"GB2-02":1407.0699376609487,"GB2-03":1314.824672912508,"GB2-04":1389.4169088209221,"GB2-05":1607.492677904962,"GB2-06":1747.5247426909118,"GB2-07":1245.3888978007144,"GB2-08":1269.6934186065935}},"per_game_tracks":{"highest":{"GB2-01":86.9649414142018,"GB2-03":24.750314831183438,"GB2-04":28.751665097677872,"GB2-05":76.51945678898174,"GB2-06":76.01828340227591,"GB2-07":68.8211824401747,"GB2-08":40.14137851728319},"medium":{"GB2-01":100.0,"GB2-02":11.97845179124309,"GB2-03":24.102140206759294,"GB2-04":2.1897990952375683,"GB2-05":60.089375827346764,"GB2-06":74.17833103941199,"GB2-07":36.81487419604614,"GB2-08":24.33824563605209},"none":{"GB2-01":65.53770640631403,"GB2-02":7.035372123370281,"GB2-03":16.637976780443772,"GB2-04":7.506285117481307,"GB2-05":51.12441746511326,"GB2-06":63.53782764787101,"GB2-07":33.93760440545099,"GB2-08":17.49023868184193}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.53855987283464,"medium":41.71140222401212,"none":32.85092857848582},"reasoning_agg":{"highest":{"max":86.9649414142018,"mean":55.53855987283464,"min":24.750314831183438},"medium":{"max":100.0,"mean":41.71140222401212,"min":2.1897990952375683},"none":{"max":65.53770640631403,"mean":32.85092857848582,"min":7.035372123370281}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":47.09774721967473,"reasoning_variance":22.68763129434882,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.7307836612305394},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":86.9649414142018,"expected_score":51.64719194797417,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.891367924860468},"medium":{"ceiling_score":100.0,"expected_score":42.836147762433505,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1247455384213865},"none":{"ceiling_score":65.53770640631403,"expected_score":38.10705458731791,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.256126008832091}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:c3cb07206f19bcb1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850016},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.25553343903391196}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850016},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.25553343903391196},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.97564625},"codegen_output_tokens":{"attempt_count":25,"output_max":73160,"output_mean":20095.833333333332,"output_min":1712,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":73160,"output_mean":40784.875,"output_min":28671,"run_count":8},"medium":{"attempt_count":8,"output_max":31721,"output_mean":16792.0,"output_min":5265,"run_count":8},"none":{"attempt_count":8,"output_max":3473,"output_mean":2710.625,"output_min":1712,"run_count":8}},"display_name":"Gemini 3.8 Flash","economics":{"all":42.987525775957984,"highest":47.22713805670986,"medium":42.925661144475804,"none":38.80977812668829},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:30:56Z","match_totals_all":{"draws":2389,"losses":3052,"wins":4617},"match_totals_tracks":{"highest":{"draws":522,"losses":956,"wins":1788},"medium":{"draws":1012,"losses":1017,"wins":1478},"none":{"draws":855,"losses":1079,"wins":1351}},"model_slug":"google-gemini-3-8-flash","overall":{"max":79.20614223860902,"mean":42.987525775957984,"min":5.591532628143695},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":46.89582654451502,"GB2-02":36.7967765243584,"GB2-03":47.86968632430597,"GB2-04":19.563185592281208,"GB2-05":55.96654820696413,"GB2-06":79.20614223860902,"GB2-07":59.031497180647904,"GB2-08":32.48744184199722},"per_game_all":{"GB2-01":50.54685077085801,"GB2-02":16.308953271652182,"GB2-03":46.58265442394543,"GB2-04":20.41452601931088,"GB2-05":51.397523685788464,"GB2-06":74.19021681809421,"GB2-07":50.12700168874397,"GB2-08":34.332479529270756},"per_game_match_totals_all":{"GB2-01":{"draws":257,"losses":370,"wins":595},"GB2-02":{"draws":806,"losses":191,"wins":212},"GB2-03":{"draws":208,"losses":287,"wins":667},"GB2-04":{"draws":511,"losses":335,"wins":281},"GB2-05":{"draws":0,"losses":599,"wins":751},"GB2-06":{"draws":75,"losses":242,"wins":861},"GB2-07":{"draws":0,"losses":585,"wins":743},"GB2-08":{"draws":532,"losses":443,"wins":507}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":35,"losses":170,"wins":237},"GB2-02":{"draws":147,"losses":52,"wins":207},"GB2-03":{"draws":25,"losses":106,"wins":238},"GB2-04":{"draws":65,"losses":166,"wins":132},"GB2-05":{"draws":0,"losses":145,"wins":225},"GB2-06":{"draws":32,"losses":49,"wins":307},"GB2-07":{"draws":0,"losses":140,"wins":266},"GB2-08":{"draws":218,"losses":128,"wins":176}},"medium":{"GB2-01":{"draws":48,"losses":95,"wins":199},"GB2-02":{"draws":331,"losses":61,"wins":3},"GB2-03":{"draws":88,"losses":29,"wins":255},"GB2-04":{"draws":236,"losses":73,"wins":95},"GB2-05":{"draws":0,"losses":259,"wins":317},"GB2-06":{"draws":23,"losses":83,"wins":292},"GB2-07":{"draws":0,"losses":215,"wins":287},"GB2-08":{"draws":286,"losses":202,"wins":30}},"none":{"GB2-01":{"draws":174,"losses":105,"wins":159},"GB2-02":{"draws":328,"losses":78,"wins":2},"GB2-03":{"draws":95,"losses":152,"wins":174},"GB2-04":{"draws":210,"losses":96,"wins":54},"GB2-05":{"draws":0,"losses":195,"wins":209},"GB2-06":{"draws":20,"losses":110,"wins":262},"GB2-07":{"draws":0,"losses":230,"wins":190},"GB2-08":{"draws":28,"losses":113,"wins":301}}},"per_game_raw_elo_all":{"GB2-01":1614.8972741278037,"GB2-02":1482.4812466376418,"GB2-03":1668.2863215309324,"GB2-04":1488.6875506421848,"GB2-05":1613.1072626975717,"GB2-06":1970.2425696867642,"GB2-07":1557.5103316593713,"GB2-08":1524.3810454713464},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1556.33026491853,"GB2-02":1649.0850154369207,"GB2-03":1683.4782171573213,"GB2-04":1482.1403292785328,"GB2-05":1707.0383915097661,"GB2-06":2075.114443233505,"GB2-07":1729.1834243685823,"GB2-08":1496.4804665457418},"medium":{"GB2-01":1747.2024529560802,"GB2-02":1403.0298633793625,"GB2-03":1833.2325601275556,"GB2-04":1521.2496358371889,"GB2-05":1583.8718876418875,"GB2-06":1958.3857928848538,"GB2-07":1566.5619624173003,"GB2-08":1287.5608030865299},"none":{"GB2-01":1541.1591045088007,"GB2-02":1395.3288610966424,"GB2-03":1488.1481873079201,"GB2-04":1462.6726868108324,"GB2-05":1548.4115089410618,"GB2-06":1877.2274729419344,"GB2-07":1376.7856081922312,"GB2-08":1789.1018667817675}},"per_game_tracks":{"highest":{"GB2-01":46.89582654451502,"GB2-02":36.7967765243584,"GB2-03":47.86968632430597,"GB2-04":19.563185592281208,"GB2-05":55.96654820696413,"GB2-06":79.20614223860902,"GB2-07":59.031497180647904,"GB2-08":32.48744184199722},"medium":{"GB2-01":58.79465819169845,"GB2-02":6.5385506624544485,"GB2-03":60.55662292262157,"GB2-04":24.648599983694023,"GB2-05":49.975448307749915,"GB2-06":73.62311807031064,"GB2-07":50.596499872800585,"GB2-08":18.67179114447688},"none":{"GB2-01":45.95006757636053,"GB2-02":5.591532628143695,"GB2-03":31.321654024908753,"GB2-04":17.03179248195741,"GB2-05":48.250574542651364,"GB2-06":69.74139014536297,"GB2-07":40.753008012783404,"GB2-08":51.83820560133817}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.22713805670986,"medium":42.925661144475804,"none":38.80977812668829},"reasoning_agg":{"highest":{"max":79.20614223860902,"mean":47.22713805670986,"min":19.563185592281208},"medium":{"max":73.62311807031064,"mean":42.925661144475804,"min":6.5385506624544485},"none":{"max":69.74139014536297,"mean":38.80977812668829,"min":5.591532628143695}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":79.20614223860902,"expected_score":43.6442138177286,"reasoning_variance":8.417359930021568,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6566880417706145},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.20614223860902,"expected_score":40.748399261720614,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.478738794989248},"medium":{"ceiling_score":73.62311807031064,"expected_score":44.16417649971832,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2385153552425194},"none":{"ceiling_score":69.74139014536297,"expected_score":46.02006569174685,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.210287565058557}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:d6d96277e1b89a88","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"cost_is_complete":false,"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},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740125},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740125},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"cost_is_complete":false,"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}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":23,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.273243,"mean":0.0832670543478261,"median":0.04626,"min":0.0,"recorded_attempt_count":24,"run_count":23,"total":1.9151422500000002},"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":43.66284534036516,"highest":52.19725052854489,"medium":47.545167124088145,"none":28.094483248675697},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:44:57Z","match_totals_all":{"draws":2074,"losses":2906,"wins":4061},"match_totals_tracks":{"highest":{"draws":467,"losses":568,"wins":1330},"medium":{"draws":547,"losses":965,"wins":1826},"none":{"draws":1060,"losses":1373,"wins":905}},"model_slug":"meta-muse-spark-1-3","overall":{"max":79.37148930917198,"mean":42.612300300436246,"min":10.92923645097764},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":16,"overall_ranking_status":"partial","per_game":{"GB2-01":63.845700304263346,"GB2-02":13.675671493890567,"GB2-03":41.06833890609554,"GB2-06":79.37148930917198,"GB2-07":53.82135224083148,"GB2-08":61.40095091701645},"per_game_all":{"GB2-01":49.941090448075045,"GB2-02":15.789942080475697,"GB2-03":36.87416548930708,"GB2-06":66.8679521430182,"GB2-07":47.19005541652074,"GB2-08":45.31386646479424},"per_game_match_totals_all":{"GB2-01":{"draws":94,"losses":405,"wins":569},"GB2-02":{"draws":919,"losses":178,"wins":145},"GB2-03":{"draws":273,"losses":379,"wins":535},"GB2-04":{"draws":407,"losses":168,"wins":197},"GB2-05":{"draws":0,"losses":437,"wins":417},"GB2-06":{"draws":65,"losses":358,"wins":807},"GB2-07":{"draws":0,"losses":646,"wins":648},"GB2-08":{"draws":316,"losses":335,"wins":743}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":90,"wins":250},"GB2-02":{"draws":317,"losses":72,"wins":31},"GB2-03":{"draws":119,"losses":82,"wins":162},"GB2-06":{"draws":27,"losses":50,"wins":311},"GB2-07":{"draws":0,"losses":186,"wins":222},"GB2-08":{"draws":2,"losses":88,"wins":354}},"medium":{"GB2-01":{"draws":0,"losses":97,"wins":269},"GB2-02":{"draws":265,"losses":48,"wins":81},"GB2-03":{"draws":59,"losses":146,"wins":187},"GB2-04":{"draws":183,"losses":72,"wins":153},"GB2-05":{"draws":0,"losses":189,"wins":223},"GB2-06":{"draws":20,"losses":83,"wins":309},"GB2-07":{"draws":0,"losses":233,"wins":245},"GB2-08":{"draws":20,"losses":97,"wins":359}},"none":{"GB2-01":{"draws":92,"losses":218,"wins":50},"GB2-02":{"draws":337,"losses":58,"wins":33},"GB2-03":{"draws":95,"losses":151,"wins":186},"GB2-04":{"draws":224,"losses":96,"wins":44},"GB2-05":{"draws":0,"losses":248,"wins":194},"GB2-06":{"draws":18,"losses":225,"wins":187},"GB2-07":{"draws":0,"losses":227,"wins":181},"GB2-08":{"draws":294,"losses":150,"wins":30}}},"per_game_raw_elo_all":{"GB2-01":1605.1801185562074,"GB2-02":1478.260728946111,"GB2-03":1553.6890450037065,"GB2-06":1817.1502585571616,"GB2-07":1500.8878480911817,"GB2-08":1690.4410967215365},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1828.227505539565,"GB2-02":1461.0678117854254,"GB2-03":1603.1963219942581,"GB2-06":2078.5714836840034,"GB2-07":1628.73509508426,"GB2-08":1933.7092817228706},"medium":{"GB2-01":1768.8781018052618,"GB2-02":1524.9772331890913,"GB2-03":1557.780240189229,"GB2-04":1581.8840297148208,"GB2-05":1588.4520807237093,"GB2-06":2000.3983459653673,"GB2-07":1529.3343022819963,"GB2-08":1828.303688506664},"none":{"GB2-01":1218.4347483237952,"GB2-02":1448.737141863816,"GB2-03":1500.0905728276323,"GB2-04":1415.741067037629,"GB2-05":1352.2550278448623,"GB2-06":1372.4809460221143,"GB2-07":1344.5941469072889,"GB2-08":1309.3103199350753}},"per_game_tracks":{"highest":{"GB2-01":63.845700304263346,"GB2-02":13.675671493890567,"GB2-03":41.06833890609554,"GB2-06":79.37148930917198,"GB2-07":53.82135224083148,"GB2-08":61.40095091701645},"medium":{"GB2-01":60.14590217937223,"GB2-02":21.534827018028352,"GB2-03":37.220764679023915,"GB2-04":32.53293868393251,"GB2-05":50.19823935441566,"GB2-06":75.63253990907806,"GB2-07":48.6655418722335,"GB2-08":54.43058329662089},"none":{"GB2-01":25.831668860589573,"GB2-02":12.15932772950817,"GB2-03":32.33339288280181,"GB2-04":10.92923645097764,"GB2-05":38.70907553748118,"GB2-06":45.599827210804584,"GB2-07":39.08327213649725,"GB2-08":20.11006518074538}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.19725052854489,"medium":47.545167124088145,"none":28.094483248675697},"reasoning_agg":{"highest":{"max":79.37148930917198,"mean":52.19725052854489,"min":13.675671493890567},"medium":{"max":75.63253990907806,"mean":47.545167124088145,"min":21.534827018028352},"none":{"max":45.599827210804584,"mean":28.094483248675697,"min":10.92923645097764}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.37148930917198,"expected_score":43.21454745802521,"reasoning_variance":24.102767279869195,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6022471575889625},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.37148930917198,"expected_score":46.02826768569566,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.168982842849232},"medium":{"ceiling_score":75.63253990907806,"expected_score":49.51467660283457,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.9695094787464242},"none":{"ceiling_score":45.599827210804584,"expected_score":32.12773177965212,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.033248530976426}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:83fa232806adfb39","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.119209325},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.0298479}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847899999999997},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.11920932499999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.008139411458333334,"median":0.005035225,"min":0.001111625,"recorded_attempt_count":28,"run_count":24,"total":0.19534587500000003},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214245,"mean_ms":417506.625,"min_ms":32605,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1196482,"mean_ms":748510.375,"min_ms":448704,"run_count":8},"medium":{"attempt_count":8,"max_ms":672648,"mean_ms":296260.625,"min_ms":146516,"run_count":8},"none":{"attempt_count":11,"max_ms":1214245,"mean_ms":207748.875,"min_ms":32605,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":65809,"output_mean":27118.375,"output_min":2294,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":65809,"output_mean":50033.0,"output_min":27276,"run_count":8},"medium":{"attempt_count":8,"output_max":58608,"output_mean":20833.875,"output_min":10904,"run_count":8},"none":{"attempt_count":11,"output_max":54017,"output_mean":10488.25,"output_min":2294,"run_count":8}},"display_name":"GLM-5.3 Flash","economics":{"all":41.40110242512653,"highest":44.65666703147755,"medium":45.67536760777394,"none":33.87127263612811},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:18:34Z","match_totals_all":{"draws":2851,"losses":3677,"wins":4965},"match_totals_tracks":{"highest":{"draws":891,"losses":1397,"wins":2262},"medium":{"draws":872,"losses":979,"wins":1610},"none":{"draws":1088,"losses":1301,"wins":1093}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":74.79573413565146,"mean":41.40110242512653,"min":10.10478428685237},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.89390926530772,"GB2-02":32.57267948257629,"GB2-03":48.89562541051377,"GB2-04":56.04242124794769,"GB2-05":62.160751329168704,"GB2-06":28.818259420762246,"GB2-07":59.4912674607339,"GB2-08":16.37842263481004},"per_game_all":{"GB2-01":47.759967568094225,"GB2-02":18.76302671316461,"GB2-03":44.31034828091049,"GB2-04":45.97501236596836,"GB2-05":48.28891873078337,"GB2-06":49.964218560757786,"GB2-07":61.40132802617404,"GB2-08":14.74599915515938},"per_game_match_totals_all":{"GB2-01":{"draws":229,"losses":506,"wins":685},"GB2-02":{"draws":898,"losses":178,"wins":260},"GB2-03":{"draws":283,"losses":395,"wins":817},"GB2-04":{"draws":420,"losses":197,"wins":825},"GB2-05":{"draws":0,"losses":601,"wins":819},"GB2-06":{"draws":98,"losses":752,"wins":574},"GB2-07":{"draws":0,"losses":444,"wins":950},"GB2-08":{"draws":923,"losses":604,"wins":35}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":221,"wins":407},"GB2-02":{"draws":257,"losses":45,"wins":196},"GB2-03":{"draws":61,"losses":130,"wins":365},"GB2-04":{"draws":136,"losses":48,"wins":362},"GB2-05":{"draws":0,"losses":149,"wins":425},"GB2-06":{"draws":24,"losses":422,"wins":100},"GB2-07":{"draws":0,"losses":187,"wins":401},"GB2-08":{"draws":405,"losses":195,"wins":6}},"medium":{"GB2-01":{"draws":11,"losses":131,"wins":218},"GB2-02":{"draws":325,"losses":78,"wins":35},"GB2-03":{"draws":65,"losses":79,"wins":233},"GB2-04":{"draws":144,"losses":84,"wins":308},"GB2-05":{"draws":0,"losses":244,"wins":224},"GB2-06":{"draws":29,"losses":77,"wins":284},"GB2-07":{"draws":0,"losses":115,"wins":287},"GB2-08":{"draws":298,"losses":171,"wins":21}},"none":{"GB2-01":{"draws":210,"losses":154,"wins":60},"GB2-02":{"draws":316,"losses":55,"wins":29},"GB2-03":{"draws":157,"losses":186,"wins":219},"GB2-04":{"draws":140,"losses":65,"wins":155},"GB2-05":{"draws":0,"losses":208,"wins":170},"GB2-06":{"draws":45,"losses":253,"wins":190},"GB2-07":{"draws":0,"losses":142,"wins":262},"GB2-08":{"draws":220,"losses":238,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1570.1921710984207,"GB2-02":1502.4373873766137,"GB2-03":1641.4644239955885,"GB2-04":1685.2601048882605,"GB2-05":1549.1997981826569,"GB2-06":1463.7306874733747,"GB2-07":1774.8722779166644,"GB2-08":1228.1951489327018},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1652.5470370264811,"GB2-02":1614.735320095722,"GB2-03":1695.588219646254,"GB2-04":1762.6833687389928,"GB2-05":1834.3803413426342,"GB2-06":1021.6155906491177,"GB2-07":1738.0475072343556,"GB2-08":1252.8805851425755},"medium":{"GB2-01":1700.6701108404052,"GB2-02":1453.9167683159603,"GB2-03":1715.7081941110498,"GB2-04":1678.9471183865048,"GB2-05":1458.670189139184,"GB2-06":1982.9025935574357,"GB2-07":1835.048999520094,"GB2-08":1273.6939602518012},"none":{"GB2-01":1357.3593654283757,"GB2-02":1438.660073718159,"GB2-03":1513.0968582294618,"GB2-04":1614.1498275392835,"GB2-05":1354.5488640661524,"GB2-06":1386.6738782135703,"GB2-07":1751.5203269955432,"GB2-08":1158.0109014037293}},"per_game_tracks":{"highest":{"GB2-01":52.89390926530772,"GB2-02":32.57267948257629,"GB2-03":48.89562541051377,"GB2-04":56.04242124794769,"GB2-05":62.160751329168704,"GB2-06":28.818259420762246,"GB2-07":59.4912674607339,"GB2-08":16.37842263481004},"medium":{"GB2-01":55.89386624984344,"GB2-02":12.796283736154237,"GB2-03":50.60015587909144,"GB2-04":45.15412968525213,"GB2-05":43.88535189577719,"GB2-06":74.79573413565146,"GB2-07":64.52262873660591,"GB2-08":17.754790543815723},"none":{"GB2-01":34.4921271891315,"GB2-02":10.920116920763308,"GB2-03":33.435263553126255,"GB2-04":36.72848616470526,"GB2-05":38.82065296740423,"GB2-06":46.278662125859654,"GB2-07":60.19008788118231,"GB2-08":10.10478428685237}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.65666703147755,"medium":45.67536760777394,"none":33.87127263612811},"reasoning_agg":{"highest":{"max":62.160751329168704,"mean":44.65666703147755,"min":16.37842263481004},"medium":{"max":74.79573413565146,"mean":45.67536760777394,"min":12.796283736154237},"none":{"max":60.19008788118231,"mean":33.87127263612811,"min":10.10478428685237}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":74.79573413565146,"expected_score":41.273424952989,"reasoning_variance":11.804094971645831,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.12767747213753466},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.160751329168704,"expected_score":36.306188868785455,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.350478162692092},"medium":{"ceiling_score":74.79573413565146,"expected_score":47.36194907457691,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.68658146680297},"none":{"ceiling_score":60.19008788118231,"expected_score":40.15213691560462,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.280864279476511}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:3259f227c08b7b73","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087455999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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":40.95071314419968,"highest":45.40461004112328,"medium":43.83557892201466,"none":33.61195046946109},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:20:34Z","match_totals_all":{"draws":3094,"losses":4172,"wins":5818},"match_totals_tracks":{"highest":{"draws":791,"losses":1242,"wins":2302},"medium":{"draws":655,"losses":837,"wins":1478},"none":{"draws":1648,"losses":2093,"wins":2038}},"model_slug":"x-ai-grok-4-5","overall":{"max":72.9908214667701,"mean":40.950713144199675,"min":0.013056900223063989},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":69.12391879365194,"GB2-02":24.281523593010878,"GB2-03":22.84929230252855,"GB2-04":11.55846142526089,"GB2-05":61.545185110475025,"GB2-06":50.63899619802259,"GB2-07":50.24868143926623,"GB2-08":72.9908214667701},"per_game_all":{"GB2-01":59.77172781727719,"GB2-02":16.878365318530292,"GB2-03":17.606422157602847,"GB2-04":11.720694541269296,"GB2-05":53.37241797808182,"GB2-06":47.56707394672102,"GB2-07":53.531750854966766,"GB2-08":67.15725253914819},"per_game_match_totals_all":{"GB2-01":{"draws":557,"losses":282,"wins":775},"GB2-02":{"draws":1022,"losses":272,"wins":269},"GB2-03":{"draws":407,"losses":762,"wins":280},"GB2-04":{"draws":970,"losses":371,"wins":187},"GB2-05":{"draws":0,"losses":630,"wins":929},"GB2-06":{"draws":127,"losses":930,"wins":808},"GB2-07":{"draws":0,"losses":674,"wins":1060},"GB2-08":{"draws":11,"losses":251,"wins":1510}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":93,"losses":45,"wins":348},"GB2-02":{"draws":268,"losses":98,"wins":168},"GB2-03":{"draws":182,"losses":173,"wins":132},"GB2-04":{"draws":209,"losses":174,"wins":111},"GB2-05":{"draws":0,"losses":126,"wins":352},"GB2-06":{"draws":33,"losses":290,"wins":309},"GB2-07":{"draws":0,"losses":275,"wins":355},"GB2-08":{"draws":6,"losses":61,"wins":527}},"medium":{"GB2-01":{"draws":22,"losses":46,"wins":236},"GB2-02":{"draws":256,"losses":71,"wins":73},"GB2-03":{"draws":88,"losses":88,"wins":104},"GB2-04":{"draws":254,"losses":82,"wins":30},"GB2-05":{"draws":0,"losses":107,"wins":235},"GB2-06":{"draws":30,"losses":234,"wins":172},"GB2-07":{"draws":0,"losses":162,"wins":234},"GB2-08":{"draws":5,"losses":47,"wins":394}},"none":{"GB2-01":{"draws":442,"losses":191,"wins":191},"GB2-02":{"draws":498,"losses":103,"wins":28},"GB2-03":{"draws":137,"losses":501,"wins":44},"GB2-04":{"draws":507,"losses":115,"wins":46},"GB2-05":{"draws":0,"losses":397,"wins":342},"GB2-06":{"draws":64,"losses":406,"wins":327},"GB2-07":{"draws":0,"losses":237,"wins":471},"GB2-08":{"draws":0,"losses":143,"wins":589}}},"per_game_raw_elo_all":{"GB2-01":1762.8758755936203,"GB2-02":1487.1116161912778,"GB2-03":1326.2560298862848,"GB2-04":1421.8277641480574,"GB2-05":1653.7076248317944,"GB2-06":1413.611711260464,"GB2-07":1623.1517618556147,"GB2-08":2020.7558222004266},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1912.896752225506,"GB2-02":1547.312939403255,"GB2-03":1388.141936523183,"GB2-04":1420.5801126924255,"GB2-05":1821.7253797611033,"GB2-06":1477.8387909866321,"GB2-07":1559.8562409937333,"GB2-08":2108.9707954802325},"medium":{"GB2-01":1880.2405110883894,"GB2-02":1488.1688006039956,"GB2-03":1472.039077400545,"GB2-04":1420.9055388173779,"GB2-05":1731.45642155335,"GB2-06":1374.3762584568979,"GB2-07":1603.1944983821745,"GB2-08":2059.041537799767},"none":{"GB2-01":1495.4903634669656,"GB2-02":1425.8531085665827,"GB2-03":1118.5870757351263,"GB2-04":1423.9976409343694,"GB2-05":1407.9410731809298,"GB2-06":1388.6200843378622,"GB2-07":1706.404546190936,"GB2-08":1894.2551333212803}},"per_game_tracks":{"highest":{"GB2-01":69.12391879365194,"GB2-02":24.281523593010878,"GB2-03":22.84929230252855,"GB2-04":11.55846142526089,"GB2-05":61.545185110475025,"GB2-06":50.63899619802259,"GB2-07":50.24868143926623,"GB2-08":72.9908214667701},"medium":{"GB2-01":67.08815276867227,"GB2-02":17.00837082530471,"GB2-03":29.95691727005692,"GB2-04":11.600776844397576,"GB2-05":57.15429692710358,"GB2-06":45.69047826432287,"GB2-07":52.49658943377073,"GB2-08":69.68904904248862},"none":{"GB2-01":43.10311188950735,"GB2-02":9.345201537275292,"GB2-03":0.013056900223063989,"GB2-04":12.002845354149422,"GB2-05":41.41777189666686,"GB2-06":46.37174737781757,"GB2-07":57.84998169186335,"GB2-08":58.79188710818583}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.40461004112328,"medium":43.83557892201466,"none":33.61195046946109},"reasoning_agg":{"highest":{"max":72.9908214667701,"mean":45.40461004112328,"min":11.55846142526089},"medium":{"max":69.68904904248862,"mean":43.83557892201466,"min":11.600776844397576},"none":{"max":58.79188710818583,"mean":33.61195046946109,"min":0.013056900223063989}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":72.9908214667701,"expected_score":39.94336356581995,"reasoning_variance":11.792659571662185,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0073495783797242},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.9908214667701,"expected_score":37.94330756762727,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.461302473496005},"medium":{"ceiling_score":69.68904904248862,"expected_score":43.83342139631797,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.002157525696688367},"none":{"ceiling_score":58.79188710818583,"expected_score":38.05336173351462,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.441411264053528}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:3c0a842d719fc8b9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296143999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.06816269999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296143999999996}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.03177873833333334,"median":0.025158225,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":0.7626897200000001},"codegen_latency_ms":{"attempt_count":29,"max_ms":579647,"mean_ms":182597.75,"min_ms":15305,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":579647,"mean_ms":375199.125,"min_ms":217884,"run_count":8},"medium":{"attempt_count":11,"max_ms":196176,"mean_ms":145630.0,"min_ms":61522,"run_count":8},"none":{"attempt_count":10,"max_ms":51111,"mean_ms":26964.125,"min_ms":15305,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":74293,"output_mean":22693.125,"output_min":2253,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":74293,"output_mean":46016.5,"output_min":25493,"run_count":8},"medium":{"attempt_count":11,"output_max":25418,"output_mean":18052.125,"output_min":8262,"run_count":8},"none":{"attempt_count":10,"output_max":6651,"output_mean":4010.75,"output_min":2253,"run_count":8}},"display_name":"GLM-5.3 FlashX","economics":{"all":40.801103090384984,"highest":50.92201886531912,"medium":35.641960613324436,"none":35.83932979251139},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[131072],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[131072],"total_output_tokens":544635,"total_reasoning_output_tokens":454317,"total_visible_output_tokens":90318,"visible_token_observations":29},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":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":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":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-10-06T16:09:10Z","match_totals_all":{"draws":1429,"losses":1944,"wins":2453},"match_totals_tracks":{"highest":{"draws":373,"losses":472,"wins":1056},"medium":{"draws":467,"losses":751,"wins":670},"none":{"draws":589,"losses":721,"wins":727}},"model_slug":"z-ai-glm-5-3-flashx","overall":{"max":74.52122545933348,"mean":40.80110309038498,"min":7.210409700318507},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":36.62981082149744,"GB2-02":38.51339404279975,"GB2-03":60.62756945170218,"GB2-04":49.50982264658132,"GB2-05":62.787397606882564,"GB2-06":74.52122545933348,"GB2-07":63.96929772612333,"GB2-08":20.8176331676329},"per_game_all":{"GB2-01":50.72819584360543,"GB2-02":22.018623607105607,"GB2-03":37.88114625000874,"GB2-04":32.357795646581756,"GB2-05":48.943230931095606,"GB2-06":63.63462928628295,"GB2-07":56.44700025854559,"GB2-08":14.398202899854178},"per_game_match_totals_all":{"GB2-01":{"draws":53,"losses":205,"wins":336},"GB2-02":{"draws":534,"losses":111,"wins":169},"GB2-03":{"draws":64,"losses":246,"wins":298},"GB2-04":{"draws":349,"losses":92,"wins":204},"GB2-05":{"draws":0,"losses":323,"wins":365},"GB2-06":{"draws":36,"losses":277,"wins":582},"GB2-07":{"draws":0,"losses":270,"wins":454},"GB2-08":{"draws":393,"losses":420,"wins":45}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":122,"wins":79},"GB2-02":{"draws":118,"losses":27,"wins":127},"GB2-03":{"draws":4,"losses":38,"wins":162},"GB2-04":{"draws":78,"losses":16,"wins":119},"GB2-05":{"draws":0,"losses":57,"wins":167},"GB2-06":{"draws":17,"losses":43,"wins":196},"GB2-07":{"draws":0,"losses":66,"wins":174},"GB2-08":{"draws":155,"losses":103,"wins":32}},"medium":{"GB2-01":{"draws":5,"losses":42,"wins":151},"GB2-02":{"draws":205,"losses":32,"wins":37},"GB2-03":{"draws":18,"losses":105,"wins":81},"GB2-04":{"draws":127,"losses":39,"wins":52},"GB2-05":{"draws":0,"losses":146,"wins":82},"GB2-06":{"draws":9,"losses":102,"wins":133},"GB2-07":{"draws":0,"losses":109,"wins":131},"GB2-08":{"draws":103,"losses":176,"wins":3}},"none":{"GB2-01":{"draws":47,"losses":41,"wins":106},"GB2-02":{"draws":211,"losses":52,"wins":5},"GB2-03":{"draws":42,"losses":103,"wins":55},"GB2-04":{"draws":144,"losses":37,"wins":33},"GB2-05":{"draws":0,"losses":120,"wins":116},"GB2-06":{"draws":10,"losses":132,"wins":253},"GB2-07":{"draws":0,"losses":95,"wins":149},"GB2-08":{"draws":135,"losses":141,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1617.806276612373,"GB2-02":1528.9113912535338,"GB2-03":1565.575266790498,"GB2-04":1580.5370946939638,"GB2-05":1562.6513091750085,"GB2-06":1749.5486502117722,"GB2-07":1679.355943393591,"GB2-08":1222.9357892252526},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1391.6504928550191,"GB2-02":1663.0442801490183,"GB2-03":1834.0700003375032,"GB2-04":1712.4445127360493,"GB2-05":1847.2630895001068,"GB2-06":1977.163226087465,"GB2-07":1824.381124406021,"GB2-08":1320.0101319766163},"medium":{"GB2-01":1790.5386534514646,"GB2-02":1498.9243358209733,"GB2-03":1464.799441344787,"GB2-04":1527.4008093927364,"GB2-05":1347.276515337824,"GB2-06":1566.5364368075113,"GB2-07":1554.2480990549018,"GB2-08":1114.242295944409},"none":{"GB2-01":1671.2296835306356,"GB2-02":1424.7655577906098,"GB2-03":1397.856358689204,"GB2-04":1501.7659619531055,"GB2-05":1493.414322687095,"GB2-06":1704.9462877403398,"GB2-07":1659.43860671985,"GB2-08":1234.5549397547318}},"per_game_tracks":{"highest":{"GB2-01":36.62981082149744,"GB2-02":38.51339404279975,"GB2-03":60.62756945170218,"GB2-04":49.50982264658132,"GB2-05":62.787397606882564,"GB2-06":74.52122545933348,"GB2-07":63.96929772612333,"GB2-08":20.8176331676329},"medium":{"GB2-01":61.49620501852963,"GB2-02":18.331015001374816,"GB2-03":29.34358745395578,"GB2-04":25.448441997679716,"GB2-05":38.46690932473272,"GB2-06":54.881323157257064,"GB2-07":49.95779325274727,"GB2-08":7.210409700318507},"none":{"GB2-01":54.05857169078922,"GB2-02":9.211461777142253,"GB2-03":23.67228184436826,"GB2-04":22.115122295484237,"GB2-05":45.57538586167155,"GB2-06":61.50133924225831,"GB2-07":55.41390979676618,"GB2-08":15.166565831611129}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.92201886531912,"medium":35.641960613324436,"none":35.83932979251139},"reasoning_agg":{"highest":{"max":74.52122545933348,"mean":50.92201886531912,"min":20.8176331676329},"medium":{"max":61.49620501852963,"mean":35.641960613324436,"min":7.210409700318507},"none":{"max":61.50133924225831,"mean":35.83932979251139,"min":9.211461777142253}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":74.52122545933348,"expected_score":40.65484662155102,"reasoning_variance":15.280058251994681,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.14625646883395405},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.52122545933348,"expected_score":44.64726199507782,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.274756870241298},"medium":{"ceiling_score":61.49620501852963,"expected_score":35.07344134410732,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.5685192692171128},"none":{"ceiling_score":61.50133924225831,"expected_score":42.24383652546792,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.404506732956527}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:481b51e2fa6718e7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449890000000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":10.45624},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":42.50189977133916,"highest":55.93504406846419,"medium":33.83212828671788,"none":34.91063624036109},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:33:29Z","match_totals_all":{"draws":2130,"losses":2449,"wins":3698},"match_totals_tracks":{"highest":{"draws":370,"losses":485,"wins":1691},"medium":{"draws":1096,"losses":1025,"wins":1032},"none":{"draws":664,"losses":939,"wins":975}},"model_slug":"claude-opus-4-8","overall":{"max":78.62115362838988,"mean":40.56506076979832,"min":6.277183328723728},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":56.232388720199246,"GB2-02":51.21388843753328,"GB2-04":36.38885043713729,"GB2-05":43.79994235368087,"GB2-06":78.62115362838988,"GB2-07":65.23626733566016,"GB2-08":60.052817566648564},"per_game_all":{"GB2-01":47.26853982548769,"GB2-02":21.995161336296146,"GB2-04":18.989392538946323,"GB2-05":38.82598627625223,"GB2-06":67.81209751558077,"GB2-07":57.08817428779967,"GB2-08":45.533946619011324},"per_game_match_totals_all":{"GB2-01":{"draws":181,"losses":299,"wins":480},"GB2-02":{"draws":792,"losses":162,"wins":244},"GB2-03":{"draws":175,"losses":233,"wins":64},"GB2-04":{"draws":672,"losses":186,"wins":199},"GB2-05":{"draws":0,"losses":595,"wins":463},"GB2-06":{"draws":50,"losses":278,"wins":766},"GB2-07":{"draws":0,"losses":361,"wins":785},"GB2-08":{"draws":260,"losses":335,"wins":697}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":44,"losses":73,"wins":221},"GB2-02":{"draws":156,"losses":8,"wins":228},"GB2-04":{"draws":154,"losses":37,"wins":153},"GB2-05":{"draws":0,"losses":162,"wins":172},"GB2-06":{"draws":15,"losses":37,"wins":286},"GB2-07":{"draws":0,"losses":85,"wins":289},"GB2-08":{"draws":1,"losses":83,"wins":342}},"medium":{"GB2-01":{"draws":61,"losses":131,"wins":128},"GB2-02":{"draws":336,"losses":66,"wins":4},"GB2-03":{"draws":175,"losses":233,"wins":64},"GB2-04":{"draws":264,"losses":77,"wins":24},"GB2-05":{"draws":0,"losses":182,"wins":188},"GB2-06":{"draws":3,"losses":60,"wins":313},"GB2-07":{"draws":0,"losses":110,"wins":286},"GB2-08":{"draws":257,"losses":166,"wins":25}},"none":{"GB2-01":{"draws":76,"losses":95,"wins":131},"GB2-02":{"draws":300,"losses":88,"wins":12},"GB2-04":{"draws":254,"losses":72,"wins":22},"GB2-05":{"draws":0,"losses":251,"wins":103},"GB2-06":{"draws":32,"losses":181,"wins":167},"GB2-07":{"draws":0,"losses":166,"wins":210},"GB2-08":{"draws":2,"losses":86,"wins":330}}},"per_game_raw_elo_all":{"GB2-01":1562.3090535558788,"GB2-02":1528.7205997432193,"GB2-04":1477.727582018055,"GB2-05":1354.6585075399562,"GB2-06":1836.8902438679797,"GB2-07":1691.7173768590749,"GB2-08":1693.7691391539745},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1706.100435979259,"GB2-02":1766.322710740576,"GB2-04":1611.5378638396965,"GB2-05":1456.9143187858388,"GB2-06":2062.8836290937506,"GB2-07":1848.8075044783704,"GB2-08":1913.3228683701104},"medium":{"GB2-01":1425.476120854617,"GB2-02":1418.9346233183744,"GB2-03":1284.1219456634253,"GB2-04":1414.27203383782,"GB2-05":1477.8855953405111,"GB2-06":2024.370021062026,"GB2-07":1731.0149687147498,"GB2-08":1276.2438877129366},"none":{"GB2-01":1555.3506038337612,"GB2-02":1400.9044651707068,"GB2-04":1407.3728483766488,"GB2-05":1129.175608493519,"GB2-06":1423.4170814481622,"GB2-07":1495.3296573841044,"GB2-08":1891.740661378876}},"per_game_tracks":{"highest":{"GB2-01":56.232388720199246,"GB2-02":51.21388843753328,"GB2-04":36.38885043713729,"GB2-05":43.79994235368087,"GB2-06":78.62115362838988,"GB2-07":65.23626733566016,"GB2-08":60.052817566648564},"medium":{"GB2-01":38.73847556236733,"GB2-02":8.494412242631434,"GB2-03":14.03689325739755,"GB2-04":10.738216889826191,"GB2-05":44.82003311624621,"GB2-06":76.7790831186457,"GB2-07":59.126497381997424,"GB2-08":17.923414724631236},"none":{"GB2-01":46.83475519389652,"GB2-02":6.277183328723728,"GB2-04":9.84111028987549,"GB2-05":27.857983358829618,"GB2-06":48.036055799706716,"GB2-07":46.90175814574142,"GB2-08":58.62560756575418}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.098596455453674,"medium":33.83212828671788,"none":33.764457567223424},"reasoning_agg":{"highest":{"max":78.62115362838988,"mean":54.098596455453674,"min":36.38885043713729},"medium":{"max":76.7790831186457,"mean":33.83212828671788,"min":8.494412242631434},"none":{"max":58.62560756575418,"mean":33.764457567223424,"min":6.277183328723728}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":78.62115362838988,"expected_score":42.481180483141884,"reasoning_variance":20.33413888823025,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.9161197133435621},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.62115362838988,"expected_score":50.63977128878026,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.4588251666734138},"medium":{"ceiling_score":76.7790831186457,"expected_score":34.23484946529096,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.4027211785730742},"none":{"ceiling_score":58.62560756575418,"expected_score":39.1211103993265,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.356652832103073}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:0c7fb41d0ab3585a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.9693815250000001},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.12751812499999998},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.1835153939999996},"codegen_latency_ms":{"attempt_count":28,"max_ms":1122981,"mean_ms":579882.5416666666,"min_ms":29109,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":995043,"mean_ms":822481.25,"min_ms":674828,"run_count":8},"medium":{"attempt_count":10,"max_ms":1122981,"mean_ms":860540.0,"min_ms":640692,"run_count":8},"none":{"attempt_count":9,"max_ms":99413,"mean_ms":56626.375,"min_ms":29109,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":69581,"output_mean":33844.916666666664,"output_min":1323,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":57331,"output_mean":47325.375,"output_min":39792,"run_count":8},"medium":{"attempt_count":10,"output_max":69581,"output_mean":50814.0,"output_min":36329,"run_count":8},"none":{"attempt_count":9,"output_max":6014,"output_mean":3395.375,"output_min":1323,"run_count":8}},"display_name":"Hy4 Preview","economics":{"all":41.77291234048598,"highest":47.765316332602296,"medium":44.543995815580026,"none":30.164706358882707},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:26:26Z","match_totals_all":{"draws":2588,"losses":3215,"wins":4124},"match_totals_tracks":{"highest":{"draws":909,"losses":812,"wins":1543},"medium":{"draws":563,"losses":1083,"wins":1619},"none":{"draws":1116,"losses":1320,"wins":962}},"model_slug":"tencent-hy4-preview","overall":{"max":74.90458726523926,"mean":40.33718646554952,"min":3.5099378505398553},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.90012382581649,"GB2-02":49.233072445439106,"GB2-03":45.30646103455824,"GB2-04":29.68908449107652,"GB2-05":58.516111009912024,"GB2-06":74.90458726523926,"GB2-07":59.74723272470667,"GB2-08":19.82585786407004},"per_game_all":{"GB2-01":43.01468467716338,"GB2-03":34.11259630541013,"GB2-04":14.187356912556837,"GB2-05":50.51164529647426,"GB2-06":58.76649728096339,"GB2-07":54.33194404367262,"GB2-08":37.48566186716129},"per_game_match_totals_all":{"GB2-01":{"draws":297,"losses":521,"wins":442},"GB2-02":{"draws":469,"losses":83,"wins":284},"GB2-03":{"draws":481,"losses":367,"wins":427},"GB2-04":{"draws":646,"losses":277,"wins":169},"GB2-05":{"draws":0,"losses":571,"wins":731},"GB2-06":{"draws":54,"losses":500,"wins":748},"GB2-07":{"draws":0,"losses":509,"wins":881},"GB2-08":{"draws":641,"losses":387,"wins":442}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":211,"losses":102,"wins":105},"GB2-02":{"draws":119,"losses":32,"wins":277},"GB2-03":{"draws":36,"losses":102,"wins":220},"GB2-04":{"draws":184,"losses":74,"wins":118},"GB2-05":{"draws":0,"losses":129,"wins":247},"GB2-06":{"draws":21,"losses":73,"wins":290},"GB2-07":{"draws":0,"losses":137,"wins":265},"GB2-08":{"draws":338,"losses":163,"wins":21}},"medium":{"GB2-01":{"draws":22,"losses":200,"wins":184},"GB2-03":{"draws":320,"losses":165,"wins":64},"GB2-04":{"draws":207,"losses":122,"wins":25},"GB2-05":{"draws":0,"losses":195,"wins":245},"GB2-06":{"draws":14,"losses":215,"wins":275},"GB2-07":{"draws":0,"losses":133,"wins":433},"GB2-08":{"draws":0,"losses":53,"wins":393}},"none":{"GB2-01":{"draws":64,"losses":219,"wins":153},"GB2-02":{"draws":350,"losses":51,"wins":7},"GB2-03":{"draws":125,"losses":100,"wins":143},"GB2-04":{"draws":255,"losses":81,"wins":26},"GB2-05":{"draws":0,"losses":247,"wins":239},"GB2-06":{"draws":19,"losses":212,"wins":183},"GB2-07":{"draws":0,"losses":239,"wins":183},"GB2-08":{"draws":303,"losses":171,"wins":28}}},"per_game_raw_elo_all":{"GB2-01":1494.0718800391285,"GB2-03":1521.0919735596635,"GB2-04":1440.797595794085,"GB2-05":1594.8951570910122,"GB2-06":1647.7668091216556,"GB2-07":1638.578985059319,"GB2-08":1572.0633303872394},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1524.316689478067,"GB2-02":1750.2150254335397,"GB2-03":1653.2223617602176,"GB2-04":1560.0134097660648,"GB2-05":1759.4529300942204,"GB2-06":1985.1784710245547,"GB2-07":1742.9823571124077,"GB2-08":1305.0125493665769},"medium":{"GB2-01":1504.108104012084,"GB2-03":1359.8350556958112,"GB2-04":1358.6830573885634,"GB2-05":1524.1058970786187,"GB2-06":1621.994657051308,"GB2-07":1861.0157432503277,"GB2-08":2120.222539477485},"none":{"GB2-01":1453.790846627234,"GB2-02":1421.2888602906446,"GB2-03":1550.2185032229622,"GB2-04":1403.6963202276268,"GB2-05":1501.1266441001976,"GB2-06":1336.1272992891043,"GB2-07":1311.7388548152212,"GB2-08":1290.9549023176564}},"per_game_tracks":{"highest":{"GB2-01":44.90012382581649,"GB2-02":49.233072445439106,"GB2-03":45.30646103455824,"GB2-04":29.68908449107652,"GB2-05":58.516111009912024,"GB2-06":74.90458726523926,"GB2-07":59.74723272470667,"GB2-08":19.82585786407004},"medium":{"GB2-01":43.64033548913045,"GB2-03":20.4511808672941,"GB2-04":3.5099378505398553,"GB2-05":47.06829409945857,"GB2-06":57.53383891090562,"GB2-07":65.86949532377076,"GB2-08":73.73488816796079},"none":{"GB2-01":40.50359471654319,"GB2-02":8.783920645295293,"GB2-03":36.580147014378056,"GB2-04":9.363048396054136,"GB2-05":45.95053078005221,"GB2-06":43.861065666745304,"GB2-07":37.37910408254044,"GB2-08":18.89623956945303}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.765316332602296,"medium":43.08153670516356,"none":30.164706358882707},"reasoning_agg":{"highest":{"max":74.90458726523926,"mean":47.765316332602296,"min":19.82585786407004},"medium":{"max":73.73488816796079,"mean":43.08153670516356,"min":3.5099378505398553},"none":{"max":45.95053078005221,"mean":30.164706358882707,"min":8.783920645295293}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":74.90458726523926,"expected_score":41.034013668810175,"reasoning_variance":17.60060997371959,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6968272032606535},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.90458726523926,"expected_score":41.05862304591508,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.706693286687219},"medium":{"ceiling_score":73.73488816796079,"expected_score":44.844470822107255,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.762934116943697},"none":{"ceiling_score":45.95053078005221,"expected_score":34.67717361347613,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.512467254593421}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:5138402c7ccae6e3","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.606316,"mean":0.33312575,"median":0.357252,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":9,"run_count":8,"total":2.665006},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.278232,"mean":0.1058585,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.8468679999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.969774}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.278232,"mean":0.1058585,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.8468680000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.969774},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.606316,"mean":0.33312575,"median":0.357252,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":9,"run_count":8,"total":2.665006}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.606316,"mean":0.18673533333333334,"median":0.11641699999999999,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":29,"run_count":24,"total":4.481648000000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":2404956,"mean_ms":688441.3478260869,"min_ms":135091,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":2404956,"mean_ms":1516855.142857143,"min_ms":951741,"run_count":7},"medium":{"attempt_count":10,"max_ms":878124,"mean_ms":297986.875,"min_ms":135091,"run_count":8},"none":{"attempt_count":10,"max_ms":640944,"mean_ms":354033.75,"min_ms":208254,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":94258,"output_mean":28537.75,"output_min":6298,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":94258,"output_mean":54376.5,"output_min":13896,"run_count":8},"medium":{"attempt_count":10,"output_max":40870,"output_mean":14338.625,"output_min":6298,"run_count":8},"none":{"attempt_count":10,"output_max":30162,"output_mean":16898.125,"output_min":10952,"run_count":8}},"display_name":"Qwen3.8 Max 0902","economics":{"all":39.42658825621675,"highest":54.343762540421785,"medium":31.856266251386053,"none":33.64605133113003},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":30,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[131072],"total_output_tokens":684906,"total_reasoning_output_tokens":570415,"total_visible_output_tokens":114491,"visible_token_observations":29},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":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":7,"first_pass_admitted":6,"first_pass_rate":0.8571428571428571,"infra_excluded_game_aliases":["GB2-07"],"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},"repaired_admitted":1,"repaired_rate":0.14285714285714285}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-10-06T14:38:28Z","match_totals_all":{"draws":1561,"losses":1747,"wins":2127},"match_totals_tracks":{"highest":{"draws":411,"losses":262,"wins":973},"medium":{"draws":533,"losses":800,"wins":580},"none":{"draws":617,"losses":685,"wins":574}},"model_slug":"qwen-qwen3-8-max-0902","overall":{"max":80.95166940629719,"mean":39.948693374312626,"min":4.915404231320315},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":22,"overall_ranking_status":"partial","per_game":{"GB2-01":55.93778214844374,"GB2-02":26.407261308973975,"GB2-03":43.30383380437477,"GB2-04":62.59306650239925,"GB2-05":80.95166940629719,"GB2-06":77.31380729125954,"GB2-08":33.89891732120405},"per_game_all":{"GB2-01":40.71270146797515,"GB2-02":17.19379651240175,"GB2-03":36.52278253817622,"GB2-04":27.55023490302977,"GB2-05":58.04538160117809,"GB2-06":69.46816473989986,"GB2-08":26.49305603085642},"per_game_match_totals_all":{"GB2-01":{"draws":177,"losses":237,"wins":172},"GB2-02":{"draws":556,"losses":140,"wins":118},"GB2-03":{"draws":79,"losses":223,"wins":306},"GB2-04":{"draws":287,"losses":159,"wins":201},"GB2-05":{"draws":0,"losses":236,"wins":446},"GB2-06":{"draws":46,"losses":175,"wins":533},"GB2-07":{"draws":0,"losses":319,"wins":169},"GB2-08":{"draws":416,"losses":258,"wins":182}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":72,"losses":24,"wins":98},"GB2-02":{"draws":162,"losses":37,"wins":75},"GB2-03":{"draws":13,"losses":64,"wins":129},"GB2-04":{"draws":29,"losses":23,"wins":164},"GB2-05":{"draws":0,"losses":17,"wins":205},"GB2-06":{"draws":19,"losses":31,"wins":198},"GB2-08":{"draws":116,"losses":66,"wins":104}},"medium":{"GB2-01":{"draws":33,"losses":131,"wins":44},"GB2-02":{"draws":195,"losses":44,"wins":33},"GB2-03":{"draws":37,"losses":79,"wins":92},"GB2-04":{"draws":136,"losses":52,"wins":25},"GB2-05":{"draws":0,"losses":135,"wins":99},"GB2-06":{"draws":9,"losses":95,"wins":148},"GB2-07":{"draws":0,"losses":159,"wins":83},"GB2-08":{"draws":123,"losses":105,"wins":56}},"none":{"GB2-01":{"draws":72,"losses":82,"wins":30},"GB2-02":{"draws":199,"losses":59,"wins":10},"GB2-03":{"draws":29,"losses":80,"wins":85},"GB2-04":{"draws":122,"losses":84,"wins":12},"GB2-05":{"draws":0,"losses":84,"wins":142},"GB2-06":{"draws":18,"losses":49,"wins":187},"GB2-07":{"draws":0,"losses":160,"wins":86},"GB2-08":{"draws":177,"losses":87,"wins":22}}},"per_game_raw_elo_all":{"GB2-01":1457.1451812680382,"GB2-02":1489.6766532402428,"GB2-03":1549.5413831493443,"GB2-04":1543.5646176355701,"GB2-05":1749.7755592413062,"GB2-06":1871.5149358188157,"GB2-08":1405.8336274118467},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1701.3745769513664,"GB2-02":1564.599105463451,"GB2-03":1629.5837061441532,"GB2-04":1813.0610122690764,"GB2-05":2220.6886524978527,"GB2-06":2035.5499173147473,"GB2-08":1517.8247367906279},"medium":{"GB2-01":1288.3021701928324,"GB2-02":1483.3377276074866,"GB2-03":1512.543924464903,"GB2-04":1448.1410641726775,"GB2-05":1379.7353523532206,"GB2-06":1654.0268790161656,"GB2-07":1300.5292998403352,"GB2-08":1365.2405708391402},"none":{"GB2-01":1381.7587966599153,"GB2-02":1421.0931266497912,"GB2-03":1506.4965188389767,"GB2-04":1369.4917764649565,"GB2-05":1648.9026728728452,"GB2-06":1924.968011125535,"GB2-07":1355.883688984648,"GB2-08":1334.4355746057722}},"per_game_tracks":{"highest":{"GB2-01":55.93778214844374,"GB2-02":26.407261308973975,"GB2-03":43.30383380437477,"GB2-04":62.59306650239925,"GB2-05":80.95166940629719,"GB2-06":77.31380729125954,"GB2-08":33.89891732120405},"medium":{"GB2-01":30.187152490707888,"GB2-02":16.41427760408446,"GB2-03":33.38841993260155,"GB2-04":15.14223397536975,"GB2-05":40.04578125065955,"GB2-06":59.06591067614868,"GB2-07":36.7976767303275,"GB2-08":23.808677351189026},"none":{"GB2-01":36.01316976477382,"GB2-02":8.759850624146823,"GB2-03":32.87609387755235,"GB2-04":4.915404231320315,"GB2-05":53.13869414657753,"GB2-06":72.02477625229137,"GB2-07":39.668848332201854,"GB2-08":21.77157342017618}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.343762540421785,"medium":31.856266251386053,"none":33.64605133113003},"reasoning_agg":{"highest":{"max":80.95166940629719,"mean":54.343762540421785,"min":26.407261308973975},"medium":{"max":59.06591067614868,"mean":31.856266251386053,"min":15.14223397536975},"none":{"max":72.02477625229137,"mean":33.64605133113003,"min":4.915404231320315}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":80.95166940629719,"expected_score":39.21492481840727,"reasoning_variance":22.487496289035732,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7337685559053568},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.95166940629719,"expected_score":48.798909872858125,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.54485266756366},"medium":{"ceiling_score":59.06591067614868,"expected_score":31.061016934701406,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7952493166846466},"none":{"ceiling_score":72.02477625229137,"expected_score":39.07678017043366,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.430728839303626}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:f743bfa9de04848a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"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":1.1978497759330724}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"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":1.1978497759330728},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":false,"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":5.470887999999998},"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":38.469477003355266,"highest":49.868761261115445,"medium":29.247198243392603,"none":36.29247150555775},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:47:17Z","match_totals_all":{"draws":2906,"losses":3295,"wins":3813},"match_totals_tracks":{"highest":{"draws":765,"losses":725,"wins":1700},"medium":{"draws":1270,"losses":1378,"wins":861},"none":{"draws":871,"losses":1192,"wins":1252}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":75.46700154910128,"mean":38.46947700335527,"min":6.633190742862919},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.85285344729716,"GB2-02":20.85075465558389,"GB2-03":45.99944615095677,"GB2-04":19.151110739407567,"GB2-05":58.02466382074558,"GB2-06":75.46700154910128,"GB2-07":58.89163419521483,"GB2-08":74.71262553061648},"per_game_all":{"GB2-01":40.513531173778624,"GB2-02":14.822361067180845,"GB2-03":33.202303717460104,"GB2-04":14.025639399051892,"GB2-05":46.93820454428137,"GB2-06":60.750499981677855,"GB2-07":45.298197986408496,"GB2-08":52.20507815700294},"per_game_match_totals_all":{"GB2-01":{"draws":440,"losses":428,"wins":282},"GB2-02":{"draws":951,"losses":206,"wins":133},"GB2-03":{"draws":358,"losses":413,"wins":447},"GB2-04":{"draws":741,"losses":267,"wins":138},"GB2-05":{"draws":0,"losses":577,"wins":637},"GB2-06":{"draws":112,"losses":469,"wins":729},"GB2-07":{"draws":0,"losses":629,"wins":647},"GB2-08":{"draws":304,"losses":306,"wins":800}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":125,"losses":139,"wins":154},"GB2-02":{"draws":285,"losses":45,"wins":74},"GB2-03":{"draws":105,"losses":76,"wins":195},"GB2-04":{"draws":208,"losses":87,"wins":65},"GB2-05":{"draws":0,"losses":123,"wins":249},"GB2-06":{"draws":40,"losses":67,"wins":293},"GB2-07":{"draws":0,"losses":146,"wins":272},"GB2-08":{"draws":2,"losses":42,"wins":398}},"medium":{"GB2-01":{"draws":173,"losses":124,"wins":73},"GB2-02":{"draws":337,"losses":87,"wins":14},"GB2-03":{"draws":193,"losses":153,"wins":99},"GB2-04":{"draws":229,"losses":97,"wins":28},"GB2-05":{"draws":0,"losses":239,"wins":245},"GB2-06":{"draws":40,"losses":241,"wins":181},"GB2-07":{"draws":0,"losses":260,"wins":172},"GB2-08":{"draws":298,"losses":177,"wins":49}},"none":{"GB2-01":{"draws":142,"losses":165,"wins":55},"GB2-02":{"draws":329,"losses":74,"wins":45},"GB2-03":{"draws":60,"losses":184,"wins":153},"GB2-04":{"draws":304,"losses":83,"wins":45},"GB2-05":{"draws":0,"losses":215,"wins":143},"GB2-06":{"draws":32,"losses":161,"wins":255},"GB2-07":{"draws":0,"losses":223,"wins":203},"GB2-08":{"draws":4,"losses":87,"wins":353}}},"per_game_raw_elo_all":{"GB2-01":1453.9502398676887,"GB2-02":1470.3925117399588,"GB2-03":1510.347041766024,"GB2-04":1439.5539095721226,"GB2-05":1521.431484037533,"GB2-06":1689.2479044136116,"GB2-07":1464.4140224502382,"GB2-08":1794.6496974659685},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1539.5996679126133,"GB2-02":1519.4144639134622,"GB2-03":1661.4022348123294,"GB2-04":1478.9712735230448,"GB2-05":1749.349638020378,"GB2-06":1996.93730607757,"GB2-07":1726.486953660425,"GB2-08":2135.0078409612715},"medium":{"GB2-01":1514.4431499645161,"GB2-02":1425.1781219457002,"GB2-03":1413.495869798518,"GB2-04":1382.702389034836,"GB2-05":1508.5226559553782,"GB2-06":1372.6871135456202,"GB2-07":1277.1643891761332,"GB2-08":1327.2229144752569},"none":{"GB2-01":1307.8079017259365,"GB2-02":1466.5849493607138,"GB2-03":1456.1430206872249,"GB2-04":1456.9880661584875,"GB2-05":1306.4221581368433,"GB2-06":1698.1192936176449,"GB2-07":1389.5907245141573,"GB2-08":1921.718336961377}},"per_game_tracks":{"highest":{"GB2-01":45.85285344729716,"GB2-02":20.85075465558389,"GB2-03":45.99944615095677,"GB2-04":19.151110739407567,"GB2-05":58.02466382074558,"GB2-06":75.46700154910128,"GB2-07":58.89163419521483,"GB2-08":74.71262553061648},"medium":{"GB2-01":44.2846146432506,"GB2-02":9.262196172593283,"GB2-03":24.99723497719298,"GB2-04":6.633190742862919,"GB2-05":46.31028967949854,"GB2-06":45.60968801415503,"GB2-07":35.585764377641375,"GB2-08":21.29460733994608},"none":{"GB2-01":31.4031254307881,"GB2-02":14.354132373365356,"GB2-03":28.610230024230557,"GB2-04":16.292616714885195,"GB2-05":36.479660132599975,"GB2-06":61.174810381777256,"GB2-07":41.417195386369286,"GB2-08":60.60800160044626}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.868761261115445,"medium":29.247198243392603,"none":36.29247150555775},"reasoning_agg":{"highest":{"max":75.46700154910128,"mean":49.868761261115445,"min":19.151110739407567},"medium":{"max":46.31028967949854,"mean":29.247198243392603,"min":6.633190742862919},"none":{"max":61.174810381777256,"mean":36.29247150555775,"min":14.354132373365356}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":75.46700154910128,"expected_score":38.13135692224871,"reasoning_variance":20.621563017722842,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.33812008110655967},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.46700154910128,"expected_score":43.703834021765815,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.16492723934963},"medium":{"ceiling_score":46.31028967949854,"expected_score":27.453872075929304,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.7933261674632988},"none":{"ceiling_score":61.174810381777256,"expected_score":43.236364669051035,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.943893163493286}}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:db7e5a1adfc6a9b7","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0},"medium":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"none":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":79,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":112,"run_count":88,"total":0.0},"codegen_latency_ms":{"attempt_count":112,"max_ms":1487583,"mean_ms":467860.5227272727,"min_ms":38538,"run_count":88},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":31,"max_ms":1487583,"mean_ms":1029047.25,"min_ms":343277,"run_count":28},"medium":{"attempt_count":39,"max_ms":676327,"mean_ms":324151.5,"min_ms":151453,"run_count":30},"none":{"attempt_count":42,"max_ms":287181,"mean_ms":87795.26666666666,"min_ms":38538,"run_count":30}},"codegen_output_tokens":{"attempt_count":112,"output_max":85105,"output_mean":23027.329545454544,"output_min":1660,"run_count":88},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":31,"output_max":85105,"output_mean":50628.67857142857,"output_min":15800,"run_count":28},"medium":{"attempt_count":39,"output_max":33467,"output_mean":16156.733333333334,"output_min":6647,"run_count":30},"none":{"attempt_count":42,"output_max":9871,"output_mean":4136.666666666667,"output_min":1660,"run_count":30}},"display_name":"Ox Alpha","economics":{"all":39.04932980787181,"highest":52.15472039582533,"medium":35.103516530720185,"none":29.889752497069917},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:43:03Z","match_totals_all":{"draws":8088,"losses":11521,"wins":13126},"match_totals_tracks":{"highest":{"draws":1324,"losses":2823,"wins":5760},"medium":{"draws":2618,"losses":4158,"wins":4174},"none":{"draws":4146,"losses":4540,"wins":3192}},"model_slug":"stealth-ox-alpha","overall":{"max":65.860076268154,"mean":38.467742601694546,"min":9.299675382017327},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.08647084554764,"GB2-02":43.13631723036697,"GB2-03":50.938830058497615,"GB2-04":49.44408295059182,"GB2-05":53.163619805036575,"GB2-06":65.860076268154,"GB2-07":56.97038901065603,"GB2-08":48.63797699775197},"per_game_all":{"GB2-01":46.56016257169326,"GB2-02":22.39176287517668,"GB2-03":36.641823046939855,"GB2-04":31.76321688597498,"GB2-05":48.37353061799937,"GB2-06":47.08737336070297,"GB2-07":45.881048299893536,"GB2-08":33.695720804593826},"per_game_match_totals_all":{"GB2-01":{"draws":526,"losses":1216,"wins":1456},"GB2-02":{"draws":2268,"losses":452,"wins":614},"GB2-03":{"draws":2073,"losses":2504,"wins":2951},"GB2-04":{"draws":1774,"losses":637,"wins":1064},"GB2-05":{"draws":0,"losses":1733,"wins":2009},"GB2-06":{"draws":204,"losses":1831,"wins":1629},"GB2-07":{"draws":0,"losses":2097,"wins":2025},"GB2-08":{"draws":1243,"losses":1051,"wins":1378}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":70,"losses":491,"wins":605},"GB2-02":{"draws":300,"losses":68,"wins":430},"GB2-03":{"draws":250,"losses":392,"wins":971},"GB2-04":{"draws":403,"losses":141,"wins":574},"GB2-05":{"draws":0,"losses":498,"wins":718},"GB2-06":{"draws":126,"losses":403,"wins":805},"GB2-07":{"draws":0,"losses":472,"wins":846},"GB2-08":{"draws":175,"losses":358,"wins":811}},"medium":{"GB2-01":{"draws":156,"losses":223,"wins":443},"GB2-02":{"draws":947,"losses":176,"wins":139},"GB2-03":{"draws":434,"losses":1067,"wins":1291},"GB2-04":{"draws":601,"losses":218,"wins":287},"GB2-05":{"draws":0,"losses":623,"wins":617},"GB2-06":{"draws":40,"losses":646,"wins":238},"GB2-07":{"draws":0,"losses":753,"wins":605},"GB2-08":{"draws":440,"losses":452,"wins":554}},"none":{"GB2-01":{"draws":300,"losses":502,"wins":408},"GB2-02":{"draws":1021,"losses":208,"wins":45},"GB2-03":{"draws":1389,"losses":1045,"wins":689},"GB2-04":{"draws":770,"losses":278,"wins":203},"GB2-05":{"draws":0,"losses":612,"wins":674},"GB2-06":{"draws":38,"losses":782,"wins":586},"GB2-07":{"draws":0,"losses":872,"wins":574},"GB2-08":{"draws":628,"losses":241,"wins":13}}},"per_game_raw_elo_all":{"GB2-01":1550.9457936664276,"GB2-02":1531.9457013205847,"GB2-03":1550.9465161409528,"GB2-04":1575.9644952493438,"GB2-05":1550.939270150972,"GB2-06":1403.5822361427863,"GB2-07":1475.6510112266924,"GB2-08":1514.752007985034},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1591.4709479156763,"GB2-02":1700.6371672223945,"GB2-03":1719.7058438844938,"GB2-04":1711.9389425453746,"GB2-05":1649.4151006842073,"GB2-06":1796.0778098187354,"GB2-07":1689.446550530818,"GB2-08":1740.7081503009524},"medium":{"GB2-01":1640.8752456258317,"GB2-02":1469.7170397346088,"GB2-03":1531.8867119940885,"GB2-04":1537.0479898769233,"GB2-05":1476.2773575824424,"GB2-06":1042.9752722031312,"GB2-07":1409.020000662281,"GB2-08":1537.286553533627},"none":{"GB2-01":1420.491187457775,"GB2-02":1425.482897004751,"GB2-03":1401.246992544276,"GB2-04":1478.9065533257337,"GB2-05":1527.1253521862666,"GB2-06":1371.6936264064923,"GB2-07":1328.486482486978,"GB2-08":1266.2613201205222}},"per_game_tracks":{"highest":{"GB2-01":49.08647084554764,"GB2-02":43.13631723036697,"GB2-03":50.938830058497615,"GB2-04":49.44408295059182,"GB2-05":53.163619805036575,"GB2-06":65.860076268154,"GB2-07":56.97038901065603,"GB2-08":48.63797699775197},"medium":{"GB2-01":52.16629838430262,"GB2-02":14.739296013145752,"GB2-03":35.02710842837523,"GB2-04":26.702872586911976,"GB2-05":44.74180476058374,"GB2-06":29.839873377464627,"GB2-07":42.42497068267024,"GB2-08":35.185908012307316},"none":{"GB2-01":38.42771848522953,"GB2-02":9.299675382017327,"GB2-03":23.959530653946718,"GB2-04":19.14269512042114,"GB2-05":47.21516728837782,"GB2-06":45.562170436490284,"GB2-07":38.24778520635433,"GB2-08":17.26327740372219}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.15472039582532,"medium":33.86987921214372,"none":29.37862819711459},"reasoning_agg":{"highest":{"max":65.860076268154,"mean":52.15472039582532,"min":43.13631723036697},"medium":{"max":52.16629838430262,"mean":33.86987921214372,"min":14.739296013145752},"none":{"max":47.21516728837782,"mean":29.37862819711459,"min":9.299675382017327}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":65.860076268154,"expected_score":37.75619971091615,"reasoning_variance":22.77609219871073,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7115428907783965},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.860076268154,"expected_score":45.602374653106736,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.552345742718586},"medium":{"ceiling_score":52.16629838430262,"expected_score":33.21858450811403,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.651294704029695},"none":{"ceiling_score":47.21516728837782,"expected_score":34.44763997152767,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.069011774413081}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:994a8b49c9f7730f","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062000000002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.023437400000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.0234374}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02304638,"mean":0.01037612625,"median":0.0072198,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"recorded_attempt_count":23,"run_count":16,"total":0.16601802000000002},"codegen_latency_ms":{"attempt_count":23,"max_ms":1374551,"mean_ms":491530.125,"min_ms":35032,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1374551,"mean_ms":925316.625,"min_ms":428464,"run_count":8},"none":{"attempt_count":12,"max_ms":114099,"mean_ms":57743.625,"min_ms":35032,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":78655,"output_mean":31302.375,"output_min":3072,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":78655,"output_mean":57997.125,"output_min":33074,"run_count":8},"none":{"attempt_count":12,"output_max":6869,"output_mean":4607.625,"output_min":3072,"run_count":8}},"display_name":"MiMo-V2.6-Flash","economics":{"medium":43.50060040215382,"none":34.00908833868845},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[131072],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":23,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[131072],"total_output_tokens":500838,"total_reasoning_output_tokens":411817,"total_visible_output_tokens":89021,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"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":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-06T16:09:39Z","match_totals_all":{"draws":890,"losses":1361,"wins":1427},"match_totals_tracks":{"medium":{"draws":333,"losses":632,"wins":933},"none":{"draws":557,"losses":729,"wins":494}},"model_slug":"xiaomi-mimo-v2-6-flash","overall":{"max":72.33677238918737,"mean":38.1965547494833,"min":8.495676225404189},"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":63,"losses":128,"wins":205},"GB2-02":{"draws":401,"losses":105,"wins":124},"GB2-03":{"draws":67,"losses":188,"wins":149},"GB2-04":{"draws":28,"losses":69,"wins":115},"GB2-05":{"draws":0,"losses":203,"wins":253},"GB2-06":{"draws":29,"losses":192,"wins":291},"GB2-07":{"draws":0,"losses":206,"wins":286},"GB2-08":{"draws":302,"losses":270,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":94,"wins":102},"GB2-02":{"draws":121,"losses":37,"wins":112},"GB2-03":{"draws":12,"losses":85,"wins":105},"GB2-04":{"draws":28,"losses":69,"wins":115},"GB2-05":{"draws":0,"losses":93,"wins":137},"GB2-06":{"draws":14,"losses":82,"wins":162},"GB2-07":{"draws":0,"losses":45,"wins":197},"GB2-08":{"draws":156,"losses":127,"wins":3}},"none":{"GB2-01":{"draws":61,"losses":34,"wins":103},"GB2-02":{"draws":280,"losses":68,"wins":12},"GB2-03":{"draws":55,"losses":103,"wins":44},"GB2-05":{"draws":0,"losses":110,"wins":116},"GB2-06":{"draws":15,"losses":110,"wins":129},"GB2-07":{"draws":0,"losses":161,"wins":89},"GB2-08":{"draws":146,"losses":143,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1516.173421314903,"GB2-02":1618.5128402154157,"GB2-03":1543.8345722950955,"GB2-04":1588.5506349643795,"GB2-05":1617.2193150828548,"GB2-06":1741.8239140171186,"GB2-07":1985.700792081772,"GB2-08":1215.954228928413},"none":{"GB2-01":1687.8657321911544,"GB2-02":1418.9449018282503,"GB2-03":1365.5073774633856,"GB2-05":1536.9773418872928,"GB2-06":1534.9622497335058,"GB2-07":1358.9337412131626,"GB2-08":1196.468699617013}},"per_game_tracks":{"medium":{"GB2-01":44.39247848509092,"GB2-02":33.03721377915075,"GB2-03":36.03931110055104,"GB2-04":33.39980269306872,"GB2-05":51.597543300353955,"GB2-06":63.26516224678867,"GB2-07":72.33677238918737,"GB2-08":13.936519223039136},"none":{"GB2-01":55.095650713778795,"GB2-02":8.495676225404189,"GB2-03":20.93173044738051,"GB2-05":47.69439055648482,"GB2-06":53.37115878028512,"GB2-07":39.827051204243574,"GB2-08":12.64796044324217}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":43.50060040215382,"none":32.89250909681278},"reasoning_agg":{"medium":{"max":72.33677238918737,"mean":43.50060040215382,"min":13.936519223039136},"none":{"max":55.095650713778795,"mean":32.89250909681278,"min":8.495676225404189}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":72.33677238918737,"reasoning_variance":10.608091305341041},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":72.33677238918737,"expected_score":44.44105600706692,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9404556049130974},"none":{"ceiling_score":55.095650713778795,"expected_score":38.46348481922957,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.57097572241679}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:9d14cc80998fd31a","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":38.050853648088484},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T02:32:57Z","match_totals_all":{"draws":106,"losses":250,"wins":208},"match_totals_tracks":{"none":{"draws":106,"losses":250,"wins":208}},"model_slug":"gpt-4-1-nano","overall":{"max":38.050853648088484,"mean":38.050853648088484,"min":38.050853648088484},"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":26,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":106,"losses":250,"wins":208}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":106,"losses":250,"wins":208}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1414.4458026508933}},"per_game_tracks":{"none":{"GB2-01":38.050853648088484}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":38.050853648088484},"reasoning_agg":{"none":{"max":38.050853648088484,"mean":38.050853648088484,"min":38.050853648088484}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":38.050853648088484},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":38.050853648088484,"expected_score":38.12431446885502,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.0734608207665346}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:95f81a9ba1db059a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"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},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"historical-provider-setting-baseline":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000002},"historical-provider-setting-intensive":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"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}},"codegen_cost_usd":{"admitted_cell_count":42,"cell_count":24,"cost_basis_counts":{"provider_reported":126},"cost_is_complete":false,"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":12.701101349999998},"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":42.11913330358063,"highest":49.97970258890688,"medium":41.18868454171324,"none":27.032607273887873},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:32:43Z","match_totals_all":{"draws":5914,"losses":7459,"wins":8963},"match_totals_tracks":{"highest":{"draws":1179,"losses":1720,"wins":3439},"medium":{"draws":1577,"losses":2078,"wins":3294},"none":{"draws":3158,"losses":3661,"wins":2230}},"model_slug":"google-gemini-3-6-flash","overall":{"max":77.51937692448381,"mean":37.793449221859454,"min":4.329415202685166},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.94023715030813,"GB2-03":45.63997872939976,"GB2-04":29.754384907739425,"GB2-05":73.87009000119858,"GB2-06":77.51937692448381,"GB2-07":47.08060052459036,"GB2-08":31.05324988462816},"per_game_all":{"GB2-01":45.854794361275275,"GB2-03":33.592764173033224,"GB2-04":17.053945756609824,"GB2-05":60.467408007149636,"GB2-06":61.665478000754035,"GB2-07":45.04333139057252,"GB2-08":31.156211435669928},"per_game_match_totals_all":{"GB2-01":{"draws":871,"losses":1040,"wins":987},"GB2-02":{"draws":1196,"losses":229,"wins":12},"GB2-03":{"draws":501,"losses":965,"wins":1061},"GB2-04":{"draws":1706,"losses":645,"wins":551},"GB2-05":{"draws":0,"losses":1053,"wins":2194},"GB2-06":{"draws":239,"losses":1126,"wins":1939},"GB2-07":{"draws":0,"losses":1412,"wins":1435},"GB2-08":{"draws":1401,"losses":989,"wins":784}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":294,"losses":338,"wins":360},"GB2-03":{"draws":41,"losses":136,"wins":295},"GB2-04":{"draws":357,"losses":212,"wins":401},"GB2-05":{"draws":0,"losses":171,"wins":831},"GB2-06":{"draws":44,"losses":194,"wins":848},"GB2-07":{"draws":0,"losses":308,"wins":328},"GB2-08":{"draws":443,"losses":361,"wins":376}},"medium":{"GB2-01":{"draws":337,"losses":147,"wins":406},"GB2-02":{"draws":316,"losses":91,"wins":5},"GB2-03":{"draws":175,"losses":455,"wins":330},"GB2-04":{"draws":568,"losses":224,"wins":77},"GB2-05":{"draws":0,"losses":332,"wins":754},"GB2-06":{"draws":86,"losses":153,"wins":871},"GB2-07":{"draws":0,"losses":505,"wins":535},"GB2-08":{"draws":95,"losses":171,"wins":316}},"none":{"GB2-01":{"draws":240,"losses":555,"wins":221},"GB2-02":{"draws":880,"losses":138,"wins":7},"GB2-03":{"draws":285,"losses":374,"wins":436},"GB2-04":{"draws":781,"losses":209,"wins":73},"GB2-05":{"draws":0,"losses":550,"wins":609},"GB2-06":{"draws":109,"losses":779,"wins":220},"GB2-07":{"draws":0,"losses":599,"wins":572},"GB2-08":{"draws":863,"losses":457,"wins":92}}},"per_game_raw_elo_all":{"GB2-01":1539.6308026079162,"GB2-03":1514.9559675320734,"GB2-04":1462.843056252332,"GB2-05":1799.568173238333,"GB2-06":1708.378065065952,"GB2-07":1459.5003542053375,"GB2-08":1476.3496587708694},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1524.9601575295703,"GB2-03":1657.1591453070487,"GB2-04":1560.5156016853684,"GB2-05":2075.1038029941465,"GB2-06":2039.847922323429,"GB2-07":1498.777626369252,"GB2-08":1474.7926787151455},"medium":{"GB2-01":1806.8493178656486,"GB2-02":1385.0655199327216,"GB2-03":1408.959764835125,"GB2-04":1407.170277651589,"GB2-05":1847.5857399050515,"GB2-06":2036.5555239830865,"GB2-07":1444.9227770790676,"GB2-08":1667.35404637287},"none":{"GB2-01":1287.0829324285298,"GB2-02":1405.1318424736214,"GB2-03":1478.7489924540464,"GB2-04":1420.8432894200387,"GB2-05":1476.0149768158012,"GB2-06":1048.7307488913398,"GB2-07":1434.800659167693,"GB2-08":1286.902251224592}},"per_game_tracks":{"highest":{"GB2-01":44.94023715030813,"GB2-03":45.63997872939976,"GB2-04":29.754384907739425,"GB2-05":73.87009000119858,"GB2-06":77.51937692448381,"GB2-07":47.08060052459036,"GB2-08":31.05324988462816},"medium":{"GB2-01":62.512999827210194,"GB2-02":4.329415202685166,"GB2-03":24.612943777803125,"GB2-04":9.814769856583661,"GB2-05":62.80309205909026,"GB2-06":77.36190453487856,"GB2-07":44.28720841430842,"GB2-08":43.787142661146554},"none":{"GB2-01":30.11114610630751,"GB2-02":6.797038069278612,"GB2-03":30.525370011896776,"GB2-04":11.592682505506392,"GB2-05":44.72904196116008,"GB2-06":30.11515254289976,"GB2-07":43.76218523281878,"GB2-08":18.628241761235078}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.51135408571454,"medium":39.83638630597594,"none":27.032607273887873},"reasoning_agg":{"highest":{"max":77.51937692448381,"mean":46.51135408571454,"min":29.754384907739425},"medium":{"max":77.36190453487856,"mean":39.83638630597594,"min":4.329415202685166},"none":{"max":44.72904196116008,"mean":27.032607273887873,"min":6.797038069278612}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":77.51937692448381,"expected_score":41.48243058460148,"reasoning_variance":19.478746811826664,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.6889813627420267},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.51937692448381,"expected_score":43.194820218063306,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.3165338676512306},"medium":{"ceiling_score":77.36190453487856,"expected_score":42.50283706810207,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.666450762126125},"none":{"ceiling_score":44.72904196116008,"expected_score":29.957065280778167,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.924458006890294}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:6761c7ca5bf9411d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.39273128399999996},"codegen_latency_ms":{"attempt_count":26,"max_ms":176041,"mean_ms":89449.0,"min_ms":6041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":176041,"mean_ms":153558.625,"min_ms":128316,"run_count":8},"medium":{"attempt_count":9,"max_ms":152315,"mean_ms":102702.875,"min_ms":61501,"run_count":8},"none":{"attempt_count":9,"max_ms":25470,"mean_ms":12085.5,"min_ms":6041,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":50785,"output_mean":25087.541666666668,"output_min":1796,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50785,"output_mean":42017.75,"output_min":28632,"run_count":8},"medium":{"attempt_count":9,"output_max":44567,"output_mean":29519.625,"output_min":16614,"run_count":8},"none":{"attempt_count":9,"output_max":8282,"output_mean":3725.25,"output_min":1796,"run_count":8}},"display_name":"DeepSeek V4.1 Flash","economics":{"all":37.52345347528231,"highest":49.523847771661295,"medium":38.795717902907946,"none":24.25079475127769},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[384000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[384000],"total_output_tokens":602101,"total_reasoning_output_tokens":512212,"total_visible_output_tokens":89889,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":384000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":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":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-06T15:46:47Z","match_totals_all":{"draws":1606,"losses":1997,"wins":2075},"match_totals_tracks":{"highest":{"draws":411,"losses":438,"wins":1045},"medium":{"draws":567,"losses":607,"wins":712},"none":{"draws":628,"losses":952,"wins":318}},"model_slug":"deepseek-deepseek-v4-1-flash","overall":{"max":77.3882806749436,"mean":37.52345347528232,"min":7.5838159313438},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":51.257039701557105,"GB2-02":23.24408386233514,"GB2-03":36.443200273875114,"GB2-04":47.63212075743326,"GB2-05":67.86250460639685,"GB2-06":77.3882806749436,"GB2-07":62.768136971174556,"GB2-08":29.59541532557478},"per_game_all":{"GB2-01":49.60217175166934,"GB2-02":19.270569556827184,"GB2-03":30.898504533937796,"GB2-04":21.1040803379848,"GB2-05":48.899647536976936,"GB2-06":60.64794205845498,"GB2-07":50.09141906494144,"GB2-08":19.673292961466046},"per_game_match_totals_all":{"GB2-01":{"draws":163,"losses":163,"wins":254},"GB2-02":{"draws":529,"losses":123,"wins":138},"GB2-03":{"draws":118,"losses":257,"wins":237},"GB2-04":{"draws":318,"losses":184,"wins":158},"GB2-05":{"draws":0,"losses":325,"wins":357},"GB2-06":{"draws":50,"losses":264,"wins":444},"GB2-07":{"draws":0,"losses":340,"wins":396},"GB2-08":{"draws":428,"losses":341,"wins":91}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":73,"wins":119},"GB2-02":{"draws":153,"losses":41,"wins":66},"GB2-03":{"draws":21,"losses":80,"wins":103},"GB2-04":{"draws":70,"losses":28,"wins":120},"GB2-05":{"draws":0,"losses":42,"wins":184},"GB2-06":{"draws":14,"losses":33,"wins":205},"GB2-07":{"draws":0,"losses":67,"wins":179},"GB2-08":{"draws":145,"losses":74,"wins":69}},"medium":{"GB2-01":{"draws":99,"losses":11,"wins":76},"GB2-02":{"draws":161,"losses":32,"wins":71},"GB2-03":{"draws":50,"losses":75,"wins":75},"GB2-04":{"draws":115,"losses":83,"wins":26},"GB2-05":{"draws":0,"losses":115,"wins":109},"GB2-06":{"draws":19,"losses":49,"wins":184},"GB2-07":{"draws":0,"losses":82,"wins":166},"GB2-08":{"draws":123,"losses":160,"wins":5}},"none":{"GB2-01":{"draws":56,"losses":79,"wins":59},"GB2-02":{"draws":215,"losses":50,"wins":1},"GB2-03":{"draws":47,"losses":102,"wins":59},"GB2-04":{"draws":133,"losses":73,"wins":12},"GB2-05":{"draws":0,"losses":168,"wins":64},"GB2-06":{"draws":17,"losses":182,"wins":55},"GB2-07":{"draws":0,"losses":191,"wins":51},"GB2-08":{"draws":160,"losses":107,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1599.743437454403,"GB2-02":1506.5646462629436,"GB2-03":1483.1534059824614,"GB2-04":1493.9905582561562,"GB2-05":1561.7553110493561,"GB2-06":1687.103645746715,"GB2-07":1556.8243209717984,"GB2-08":1302.7054696056912},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1626.2895955877575,"GB2-02":1538.8766420523466,"GB2-03":1548.6020082568996,"GB2-04":1698.0040732445377,"GB2-05":1951.598386257145,"GB2-06":2037.106990560767,"GB2-07":1801.2234978082568,"GB2-08":1452.7473684995864},"medium":{"GB2-01":1705.025562549401,"GB2-02":1556.2959062666678,"GB2-03":1497.550356045261,"GB2-04":1393.9544430891706,"GB2-05":1529.4880498738632,"GB2-06":1903.6684547307086,"GB2-07":1742.2245607179589,"GB2-08":1164.8284031338794},"none":{"GB2-01":1467.9151542260508,"GB2-02":1424.5213904698167,"GB2-03":1403.307853645224,"GB2-04":1390.013158434761,"GB2-05":1204.17949701706,"GB2-06":1120.5354919486692,"GB2-07":1127.0249043891802,"GB2-08":1290.5406371836082}},"per_game_tracks":{"highest":{"GB2-01":51.257039701557105,"GB2-02":23.24408386233514,"GB2-03":36.443200273875114,"GB2-04":47.63212075743326,"GB2-05":67.86250460639685,"GB2-06":77.3882806749436,"GB2-07":62.768136971174556,"GB2-08":29.59541532557478},"medium":{"GB2-01":56.16538190210066,"GB2-02":25.386189103934857,"GB2-03":32.118189980336886,"GB2-04":8.096304325177341,"GB2-05":47.33009429721148,"GB2-06":71.00603802674722,"GB2-07":59.707926654828974,"GB2-08":10.555618932926183},"none":{"GB2-01":41.38409365135024,"GB2-02":9.181435704211548,"GB2-03":24.134123347601395,"GB2-04":7.5838159313438,"GB2-05":31.50634370732247,"GB2-06":33.54950747367411,"GB2-07":27.798193568820775,"GB2-08":18.86884462589718}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.523847771661295,"medium":38.795717902907946,"none":24.25079475127769},"reasoning_agg":{"highest":{"max":77.3882806749436,"mean":49.523847771661295,"min":23.24408386233514},"medium":{"max":71.00603802674722,"mean":38.795717902907946,"min":8.096304325177341},"none":{"max":41.38409365135024,"mean":24.25079475127769,"min":7.5838159313438}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":77.3882806749436,"expected_score":36.54630488536711,"reasoning_variance":25.273053020383603,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9771485899152097},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.3882806749436,"expected_score":43.173404527749376,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.3504432439119185},"medium":{"ceiling_score":71.00603802674722,"expected_score":39.460085975417655,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6643680725097099},"none":{"ceiling_score":41.38409365135024,"expected_score":27.005424152934317,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.7546294016566257}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:3a757501be621bab","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885474999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475000000003}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.4173,"mean":1.10693125,"median":0.4176025,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566349999999996},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":38.70685955979037,"highest":52.67442279076681,"medium":35.71619724118586,"none":26.098756008742956},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:40:50Z","match_totals_all":{"draws":2653,"losses":2292,"wins":3090},"match_totals_tracks":{"highest":{"draws":530,"losses":463,"wins":1407},"medium":{"draws":962,"losses":876,"wins":1068},"none":{"draws":1161,"losses":953,"wins":615}},"model_slug":"gpt-5-5","overall":{"max":77.66600441046111,"mean":37.301037195753416,"min":5.074216631347317},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.40949690017925,"GB2-03":29.15379710433052,"GB2-04":5.074216631347317,"GB2-05":70.09408309485242,"GB2-06":76.63824599660295,"GB2-07":77.66600441046111,"GB2-08":49.68511539759412},"per_game_all":{"GB2-01":50.32416876316936,"GB2-03":21.93023689956371,"GB2-04":8.614048559282226,"GB2-05":59.45367896013087,"GB2-07":57.55716670781289,"GB2-08":34.36185746878317},"per_game_match_totals_all":{"GB2-01":{"draws":544,"losses":98,"wins":306},"GB2-02":{"draws":584,"losses":121,"wins":83},"GB2-03":{"draws":279,"losses":377,"wins":220},"GB2-04":{"draws":640,"losses":311,"wins":108},"GB2-05":{"draws":0,"losses":376,"wins":756},"GB2-06":{"draws":27,"losses":311,"wins":402},"GB2-07":{"draws":0,"losses":398,"wins":776},"GB2-08":{"draws":579,"losses":300,"wins":439}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":100,"losses":31,"wins":159},"GB2-03":{"draws":85,"losses":114,"wins":99},"GB2-04":{"draws":201,"losses":120,"wins":25},"GB2-05":{"draws":0,"losses":58,"wins":250},"GB2-06":{"draws":23,"losses":46,"wins":281},"GB2-07":{"draws":0,"losses":43,"wins":339},"GB2-08":{"draws":121,"losses":51,"wins":254}},"medium":{"GB2-01":{"draws":204,"losses":18,"wins":102},"GB2-02":{"draws":248,"losses":53,"wins":83},"GB2-03":{"draws":100,"losses":129,"wins":59},"GB2-04":{"draws":222,"losses":100,"wins":44},"GB2-05":{"draws":0,"losses":69,"wins":231},"GB2-06":{"draws":4,"losses":265,"wins":121},"GB2-07":{"draws":0,"losses":124,"wins":262},"GB2-08":{"draws":184,"losses":118,"wins":166}},"none":{"GB2-01":{"draws":240,"losses":49,"wins":45},"GB2-02":{"draws":336,"losses":68,"wins":0},"GB2-03":{"draws":94,"losses":134,"wins":62},"GB2-04":{"draws":217,"losses":91,"wins":39},"GB2-05":{"draws":0,"losses":249,"wins":275},"GB2-07":{"draws":0,"losses":231,"wins":175},"GB2-08":{"draws":274,"losses":131,"wins":19}}},"per_game_raw_elo_all":{"GB2-01":1611.3251753449633,"GB2-03":1377.293570019758,"GB2-04":1397.936147707928,"GB2-05":1778.727682395075,"GB2-07":1700.7592568032057,"GB2-08":1524.8252973832132},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1773.106491836101,"GB2-03":1462.5591898159826,"GB2-04":1370.7131209533152,"GB2-05":1997.475725168801,"GB2-06":2021.4254292638411,"GB2-07":2088.4450456656887,"GB2-08":1756.542931222962},"medium":{"GB2-01":1586.8878422926766,"GB2-02":1515.2695763565089,"GB2-03":1335.2729676424228,"GB2-04":1406.80188127492,"GB2-05":1850.9147276503256,"GB2-06":1171.0045016830743,"GB2-07":1665.2461917450507,"GB2-08":1516.4351181722745},"none":{"GB2-01":1473.9811919061128,"GB2-02":1410.6504005156378,"GB2-03":1334.0485526008686,"GB2-04":1416.293440895549,"GB2-05":1487.792594366098,"GB2-07":1348.586532998877,"GB2-08":1301.4978427544033}},"per_game_tracks":{"highest":{"GB2-01":60.40949690017925,"GB2-03":29.15379710433052,"GB2-04":5.074216631347317,"GB2-05":70.09408309485242,"GB2-06":76.63824599660295,"GB2-07":77.66600441046111,"GB2-08":49.68511539759412},"medium":{"GB2-01":48.80076341593193,"GB2-02":20.34104395527248,"GB2-03":18.370321990850552,"GB2-04":9.766866981270683,"GB2-05":62.96502162207106,"GB2-06":35.9633938696503,"GB2-07":55.71514287796513,"GB2-08":33.80702321647471},"none":{"GB2-01":41.762245973396915,"GB2-02":7.475673628302793,"GB2-03":18.26659160351006,"GB2-04":11.001062065228679,"GB2-05":45.301932163469125,"GB2-07":39.290352835012435,"GB2-08":19.59343379228067}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.945027210378804,"medium":35.71619724118586,"none":25.24188713569559},"reasoning_agg":{"highest":{"max":77.66600441046111,"mean":50.945027210378804,"min":5.074216631347317},"medium":{"max":62.96502162207106,"mean":35.71619724118586,"min":9.766866981270683},"none":{"max":45.301932163469125,"mean":25.24188713569559,"min":7.475673628302793}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":77.66600441046111,"expected_score":38.68828169633823,"reasoning_variance":25.703140074683215,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3872445005848135},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.66600441046111,"expected_score":46.48715182649726,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.457875383881543},"medium":{"ceiling_score":62.96502162207106,"expected_score":34.33992669506628,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.3762705461195779},"none":{"ceiling_score":45.301932163469125,"expected_score":30.45065149183368,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.20876435613809}}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:4f94c50e4fd20b19","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.139997},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5826720000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399970000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.5826720000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816},"codegen_latency_ms":{"attempt_count":28,"max_ms":413691,"mean_ms":128683.25,"min_ms":28133,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":413691,"mean_ms":243828.625,"min_ms":115297,"run_count":8},"medium":{"attempt_count":10,"max_ms":159798,"mean_ms":101243.125,"min_ms":39983,"run_count":8},"none":{"attempt_count":9,"max_ms":84315,"mean_ms":40978.0,"min_ms":28133,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":30544,"output_mean":9612.333333333334,"output_min":2170,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":30544,"output_mean":18138.375,"output_min":8542,"run_count":8},"medium":{"attempt_count":10,"output_max":11696,"output_mean":7576.625,"output_min":3317,"run_count":8},"none":{"attempt_count":9,"output_max":6625,"output_mean":3122.0,"output_min":2170,"run_count":8}},"display_name":"Ember-1","economics":{"all":36.74185600961049,"highest":46.14533737065709,"medium":37.90203365555426,"none":26.17819700262012},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[262144],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[262144],"total_output_tokens":230696,"total_reasoning_output_tokens":146257,"total_visible_output_tokens":84439,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"fireworks/ember-1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":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":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-10-06T15:08:50Z","match_totals_all":{"draws":1636,"losses":2031,"wins":2078},"match_totals_tracks":{"highest":{"draws":357,"losses":530,"wins":1009},"medium":{"draws":578,"losses":632,"wins":721},"none":{"draws":701,"losses":869,"wins":348}},"model_slug":"fireworks-ember-1","overall":{"max":66.41453435796264,"mean":36.741856009610494,"min":8.64884714785417},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":62.360383429216355,"GB2-02":9.05437535458221,"GB2-03":54.11593501868573,"GB2-04":10.326341453824497,"GB2-05":52.17278392982279,"GB2-06":50.798590509112614,"GB2-07":63.91975491204987,"GB2-08":66.41453435796264},"per_game_all":{"GB2-01":49.89524483479445,"GB2-02":10.36150571746382,"GB2-03":36.028118031330855,"GB2-04":14.008600694498574,"GB2-05":41.87720888337402,"GB2-06":50.98070005381152,"GB2-07":52.113202702803,"GB2-08":38.67026715880769},"per_game_match_totals_all":{"GB2-01":{"draws":190,"losses":167,"wins":269},"GB2-02":{"draws":601,"losses":171,"wins":46},"GB2-03":{"draws":126,"losses":219,"wins":273},"GB2-04":{"draws":394,"losses":171,"wins":84},"GB2-05":{"draws":0,"losses":382,"wins":286},"GB2-06":{"draws":47,"losses":353,"wins":354},"GB2-07":{"draws":0,"losses":333,"wins":407},"GB2-08":{"draws":278,"losses":235,"wins":359}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":47,"wins":158},"GB2-02":{"draws":201,"losses":59,"wins":12},"GB2-03":{"draws":7,"losses":48,"wins":155},"GB2-04":{"draws":129,"losses":59,"wins":16},"GB2-05":{"draws":0,"losses":86,"wins":130},"GB2-06":{"draws":14,"losses":126,"wins":112},"GB2-07":{"draws":0,"losses":64,"wins":184},"GB2-08":{"draws":3,"losses":41,"wins":242}},"medium":{"GB2-01":{"draws":104,"losses":52,"wins":54},"GB2-02":{"draws":206,"losses":52,"wins":18},"GB2-03":{"draws":14,"losses":79,"wins":105},"GB2-04":{"draws":134,"losses":38,"wins":47},"GB2-05":{"draws":0,"losses":129,"wins":105},"GB2-06":{"draws":17,"losses":102,"wins":131},"GB2-07":{"draws":0,"losses":98,"wins":152},"GB2-08":{"draws":103,"losses":82,"wins":109}},"none":{"GB2-01":{"draws":83,"losses":68,"wins":57},"GB2-02":{"draws":194,"losses":60,"wins":16},"GB2-03":{"draws":105,"losses":92,"wins":13},"GB2-04":{"draws":131,"losses":74,"wins":21},"GB2-05":{"draws":0,"losses":167,"wins":51},"GB2-06":{"draws":16,"losses":125,"wins":111},"GB2-07":{"draws":0,"losses":171,"wins":71},"GB2-08":{"draws":172,"losses":112,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1604.4446974007308,"GB2-02":1434.1175349323023,"GB2-03":1543.7024512969413,"GB2-04":1439.422873658734,"GB2-05":1417.3862916470307,"GB2-06":1484.9830605980117,"GB2-07":1595.803042474454,"GB2-08":1589.976879613494},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1804.4011593674663,"GB2-02":1423.4881556135756,"GB2-03":1757.2078257201729,"GB2-04":1411.1045116949301,"GB2-05":1629.045253292252,"GB2-06":1481.1755539980916,"GB2-07":1823.4259699987622,"GB2-08":2009.5244704635031},"medium":{"GB2-01":1525.9799122346915,"GB2-02":1443.8730775007016,"GB2-03":1546.8815531483783,"GB2-04":1508.9603435262159,"GB2-05":1466.5818127349185,"GB2-06":1570.5629988052476,"GB2-07":1657.3051198855162,"GB2-08":1499.0275021047103},"none":{"GB2-01":1482.9530206000347,"GB2-02":1434.99137168263,"GB2-03":1327.0179750222726,"GB2-04":1398.2037657550566,"GB2-05":1156.5318089139219,"GB2-06":1403.2106289906958,"GB2-07":1306.6780375390842,"GB2-08":1261.3786662722687}},"per_game_tracks":{"highest":{"GB2-01":62.360383429216355,"GB2-02":9.05437535458221,"GB2-03":54.11593501868573,"GB2-04":10.326341453824497,"GB2-05":52.17278392982279,"GB2-06":50.798590509112614,"GB2-07":63.91975491204987,"GB2-08":66.41453435796264},"medium":{"GB2-01":45.003807907695126,"GB2-02":11.561177449478562,"GB2-03":36.29744620458314,"GB2-04":23.05061348181705,"GB2-05":44.270191327266375,"GB2-06":55.07390992050129,"GB2-07":55.303248168909676,"GB2-08":32.65587478418287},"none":{"GB2-01":42.32154316747186,"GB2-02":10.468964348330687,"GB2-03":17.67097287072369,"GB2-04":8.64884714785417,"GB2-05":29.188651393032888,"GB2-06":47.06959973182063,"GB2-07":37.116605027449474,"GB2-08":16.94039233427757}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.14533737065709,"medium":37.90203365555426,"none":26.17819700262012},"reasoning_agg":{"highest":{"max":66.41453435796264,"mean":46.14533737065709,"min":9.05437535458221},"medium":{"max":55.303248168909676,"mean":37.90203365555426,"min":11.561177449478562},"none":{"max":47.06959973182063,"mean":26.17819700262012,"min":8.64884714785417}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":66.41453435796264,"expected_score":35.424723668166486,"reasoning_variance":19.96714036803697,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.3171323414440081},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.41453435796264,"expected_score":39.13495527437036,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.010382096286726},"medium":{"ceiling_score":55.303248168909676,"expected_score":37.648476105087035,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.25355755046722805},"none":{"ceiling_score":47.06959973182063,"expected_score":29.490739625042078,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.312542622421958}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:5574ed529072bdba","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.1645493884651272},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478314},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870414}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.13084687320145388,"mean":0.0871504498983802,"median":0.08084431374719805,"min":0.0619993303028941,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.6972035991870417},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.164549388465127}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":32,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.5094276945411561,"mean":0.1819473937669366,"median":0.18692147314407714,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":32},"recorded_attempt_count":14,"run_count":32,"token_priced_attempt_count":32,"total":4.982416500000001},"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":36.61384130789785,"highest":45.83241748075968,"medium":39.91822705430019,"none":24.090879388633674},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:44:48Z","match_totals_all":{"draws":3118,"losses":4445,"wins":4296},"match_totals_tracks":{"highest":{"draws":714,"losses":986,"wins":1690},"medium":{"draws":862,"losses":1079,"wins":1328},"none":{"draws":1542,"losses":2380,"wins":1278}},"model_slug":"google-gemini-3-5-flash","overall":{"max":78.6879908633185,"mean":36.61384130789785,"min":5.831400370752337},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":31,"overall_ranking_status":"partial","per_game":{"GB2-01":78.6879908633185,"GB2-02":27.249276334541477,"GB2-03":42.66885436031372,"GB2-04":13.649323512078197,"GB2-05":48.06378442866921,"GB2-06":72.05110943911188,"GB2-07":48.018257320837385,"GB2-08":36.27074358720707},"per_game_all":{"GB2-01":60.004137751380284,"GB2-02":14.302711200163593,"GB2-03":30.75728283023105,"GB2-04":16.39473664817203,"GB2-05":42.17264545380045,"GB2-06":61.49337832011681,"GB2-07":47.19526568753927,"GB2-08":20.590572571779294},"per_game_match_totals_all":{"GB2-01":{"draws":166,"losses":356,"wins":824},"GB2-02":{"draws":956,"losses":202,"wins":140},"GB2-03":{"draws":224,"losses":450,"wins":441},"GB2-04":{"draws":840,"losses":359,"wins":215},"GB2-05":{"draws":0,"losses":878,"wins":608},"GB2-06":{"draws":47,"losses":718,"wins":959},"GB2-07":{"draws":0,"losses":871,"wins":883},"GB2-08":{"draws":885,"losses":611,"wins":226}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":29,"wins":310},"GB2-02":{"draws":234,"losses":56,"wins":134},"GB2-03":{"draws":79,"losses":98,"wins":197},"GB2-04":{"draws":207,"losses":125,"wins":68},"GB2-05":{"draws":0,"losses":217,"wins":247},"GB2-06":{"draws":12,"losses":101,"wins":283},"GB2-07":{"draws":0,"losses":240,"wins":252},"GB2-08":{"draws":167,"losses":120,"wins":199}},"medium":{"GB2-01":{"draws":6,"losses":108,"wins":236},"GB2-02":{"draws":375,"losses":67,"wins":4},"GB2-03":{"draws":68,"losses":100,"wins":189},"GB2-04":{"draws":194,"losses":91,"wins":91},"GB2-05":{"draws":0,"losses":132,"wins":254},"GB2-06":{"draws":20,"losses":130,"wins":262},"GB2-07":{"draws":0,"losses":207,"wins":291},"GB2-08":{"draws":199,"losses":244,"wins":1}},"none":{"GB2-01":{"draws":145,"losses":219,"wins":278},"GB2-02":{"draws":347,"losses":79,"wins":2},"GB2-03":{"draws":77,"losses":252,"wins":55},"GB2-04":{"draws":439,"losses":143,"wins":56},"GB2-05":{"draws":0,"losses":529,"wins":107},"GB2-06":{"draws":15,"losses":487,"wins":414},"GB2-07":{"draws":0,"losses":424,"wins":340},"GB2-08":{"draws":519,"losses":247,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1766.6040225209215,"GB2-02":1466.166800436554,"GB2-03":1481.4864501111324,"GB2-04":1457.7734180431655,"GB2-05":1423.459949256865,"GB2-06":1704.7798425183425,"GB2-07":1500.9882988511845,"GB2-08":1316.5765316121326},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2066.31646742235,"GB2-02":1571.4462397302227,"GB2-03":1622.0885217307944,"GB2-04":1436.6598576318524,"GB2-05":1544.571431879539,"GB2-06":1925.518579646157,"GB2-07":1516.8550617790281,"GB2-08":1553.6913894822746},"medium":{"GB2-01":1745.887017824967,"GB2-02":1429.7747335807376,"GB2-03":1614.4297932151383,"GB2-04":1514.0254943036773,"GB2-05":1734.1203320791053,"GB2-06":1842.993161025372,"GB2-07":1594.203425201118,"GB2-08":1121.0159300538894},"none":{"GB2-01":1487.6085823154472,"GB2-02":1397.279427998702,"GB2-03":1207.9410353874648,"GB2-04":1422.6349021939668,"GB2-05":991.6880838119507,"GB2-06":1345.8277868834984,"GB2-07":1391.9064095734075,"GB2-08":1275.0222753002342}},"per_game_tracks":{"highest":{"GB2-01":78.6879908633185,"GB2-02":27.249276334541477,"GB2-03":42.66885436031372,"GB2-04":13.649323512078197,"GB2-05":48.06378442866921,"GB2-06":72.05110943911188,"GB2-07":48.018257320837385,"GB2-08":36.27074358720707},"medium":{"GB2-01":58.71265493428922,"GB2-02":9.827456895196969,"GB2-03":42.02001973438802,"GB2-04":23.709239085923475,"GB2-05":57.28387561596114,"GB2-06":68.10399443964418,"GB2-07":52.03023230497066,"GB2-08":7.6583434240278585},"none":{"GB2-01":42.61176745653312,"GB2-02":5.831400370752337,"GB2-03":7.5829743959914016,"GB2-04":11.825647346514433,"GB2-05":21.170276316770995,"GB2-06":44.32503108159436,"GB2-07":41.53730743680978,"GB2-08":17.84263070410295}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.83241748075968,"medium":39.91822705430019,"none":24.090879388633674},"reasoning_agg":{"highest":{"max":78.6879908633185,"mean":45.83241748075968,"min":13.649323512078197},"medium":{"max":68.10399443964418,"mean":39.91822705430019,"min":7.6583434240278585},"none":{"max":44.32503108159436,"mean":24.090879388633674,"min":5.831400370752337}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":78.6879908633185,"expected_score":35.3033676458388,"reasoning_variance":21.741538092126007,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.310473662059053},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.6879908633185,"expected_score":39.06752001914427,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.764897461615412},"medium":{"ceiling_score":68.10399443964418,"expected_score":40.597044748256344,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6788176939561552},"none":{"ceiling_score":44.32503108159436,"expected_score":26.24553817011576,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1546587814820874}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:2ee7e4bbead73221","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233296000000005},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233295999999997},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262000000001},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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":4.208937000000001}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":40},"cost_is_complete":false,"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":30.88182783142896,"highest":36.638860917303404,"medium":33.79179344607018,"none":38.32234748640703},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:45:01Z","match_totals_all":{"draws":3642,"losses":3983,"wins":4515},"match_totals_tracks":{"highest":{"draws":876,"losses":749,"wins":1025},"medium":{"draws":1505,"losses":1589,"wins":1420},"none":{"draws":1261,"losses":1645,"wins":2070}},"model_slug":"moonshotai-kimi-k3","overall":{"max":78.13006856879633,"mean":35.26569267790691,"min":7.630937757167121},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":32,"overall_ranking_status":"partial","per_game":{"GB2-01":54.82150765770454,"GB2-02":10.268380237083134,"GB2-03":25.85146864835828,"GB2-04":40.82826992832792,"GB2-07":51.424678115043186},"per_game_all":{"GB2-01":49.910454157237815,"GB2-02":9.163875512652396,"GB2-03":32.54616766284305,"GB2-04":25.288179392540627,"GB2-07":37.50046243187091},"per_game_match_totals_all":{"GB2-01":{"draws":495,"losses":461,"wins":649},"GB2-02":{"draws":1292,"losses":240,"wins":46},"GB2-03":{"draws":499,"losses":466,"wins":568},"GB2-04":{"draws":778,"losses":333,"wins":458},"GB2-05":{"draws":0,"losses":543,"wins":720},"GB2-06":{"draws":121,"losses":654,"wins":663},"GB2-07":{"draws":0,"losses":1038,"wins":694},"GB2-08":{"draws":457,"losses":248,"wins":717}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":53,"losses":164,"wins":285},"GB2-02":{"draws":439,"losses":82,"wins":17},"GB2-03":{"draws":240,"losses":163,"wins":121},"GB2-04":{"draws":144,"losses":80,"wins":250},"GB2-07":{"draws":0,"losses":260,"wins":352}},"medium":{"GB2-01":{"draws":79,"losses":162,"wins":237},"GB2-02":{"draws":408,"losses":83,"wins":13},"GB2-03":{"draws":129,"losses":113,"wins":235},"GB2-04":{"draws":379,"losses":89,"wins":79},"GB2-05":{"draws":0,"losses":286,"wins":342},"GB2-06":{"draws":53,"losses":269,"wins":320},"GB2-07":{"draws":0,"losses":391,"wins":161},"GB2-08":{"draws":457,"losses":196,"wins":33}},"none":{"GB2-01":{"draws":363,"losses":135,"wins":127},"GB2-02":{"draws":445,"losses":75,"wins":16},"GB2-03":{"draws":130,"losses":190,"wins":212},"GB2-04":{"draws":255,"losses":164,"wins":129},"GB2-05":{"draws":0,"losses":257,"wins":378},"GB2-06":{"draws":68,"losses":385,"wins":343},"GB2-07":{"draws":0,"losses":387,"wins":181},"GB2-08":{"draws":0,"losses":52,"wins":684}}},"per_game_raw_elo_all":{"GB2-01":1604.6886740145208,"GB2-02":1424.3785937432683,"GB2-03":1502.6021284848066,"GB2-04":1526.1683121227288,"GB2-07":1314.0785677360248},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1683.468133628561,"GB2-02":1433.3602531161087,"GB2-03":1423.5790921096782,"GB2-04":1645.6791558682526,"GB2-07":1582.528719915188},"medium":{"GB2-01":1651.0812807862048,"GB2-02":1411.912984085843,"GB2-03":1600.6205418317847,"GB2-04":1473.992411478676,"GB2-05":1528.8765120381727,"GB2-06":1539.5367874266358,"GB2-07":1168.162295596606,"GB2-08":1303.484338445547},"none":{"GB2-01":1479.5166076287958,"GB2-02":1427.8625440278527,"GB2-03":1483.6067515129569,"GB2-04":1458.8333690212578,"GB2-05":1576.0610795433554,"GB2-06":1433.9394709398136,"GB2-07":1191.5446876962808,"GB2-08":2186.6862645881592}},"per_game_tracks":{"highest":{"GB2-01":54.82150765770454,"GB2-02":10.268380237083134,"GB2-03":25.85146864835828,"GB2-04":40.82826992832792,"GB2-07":51.424678115043186},"medium":{"GB2-01":52.802535100647205,"GB2-02":7.630937757167121,"GB2-03":40.85012313375567,"GB2-04":18.50370532823472,"GB2-05":47.300347700931525,"GB2-06":53.589954717899865,"GB2-07":29.931945042475906,"GB2-08":19.724798787449398},"none":{"GB2-01":42.10731971336169,"GB2-02":9.592308543706935,"GB2-03":30.936911206415186,"GB2-04":16.53256292105924,"GB2-05":49.59551277217529,"GB2-06":48.53933202764794,"GB2-07":31.144764138093635,"GB2-08":78.13006856879633}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.68293710124351,"medium":33.79179344607018,"none":38.32234748640703},"reasoning_agg":{"highest":{"max":54.82150765770454,"mean":33.68293710124351,"min":10.268380237083134},"medium":{"max":53.589954717899865,"mean":33.79179344607018,"min":7.630937757167121},"none":{"max":78.13006856879633,"mean":38.32234748640703,"min":9.592308543706935}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":78.13006856879633,"expected_score":30.319758852940687,"reasoning_variance":4.639410385163522,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.945933824966225},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.82150765770454,"expected_score":29.943585770938522,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.739351330304988},"medium":{"ceiling_score":53.589954717899865,"expected_score":32.919861507396874,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.8719319386733062},"none":{"ceiling_score":78.13006856879633,"expected_score":45.58046185181042,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":7.258114365403387}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:4db09d4d46740775","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":2,"cell_count":2,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.376168},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.376168},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.8154702500000002},"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":39.69534100267538,"highest":40.264840006975746,"medium":37.68245874546214,"none":28.94992291950591},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T12:48:34Z","match_totals_all":{"draws":1962,"losses":3420,"wins":3442},"match_totals_tracks":{"highest":{"draws":120,"losses":402,"wins":506},"medium":{"draws":880,"losses":1115,"wins":1591},"none":{"draws":962,"losses":1903,"wins":1345}},"model_slug":"meta-muse-spark-1-2","overall":{"max":68.04145206229401,"mean":35.220013034924115,"min":7.024257379983879},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":33,"overall_ranking_status":"partial","per_game":{"GB2-01":50.07243402798134,"GB2-03":30.457245985970147},"per_game_all":{"GB2-01":50.81203013999951,"GB2-03":28.578651865351247},"per_game_match_totals_all":{"GB2-01":{"draws":243,"losses":434,"wins":721},"GB2-02":{"draws":732,"losses":182,"wins":55},"GB2-03":{"draws":290,"losses":661,"wins":616},"GB2-04":{"draws":586,"losses":210,"wins":142},"GB2-05":{"draws":0,"losses":552,"wins":580},"GB2-06":{"draws":3,"losses":397,"wins":108},"GB2-07":{"draws":0,"losses":525,"wins":511},"GB2-08":{"draws":108,"losses":459,"wins":709}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":182,"wins":271},"GB2-03":{"draws":69,"losses":220,"wins":235}},"medium":{"GB2-01":{"draws":14,"losses":73,"wins":361},"GB2-02":{"draws":378,"losses":88,"wins":41},"GB2-03":{"draws":141,"losses":208,"wins":172},"GB2-04":{"draws":253,"losses":122,"wins":73},"GB2-05":{"draws":0,"losses":282,"wins":286},"GB2-07":{"draws":0,"losses":193,"wins":321},"GB2-08":{"draws":94,"losses":149,"wins":337}},"none":{"GB2-01":{"draws":178,"losses":179,"wins":89},"GB2-02":{"draws":354,"losses":94,"wins":14},"GB2-03":{"draws":80,"losses":233,"wins":209},"GB2-04":{"draws":333,"losses":88,"wins":69},"GB2-05":{"draws":0,"losses":270,"wins":294},"GB2-06":{"draws":3,"losses":397,"wins":108},"GB2-07":{"draws":0,"losses":332,"wins":190},"GB2-08":{"draws":14,"losses":310,"wins":372}}},"per_game_raw_elo_all":{"GB2-01":1619.1510839060468,"GB2-03":1455.7702777166476},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1607.287034363133,"GB2-03":1477.9448685692873},"medium":{"GB2-01":1895.532627778796,"GB2-02":1448.7357479724174,"GB2-03":1448.070680387355,"GB2-04":1417.905892064722,"GB2-05":1500.5058429205942,"GB2-07":1667.4577709414789,"GB2-08":1650.7529547321142},"none":{"GB2-01":1354.633589576211,"GB2-02":1406.9795543091122,"GB2-03":1441.2952841933006,"GB2-04":1470.859896165415,"GB2-05":1513.5651595681325,"GB2-06":1037.4020951082339,"GB2-07":1270.6472463230389,"GB2-08":1510.697130571167}},"per_game_tracks":{"highest":{"GB2-01":50.07243402798134,"GB2-03":30.457245985970147},"medium":{"GB2-01":68.04145206229401,"GB2-02":12.159156318016004,"GB2-03":27.926354902125862,"GB2-04":11.210730379568732,"GB2-05":45.92033359357898,"GB2-07":55.8298550712029,"GB2-08":42.68932889144849},"none":{"GB2-01":34.32220432972317,"GB2-02":7.024257379983879,"GB2-03":27.352354707957726,"GB2-04":18.096381858270167,"GB2-05":46.55556856570095,"GB2-06":29.573313434193782,"GB2-07":35.24772730823429,"GB2-08":33.4275757719833}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.264840006975746,"medium":36.44527617829068,"none":28.94992291950591},"reasoning_agg":{"highest":{"max":50.07243402798134,"mean":40.264840006975746,"min":30.457245985970147},"medium":{"max":68.04145206229401,"mean":36.44527617829068,"min":11.210730379568732},"none":{"max":46.55556856570095,"mean":28.94992291950591,"min":7.024257379983879}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":68.04145206229401,"expected_score":37.8301777512985,"reasoning_variance":11.314917087469837,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.610164716374385},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":50.07243402798134,"expected_score":31.96541150776412,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.299428499211626},"medium":{"ceiling_score":68.04145206229401,"expected_score":38.77017026970615,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.324894091415466},"none":{"ceiling_score":46.55556856570095,"expected_score":32.87099602984797,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.921073110342064}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:9d90f5bb44fd1cec","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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":4.659585999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.957684},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586000000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.45275},"codegen_latency_ms":{"attempt_count":30,"max_ms":1708792,"mean_ms":723489.2413793104,"min_ms":155474,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1708792,"mean_ms":1260718.7692307692,"min_ms":853424,"run_count":13},"medium":{"attempt_count":8,"max_ms":700604,"mean_ms":265043.125,"min_ms":183145,"run_count":8},"none":{"attempt_count":8,"max_ms":461859,"mean_ms":308937.375,"min_ms":155474,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":76211,"output_mean":34293.10344827586,"output_min":8500,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":76211,"output_mean":56804.769230769234,"output_min":37117,"run_count":13},"medium":{"attempt_count":8,"output_max":40473,"output_mean":14733.75,"output_min":10090,"run_count":8},"none":{"attempt_count":8,"output_max":26415,"output_mean":17271.0,"output_min":8500,"run_count":8}},"display_name":"Qwen3.8 Max","economics":{"all":35.611934470805124,"highest":38.77292264817264,"medium":34.80184101144163,"none":33.26103975280111},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:45:05Z","match_totals_all":{"draws":3036,"losses":3605,"wins":3559},"match_totals_tracks":{"highest":{"draws":947,"losses":1204,"wins":1325},"medium":{"draws":1002,"losses":1227,"wins":1195},"none":{"draws":1087,"losses":1174,"wins":1039}},"model_slug":"qwen-qwen3-8-max","overall":{"max":81.84706709244021,"mean":34.91068233842707,"min":7.175526187200254},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.15477945593377,"GB2-02":18.57566297188059,"GB2-03":36.94390003156534,"GB2-04":36.13063032734346,"GB2-05":42.69248693620103,"GB2-06":52.150712722710104,"GB2-07":67.23309356714772,"GB2-08":24.302115172599088},"per_game_all":{"GB2-01":31.793861321926666,"GB2-02":11.662741129264461,"GB2-03":30.259503669533984,"GB2-04":18.459777595116268,"GB2-05":60.321270314729,"GB2-06":43.89099393100826,"GB2-07":56.0082647815183,"GB2-08":32.49906302334406},"per_game_match_totals_all":{"GB2-01":{"draws":305,"losses":608,"wins":237},"GB2-02":{"draws":1017,"losses":181,"wins":76},"GB2-03":{"draws":295,"losses":451,"wins":428},"GB2-04":{"draws":681,"losses":241,"wins":201},"GB2-05":{"draws":0,"losses":424,"wins":827},"GB2-06":{"draws":114,"losses":768,"wins":529},"GB2-07":{"draws":0,"losses":480,"wins":777},"GB2-08":{"draws":624,"losses":452,"wins":484}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":66,"losses":207,"wins":85},"GB2-02":{"draws":324,"losses":45,"wins":58},"GB2-03":{"draws":44,"losses":143,"wins":196},"GB2-04":{"draws":166,"losses":63,"wins":146},"GB2-05":{"draws":0,"losses":259,"wins":217},"GB2-06":{"draws":41,"losses":222,"wins":226},"GB2-07":{"draws":0,"losses":107,"wins":309},"GB2-08":{"draws":306,"losses":158,"wins":88}},"medium":{"GB2-01":{"draws":144,"losses":176,"wins":94},"GB2-02":{"draws":362,"losses":78,"wins":6},"GB2-03":{"draws":96,"losses":147,"wins":151},"GB2-04":{"draws":265,"losses":91,"wins":16},"GB2-05":{"draws":0,"losses":140,"wins":270},"GB2-06":{"draws":44,"losses":225,"wins":235},"GB2-07":{"draws":0,"losses":232,"wins":186},"GB2-08":{"draws":91,"losses":138,"wins":237}},"none":{"GB2-01":{"draws":95,"losses":225,"wins":58},"GB2-02":{"draws":331,"losses":58,"wins":12},"GB2-03":{"draws":155,"losses":161,"wins":81},"GB2-04":{"draws":250,"losses":87,"wins":39},"GB2-05":{"draws":0,"losses":25,"wins":340},"GB2-06":{"draws":29,"losses":321,"wins":68},"GB2-07":{"draws":0,"losses":141,"wins":282},"GB2-08":{"draws":227,"losses":156,"wins":159}}},"per_game_raw_elo_all":{"GB2-01":1314.075795641729,"GB2-02":1444.6989774324193,"GB2-03":1475.6107534386701,"GB2-04":1473.6545858761338,"GB2-05":1796.5638386484309,"GB2-06":1336.7530329039664,"GB2-07":1670.8973983484495,"GB2-08":1496.6562015399984},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1319.8653753234175,"GB2-02":1500.913774787359,"GB2-03":1554.51217913678,"GB2-04":1609.5520257828039,"GB2-05":1434.1469781880924,"GB2-06":1509.4454300261887,"GB2-07":1887.3050628267379,"GB2-08":1372.7023159168107},"medium":{"GB2-01":1411.3045182881913,"GB2-02":1424.973508960263,"GB2-03":1518.127431867521,"GB2-04":1388.8894090673878,"GB2-05":1716.4480796094886,"GB2-06":1497.0969787728231,"GB2-07":1353.9036813303237,"GB2-08":1647.4820062344222},"none":{"GB2-01":1211.057493313578,"GB2-02":1408.2096485496359,"GB2-03":1354.1926493117091,"GB2-04":1422.5223227782099,"GB2-05":2239.0964581477115,"GB2-06":1003.7166899128873,"GB2-07":1771.483450888287,"GB2-08":1469.7842824687623}},"per_game_tracks":{"highest":{"GB2-01":32.15477945593377,"GB2-02":18.57566297188059,"GB2-03":36.94390003156534,"GB2-04":36.13063032734346,"GB2-05":42.69248693620103,"GB2-06":52.150712722710104,"GB2-07":67.23309356714772,"GB2-08":24.302115172599088},"medium":{"GB2-01":37.85502829410675,"GB2-02":9.237034228712542,"GB2-03":33.8614453087492,"GB2-04":7.437693902905128,"GB2-05":56.424256915545776,"GB2-06":51.56009763735894,"GB2-07":39.56614750149142,"GB2-08":42.473024302663276},"none":{"GB2-01":25.371776215739473,"GB2-02":7.175526187200254,"GB2-03":19.9731656682874,"GB2-04":11.81100855510022,"GB2-05":81.84706709244021,"GB2-06":27.962171432955724,"GB2-07":61.22555327591576,"GB2-08":30.722049594769803}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":36.66916625103847,"medium":34.80184101144163,"none":33.26103975280111},"reasoning_agg":{"highest":{"max":67.23309356714772,"mean":36.66916625103847,"min":18.57566297188059},"medium":{"max":56.424256915545776,"mean":34.80184101144163,"min":7.437693902905128},"none":{"max":81.84706709244021,"mean":33.26103975280111,"min":7.175526187200254}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":81.84706709244021,"expected_score":33.742292728872,"reasoning_variance":3.4081264982373582,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.1683896095550708},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.23309356714772,"expected_score":30.326571417690708,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.342594833347761},"medium":{"ceiling_score":56.424256915545776,"expected_score":34.02447895385551,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7773620575861244},"none":{"ceiling_score":81.84706709244021,"expected_score":36.87582781506979,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.61478806226868}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:6b4b6c0d4b1022d9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.43048093750000005,"median":0.4308725,"min":0.32672249999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-08-08":9},"run_count":16,"token_priced_attempt_count":17,"total":6.887694999999999},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.266665,"mean":0.20888499999999996,"median":0.20905875000000002,"min":0.14104,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-08-08":8},"run_count":16,"token_priced_attempt_count":16,"total":3.34216},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.19681749999999998,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.42452},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.5886581249999999,"median":0.58241,"min":0.410635,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":4.709264999999999},"historical-thinking-budget-setting":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":17},"run_count":16,"token_priced_attempt_count":17,"total":4.09607}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-08-08":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203784999999998},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333333,"min_ms":22230,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319301,"mean_ms":209645.0,"min_ms":137590,"run_count":8},"medium":{"attempt_count":8,"max_ms":81353,"mean_ms":54764.0,"min_ms":30922,"run_count":8},"none":{"attempt_count":8,"max_ms":40585,"mean_ms":32235.375,"min_ms":22230,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27669,"output_mean":9998.125,"output_min":2138,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27669,"output_mean":21703.125,"output_min":14720,"run_count":8},"medium":{"attempt_count":8,"output_max":8008,"output_mean":5259.0,"output_min":2375,"run_count":8},"none":{"attempt_count":8,"output_max":4031,"output_mean":3032.25,"output_min":2138,"run_count":8}},"display_name":"Claude Opus 4.5","economics":{"all":34.43277692270281,"highest":33.362283686828796,"medium":36.2018731107287,"none":33.7341739705509},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-10-06T15:22:46Z","match_totals_all":{"draws":3435,"losses":4386,"wins":4358},"match_totals_tracks":{"highest":{"draws":1329,"losses":1757,"wins":1590},"medium":{"draws":1128,"losses":1623,"wins":1794},"none":{"draws":978,"losses":1006,"wins":974}},"model_slug":"claude-opus-4-5","overall":{"max":57.02770131570286,"mean":34.4327769227028,"min":8.952585790686866},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":56.20440736076151,"GB2-02":9.176814293531638,"GB2-03":26.511550987145643,"GB2-04":9.52119103693566,"GB2-05":47.06620639759133,"GB2-06":53.58320516585284,"GB2-07":44.84191116856644,"GB2-08":19.992983084245328},"per_game_all":{"GB2-01":47.001427955063356,"GB2-02":9.635019879799524,"GB2-03":25.16228149987082,"GB2-04":13.772137827159106,"GB2-05":45.520338876855014,"GB2-06":49.4115527671893,"GB2-07":41.20479999652407,"GB2-08":43.754656579161214},"per_game_match_totals_all":{"GB2-01":{"draws":423,"losses":393,"wins":583},"GB2-02":{"draws":1301,"losses":249,"wins":50},"GB2-03":{"draws":442,"losses":503,"wins":356},"GB2-04":{"draws":767,"losses":318,"wins":158},"GB2-05":{"draws":0,"losses":736,"wins":832},"GB2-06":{"draws":116,"losses":777,"wins":781},"GB2-07":{"draws":0,"losses":930,"wins":766},"GB2-08":{"draws":386,"losses":480,"wins":832}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":64,"losses":135,"wins":282},"GB2-02":{"draws":438,"losses":92,"wins":14},"GB2-03":{"draws":118,"losses":209,"wins":183},"GB2-04":{"draws":311,"losses":185,"wins":67},"GB2-05":{"draws":0,"losses":279,"wins":333},"GB2-06":{"draws":47,"losses":274,"wins":323},"GB2-07":{"draws":0,"losses":322,"wins":322},"GB2-08":{"draws":351,"losses":261,"wins":66}},"medium":{"GB2-01":{"draws":167,"losses":172,"wins":243},"GB2-02":{"draws":462,"losses":83,"wins":11},"GB2-03":{"draws":192,"losses":185,"wins":122},"GB2-04":{"draws":250,"losses":69,"wins":33},"GB2-05":{"draws":0,"losses":302,"wins":328},"GB2-06":{"draws":51,"losses":311,"wins":296},"GB2-07":{"draws":0,"losses":371,"wins":291},"GB2-08":{"draws":6,"losses":130,"wins":470}},"none":{"GB2-01":{"draws":192,"losses":86,"wins":58},"GB2-02":{"draws":401,"losses":74,"wins":25},"GB2-03":{"draws":132,"losses":109,"wins":51},"GB2-04":{"draws":206,"losses":64,"wins":58},"GB2-05":{"draws":0,"losses":155,"wins":171},"GB2-06":{"draws":18,"losses":192,"wins":162},"GB2-07":{"draws":0,"losses":237,"wins":153},"GB2-08":{"draws":29,"losses":89,"wins":296}}},"per_game_raw_elo_all":{"GB2-01":1558.02424403252,"GB2-02":1428.2098659212381,"GB2-03":1415.444049595241,"GB2-04":1437.604359363393,"GB2-05":1492.2826532470292,"GB2-06":1452.1756717269934,"GB2-07":1385.4958745043998,"GB2-08":1666.8627932669485},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1705.651579868129,"GB2-02":1424.4838098822186,"GB2-03":1431.370586627313,"GB2-04":1404.9125139428675,"GB2-05":1524.0629775906395,"GB2-06":1539.395669266091,"GB2-07":1455.6170985534707,"GB2-08":1307.5398096107024},"medium":{"GB2-01":1586.5498714840492,"GB2-02":1422.66041882767,"GB2-03":1437.2446010170324,"GB2-04":1425.4527827124034,"GB2-05":1464.2471137921489,"GB2-06":1458.6659783715177,"GB2-07":1396.4919146572288,"GB2-08":1867.5771931999932},"none":{"GB2-01":1381.8712807453824,"GB2-02":1437.4853690538262,"GB2-03":1377.716961141377,"GB2-04":1482.4477814349082,"GB2-05":1488.5378683582994,"GB2-06":1358.465367543371,"GB2-07":1304.3786103025004,"GB2-08":1825.4713769901498}},"per_game_tracks":{"highest":{"GB2-01":56.20440736076151,"GB2-02":9.176814293531638,"GB2-03":26.511550987145643,"GB2-04":9.52119103693566,"GB2-05":47.06620639759133,"GB2-06":53.58320516585284,"GB2-07":44.84191116856644,"GB2-08":19.992983084245328},"medium":{"GB2-01":48.77969456459813,"GB2-02":8.952585790686866,"GB2-03":27.009187627672162,"GB2-04":12.192058602624218,"GB2-05":44.156626241293594,"GB2-06":49.72197817472907,"GB2-07":41.775152568522714,"GB2-08":57.02770131570286},"none":{"GB2-01":36.02018193983044,"GB2-02":10.77565955518007,"GB2-03":21.966105884794658,"GB2-04":19.603163841917443,"GB2-05":45.338183991680104,"GB2-06":44.92947496098599,"GB2-07":36.997336252483066,"GB2-08":54.24328533753546}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.362283686828796,"medium":36.2018731107287,"none":33.7341739705509},"reasoning_agg":{"highest":{"max":56.20440736076151,"mean":33.362283686828796,"min":9.176814293531638},"medium":{"max":57.02770131570286,"mean":36.2018731107287,"min":8.952585790686866},"none":{"max":54.24328533753546,"mean":33.7341739705509,"min":10.77565955518007}},"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":57.02770131570286,"expected_score":33.14796320083772,"reasoning_variance":2.839589423899902,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2848137218650777},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.20440736076151,"expected_score":24.515951056873014,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.846332629955782},"medium":{"ceiling_score":57.02770131570286,"expected_score":35.44221696935533,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7596561413733696},"none":{"ceiling_score":54.24328533753546,"expected_score":39.48572157628481,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.751547605733911}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:329298b57681e3ed","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.8079499999999995},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337000000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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":0.4933700000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":false,"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":33.08166183525949,"highest":40.05952834449005,"medium":30.206081668143632,"none":28.979375493144786},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:13:27Z","match_totals_all":{"draws":3430,"losses":4749,"wins":4108},"match_totals_tracks":{"highest":{"draws":869,"losses":1315,"wins":1719},"medium":{"draws":1329,"losses":1673,"wins":1222},"none":{"draws":1232,"losses":1761,"wins":1167}},"model_slug":"claude-sonnet-5","overall":{"max":58.47957734108064,"mean":33.08166183525949,"min":8.289807396215556},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":51.301997355987325,"GB2-02":8.289807396215556,"GB2-03":32.62092205825619,"GB2-04":27.11776345647468,"GB2-05":49.83365894715362,"GB2-06":34.90964662460475,"GB2-07":57.922853576147595,"GB2-08":58.47957734108064},"per_game_all":{"GB2-01":44.4437713268602,"GB2-02":9.028205964331177,"GB2-03":28.00223083308082,"GB2-04":18.226456407789133,"GB2-05":40.12114389321038,"GB2-06":41.261617021213134,"GB2-07":47.24047219846759,"GB2-08":36.329397037123464},"per_game_match_totals_all":{"GB2-01":{"draws":256,"losses":641,"wins":702},"GB2-02":{"draws":1254,"losses":216,"wins":28},"GB2-03":{"draws":471,"losses":557,"wins":459},"GB2-04":{"draws":795,"losses":295,"wins":249},"GB2-05":{"draws":0,"losses":830,"wins":626},"GB2-06":{"draws":83,"losses":890,"wins":573},"GB2-07":{"draws":0,"losses":795,"wins":823},"GB2-08":{"draws":571,"losses":525,"wins":648}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":72,"losses":175,"wins":323},"GB2-02":{"draws":393,"losses":66,"wins":7},"GB2-03":{"draws":144,"losses":154,"wins":161},"GB2-04":{"draws":229,"losses":86,"wins":121},"GB2-05":{"draws":0,"losses":216,"wins":262},"GB2-06":{"draws":25,"losses":321,"wins":122},"GB2-07":{"draws":0,"losses":186,"wins":312},"GB2-08":{"draws":6,"losses":111,"wins":411}},"medium":{"GB2-01":{"draws":95,"losses":217,"wins":189},"GB2-02":{"draws":434,"losses":67,"wins":11},"GB2-03":{"draws":154,"losses":221,"wins":131},"GB2-04":{"draws":281,"losses":121,"wins":75},"GB2-05":{"draws":0,"losses":279,"wins":241},"GB2-06":{"draws":28,"losses":285,"wins":195},"GB2-07":{"draws":0,"losses":275,"wins":305},"GB2-08":{"draws":337,"losses":208,"wins":75}},"none":{"GB2-01":{"draws":89,"losses":249,"wins":190},"GB2-02":{"draws":427,"losses":83,"wins":10},"GB2-03":{"draws":173,"losses":182,"wins":167},"GB2-04":{"draws":285,"losses":88,"wins":53},"GB2-05":{"draws":0,"losses":335,"wins":123},"GB2-06":{"draws":30,"losses":284,"wins":256},"GB2-07":{"draws":0,"losses":334,"wins":206},"GB2-08":{"draws":228,"losses":206,"wins":162}}},"per_game_raw_elo_all":{"GB2-01":1516.996222849496,"GB2-02":1423.275350232095,"GB2-03":1448.9663063802302,"GB2-04":1471.8602326259415,"GB2-05":1381.2846760769742,"GB2-06":1281.7785945554685,"GB2-07":1501.8598520513308,"GB2-08":1554.5783443775263},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1627.01077276923,"GB2-02":1417.2708087634055,"GB2-03":1503.484516071635,"GB2-04":1540.2387021684356,"GB2-05":1580.956947126107,"GB2-06":1148.9729843521604,"GB2-07":1707.809470451721,"GB2-08":1889.5323987308384},"medium":{"GB2-01":1472.7400897350062,"GB2-02":1432.2592140246302,"GB2-03":1383.7395808489332,"GB2-04":1445.503484823653,"GB2-05":1422.8690809860448,"GB2-06":1297.1216390514444,"GB2-07":1488.003680738042,"GB2-08":1336.287851727577},"none":{"GB2-01":1451.2378060442518,"GB2-02":1420.296027908249,"GB2-03":1459.6748222201231,"GB2-04":1429.8385108857358,"GB2-05":1140.0280001187707,"GB2-06":1399.2411602628013,"GB2-07":1309.7664049642303,"GB2-08":1437.914782674164}},"per_game_tracks":{"highest":{"GB2-01":51.301997355987325,"GB2-02":8.289807396215556,"GB2-03":32.62092205825619,"GB2-04":27.11776345647468,"GB2-05":49.83365894715362,"GB2-06":34.90964662460475,"GB2-07":57.922853576147595,"GB2-08":58.47957734108064},"medium":{"GB2-01":41.68487657797695,"GB2-02":10.132981773632356,"GB2-03":22.47633211843864,"GB2-04":14.79926742443116,"GB2-05":42.14390427233801,"GB2-06":41.9954607517836,"GB2-07":46.52176775243527,"GB2-08":21.894062674113055},"none":{"GB2-01":40.344440046616334,"GB2-02":8.661828723145618,"GB2-03":28.909438322547622,"GB2-04":12.762338342461558,"GB2-05":28.3858684601395,"GB2-06":46.87974368725106,"GB2-07":37.27679526681994,"GB2-08":28.61455109617669}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.05952834449005,"medium":30.206081668143632,"none":28.979375493144786},"reasoning_agg":{"highest":{"max":58.47957734108064,"mean":40.05952834449005,"min":8.289807396215556},"medium":{"max":46.52176775243527,"mean":30.206081668143632,"min":10.132981773632356},"none":{"max":46.87974368725106,"mean":28.979375493144786,"min":8.661828723145618}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":58.47957734108064,"expected_score":31.054452542400405,"reasoning_variance":11.080152851345261,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.0272092928590837},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.47957734108064,"expected_score":31.47756315762743,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.581965186862618},"medium":{"ceiling_score":46.52176775243527,"expected_score":28.362323819597517,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8437578485461152},"none":{"ceiling_score":46.87974368725106,"expected_score":33.32347064997626,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.344095156831472}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:d2b3d8dc07f29797","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.30150960000000004},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":false,"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":42.509706985019655,"none":23.424728853104142},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:47:17Z","match_totals_all":{"draws":2400,"losses":2757,"wins":2202},"match_totals_tracks":{"medium":{"draws":1156,"losses":898,"wins":1483},"none":{"draws":1244,"losses":1859,"wins":719}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":73.72211439491096,"mean":32.967217919061895,"min":8.704285541647643},"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":37,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":320,"losses":448,"wins":262},"GB2-02":{"draws":630,"losses":135,"wins":119},"GB2-03":{"draws":251,"losses":291,"wins":383},"GB2-04":{"draws":495,"losses":172,"wins":89},"GB2-05":{"draws":0,"losses":586,"wins":382},"GB2-06":{"draws":62,"losses":302,"wins":550},"GB2-07":{"draws":0,"losses":482,"wins":348},"GB2-08":{"draws":642,"losses":341,"wins":69}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":159,"losses":160,"wins":117},"GB2-02":{"draws":248,"losses":73,"wins":109},"GB2-03":{"draws":133,"losses":131,"wins":281},"GB2-04":{"draws":235,"losses":86,"wins":59},"GB2-05":{"draws":0,"losses":109,"wins":271},"GB2-06":{"draws":48,"losses":76,"wins":290},"GB2-07":{"draws":0,"losses":109,"wins":305},"GB2-08":{"draws":333,"losses":154,"wins":51}},"none":{"GB2-01":{"draws":161,"losses":288,"wins":145},"GB2-02":{"draws":382,"losses":62,"wins":10},"GB2-03":{"draws":118,"losses":160,"wins":102},"GB2-04":{"draws":260,"losses":86,"wins":30},"GB2-05":{"draws":0,"losses":477,"wins":111},"GB2-06":{"draws":14,"losses":226,"wins":260},"GB2-07":{"draws":0,"losses":373,"wins":43},"GB2-08":{"draws":309,"losses":187,"wins":18}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1476.16816135807,"GB2-02":1531.352312898428,"GB2-03":1615.475298942157,"GB2-04":1434.3669454453366,"GB2-05":1799.7315987886445,"GB2-06":1960.4555864253668,"GB2-07":1828.9242793354483,"GB2-08":1337.8610753961043},"none":{"GB2-01":1334.3925012874615,"GB2-02":1420.6412801044642,"GB2-03":1430.577779620462,"GB2-04":1411.7989301680873,"GB2-05":1023.307965396893,"GB2-06":1560.8158435106388,"GB2-07":858.4211146248036,"GB2-08":1271.2030891412637}},"per_game_tracks":{"medium":{"GB2-01":41.898580038584306,"GB2-02":22.318791914189624,"GB2-03":42.10859322487103,"GB2-04":13.351174307768849,"GB2-05":60.475357398966835,"GB2-06":73.72211439491096,"GB2-07":64.20494620166302,"GB2-08":21.99809839920261},"none":{"GB2-01":33.060389791000404,"GB2-02":8.704285541647643,"GB2-03":26.44438570812186,"GB2-04":10.41663724292932,"GB2-05":22.708339535484445,"GB2-06":54.60771243240031,"GB2-07":13.866008872197817,"GB2-08":17.59007170105132}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":42.509706985019655,"none":23.424728853104142},"reasoning_agg":{"medium":{"max":73.72211439491096,"mean":42.509706985019655,"min":13.351174307768849},"none":{"max":54.60771243240031,"mean":23.424728853104142,"min":8.704285541647643}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":73.72211439491096,"reasoning_variance":19.084978131915513},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":73.72211439491096,"expected_score":43.83801980512621,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3283128201065537},"none":{"ceiling_score":54.60771243240031,"expected_score":26.663662094625682,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.23893324152154}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:93c1ac9705318aae","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.06723375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.77569875},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.77569875},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425000000001},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.0672337499999998}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":false,"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":31.802473192549623,"highest":37.90151950302216,"medium":34.35221465764033,"none":27.01490348335258},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:17:19Z","match_totals_all":{"draws":3505,"losses":4010,"wins":3533},"match_totals_tracks":{"highest":{"draws":911,"losses":1128,"wins":1379},"medium":{"draws":947,"losses":1320,"wins":1211},"none":{"draws":1647,"losses":1562,"wins":943}},"model_slug":"gpt-5-6-terra","overall":{"max":73.56397097182385,"mean":32.79389666986497,"min":10.176367293313053},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.94454142150639,"GB2-02":23.05691078788848,"GB2-03":21.441405385173457,"GB2-04":10.413194483801846,"GB2-05":49.5474152554217,"GB2-06":73.56397097182385,"GB2-07":42.30304080076536,"GB2-08":24.941676917796183},"per_game_all":{"GB2-01":55.4832461661729,"GB2-02":15.164600948812136,"GB2-03":17.276986137404144,"GB2-04":12.61550559227038,"GB2-06":52.83956248360382,"GB2-07":43.55376203412741,"GB2-08":25.68364898545656},"per_game_match_totals_all":{"GB2-01":{"draws":270,"losses":375,"wins":815},"GB2-02":{"draws":1055,"losses":214,"wins":155},"GB2-03":{"draws":560,"losses":522,"wins":180},"GB2-04":{"draws":841,"losses":336,"wins":161},"GB2-05":{"draws":0,"losses":376,"wins":520},"GB2-06":{"draws":84,"losses":686,"wins":680},"GB2-07":{"draws":0,"losses":917,"wins":647},"GB2-08":{"draws":695,"losses":584,"wins":375}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":66,"losses":89,"wins":259},"GB2-02":{"draws":227,"losses":65,"wins":114},"GB2-03":{"draws":137,"losses":135,"wins":84},"GB2-04":{"draws":260,"losses":68,"wins":22},"GB2-05":{"draws":0,"losses":184,"wins":270},"GB2-06":{"draws":37,"losses":89,"wins":284},"GB2-07":{"draws":0,"losses":296,"wins":216},"GB2-08":{"draws":184,"losses":202,"wins":130}},"medium":{"GB2-01":{"draws":5,"losses":92,"wins":309},"GB2-02":{"draws":360,"losses":72,"wins":32},"GB2-03":{"draws":186,"losses":144,"wins":30},"GB2-04":{"draws":206,"losses":145,"wins":71},"GB2-05":{"draws":0,"losses":192,"wins":250},"GB2-06":{"draws":45,"losses":276,"wins":157},"GB2-07":{"draws":0,"losses":186,"wins":230},"GB2-08":{"draws":145,"losses":213,"wins":132}},"none":{"GB2-01":{"draws":199,"losses":194,"wins":247},"GB2-02":{"draws":468,"losses":77,"wins":9},"GB2-03":{"draws":237,"losses":243,"wins":66},"GB2-04":{"draws":375,"losses":123,"wins":68},"GB2-06":{"draws":2,"losses":321,"wins":239},"GB2-07":{"draws":0,"losses":435,"wins":201},"GB2-08":{"draws":366,"losses":169,"wins":113}}},"per_game_raw_elo_all":{"GB2-01":1694.0832495294535,"GB2-02":1473.1755528375854,"GB2-03":1322.3674257009266,"GB2-04":1428.7092957229017,"GB2-06":1523.847750427861,"GB2-07":1430.7823905140424,"GB2-08":1393.5938095973443},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1733.5655133955156,"GB2-02":1537.3545799359408,"GB2-03":1371.5234897727757,"GB2-04":1411.7724536783146,"GB2-05":1575.0722789753588,"GB2-06":1957.1491582634947,"GB2-07":1406.6692689516176,"GB2-08":1382.3737405564004},"medium":{"GB2-01":1820.5923382398566,"GB2-02":1449.5600603034877,"GB2-03":1292.6970902460653,"GB2-04":1421.1977450954007,"GB2-05":1578.9255133223733,"GB2-06":1310.3424513200644,"GB2-07":1638.4206622222018,"GB2-08":1399.8739382173358},"none":{"GB2-01":1528.0918969529885,"GB2-02":1432.6120182733277,"GB2-03":1302.8816970839384,"GB2-04":1453.1576883949901,"GB2-06":1304.051641700024,"GB2-07":1247.2572403683075,"GB2-08":1398.5337500182966}},"per_game_tracks":{"highest":{"GB2-01":57.94454142150639,"GB2-02":23.05691078788848,"GB2-03":21.441405385173457,"GB2-04":10.413194483801846,"GB2-05":49.5474152554217,"GB2-06":73.56397097182385,"GB2-07":42.30304080076536,"GB2-08":24.941676917796183},"medium":{"GB2-01":63.369729597208654,"GB2-02":12.260524765234882,"GB2-03":14.763365114463934,"GB2-04":11.638772660285792,"GB2-05":49.73484536980418,"GB2-06":42.6278000635102,"GB2-07":54.32373201133183,"GB2-08":26.09894767928316},"none":{"GB2-01":45.13546747980364,"GB2-02":10.176367293313053,"GB2-03":15.626187912575043,"GB2-04":15.794549632723497,"GB2-06":42.326916415477385,"GB2-07":34.03451329028506,"GB2-08":26.010322359290342}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.90151950302216,"medium":34.35221465764033,"none":26.12795584893241},"reasoning_agg":{"highest":{"max":73.56397097182385,"mean":37.90151950302216,"min":10.413194483801846},"medium":{"max":63.369729597208654,"mean":34.35221465764033,"min":11.638772660285792},"none":{"max":45.13546747980364,"mean":26.12795584893241,"min":10.176367293313053}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":73.56397097182385,"expected_score":29.87324715051099,"reasoning_variance":11.773563654089749,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.9206495193539794},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.56397097182385,"expected_score":30.007949122996173,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.893570380025984},"medium":{"ceiling_score":63.369729597208654,"expected_score":33.06013200809488,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2920826495454492},"none":{"ceiling_score":45.13546747980364,"expected_score":31.54486955507258,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.416913706140171}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:18806ce450191f0d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.913572594249},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.372620130294},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.20237245442100002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.372620130294},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.202372454421},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.9135725942490001}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640002},"codegen_latency_ms":{"attempt_count":35,"max_ms":1560134,"mean_ms":432334.7916666667,"min_ms":52746,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1560134,"mean_ms":818090.375,"min_ms":426935,"run_count":8},"medium":{"attempt_count":12,"max_ms":673313,"mean_ms":392142.875,"min_ms":86869,"run_count":8},"none":{"attempt_count":12,"max_ms":170011,"mean_ms":86771.125,"min_ms":52746,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":74570,"output_mean":21422.416666666668,"output_min":2493,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":74570,"output_mean":43080.25,"output_min":21434,"run_count":8},"medium":{"attempt_count":12,"output_max":23131,"output_mean":16655.5,"output_min":5286,"run_count":8},"none":{"attempt_count":12,"output_max":8274,"output_mean":4531.5,"output_min":2493,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"all":33.64756151776351,"highest":34.3107904184104,"medium":37.72870719115047,"none":28.065939064739766},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:31:14Z","match_totals_all":{"draws":2751,"losses":3514,"wins":3268},"match_totals_tracks":{"highest":{"draws":1097,"losses":1212,"wins":1134},"medium":{"draws":824,"losses":1332,"wins":1484},"none":{"draws":830,"losses":970,"wins":650}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":72.94601860690389,"mean":32.719265626157046,"min":5.987992773130906},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":25.468096142290868,"GB2-02":10.014962553999606,"GB2-03":26.868011586123032,"GB2-04":15.79149388976589,"GB2-05":41.983124649723834,"GB2-06":72.94601860690389,"GB2-07":63.39200007671138,"GB2-08":18.02261584176466},"per_game_all":{"GB2-01":34.83616072613499,"GB2-03":20.97983505352255,"GB2-04":13.850701715204204,"GB2-05":41.63150536111127,"GB2-07":58.01510300439682,"GB2-08":32.57206324621124},"per_game_match_totals_all":{"GB2-01":{"draws":177,"losses":620,"wins":383},"GB2-02":{"draws":676,"losses":167,"wins":29},"GB2-03":{"draws":422,"losses":498,"wins":292},"GB2-04":{"draws":845,"losses":339,"wins":165},"GB2-05":{"draws":0,"losses":681,"wins":599},"GB2-06":{"draws":36,"losses":351,"wins":529},"GB2-07":{"draws":0,"losses":483,"wins":863},"GB2-08":{"draws":595,"losses":375,"wins":408}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":255,"wins":90},"GB2-02":{"draws":336,"losses":81,"wins":23},"GB2-03":{"draws":180,"losses":163,"wins":119},"GB2-04":{"draws":224,"losses":116,"wins":55},"GB2-05":{"draws":0,"losses":224,"wins":196},"GB2-06":{"draws":26,"losses":89,"wins":299},"GB2-07":{"draws":0,"losses":129,"wins":329},"GB2-08":{"draws":310,"losses":155,"wins":23}},"medium":{"GB2-01":{"draws":28,"losses":158,"wins":226},"GB2-02":{"draws":340,"losses":86,"wins":6},"GB2-03":{"draws":91,"losses":213,"wins":70},"GB2-04":{"draws":353,"losses":157,"wins":80},"GB2-05":{"draws":0,"losses":237,"wins":235},"GB2-06":{"draws":10,"losses":262,"wins":230},"GB2-07":{"draws":0,"losses":142,"wins":262},"GB2-08":{"draws":2,"losses":77,"wins":375}},"none":{"GB2-01":{"draws":128,"losses":207,"wins":67},"GB2-03":{"draws":151,"losses":122,"wins":103},"GB2-04":{"draws":268,"losses":66,"wins":30},"GB2-05":{"draws":0,"losses":220,"wins":168},"GB2-07":{"draws":0,"losses":212,"wins":272},"GB2-08":{"draws":283,"losses":143,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1362.8780949905085,"GB2-03":1366.0751956778786,"GB2-04":1438.2085538194406,"GB2-05":1412.3350582618066,"GB2-07":1709.5879816164015,"GB2-08":1497.7601077061117},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1212.6025857795962,"GB2-02":1431.2995002210191,"GB2-03":1435.57818413369,"GB2-04":1453.1341882475301,"GB2-05":1419.563733997392,"GB2-06":1944.2291451375534,"GB2-07":1813.251187513087,"GB2-08":1277.7440026521492},"medium":{"GB2-01":1609.9237885459781,"GB2-02":1398.5528128810201,"GB2-03":1267.3769558561785,"GB2-04":1435.150625390437,"GB2-05":1484.3983727050183,"GB2-06":1466.7061878378756,"GB2-07":1767.8063546572955,"GB2-08":1961.7507420096395},"none":{"GB2-01":1266.1079106459513,"GB2-03":1395.270447043768,"GB2-04":1426.3408478203544,"GB2-05":1333.0430680830088,"GB2-07":1547.7064026788225,"GB2-08":1253.7855784565465}},"per_game_tracks":{"highest":{"GB2-01":25.468096142290868,"GB2-02":10.014962553999606,"GB2-03":26.868011586123032,"GB2-04":15.79149388976589,"GB2-05":41.983124649723834,"GB2-06":72.94601860690389,"GB2-07":63.39200007671138,"GB2-08":18.02261584176466},"medium":{"GB2-01":50.23680734207835,"GB2-02":5.987992773130906,"GB2-03":12.618285824648789,"GB2-04":13.453076837416056,"GB2-05":45.13682947391468,"GB2-06":50.10653401114782,"GB2-07":61.03482631751219,"GB2-08":63.25530494935493},"none":{"GB2-01":28.80357869403575,"GB2-03":23.453207749795833,"GB2-04":12.307534418430672,"GB2-05":37.77456195969532,"GB2-07":49.61848261896689,"GB2-08":16.438268947514143}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.3107904184104,"medium":37.72870719115047,"none":26.11829926891026},"reasoning_agg":{"highest":{"max":72.94601860690389,"mean":34.3107904184104,"min":10.014962553999606},"medium":{"max":63.25530494935493,"mean":37.72870719115047,"min":5.987992773130906},"none":{"max":49.61848261896689,"mean":26.11829926891026,"min":12.307534418430672}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":72.94601860690389,"expected_score":32.60617036826014,"reasoning_variance":11.61040792224021,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.11309525789690866},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.94601860690389,"expected_score":25.994257576939265,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.316532841471133},"medium":{"ceiling_score":63.25530494935493,"expected_score":37.225976186393694,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.5027310047567752},"none":{"ceiling_score":49.61848261896689,"expected_score":32.24803525803386,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.129735989123599}}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:700e1a9c5451e110","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.5923719999999997},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.6420659999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.642066},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3670399999999999},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.592372}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.15006158333333333,"median":0.080065,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":3.6014779999999997},"codegen_latency_ms":{"attempt_count":28,"max_ms":255692,"mean_ms":76920.70833333333,"min_ms":12384,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":255692,"mean_ms":175619.75,"min_ms":52003,"run_count":8},"medium":{"attempt_count":8,"max_ms":58005,"mean_ms":37933.625,"min_ms":21700,"run_count":8},"none":{"attempt_count":9,"max_ms":20748,"mean_ms":17208.75,"min_ms":12384,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":36035,"output_mean":10826.541666666666,"output_min":1554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":36035,"output_mean":24993.125,"output_min":6631,"run_count":8},"medium":{"attempt_count":8,"output_max":7812,"output_mean":5238.375,"output_min":2903,"run_count":8},"none":{"attempt_count":9,"output_max":3115,"output_mean":2248.125,"output_min":1554,"run_count":8}},"display_name":"Gemini 3.1 Pro Preview","economics":{"all":32.6630960427772,"highest":49.31984674428979,"medium":28.81593303930414,"none":19.853508344737644},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[65536],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[65536],"total_output_tokens":259837,"total_reasoning_output_tokens":197903,"total_visible_output_tokens":61934,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-3.1-pro-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":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":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-10-06T15:24:16Z","match_totals_all":{"draws":1492,"losses":2517,"wins":1737},"match_totals_tracks":{"highest":{"draws":267,"losses":583,"wins":1056},"medium":{"draws":622,"losses":853,"wins":452},"none":{"draws":603,"losses":1081,"wins":229}},"model_slug":"gemini-3-1-pro-preview","overall":{"max":74.05967966028881,"mean":32.66309604277719,"min":8.450021605434541},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.324475294504126,"GB2-02":8.998879293875396,"GB2-03":40.90368136552399,"GB2-04":61.133201873284335,"GB2-05":74.05967966028881,"GB2-06":29.2436940131614,"GB2-07":60.6187215715657,"GB2-08":62.27644088211457},"per_game_all":{"GB2-01":42.09930568645952,"GB2-02":9.227559573179612,"GB2-03":31.15048078208181,"GB2-04":28.40830303009324,"GB2-05":39.416561860887974,"GB2-06":29.67976014294373,"GB2-07":48.818064210290565,"GB2-08":32.50473305628109},"per_game_match_totals_all":{"GB2-01":{"draws":99,"losses":286,"wins":223},"GB2-02":{"draws":637,"losses":162,"wins":17},"GB2-03":{"draws":114,"losses":263,"wins":243},"GB2-04":{"draws":301,"losses":141,"wins":200},"GB2-05":{"draws":0,"losses":428,"wins":258},"GB2-06":{"draws":15,"losses":606,"wins":147},"GB2-07":{"draws":0,"losses":353,"wins":389},"GB2-08":{"draws":326,"losses":278,"wins":260}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":59,"wins":132},"GB2-02":{"draws":207,"losses":58,"wins":7},"GB2-03":{"draws":9,"losses":79,"wins":122},"GB2-04":{"draws":42,"losses":16,"wins":148},"GB2-05":{"draws":0,"losses":33,"wins":193},"GB2-06":{"draws":4,"losses":208,"wins":52},"GB2-07":{"draws":0,"losses":78,"wins":170},"GB2-08":{"draws":0,"losses":52,"wins":232}},"medium":{"GB2-01":{"draws":68,"losses":105,"wins":37},"GB2-02":{"draws":220,"losses":50,"wins":8},"GB2-03":{"draws":35,"losses":69,"wins":100},"GB2-04":{"draws":125,"losses":59,"wins":31},"GB2-05":{"draws":0,"losses":190,"wins":38},"GB2-06":{"draws":9,"losses":177,"wins":64},"GB2-07":{"draws":0,"losses":86,"wins":160},"GB2-08":{"draws":165,"losses":117,"wins":14}},"none":{"GB2-01":{"draws":26,"losses":122,"wins":54},"GB2-02":{"draws":210,"losses":54,"wins":2},"GB2-03":{"draws":70,"losses":115,"wins":21},"GB2-04":{"draws":134,"losses":66,"wins":21},"GB2-05":{"draws":0,"losses":205,"wins":27},"GB2-06":{"draws":2,"losses":221,"wins":31},"GB2-07":{"draws":0,"losses":189,"wins":59},"GB2-08":{"draws":161,"losses":109,"wins":14}}},"per_game_raw_elo_all":{"GB2-01":1479.3880525827908,"GB2-02":1424.8964625458932,"GB2-03":1486.1276887963224,"GB2-04":1550.1635782799974,"GB2-05":1366.7997055257974,"GB2-06":1039.6276596538778,"GB2-07":1532.274837375231,"GB2-08":1496.741943529206},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1723.6188747760082,"GB2-02":1423.0368703426502,"GB2-03":1601.2527336731293,"GB2-04":1801.8339442428005,"GB2-05":2079.0014337919088,"GB2-06":1030.5104842203052,"GB2-07":1759.7841159248974,"GB2-08":1946.9484025485763},"medium":{"GB2-01":1333.0599724726399,"GB2-02":1433.0788716835195,"GB2-03":1588.1148644827358,"GB2-04":1442.3396648832597,"GB2-05":1044.0189680967364,"GB2-06":1140.3014587837206,"GB2-07":1694.293173361366,"GB2-08":1272.946859430844},"none":{"GB2-01":1381.4853104997246,"GB2-02":1418.57364561151,"GB2-03":1269.0154682331017,"GB2-04":1406.3171257139318,"GB2-05":977.3787146887474,"GB2-06":948.0710359576074,"GB2-07":1142.7472228394302,"GB2-08":1270.330568608199}},"per_game_tracks":{"highest":{"GB2-01":57.324475294504126,"GB2-02":8.998879293875396,"GB2-03":40.90368136552399,"GB2-04":61.133201873284335,"GB2-05":74.05967966028881,"GB2-06":29.2436940131614,"GB2-07":60.6187215715657,"GB2-08":62.27644088211457},"medium":{"GB2-01":32.97732092593629,"GB2-02":10.2337778202289,"GB2-03":39.790663137474226,"GB2-04":14.387873388779207,"GB2-05":23.715769983626092,"GB2-06":34.49489551868505,"GB2-07":57.22177803420368,"GB2-08":17.705385505499684},"none":{"GB2-01":35.99612083893815,"GB2-02":8.450021605434541,"GB2-03":12.757097843247223,"GB2-04":9.703833828216174,"GB2-05":20.474235938749025,"GB2-06":25.30069089698475,"GB2-07":28.6136930251023,"GB2-08":17.53237278122901}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.31984674428979,"medium":28.81593303930414,"none":19.853508344737644},"reasoning_agg":{"highest":{"max":74.05967966028881,"mean":49.31984674428979,"min":8.998879293875396},"medium":{"max":57.22177803420368,"mean":28.81593303930414,"min":10.2337778202289},"none":{"max":35.99612083893815,"mean":19.853508344737644,"min":8.450021605434541}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":74.05967966028881,"expected_score":29.682807685041013,"reasoning_variance":29.466338399552146,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.9802883577361783},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.05967966028881,"expected_score":41.70348138015859,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.616365364131198},"medium":{"ceiling_score":57.22177803420368,"expected_score":26.321624016169874,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.4943090231342673},"none":{"ceiling_score":35.99612083893815,"expected_score":21.023317658794575,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1698093140569306}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:db776b04924b79d2","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.1725616482799999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.98845232184},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.98845232184},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784000002},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.1725616482799999}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.3773764379599998},"codegen_latency_ms":{"attempt_count":31,"max_ms":1461124,"mean_ms":482100.7083333333,"min_ms":19301,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1461124,"mean_ms":902169.625,"min_ms":499972,"run_count":8},"medium":{"attempt_count":9,"max_ms":676490,"mean_ms":489467.75,"min_ms":326732,"run_count":8},"none":{"attempt_count":12,"max_ms":131002,"mean_ms":54664.75,"min_ms":19301,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":106197,"output_mean":33246.666666666664,"output_min":2345,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":106197,"output_mean":60744.125,"output_min":32963,"run_count":8},"medium":{"attempt_count":9,"output_max":42157,"output_mean":35085.125,"output_min":20989,"run_count":8},"none":{"attempt_count":12,"output_max":10866,"output_mean":3910.75,"output_min":2345,"run_count":8}},"display_name":"DeepSeek V4 Pro 0813","economics":{"all":34.10378534732576,"highest":39.28463662419933,"medium":31.480415312191717,"none":28.412800038114227},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:40:12Z","match_totals_all":{"draws":2854,"losses":3415,"wins":3143},"match_totals_tracks":{"highest":{"draws":1028,"losses":1097,"wins":1471},"medium":{"draws":965,"losses":1319,"wins":1156},"none":{"draws":861,"losses":999,"wins":516}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":68.47588121456921,"mean":32.40204723751882,"min":1.3159347787409597},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":41,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.208315393002856,"GB2-02":10.046329911759482,"GB2-03":41.50627676777144,"GB2-04":13.619329126464095,"GB2-05":63.67036498018146,"GB2-06":64.08217837051069,"GB2-07":68.47588121456921,"GB2-08":13.668417229335452},"per_game_all":{"GB2-01":37.47531044824347,"GB2-03":28.262351429166298,"GB2-04":9.662603142439826,"GB2-06":55.30866983230357,"GB2-07":53.71675601123943,"GB2-08":20.197021220561993},"per_game_match_totals_all":{"GB2-01":{"draws":366,"losses":452,"wins":376},"GB2-02":{"draws":658,"losses":181,"wins":29},"GB2-03":{"draws":269,"losses":508,"wins":435},"GB2-04":{"draws":739,"losses":432,"wins":187},"GB2-05":{"draws":0,"losses":272,"wins":500},"GB2-06":{"draws":45,"losses":613,"wins":704},"GB2-07":{"draws":0,"losses":495,"wins":731},"GB2-08":{"draws":777,"losses":462,"wins":181}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":172,"wins":189},"GB2-02":{"draws":353,"losses":74,"wins":15},"GB2-03":{"draws":36,"losses":140,"wins":226},"GB2-04":{"draws":324,"losses":182,"wins":106},"GB2-05":{"draws":0,"losses":99,"wins":293},"GB2-06":{"draws":17,"losses":163,"wins":318},"GB2-07":{"draws":0,"losses":84,"wins":320},"GB2-08":{"draws":285,"losses":183,"wins":4}},"medium":{"GB2-01":{"draws":266,"losses":97,"wins":87},"GB2-02":{"draws":305,"losses":107,"wins":14},"GB2-03":{"draws":58,"losses":228,"wins":156},"GB2-04":{"draws":129,"losses":171,"wins":58},"GB2-05":{"draws":0,"losses":173,"wins":207},"GB2-06":{"draws":24,"losses":260,"wins":174},"GB2-07":{"draws":0,"losses":114,"wins":304},"GB2-08":{"draws":183,"losses":169,"wins":156}},"none":{"GB2-01":{"draws":87,"losses":183,"wins":100},"GB2-03":{"draws":175,"losses":140,"wins":53},"GB2-04":{"draws":286,"losses":79,"wins":23},"GB2-06":{"draws":4,"losses":190,"wins":212},"GB2-07":{"draws":0,"losses":297,"wins":107},"GB2-08":{"draws":309,"losses":110,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1405.213367641986,"GB2-03":1452.0367236285501,"GB2-04":1406.0000417153544,"GB2-06":1575.4713077852177,"GB2-07":1626.7185453273294,"GB2-08":1310.625265352557},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1433.0129412046908,"GB2-02":1431.5545746598998,"GB2-03":1608.3656626170978,"GB2-04":1436.4291862387795,"GB2-05":1865.415349724126,"GB2-06":1758.9059087497735,"GB2-07":1911.2652298241424,"GB2-08":1211.9000023470062},"medium":{"GB2-01":1471.9454769482304,"GB2-02":1403.4400425101599,"GB2-03":1402.8414770405398,"GB2-04":1341.8101081810205,"GB2-05":1428.614875071472,"GB2-06":1332.9288575001933,"GB2-07":1815.7846612359988,"GB2-08":1436.9923829808756},"none":{"GB2-01":1310.6816847730365,"GB2-03":1344.9030312280129,"GB2-04":1439.760830726264,"GB2-06":1634.5791571056864,"GB2-07":1153.1057449218465,"GB2-08":1282.9834107297893}},"per_game_tracks":{"highest":{"GB2-01":39.208315393002856,"GB2-02":10.046329911759482,"GB2-03":41.50627676777144,"GB2-04":13.619329126464095,"GB2-05":63.67036498018146,"GB2-06":64.08217837051069,"GB2-07":68.47588121456921,"GB2-08":13.668417229335452},"medium":{"GB2-01":41.63534100198887,"GB2-02":6.588991763482898,"GB2-03":24.09461270438925,"GB2-04":1.3159347787409597,"GB2-05":42.42339281252614,"GB2-06":43.70808713272603,"GB2-07":63.523408586854195,"GB2-08":28.553553716825373},"none":{"GB2-01":31.58227494973869,"GB2-03":19.186164815338206,"GB2-04":14.052545522114425,"GB2-06":58.135743993674005,"GB2-07":29.150978232294904,"GB2-08":18.369092715525152}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.28463662419933,"medium":31.480415312191717,"none":26.441089776165416},"reasoning_agg":{"highest":{"max":68.47588121456921,"mean":39.28463662419933,"min":10.046329911759482},"medium":{"max":63.523408586854195,"mean":31.480415312191717,"min":1.3159347787409597},"none":{"max":58.135743993674005,"mean":26.441089776165416,"min":14.052545522114425}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":68.47588121456921,"expected_score":31.831200583593713,"reasoning_variance":12.843546848033913,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.5708466539251091},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.47588121456921,"expected_score":31.717575811565883,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.567060812633446},"medium":{"ceiling_score":63.523408586854195,"expected_score":29.864219517565903,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6161957946258134},"none":{"ceiling_score":58.135743993674005,"expected_score":32.733369147735395,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.292279371569979}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:7e0a049c900677df","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.030688899999999998},"none":{"admitted_cell_count":7,"cell_count":7,"cost_basis_counts":{"local_standard_estimate":7},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0030818,"mean":0.0023309607142857143,"median":0.0023213,"min":0.00161355,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":7},"run_count":7,"token_priced_attempt_count":7,"total":0.016316725}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0306889},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":7,"cost_basis_counts":{"local_standard_estimate":7},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0030818,"mean":0.0023309607142857143,"median":0.0023213,"min":0.00161355,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":7},"run_count":7,"token_priced_attempt_count":7,"total":0.016316724999999997},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":23,"cost_basis_counts":{"local_standard_estimate":23},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0061271967391304345,"median":0.0038602999999999997,"min":0.00161355,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"run_count":23,"token_priced_attempt_count":23,"total":0.14092552499999997},"codegen_output_tokens":{"attempt_count":23,"output_max":26534,"output_mean":10310.565217391304,"output_min":1431,"run_count":23},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":26534,"output_mean":21543.25,"output_min":15583,"run_count":8},"medium":{"attempt_count":8,"output_max":6895,"output_mean":5735.5,"output_min":3866,"run_count":8},"none":{"attempt_count":7,"output_max":4321,"output_mean":2701.8571428571427,"output_min":1431,"run_count":7}},"display_name":"GPT-6 Luna","economics":{"all":31.43667971169569,"highest":42.247453313839394,"medium":30.575755147959228,"none":23.565824435773447},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[65536],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":23,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[65536],"total_output_tokens":237143,"total_reasoning_output_tokens":163396,"total_visible_output_tokens":73747,"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":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":7,"first_pass_admitted":7,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-07"],"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}},"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-luna","is_recent_addition":false,"last_measured_at":"2026-10-06T16:11:02Z","match_totals_all":{"draws":1750,"losses":2710,"wins":2396},"match_totals_tracks":{"highest":{"draws":479,"losses":1104,"wins":1604},"medium":{"draws":610,"losses":785,"wins":487},"none":{"draws":661,"losses":821,"wins":305}},"model_slug":"gpt-6-luna","overall":{"max":79.89700625199762,"mean":32.12967763252403,"min":9.657819102318886},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":29.80362482721765,"GB2-02":28.33704183660564,"GB2-03":26.737840848721905,"GB2-04":34.20787494379666,"GB2-05":49.087409708993604,"GB2-06":79.89700625199762,"GB2-07":38.99051049363306,"GB2-08":50.918317599749},"per_game_all":{"GB2-01":29.61323111506682,"GB2-02":16.215245652904652,"GB2-03":26.579204412896868,"GB2-04":21.652770028386914,"GB2-05":47.54080592923685,"GB2-06":50.08710312061266,"GB2-08":28.36839772276508},"per_game_match_totals_all":{"GB2-01":{"draws":96,"losses":525,"wins":197},"GB2-02":{"draws":642,"losses":126,"wins":132},"GB2-03":{"draws":97,"losses":379,"wins":302},"GB2-04":{"draws":432,"losses":165,"wins":215},"GB2-05":{"draws":0,"losses":394,"wins":472},"GB2-06":{"draws":42,"losses":397,"wins":461},"GB2-07":{"draws":0,"losses":373,"wins":279},"GB2-08":{"draws":441,"losses":351,"wins":338}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":290,"wins":123},"GB2-02":{"draws":218,"losses":25,"wins":117},"GB2-03":{"draws":19,"losses":193,"wins":168},"GB2-04":{"draws":186,"losses":45,"wins":152},"GB2-05":{"draws":0,"losses":176,"wins":244},"GB2-06":{"draws":22,"losses":40,"wins":334},"GB2-07":{"draws":0,"losses":250,"wins":160},"GB2-08":{"draws":33,"losses":85,"wins":306}},"medium":{"GB2-01":{"draws":71,"losses":86,"wins":45},"GB2-02":{"draws":219,"losses":47,"wins":6},"GB2-03":{"draws":39,"losses":87,"wins":74},"GB2-04":{"draws":114,"losses":58,"wins":38},"GB2-05":{"draws":0,"losses":99,"wins":119},"GB2-06":{"draws":16,"losses":162,"wins":78},"GB2-07":{"draws":0,"losses":123,"wins":119},"GB2-08":{"draws":151,"losses":123,"wins":8}},"none":{"GB2-01":{"draws":24,"losses":149,"wins":29},"GB2-02":{"draws":205,"losses":54,"wins":9},"GB2-03":{"draws":39,"losses":99,"wins":60},"GB2-04":{"draws":132,"losses":62,"wins":25},"GB2-05":{"draws":0,"losses":119,"wins":109},"GB2-06":{"draws":4,"losses":195,"wins":49},"GB2-08":{"draws":257,"losses":143,"wins":24}}},"per_game_raw_elo_all":{"GB2-01":1279.0957512789164,"GB2-02":1481.7192309634545,"GB2-03":1432.1691556313078,"GB2-04":1498.210248463457,"GB2-05":1533.819911381341,"GB2-06":1466.299931020984,"GB2-08":1434.1924621654578},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1282.1499052920478,"GB2-02":1580.291778369365,"GB2-03":1434.0416719029877,"GB2-04":1594.7651030377438,"GB2-05":1565.6153719188078,"GB2-06":2089.5588771865614,"GB2-07":1342.8057605658323,"GB2-08":1775.1913607969377},"medium":{"GB2-01":1391.4509997910677,"GB2-02":1436.4706488942586,"GB2-03":1455.5385770517182,"GB2-04":1469.068888364905,"GB2-05":1542.6379794891216,"GB2-06":1244.9796105729251,"GB2-07":1523.9382453997957,"GB2-08":1232.9181377625885},"none":{"GB2-01":1163.6863487536339,"GB2-02":1428.3952656267397,"GB2-03":1406.9272179392171,"GB2-04":1430.7967539877225,"GB2-05":1493.2063827360935,"GB2-06":1064.3613053034658,"GB2-08":1294.4678879368466}},"per_game_tracks":{"highest":{"GB2-01":29.80362482721765,"GB2-02":28.33704183660564,"GB2-03":26.737840848721905,"GB2-04":34.20787494379666,"GB2-05":49.087409708993604,"GB2-06":79.89700625199762,"GB2-07":38.99051049363306,"GB2-08":50.918317599749},"medium":{"GB2-01":36.617374570794055,"GB2-02":10.650876019789434,"GB2-03":28.55902257389002,"GB2-04":17.863495682439204,"GB2-05":47.96973689092477,"GB2-06":39.50155540540829,"GB2-07":48.38565430556048,"GB2-08":15.058325734867568},"none":{"GB2-01":22.418693947188764,"GB2-02":9.657819102318886,"GB2-03":24.440749816078675,"GB2-04":12.886939458924887,"GB2-05":45.56527118779216,"GB2-06":30.862747704432092,"GB2-08":19.128549833678683}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.247453313839394,"medium":30.575755147959228,"none":23.565824435773447},"reasoning_agg":{"highest":{"max":79.89700625199762,"mean":42.247453313839394,"min":26.737840848721905},"medium":{"max":48.38565430556048,"mean":30.575755147959228,"min":10.650876019789434},"none":{"max":45.56527118779216,"mean":23.565824435773447,"min":9.657819102318886}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.89700625199762,"expected_score":29.1396095316833,"reasoning_variance":18.681628878065947,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.9900681008407304},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.89700625199762,"expected_score":34.712820443229425,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.534632870609968},"medium":{"ceiling_score":48.38565430556048,"expected_score":28.684219472121782,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8915356758374458},"none":{"ceiling_score":45.56527118779216,"expected_score":26.09177774034173,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.525953304568283}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:142785f117a901df","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"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},"cost_is_complete":true,"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},"cost_is_complete":true,"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},"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.045896320000000004,"mean":0.021958409999999998,"median":0.019045885,"min":0.011539076,"recorded_attempt_count":15,"run_count":8,"total":0.17566728},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":24,"cost_basis_counts":{"provider_reported":41},"cost_is_complete":true,"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":46.87610100445917,"medium":37.249275418414804,"none":18.609442688258305},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:44:56Z","match_totals_all":{"draws":1262,"losses":2258,"wins":2388},"match_totals_tracks":{"highest":{"draws":377,"losses":938,"wins":1417},"medium":{"draws":359,"losses":1073,"wins":852},"none":{"draws":526,"losses":247,"wins":119}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":66.17036751360885,"mean":30.809969428634588,"min":14.562675897575328},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","generation_incomplete"],"overall_official_rank":43,"overall_ranking_status":"partial","per_game":{"GB2-01":59.3297797384975,"GB2-04":43.449377995527605,"GB2-05":50.759573570676416,"GB2-06":35.61009653210012,"GB2-07":66.17036751360885,"GB2-08":25.93741067634455},"per_game_match_totals_all":{"GB2-01":{"draws":211,"losses":196,"wins":335},"GB2-03":{"draws":147,"losses":260,"wins":222},"GB2-04":{"draws":411,"losses":180,"wins":387},"GB2-05":{"draws":0,"losses":358,"wins":456},"GB2-06":{"draws":30,"losses":507,"wins":398},"GB2-07":{"draws":0,"losses":415,"wins":413},"GB2-08":{"draws":463,"losses":342,"wins":177}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":101,"wins":267},"GB2-04":{"draws":166,"losses":83,"wins":301},"GB2-05":{"draws":0,"losses":175,"wins":259},"GB2-06":{"draws":19,"losses":292,"wins":131},"GB2-07":{"draws":0,"losses":95,"wins":315},"GB2-08":{"draws":182,"losses":192,"wins":144}},"medium":{"GB2-01":{"draws":201,"losses":95,"wins":68},"GB2-03":{"draws":147,"losses":260,"wins":222},"GB2-05":{"draws":0,"losses":183,"wins":197},"GB2-06":{"draws":11,"losses":215,"wins":267},"GB2-07":{"draws":0,"losses":320,"wins":98}},"none":{"GB2-04":{"draws":245,"losses":97,"wins":86},"GB2-08":{"draws":281,"losses":150,"wins":33}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1755.78647393664,"GB2-04":1665.8367499271706,"GB2-05":1599.9921274732753,"GB2-06":1163.617838086278,"GB2-07":1866.8163705162585,"GB2-08":1397.4311827489885},"medium":{"GB2-01":1375.9370501971086,"GB2-03":1440.4854396464555,"GB2-05":1408.2093505308953,"GB2-06":1565.704012673522,"GB2-07":1112.4084502225417},"none":{"GB2-04":1481.4667871363713,"GB2-08":1273.5199135463047}},"per_game_tracks":{"highest":{"GB2-01":59.3297797384975,"GB2-04":43.449377995527605,"GB2-05":50.759573570676416,"GB2-06":35.61009653210012,"GB2-07":66.17036751360885,"GB2-08":25.93741067634455},"medium":{"GB2-01":35.65024637731889,"GB2-03":27.283746037140354,"GB2-05":41.4308215193635,"GB2-06":54.841509075243295,"GB2-07":27.040054083007984},"none":{"GB2-04":19.47560436918194,"GB2-08":17.743281007334666}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.62312737051051,"medium":34.24410501781791,"none":14.562675897575328},"reasoning_agg":{"highest":{"max":66.17036751360885,"mean":43.62312737051051,"min":25.93741067634455},"medium":{"max":54.841509075243295,"mean":34.24410501781791,"min":27.040054083007984},"none":{"max":19.47560436918194,"mean":14.562675897575328,"min":17.743281007334666}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":66.17036751360885,"reasoning_variance":29.06045147293518},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.17036751360885,"expected_score":38.48668514586403,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.13644222464648},"medium":{"ceiling_score":54.841509075243295,"expected_score":34.62036646055716,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.3762614427392492},"none":{"ceiling_score":19.47560436918194,"expected_score":26.986906485391607,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":12.424230587816279}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:b29e4d9c6bf2b87d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.4205012499999998},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.779305}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.779305},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561124999999995}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-08-08":19},"run_count":24,"token_priced_attempt_count":31,"total":4.45591875},"codegen_latency_ms":{"attempt_count":19,"max_ms":452838,"mean_ms":201000.75,"min_ms":115295,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":452838,"mean_ms":260996.125,"min_ms":140461,"run_count":8},"medium":{"attempt_count":9,"max_ms":181508,"mean_ms":141005.375,"min_ms":115295,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43637,"output_mean":21815.875,"output_min":13286,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43637,"output_mean":26965.5,"output_min":16148,"run_count":8},"medium":{"attempt_count":9,"output_max":19618,"output_mean":16666.25,"output_min":13286,"run_count":8}},"display_name":"GPT-5","economics":{"all":33.8803350209102,"highest":34.14850741163173,"medium":31.5356057504977,"none":28.21082001262157},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":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":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":2,"repaired_rate":0.25},"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":"2026-10-06T09:08:25Z","match_totals_all":{"draws":2195,"losses":2683,"wins":2220},"match_totals_tracks":{"highest":{"draws":919,"losses":940,"wins":953},"medium":{"draws":649,"losses":1002,"wins":809},"none":{"draws":627,"losses":741,"wins":458}},"model_slug":"gpt-5","overall":{"max":68.05172645872983,"mean":30.30062298794242,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","fixed_coverage_incomplete"],"overall_official_rank":44,"overall_ranking_status":"partial","per_game":{"GB2-01":37.594458241599234,"GB2-02":8.406753942516927,"GB2-03":17.878883189703075,"GB2-04":9.318841859600548,"GB2-05":61.3121056192947,"GB2-06":68.05172645872983,"GB2-07":50.58968277423404,"GB2-08":20.03560720737554},"per_game_all":{"GB2-01":38.14415197925684,"GB2-03":10.017565470665177,"GB2-05":53.24332327467522,"GB2-07":49.15716554520791,"GB2-08":18.839468834745883},"per_game_match_totals_all":{"GB2-01":{"draws":116,"losses":430,"wins":312},"GB2-02":{"draws":634,"losses":163,"wins":21},"GB2-03":{"draws":249,"losses":438,"wins":107},"GB2-04":{"draws":446,"losses":170,"wins":66},"GB2-05":{"draws":0,"losses":322,"wins":552},"GB2-06":{"draws":33,"losses":259,"wins":442},"GB2-07":{"draws":0,"losses":474,"wins":620},"GB2-08":{"draws":717,"losses":427,"wins":100}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":43,"losses":152,"wins":133},"GB2-02":{"draws":305,"losses":69,"wins":16},"GB2-03":{"draws":102,"losses":146,"wins":58},"GB2-04":{"draws":225,"losses":83,"wins":18},"GB2-05":{"draws":0,"losses":89,"wins":213},"GB2-06":{"draws":12,"losses":89,"wins":243},"GB2-07":{"draws":0,"losses":154,"wins":222},"GB2-08":{"draws":232,"losses":158,"wins":50}},"medium":{"GB2-01":{"draws":45,"losses":219,"wins":52},"GB2-03":{"draws":105,"losses":126,"wins":31},"GB2-04":{"draws":221,"losses":87,"wins":48},"GB2-05":{"draws":0,"losses":105,"wins":203},"GB2-06":{"draws":21,"losses":170,"wins":199},"GB2-07":{"draws":0,"losses":136,"wins":258},"GB2-08":{"draws":257,"losses":159,"wins":18}},"none":{"GB2-01":{"draws":28,"losses":59,"wins":127},"GB2-02":{"draws":329,"losses":94,"wins":5},"GB2-03":{"draws":42,"losses":166,"wins":18},"GB2-05":{"draws":0,"losses":128,"wins":136},"GB2-07":{"draws":0,"losses":184,"wins":140},"GB2-08":{"draws":228,"losses":110,"wins":32}}},"per_game_raw_elo_all":{"GB2-01":1415.9424249360375,"GB2-03":1236.6785153901137,"GB2-05":1651.0536641978651,"GB2-07":1538.8124986003968,"GB2-08":1290.0964177591638},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1407.1246477316613,"GB2-02":1418.221799755545,"GB2-03":1329.4721114463186,"GB2-04":1403.3563504920278,"GB2-05":1816.9336743088622,"GB2-06":1841.900353492275,"GB2-07":1566.4305330291575,"GB2-08":1308.1843697298436},"medium":{"GB2-01":1130.6138587727305,"GB2-03":1262.130480316687,"GB2-04":1429.9830054317704,"GB2-05":1656.78723441878,"GB2-06":1480.8928632458615,"GB2-07":1655.9419602950393,"GB2-08":1245.6079612611836},"none":{"GB2-01":1710.088768303721,"GB2-02":1395.8341955192768,"GB2-03":1118.4329544073353,"GB2-05":1479.4400838659535,"GB2-07":1394.0650024769943,"GB2-08":1316.496922286464}},"per_game_tracks":{"highest":{"GB2-01":37.594458241599234,"GB2-02":8.406753942516927,"GB2-03":17.878883189703075,"GB2-04":9.318841859600548,"GB2-05":61.3121056192947,"GB2-06":68.05172645872983,"GB2-07":50.58968277423404,"GB2-08":20.03560720737554},"medium":{"GB2-01":20.35697927580609,"GB2-03":12.173813222292459,"GB2-04":12.78112708377516,"GB2-05":53.52221721819015,"GB2-06":50.785069669994364,"GB2-07":55.23254257237973,"GB2-08":15.897491211045946},"none":{"GB2-01":56.48101842036519,"GB2-02":5.653675293997283,"GB2-03":0.0,"GB2-05":44.895646986540825,"GB2-07":41.649271289009974,"GB2-08":20.58530808581616}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.14850741163173,"medium":30.500235369195128,"none":26.253126183000386},"reasoning_agg":{"highest":{"max":68.05172645872983,"mean":34.14850741163173,"min":8.406753942516927},"medium":{"max":55.23254257237973,"mean":30.500235369195128,"min":12.173813222292459},"none":{"max":56.48101842036519,"mean":26.253126183000386,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":68.05172645872983,"expected_score":32.11262471679178,"reasoning_variance":7.895381228631347,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.81200172884936},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.05172645872983,"expected_score":25.798077610806335,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.350429800825399},"medium":{"ceiling_score":55.23254257237973,"expected_score":30.000961348558405,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.4992740206367223},"none":{"ceiling_score":56.48101842036519,"expected_score":31.495142069931205,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.242015886930819}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:6fafe856221ab012","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.72882375},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999998},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":31.948730148684337,"none":30.480550506642288},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:31:42Z","match_totals_all":{"draws":1720,"losses":2040,"wins":1521},"match_totals_tracks":{"medium":{"draws":917,"losses":968,"wins":836},"none":{"draws":803,"losses":1072,"wins":685}},"model_slug":"qwen-qwen3-7-max","overall":{"max":65.68350523356004,"mean":30.18980781567754,"min":9.720253436630065},"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":176,"losses":307,"wins":195},"GB2-02":{"draws":606,"losses":131,"wins":61},"GB2-03":{"draws":155,"losses":120,"wins":21},"GB2-04":{"draws":202,"losses":97,"wins":68},"GB2-05":{"draws":0,"losses":398,"wins":324},"GB2-06":{"draws":42,"losses":419,"wins":297},"GB2-07":{"draws":0,"losses":227,"wins":519},"GB2-08":{"draws":539,"losses":341,"wins":36}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":82,"losses":237,"wins":45},"GB2-02":{"draws":326,"losses":68,"wins":18},"GB2-04":{"draws":202,"losses":97,"wins":68},"GB2-05":{"draws":0,"losses":189,"wins":167},"GB2-06":{"draws":39,"losses":138,"wins":211},"GB2-07":{"draws":0,"losses":74,"wins":302},"GB2-08":{"draws":268,"losses":165,"wins":25}},"none":{"GB2-01":{"draws":94,"losses":70,"wins":150},"GB2-02":{"draws":280,"losses":63,"wins":43},"GB2-03":{"draws":155,"losses":120,"wins":21},"GB2-05":{"draws":0,"losses":209,"wins":157},"GB2-06":{"draws":3,"losses":281,"wins":86},"GB2-07":{"draws":0,"losses":153,"wins":217},"GB2-08":{"draws":271,"losses":176,"wins":11}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1129.2678048829903,"GB2-02":1428.9029718515746,"GB2-04":1439.0011595179828,"GB2-05":1404.7123667842025,"GB2-06":1570.9125980863187,"GB2-07":1857.429970869537,"GB2-08":1272.247976292666},"none":{"GB2-01":1656.152026444578,"GB2-02":1444.5456145299472,"GB2-03":1288.5603005887963,"GB2-05":1354.4932248981681,"GB2-06":981.8900115600828,"GB2-07":1604.7907017980542,"GB2-08":1245.2357359628932}},"per_game_tracks":{"medium":{"GB2-01":20.27306726753119,"GB2-02":9.720253436630065,"GB2-04":13.953764867705717,"GB2-05":41.26072024739073,"GB2-06":55.090630933119954,"GB2-07":65.68350523356004,"GB2-08":17.659169054852672},"none":{"GB2-01":53.11864165097815,"GB2-02":11.64388157967555,"GB2-03":14.4129032376236,"GB2-05":38.817946551266445,"GB2-06":26.91822144815415,"GB2-07":52.5793827585519,"GB2-08":15.872876320246233}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.89979615395191,"none":29.47981947740317},"reasoning_agg":{"medium":{"max":65.68350523356004,"mean":30.89979615395191,"min":9.720253436630065},"none":{"max":53.11864165097815,"mean":29.47981947740317,"min":11.64388157967555}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":65.68350523356004,"reasoning_variance":1.4199766765487425},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":65.68350523356004,"expected_score":31.17949319165364,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.27969703770173027},"none":{"ceiling_score":53.11864165097815,"expected_score":33.38020167650696,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.900382199103788}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:50a525899769c3c6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303000003},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14635563000000001,"mean":0.0939111476625,"median":0.10304704349999999,"min":0.032703412,"recorded_attempt_count":26,"run_count":16,"total":1.5025783626000002},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666666,"min":0.013816857666666666,"recorded_attempt_count":37,"run_count":24,"total":0.5651094239}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23894740000000003,"mean":0.121926546075,"median":0.109979,"min":0.0289264146,"recorded_attempt_count":10,"run_count":8,"total":0.9754123685999999},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.2059380435},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.09944282164861112,"median":0.056673037849999996,"min":0.013816857666666666,"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":30.052786621434617,"highest":29.744753052060094,"medium":33.25153911802924,"none":27.162067694214514},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:47:17Z","match_totals_all":{"draws":5915,"losses":6997,"wins":5141},"match_totals_tracks":{"highest":{"draws":1014,"losses":1401,"wins":918},"medium":{"draws":2095,"losses":2014,"wins":1859},"none":{"draws":2806,"losses":3582,"wins":2364}},"model_slug":"z-ai-glm-5-2","overall":{"max":73.30909787004411,"mean":30.052786621434617,"min":7.2905647261160285},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":46,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.87521916266144,"GB2-02":26.982611533604377,"GB2-03":20.390674230177815,"GB2-04":22.463280615755806,"GB2-05":49.9377250820058,"GB2-06":43.74242882403986,"GB2-07":14.130503246900673,"GB2-08":15.435581721335017},"per_game_all":{"GB2-01":36.08564926017006,"GB2-02":16.19142599026765,"GB2-03":17.609930238619526,"GB2-04":16.499792276271634,"GB2-05":43.080782133380715,"GB2-06":54.21853363143439,"GB2-07":37.551988068178886,"GB2-08":19.184191373154096},"per_game_match_totals_all":{"GB2-01":{"draws":613,"losses":934,"wins":539},"GB2-02":{"draws":1792,"losses":367,"wins":237},"GB2-03":{"draws":814,"losses":802,"wins":282},"GB2-04":{"draws":1182,"losses":542,"wins":355},"GB2-05":{"draws":0,"losses":1161,"wins":981},"GB2-06":{"draws":127,"losses":918,"wins":1229},"GB2-07":{"draws":0,"losses":1341,"wins":1125},"GB2-08":{"draws":1387,"losses":932,"wins":393}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":174,"losses":136,"wins":178},"GB2-02":{"draws":200,"losses":63,"wins":141},"GB2-03":{"draws":168,"losses":141,"wins":69},"GB2-04":{"draws":144,"losses":118,"wins":111},"GB2-05":{"draws":0,"losses":179,"wins":199},"GB2-06":{"draws":21,"losses":224,"wins":177},"GB2-07":{"draws":0,"losses":375,"wins":39},"GB2-08":{"draws":307,"losses":165,"wins":4}},"medium":{"GB2-01":{"draws":222,"losses":262,"wins":174},"GB2-02":{"draws":598,"losses":112,"wins":88},"GB2-03":{"draws":317,"losses":284,"wins":31},"GB2-04":{"draws":404,"losses":169,"wins":111},"GB2-05":{"draws":0,"losses":348,"wins":410},"GB2-06":{"draws":34,"losses":148,"wins":564},"GB2-07":{"draws":0,"losses":309,"wins":471},"GB2-08":{"draws":520,"losses":382,"wins":10}},"none":{"GB2-01":{"draws":217,"losses":536,"wins":187},"GB2-02":{"draws":994,"losses":192,"wins":8},"GB2-03":{"draws":329,"losses":377,"wins":182},"GB2-04":{"draws":634,"losses":255,"wins":133},"GB2-05":{"draws":0,"losses":634,"wins":372},"GB2-06":{"draws":72,"losses":546,"wins":488},"GB2-07":{"draws":0,"losses":657,"wins":615},"GB2-08":{"draws":560,"losses":385,"wins":379}}},"per_game_raw_elo_all":{"GB2-01":1382.9214586997143,"GB2-02":1481.525533198792,"GB2-03":1326.2974386506203,"GB2-04":1458.5813468467647,"GB2-05":1442.1296462640466,"GB2-06":1552.6789781108773,"GB2-07":1315.0719497133466,"GB2-08":1295.3092968546068},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1523.9171874353713,"GB2-02":1569.2777633482156,"GB2-03":1359.120846113658,"GB2-04":1504.4434685298438,"GB2-05":1583.096364297646,"GB2-06":1333.6468660842356,"GB2-07":863.5204004126074,"GB2-08":1238.6229862316438},"medium":{"GB2-01":1371.9921878521782,"GB2-02":1466.1537123235107,"GB2-03":1267.7484820652564,"GB2-04":1451.279686458593,"GB2-05":1527.0316180773561,"GB2-06":1951.8203270988624,"GB2-07":1631.8662747494643,"GB2-08":1210.9153539749336},"none":{"GB2-01":1252.8550008115933,"GB2-02":1409.145123924649,"GB2-03":1352.0229877729464,"GB2-04":1420.0208855518567,"GB2-05":1216.2609564171378,"GB2-06":1372.569741149534,"GB2-07":1449.8291739779684,"GB2-08":1436.3895503572435}},"per_game_tracks":{"highest":{"GB2-01":44.87521916266144,"GB2-02":26.982611533604377,"GB2-03":20.390674230177815,"GB2-04":22.463280615755806,"GB2-05":49.9377250820058,"GB2-06":43.74242882403986,"GB2-07":14.130503246900673,"GB2-08":15.435581721335017},"medium":{"GB2-01":35.40432656366637,"GB2-02":14.301101711082547,"GB2-03":12.649760901536016,"GB2-04":15.550351539869766,"GB2-05":47.21060784735441,"GB2-06":73.30909787004411,"GB2-07":53.98376310425305,"GB2-08":13.603303406427669},"none":{"GB2-01":27.97740205418236,"GB2-02":7.2905647261160285,"GB2-03":19.789355584144744,"GB2-04":11.485744673189327,"GB2-05":32.094013470781945,"GB2-06":45.60407420021919,"GB2-07":44.54169785338293,"GB2-08":28.5136889916996}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.744753052060094,"medium":33.25153911802924,"none":27.162067694214514},"reasoning_agg":{"highest":{"max":49.9377250820058,"mean":29.744753052060094,"min":14.130503246900673},"medium":{"max":73.30909787004411,"mean":33.25153911802924,"min":12.649760901536016},"none":{"max":45.60407420021919,"mean":27.162067694214514,"min":7.2905647261160285}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":73.30909787004411,"expected_score":27.787032165525336,"reasoning_variance":6.089471423814729,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.2657544559092813},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.9377250820058,"expected_score":19.71553963784743,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.029213414212663},"medium":{"ceiling_score":73.30909787004411,"expected_score":33.43935982290526,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.18782070487601743},"none":{"ceiling_score":45.60407420021919,"expected_score":30.206197035823305,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.044129341608791}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:ffefb72279541bdb","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","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":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","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":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.2996388,"mean":0.08320818615,"median":0.048126608099999996,"min":0.0057139812,"recorded_attempt_count":28,"run_count":16,"total":1.3313309784},"codegen_latency_ms":{"attempt_count":28,"max_ms":2144825,"mean_ms":691475.625,"min_ms":43161,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":11,"max_ms":886851,"mean_ms":223216.625,"min_ms":43161,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":131072,"output_mean":41065.3125,"output_min":2846,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":11,"output_max":42691,"output_mean":10871.125,"output_min":2846,"run_count":8}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":36.954772920486796,"none":26.015558948966554},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["error","length","stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":657045},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":true,"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":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":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-06T16:17:55Z","match_totals_all":{"draws":1323,"losses":2442,"wins":1687},"match_totals_tracks":{"medium":{"draws":506,"losses":996,"wins":960},"none":{"draws":817,"losses":1446,"wins":727}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":65.41759625194916,"mean":29.775856415561474,"min":5.871991797890446},"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":47,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":155,"losses":313,"wins":404},"GB2-02":{"draws":354,"losses":111,"wins":25},"GB2-03":{"draws":131,"losses":131,"wins":40},"GB2-04":{"draws":179,"losses":85,"wins":80},"GB2-05":{"draws":0,"losses":655,"wins":241},"GB2-06":{"draws":9,"losses":349,"wins":426},"GB2-07":{"draws":0,"losses":504,"wins":462},"GB2-08":{"draws":495,"losses":294,"wins":9}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":59,"losses":146,"wins":313},"GB2-04":{"draws":179,"losses":85,"wins":80},"GB2-05":{"draws":0,"losses":247,"wins":103},"GB2-06":{"draws":4,"losses":117,"wins":285},"GB2-07":{"draws":0,"losses":231,"wins":177},"GB2-08":{"draws":264,"losses":170,"wins":2}},"none":{"GB2-01":{"draws":96,"losses":167,"wins":91},"GB2-02":{"draws":354,"losses":111,"wins":25},"GB2-03":{"draws":131,"losses":131,"wins":40},"GB2-05":{"draws":0,"losses":408,"wins":138},"GB2-06":{"draws":5,"losses":232,"wins":141},"GB2-07":{"draws":0,"losses":273,"wins":285},"GB2-08":{"draws":231,"losses":124,"wins":7}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1703.457163250562,"GB2-04":1469.332241194693,"GB2-05":1143.2558944792809,"GB2-06":1786.8265342482082,"GB2-07":1343.301346759543,"GB2-08":1228.8090518434801},"none":{"GB2-01":1319.5094884546966,"GB2-02":1397.6095111246025,"GB2-03":1300.6110569895654,"GB2-05":1097.5562787476076,"GB2-06":1254.2561314535683,"GB2-07":1469.4172938592078,"GB2-08":1259.9754942267957}},"per_game_tracks":{"medium":{"GB2-01":56.06760904475397,"GB2-04":17.897739661391252,"GB2-05":28.5428806101204,"GB2-06":65.41759625194916,"GB2-07":39.01621600728174,"GB2-08":14.786595947424255},"none":{"GB2-01":32.13259373060683,"GB2-02":5.871991797890446,"GB2-03":15.433823094677045,"GB2-05":26.31994698282631,"GB2-06":39.94524288161626,"GB2-07":45.55771220033021,"GB2-08":16.847601954818796}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.3902912468197,"none":25.16142158430325},"reasoning_agg":{"medium":{"max":65.41759625194916,"mean":34.3902912468197,"min":14.786595947424255},"none":{"max":45.55771220033021,"mean":25.16142158430325,"min":5.871991797890446}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":65.41759625194916,"reasoning_variance":9.228869662516452},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":65.41759625194916,"expected_score":36.843843838685615,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.4535525918659147},"none":{"ceiling_score":45.55771220033021,"expected_score":27.289671041412483,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1282494571092343}}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:4dc2ad4e206ba4e8","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840574999999999,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840574999999999,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":19,"max":0.17217,"mean":0.08358424999999998,"median":0.08653749999999999,"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":4.2016860000000005},"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":36.295891618339105,"highest":37.98179970185385,"medium":36.36851261414102,"none":26.323797625677205},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:43:25Z","match_totals_all":{"draws":2383,"losses":7233,"wins":5816},"match_totals_tracks":{"highest":{"draws":1203,"losses":5075,"wins":4574},"medium":{"draws":580,"losses":889,"wins":857},"none":{"draws":600,"losses":1269,"wins":385}},"model_slug":"o3","overall":{"max":52.06284266061985,"mean":29.773711503819175,"min":9.457259962016074},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":48,"overall_ranking_status":"partial","per_game":{"GB2-01":49.56339951999929,"GB2-03":17.947183390710805,"GB2-05":44.43149014509311,"GB2-06":45.223357080244256,"GB2-07":41.60052010693522,"GB2-08":29.124847968140447},"per_game_all":{"GB2-01":35.97562487009177,"GB2-06":40.28407821210249,"GB2-07":44.80457097826462,"GB2-08":24.119292412897533},"per_game_match_totals_all":{"GB2-01":{"draws":427,"losses":1132,"wins":973},"GB2-03":{"draws":151,"losses":233,"wins":112},"GB2-04":{"draws":260,"losses":73,"wins":19},"GB2-05":{"draws":0,"losses":1208,"wins":1279},"GB2-06":{"draws":149,"losses":1910,"wins":1262},"GB2-07":{"draws":0,"losses":1784,"wins":1586},"GB2-08":{"draws":1396,"losses":893,"wins":585}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":208,"losses":630,"wins":816},"GB2-03":{"draws":151,"losses":233,"wins":112},"GB2-05":{"draws":0,"losses":1013,"wins":1094},"GB2-06":{"draws":48,"losses":1315,"wins":1010},"GB2-07":{"draws":0,"losses":1341,"wins":1087},"GB2-08":{"draws":796,"losses":543,"wins":455}},"medium":{"GB2-01":{"draws":63,"losses":144,"wins":123},"GB2-04":{"draws":260,"losses":73,"wins":19},"GB2-05":{"draws":0,"losses":195,"wins":185},"GB2-06":{"draws":30,"losses":189,"wins":187},"GB2-07":{"draws":0,"losses":149,"wins":239},"GB2-08":{"draws":227,"losses":139,"wins":104}},"none":{"GB2-01":{"draws":156,"losses":358,"wins":34},"GB2-06":{"draws":71,"losses":406,"wins":65},"GB2-07":{"draws":0,"losses":294,"wins":260},"GB2-08":{"draws":373,"losses":211,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1381.1565294449408,"GB2-06":1261.3404265642146,"GB2-07":1454.8972030852444,"GB2-08":1369.9376781689564},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1599.1214822143093,"GB2-03":1330.2783148703986,"GB2-05":1469.8978334663282,"GB2-06":1364.6097907284625,"GB2-07":1393.1251102385613,"GB2-08":1445.6314695743395},"medium":{"GB2-01":1412.2157192863774,"GB2-04":1404.4208529266332,"GB2-05":1461.2416059825493,"GB2-06":1448.153568111337,"GB2-07":1594.8321324213905,"GB2-08":1391.5656748972874},"none":{"GB2-01":1132.1323868341356,"GB2-06":971.2579208528447,"GB2-07":1376.7343665957815,"GB2-08":1272.6158900352425}},"per_game_tracks":{"highest":{"GB2-01":49.56339951999929,"GB2-03":17.947183390710805,"GB2-05":44.43149014509311,"GB2-06":45.223357080244256,"GB2-07":41.60052010693522,"GB2-08":29.124847968140447},"medium":{"GB2-01":37.91183189334055,"GB2-04":9.457259962016074,"GB2-05":44.01043148078879,"GB2-06":49.21917924426637,"GB2-07":52.06284266061985,"GB2-08":25.549530443814472},"none":{"GB2-01":20.45164319693549,"GB2-06":26.409698311796845,"GB2-07":40.75035016723881,"GB2-08":17.68349882673768}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.34083289512571,"medium":33.84471455703563,"none":22.135587059296203},"reasoning_agg":{"highest":{"max":49.56339951999929,"mean":33.34083289512571,"min":17.947183390710805},"medium":{"max":52.06284266061985,"mean":33.84471455703563,"min":9.457259962016074},"none":{"max":40.75035016723881,"mean":22.135587059296203,"min":17.68349882673768}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":52.06284266061985,"expected_score":31.167936514642065,"reasoning_variance":11.709127497739427,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3942250108228897},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.56339951999929,"expected_score":27.03681165899722,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.304021236128488},"medium":{"ceiling_score":52.06284266061985,"expected_score":35.23271921905095,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3880046620153195},"none":{"ceiling_score":40.75035016723881,"expected_score":24.40241272658171,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.266825667285506}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:7be2c8576cd6d2e6","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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},"cost_is_complete":false,"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":1.2830031540000002},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":30.56339740809739},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T09:14:07Z","match_totals_all":{"draws":638,"losses":871,"wins":928},"match_totals_tracks":{"medium":{"draws":638,"losses":871,"wins":928}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":47.16776838954384,"mean":28.442446138643948,"min":8.409509482210199},"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":49,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":9,"losses":181,"wins":141},"GB2-02":{"draws":325,"losses":74,"wins":17},"GB2-04":{"draws":240,"losses":88,"wins":24},"GB2-05":{"draws":0,"losses":165,"wins":211},"GB2-07":{"draws":0,"losses":213,"wins":183},"GB2-08":{"draws":64,"losses":150,"wins":352}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":9,"losses":181,"wins":141},"GB2-02":{"draws":325,"losses":74,"wins":17},"GB2-04":{"draws":240,"losses":88,"wins":24},"GB2-05":{"draws":0,"losses":165,"wins":211},"GB2-07":{"draws":0,"losses":213,"wins":183},"GB2-08":{"draws":64,"losses":150,"wins":352}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1372.6618313639342,"GB2-02":1418.2442073726115,"GB2-04":1396.93650997793,"GB2-05":1526.1509139771265,"GB2-07":1378.6356878698211,"GB2-08":1655.8138432304706}},"per_game_tracks":{"medium":{"GB2-01":35.446071647075,"GB2-02":8.409509482210199,"GB2-04":8.484064866252345,"GB2-05":47.16776838954384,"GB2-07":40.848969621494376,"GB2-08":43.02400044200861}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":28.442446138643948},"reasoning_agg":{"medium":{"max":47.16776838954384,"mean":28.442446138643948,"min":8.409509482210199}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":47.16776838954384},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":47.16776838954384,"expected_score":31.24921914565032,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.8067730070063703}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:f5683b7fa659b0de","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.24666659999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"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}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054444999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"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":0.33399885000000007},"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":28.394262491749128,"highest":38.21988690002514,"medium":30.092891109549782,"none":16.870009465672478},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:46:48Z","match_totals_all":{"draws":3762,"losses":4864,"wins":3014},"match_totals_tracks":{"highest":{"draws":1301,"losses":1083,"wins":1474},"medium":{"draws":1326,"losses":1588,"wins":1114},"none":{"draws":1135,"losses":2193,"wins":426}},"model_slug":"gpt-5-6-luna","overall":{"max":75.82145949754997,"mean":28.39426249174913,"min":0.1603179813568868},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":50,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.97164758786678,"GB2-02":10.035425421796178,"GB2-03":21.206669995972664,"GB2-04":7.682765770881317,"GB2-05":47.925117266099086,"GB2-06":75.82145949754997,"GB2-07":61.787477244233365,"GB2-08":17.32853241580175},"per_game_all":{"GB2-01":43.23598907623735,"GB2-02":9.101613369079615,"GB2-03":19.241669001540757,"GB2-04":12.226692803915498,"GB2-05":39.39867271853194,"GB2-06":53.66466636556495,"GB2-07":38.59429670204993,"GB2-08":11.690499897073023},"per_game_match_totals_all":{"GB2-01":{"draws":163,"losses":643,"wins":551},"GB2-02":{"draws":1205,"losses":219,"wins":42},"GB2-03":{"draws":640,"losses":591,"wins":239},"GB2-04":{"draws":866,"losses":304,"wins":132},"GB2-05":{"draws":0,"losses":793,"wins":656},"GB2-06":{"draws":104,"losses":680,"wins":756},"GB2-07":{"draws":0,"losses":882,"wins":582},"GB2-08":{"draws":784,"losses":752,"wins":56}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":107,"wins":313},"GB2-02":{"draws":378,"losses":67,"wins":27},"GB2-03":{"draws":227,"losses":196,"wins":90},"GB2-04":{"draws":273,"losses":119,"wins":36},"GB2-05":{"draws":0,"losses":230,"wins":298},"GB2-06":{"draws":58,"losses":65,"wins":356},"GB2-07":{"draws":0,"losses":140,"wins":348},"GB2-08":{"draws":365,"losses":159,"wins":6}},"medium":{"GB2-01":{"draws":74,"losses":251,"wins":180},"GB2-02":{"draws":425,"losses":82,"wins":11},"GB2-03":{"draws":175,"losses":199,"wins":129},"GB2-04":{"draws":301,"losses":77,"wins":58},"GB2-05":{"draws":0,"losses":237,"wins":238},"GB2-06":{"draws":20,"losses":229,"wins":316},"GB2-07":{"draws":0,"losses":334,"wins":156},"GB2-08":{"draws":331,"losses":179,"wins":26}},"none":{"GB2-01":{"draws":89,"losses":285,"wins":58},"GB2-02":{"draws":402,"losses":70,"wins":4},"GB2-03":{"draws":238,"losses":196,"wins":20},"GB2-04":{"draws":292,"losses":108,"wins":38},"GB2-05":{"draws":0,"losses":326,"wins":120},"GB2-06":{"draws":26,"losses":386,"wins":84},"GB2-07":{"draws":0,"losses":408,"wins":78},"GB2-08":{"draws":88,"losses":414,"wins":24}}},"per_game_raw_elo_all":{"GB2-01":1497.621880251425,"GB2-02":1423.87228774654,"GB2-03":1345.5581927693706,"GB2-04":1425.7191365415038,"GB2-05":1366.4319361415019,"GB2-06":1541.0988422439495,"GB2-07":1335.167006968061,"GB2-08":1181.9900232621574},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1830.2478579835347,"GB2-02":1431.465901055959,"GB2-03":1368.7527149912344,"GB2-04":1390.7741307588526,"GB2-05":1541.7206782779706,"GB2-06":2004.3482354736318,"GB2-07":1782.3169928442828,"GB2-08":1267.2481035490534},"medium":{"GB2-01":1451.3254848670485,"GB2-02":1424.7131938155133,"GB2-03":1394.8524964915855,"GB2-04":1481.2054677463425,"GB2-05":1414.7425136830495,"GB2-06":1602.1850079938267,"GB2-07":1215.9599242321012,"GB2-08":1271.0908478285276},"none":{"GB2-01":1211.292297903692,"GB2-02":1415.4377683681482,"GB2-03":1273.069366825292,"GB2-04":1405.1778111193162,"GB2-05":1142.8326164634855,"GB2-06":1016.7632832643902,"GB2-07":1007.2241038277991,"GB2-08":1007.6311184088914}},"per_game_tracks":{"highest":{"GB2-01":63.97164758786678,"GB2-02":10.035425421796178,"GB2-03":21.206669995972664,"GB2-04":7.682765770881317,"GB2-05":47.925117266099086,"GB2-06":75.82145949754997,"GB2-07":61.787477244233365,"GB2-08":17.32853241580175},"medium":{"GB2-01":40.34990587986427,"GB2-02":9.205022403805625,"GB2-03":23.417799680476445,"GB2-04":19.4416248000271,"GB2-05":41.74860948827757,"GB2-06":56.586361585304,"GB2-07":32.4111557445828,"GB2-08":17.58264929406043},"none":{"GB2-01":25.386413760981018,"GB2-02":8.06439228163704,"GB2-03":13.100537328173159,"GB2-04":9.555687840838075,"GB2-05":28.522291401219157,"GB2-06":28.586178013840886,"GB2-07":21.58425711733362,"GB2-08":0.1603179813568868}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.21988690002514,"medium":30.092891109549782,"none":16.870009465672478},"reasoning_agg":{"highest":{"max":75.82145949754997,"mean":38.21988690002514,"min":7.682765770881317},"medium":{"max":56.586361585304,"mean":30.092891109549782,"min":9.205022403805625},"none":{"max":28.586178013840886,"mean":16.870009465672478,"min":0.1603179813568868}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":75.82145949754997,"expected_score":25.592579987600633,"reasoning_variance":21.34987743435266,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.8016825041484985},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.82145949754997,"expected_score":30.66371848443494,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.5561684155901965},"medium":{"ceiling_score":56.586361585304,"expected_score":28.967477088471814,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.1254140210779688},"none":{"ceiling_score":28.586178013840886,"expected_score":17.146544389895155,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.2765349242226769}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:75e8a28268f557f2","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564},"codegen_latency_ms":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8}},"codegen_output_tokens":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8}},"display_name":"GPT-4.1","economics":{"none":27.742817448520064},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:28:38Z","match_totals_all":{"draws":990,"losses":1259,"wins":860},"match_totals_tracks":{"none":{"draws":990,"losses":1259,"wins":860}},"model_slug":"gpt-4-1","overall":{"max":50.1059873599037,"mean":27.742817448520064,"min":6.823591769152568},"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":26,"losses":120,"wins":177},"GB2-02":{"draws":344,"losses":65,"wins":3},"GB2-03":{"draws":69,"losses":141,"wins":88},"GB2-04":{"draws":245,"losses":86,"wins":15},"GB2-05":{"draws":0,"losses":295,"wins":69},"GB2-06":{"draws":34,"losses":238,"wins":266},"GB2-07":{"draws":0,"losses":186,"wins":192},"GB2-08":{"draws":272,"losses":128,"wins":50}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":26,"losses":120,"wins":177},"GB2-02":{"draws":344,"losses":65,"wins":3},"GB2-03":{"draws":69,"losses":141,"wins":88},"GB2-04":{"draws":245,"losses":86,"wins":15},"GB2-05":{"draws":0,"losses":295,"wins":69},"GB2-06":{"draws":34,"losses":238,"wins":266},"GB2-07":{"draws":0,"losses":186,"wins":192},"GB2-08":{"draws":272,"losses":128,"wins":50}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1584.0015894052947,"GB2-02":1415.2917932274665,"GB2-03":1368.293693602861,"GB2-04":1384.1666654011472,"GB2-05":960.2049374542476,"GB2-06":1466.6947585730159,"GB2-07":1455.3226231905257,"GB2-08":1348.662697023213}},"per_game_tracks":{"none":{"GB2-01":48.62083653632076,"GB2-02":8.04644122985034,"GB2-03":21.16778247434184,"GB2-04":6.823591769152568,"GB2-05":19.63886421163473,"GB2-06":50.1059873599037,"GB2-07":44.826637053674936,"GB2-08":22.71239895328162}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":27.742817448520064},"reasoning_agg":{"none":{"max":50.1059873599037,"mean":27.742817448520064,"min":6.823591769152568}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":50.1059873599037},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":50.1059873599037,"expected_score":31.331091431188657,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.5882739826685928}}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:9672f7cfe3f2d2e4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":8,"total":0.0},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16},"recorded_attempt_count":16,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16},"recorded_attempt_count":16,"run_count":8,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":42},"recorded_attempt_count":42,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":42,"max_ms":537122,"mean_ms":137533.5,"min_ms":13879,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":537122,"mean_ms":335588.75,"min_ms":221492,"run_count":8},"medium":{"attempt_count":11,"max_ms":84351,"mean_ms":41299.125,"min_ms":13879,"run_count":8},"none":{"attempt_count":16,"max_ms":68645,"mean_ms":35712.625,"min_ms":19448,"run_count":8}},"codegen_output_tokens":{"attempt_count":42,"output_max":39424,"output_mean":14219.625,"output_min":2263,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":39424,"output_mean":32529.75,"output_min":24807,"run_count":8},"medium":{"attempt_count":11,"output_max":9849,"output_mean":5340.25,"output_min":2263,"run_count":8},"none":{"attempt_count":16,"output_max":8167,"output_mean":4788.875,"output_min":2672,"run_count":8}},"display_name":"Space Bunny Alpha","economics":{"all":29.85361726188459,"highest":37.00696978794228,"medium":27.665205885073295,"none":20.90781139210461},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":42,"effective_max_output_tokens":[262144],"finish_reason_observations":42,"finish_reasons":["stop"],"indexed_attempts":42,"output_token_observations":42,"provider_post_attempt_observations":42,"provider_post_attempts":42,"reasoning_token_observations":42,"reconciliation_get_attempt_observations":42,"requested_max_output_token_observations":42,"requested_max_output_tokens":[262144],"total_output_tokens":341271,"total_visible_output_tokens":341271,"visible_token_observations":42},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"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}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-10-06T16:20:34Z","match_totals_all":{"draws":1348,"losses":2098,"wins":1119},"match_totals_tracks":{"highest":{"draws":329,"losses":619,"wins":504},"medium":{"draws":450,"losses":819,"wins":389},"none":{"draws":569,"losses":660,"wins":226}},"model_slug":"stealth-space-bunny-alpha","overall":{"max":64.37550841958864,"mean":26.884228146278943,"min":8.096142307542529},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-01":51.923991066175404,"GB2-04":8.258493731727858,"GB2-05":43.39212625808209,"GB2-06":43.60569864165186,"GB2-07":64.37550841958864,"GB2-08":10.48600061042786},"per_game_all":{"GB2-04":9.989502691492135,"GB2-05":35.13724655239375,"GB2-07":44.43410254176789},"per_game_match_totals_all":{"GB2-01":{"draws":97,"losses":162,"wins":159},"GB2-02":{"draws":444,"losses":113,"wins":7},"GB2-03":{"draws":93,"losses":241,"wins":88},"GB2-04":{"draws":403,"losses":190,"wins":50},"GB2-05":{"draws":0,"losses":468,"wins":220},"GB2-06":{"draws":12,"losses":257,"wins":241},"GB2-07":{"draws":0,"losses":405,"wins":339},"GB2-08":{"draws":299,"losses":262,"wins":15}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":58,"losses":50,"wins":102},"GB2-04":{"draws":132,"losses":72,"wins":18},"GB2-05":{"draws":0,"losses":126,"wins":98},"GB2-06":{"draws":7,"losses":149,"wins":102},"GB2-07":{"draws":0,"losses":63,"wins":181},"GB2-08":{"draws":132,"losses":159,"wins":3}},"medium":{"GB2-01":{"draws":39,"losses":112,"wins":57},"GB2-02":{"draws":225,"losses":57,"wins":4},"GB2-03":{"draws":44,"losses":109,"wins":53},"GB2-04":{"draws":137,"losses":65,"wins":12},"GB2-05":{"draws":0,"losses":201,"wins":33},"GB2-06":{"draws":5,"losses":108,"wins":139},"GB2-07":{"draws":0,"losses":167,"wins":91}},"none":{"GB2-02":{"draws":219,"losses":56,"wins":3},"GB2-03":{"draws":49,"losses":132,"wins":35},"GB2-04":{"draws":134,"losses":53,"wins":20},"GB2-05":{"draws":0,"losses":141,"wins":89},"GB2-07":{"draws":0,"losses":175,"wins":67},"GB2-08":{"draws":167,"losses":103,"wins":12}}},"per_game_raw_elo_all":{"GB2-04":1408.5140580164377,"GB2-05":1278.824489895583,"GB2-07":1447.7548037991348},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1636.9883322414069,"GB2-04":1395.2017583978427,"GB2-05":1448.5303352834874,"GB2-06":1330.7881412836691,"GB2-07":1832.2126120071034,"GB2-08":1163.7756379167076},"medium":{"GB2-01":1423.8545992094753,"GB2-02":1416.878933100379,"GB2-03":1384.4302360168908,"GB2-04":1399.4294429299655,"GB2-05":993.2866756241572,"GB2-06":1585.2323400145112,"GB2-07":1331.6293104799388},"none":{"GB2-02":1415.6959546044352,"GB2-03":1297.78745243267,"GB2-04":1430.9109727215043,"GB2-05":1394.656458779104,"GB2-07":1179.4224889103623,"GB2-08":1276.899136819464}},"per_game_tracks":{"highest":{"GB2-01":51.923991066175404,"GB2-04":8.258493731727858,"GB2-05":43.39212625808209,"GB2-06":43.60569864165186,"GB2-07":64.37550841958864,"GB2-08":10.48600061042786},"medium":{"GB2-01":38.637391097070534,"GB2-02":8.24161713390045,"GB2-03":22.5348432651165,"GB2-04":8.808222930576365,"GB2-05":21.24803547160799,"GB2-06":55.775531041449,"GB2-07":38.41080025579223},"none":{"GB2-02":8.096142307542529,"GB2-03":15.194612055574382,"GB2-04":12.90179141217218,"GB2-05":40.771577927491165,"GB2-07":30.51599894992281,"GB2-08":17.966745699924584}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.43886590530368,"medium":26.75690765885037,"none":19.45691087468278},"reasoning_agg":{"highest":{"max":64.37550841958864,"mean":34.43886590530368,"min":8.258493731727858},"medium":{"max":55.775531041449,"mean":26.75690765885037,"min":8.24161713390045},"none":{"max":40.771577927491165,"mean":19.45691087468278,"min":8.096142307542529}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":64.37550841958864,"expected_score":29.16596375247853,"reasoning_variance":14.981955030620899,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.281735606199586},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.37550841958864,"expected_score":27.99259457653628,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.4462713287673985},"medium":{"ceiling_score":55.775531041449,"expected_score":25.398398098671805,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.3585095601785646},"none":{"ceiling_score":40.771577927491165,"expected_score":25.417731908986685,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.960821034303905}}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:df664de0bc398e51","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.42810400000000004},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760899999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.428104},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760899999999998},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"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":28.424927715907902,"highest":28.09466203761253,"medium":30.857685125418147,"none":22.814712750073614},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:07:43Z","match_totals_all":{"draws":2744,"losses":4123,"wins":2411},"match_totals_tracks":{"highest":{"draws":1170,"losses":1365,"wins":883},"medium":{"draws":773,"losses":1222,"wins":1033},"none":{"draws":801,"losses":1536,"wins":495}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":68.20604546075417,"mean":26.668299674814307,"min":5.811392692822215},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":53,"overall_ranking_status":"ranked","per_game":{"GB2-01":35.31387198656496,"GB2-02":7.0169830995536415,"GB2-03":22.85677833858476,"GB2-04":8.35301333688669,"GB2-05":45.22969662808351,"GB2-06":29.999213098662896,"GB2-07":42.983084886253515,"GB2-08":33.004654926310245},"per_game_all":{"GB2-01":32.45203881763076,"GB2-03":23.661462501990297,"GB2-04":10.467233754616228,"GB2-05":36.62314929465964,"GB2-06":27.71425162031245,"GB2-08":39.63143030623805},"per_game_match_totals_all":{"GB2-01":{"draws":356,"losses":600,"wins":328},"GB2-02":{"draws":692,"losses":152,"wins":10},"GB2-03":{"draws":339,"losses":589,"wins":354},"GB2-04":{"draws":780,"losses":250,"wins":84},"GB2-05":{"draws":0,"losses":695,"wins":505},"GB2-06":{"draws":10,"losses":996,"wins":228},"GB2-07":{"draws":0,"losses":543,"wins":375},"GB2-08":{"draws":567,"losses":298,"wins":527}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":165,"losses":120,"wins":65},"GB2-02":{"draws":364,"losses":63,"wins":3},"GB2-03":{"draws":141,"losses":184,"wins":113},"GB2-04":{"draws":244,"losses":94,"wins":24},"GB2-05":{"draws":0,"losses":220,"wins":228},"GB2-06":{"draws":2,"losses":310,"wins":90},"GB2-07":{"draws":0,"losses":271,"wins":229},"GB2-08":{"draws":254,"losses":103,"wins":131}},"medium":{"GB2-01":{"draws":92,"losses":251,"wins":237},"GB2-02":{"draws":328,"losses":89,"wins":7},"GB2-03":{"draws":91,"losses":209,"wins":100},"GB2-04":{"draws":258,"losses":90,"wins":32},"GB2-05":{"draws":0,"losses":174,"wins":216},"GB2-06":{"draws":2,"losses":344,"wins":60},"GB2-08":{"draws":2,"losses":65,"wins":381}},"none":{"GB2-01":{"draws":99,"losses":229,"wins":26},"GB2-03":{"draws":107,"losses":196,"wins":141},"GB2-04":{"draws":278,"losses":66,"wins":28},"GB2-05":{"draws":0,"losses":301,"wins":61},"GB2-06":{"draws":6,"losses":342,"wins":78},"GB2-07":{"draws":0,"losses":272,"wins":146},"GB2-08":{"draws":311,"losses":130,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":1324.6337884301934,"GB2-03":1397.7286490962204,"GB2-04":1412.1880419167194,"GB2-05":1309.3720435887851,"GB2-06":998.533236599383,"GB2-08":1604.5115465421093},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1370.5411829500754,"GB2-02":1406.920401000338,"GB2-03":1388.2303003612428,"GB2-04":1395.928660067882,"GB2-05":1486.3075584798432,"GB2-06":1046.3067123047192,"GB2-07":1419.7800927417475,"GB2-08":1504.3017401055006},"medium":{"GB2-01":1448.2462412260868,"GB2-02":1397.11672869644,"GB2-03":1380.3232333203716,"GB2-04":1414.6740524280547,"GB2-05":1453.6882850974132,"GB2-06":946.1329146938264,"GB2-08":2036.6156227279293},"none":{"GB2-01":1155.1139411144181,"GB2-03":1424.6324136070461,"GB2-04":1425.9614132542217,"GB2-05":988.1202871890987,"GB2-06":1003.1600827996037,"GB2-07":1227.3880835399218,"GB2-08":1272.6172767928977}},"per_game_tracks":{"highest":{"GB2-01":35.31387198656496,"GB2-02":7.0169830995536415,"GB2-03":22.85677833858476,"GB2-04":8.35301333688669,"GB2-05":45.22969662808351,"GB2-06":29.999213098662896,"GB2-07":42.983084886253515,"GB2-08":33.004654926310245},"medium":{"GB2-01":40.15794809879008,"GB2-02":5.811392692822215,"GB2-03":22.186904889598356,"GB2-04":10.790491688442964,"GB2-05":43.64302071103751,"GB2-06":25.207992336481716,"GB2-08":68.20604546075417},"none":{"GB2-01":21.884296367537242,"GB2-03":25.94070427778778,"GB2-04":12.25819623851903,"GB2-05":20.99673054485792,"GB2-06":27.935549425792725,"GB2-07":33.003921864370824,"GB2-08":17.68359053164974}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.09466203761253,"medium":29.844572091624123,"none":22.065664895206275},"reasoning_agg":{"highest":{"max":45.22969662808351,"mean":28.09466203761253,"min":7.0169830995536415},"medium":{"max":68.20604546075417,"mean":29.844572091624123,"min":5.811392692822215},"none":{"max":33.003921864370824,"mean":22.065664895206275,"min":12.25819623851903}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":68.20604546075417,"expected_score":24.10029248962608,"reasoning_variance":7.778907196417848,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.5680071851882253},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":45.22969662808351,"expected_score":17.85212524308439,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.242536794528139},"medium":{"ceiling_score":68.20604546075417,"expected_score":28.07998556359151,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.7645865280326127},"none":{"ceiling_score":33.003921864370824,"expected_score":24.261897317278233,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.196232422071958}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:a0899136559def04","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":0.2156185632352941,"median":0.169101,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":2},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.1688104},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":33.67316023092752,"none":19.029347494925542},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:45:01Z","match_totals_all":{"draws":2100,"losses":2387,"wins":1344},"match_totals_tracks":{"medium":{"draws":891,"losses":1036,"wins":1026},"none":{"draws":1209,"losses":1351,"wins":318}},"model_slug":"gpt-5-4-mini","overall":{"max":54.06047333762149,"mean":26.351253862926534,"min":7.949340507339652},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":54,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":134,"losses":241,"wins":247},"GB2-02":{"draws":659,"losses":113,"wins":8},"GB2-03":{"draws":374,"losses":137,"wins":70},"GB2-04":{"draws":431,"losses":139,"wins":108},"GB2-05":{"draws":0,"losses":460,"wins":244},"GB2-06":{"draws":58,"losses":425,"wins":293},"GB2-07":{"draws":0,"losses":545,"wins":243},"GB2-08":{"draws":444,"losses":327,"wins":131}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":19,"losses":93,"wins":194},"GB2-02":{"draws":327,"losses":61,"wins":8},"GB2-03":{"draws":132,"losses":110,"wins":63},"GB2-04":{"draws":222,"losses":54,"wins":60},"GB2-05":{"draws":0,"losses":179,"wins":189},"GB2-06":{"draws":40,"losses":174,"wins":182},"GB2-07":{"draws":0,"losses":185,"wins":213},"GB2-08":{"draws":151,"losses":180,"wins":117}},"none":{"GB2-01":{"draws":115,"losses":148,"wins":53},"GB2-02":{"draws":332,"losses":52,"wins":0},"GB2-03":{"draws":242,"losses":27,"wins":7},"GB2-04":{"draws":209,"losses":85,"wins":48},"GB2-05":{"draws":0,"losses":281,"wins":55},"GB2-06":{"draws":18,"losses":251,"wins":111},"GB2-07":{"draws":0,"losses":360,"wins":30},"GB2-08":{"draws":293,"losses":147,"wins":14}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1671.260188331654,"GB2-02":1416.039273805925,"GB2-03":1401.0820340959244,"GB2-04":1475.2949742137369,"GB2-05":1484.9000531743568,"GB2-06":1447.276485800077,"GB2-07":1477.1296558474255,"GB2-08":1372.2409771969988},"none":{"GB2-01":1304.486069593193,"GB2-02":1414.5021853650853,"GB2-03":1389.3628313527774,"GB2-04":1426.7716761481538,"GB2-05":906.9309886315335,"GB2-06":1140.5863430087127,"GB2-07":749.4650544147921,"GB2-08":1277.4400917824253}},"per_game_tracks":{"medium":{"GB2-01":54.06047333762149,"GB2-02":8.138361419211343,"GB2-03":23.94555565105808,"GB2-04":18.673078601797144,"GB2-05":45.16123235712484,"GB2-06":49.177229202637974,"GB2-07":45.95774397859112,"GB2-08":24.271607299378207},"none":{"GB2-01":31.19604486177433,"GB2-02":7.949340507339652,"GB2-03":22.952724463419905,"GB2-04":12.363555370250248,"GB2-05":17.047497732929777,"GB2-06":34.508521269591505,"GB2-07":8.214577237544182,"GB2-08":18.002518516554748}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.67316023092752,"none":19.029347494925542},"reasoning_agg":{"medium":{"max":54.06047333762149,"mean":33.67316023092752,"min":8.138361419211343},"none":{"max":34.508521269591505,"mean":19.029347494925542,"min":7.949340507339652}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.06047333762149,"reasoning_variance":14.64381273600198},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":54.06047333762149,"expected_score":32.60511292557414,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0680473053533817},"none":{"ceiling_score":34.508521269591505,"expected_score":20.841814414641686,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8124669197161438}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:5fe751f34e1b07fe","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":16,"token_priced_attempt_count":25,"total":0.3954491500000001},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":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},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":8,"max":0.26962149999999996,"mean":0.03182758529411764,"median":0.01676735,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-08-08":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":29.71932667417793,"none":25.82603199880419},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:49:11Z","match_totals_all":{"draws":2028,"losses":4149,"wins":2673},"match_totals_tracks":{"medium":{"draws":831,"losses":2033,"wins":1544},"none":{"draws":1197,"losses":2116,"wins":1129}},"model_slug":"gpt-5-4-nano","overall":{"max":56.7486314206886,"mean":25.845390340823055,"min":6.617049607884969},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":55,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":230,"losses":714,"wins":282},"GB2-02":{"draws":951,"losses":227,"wins":10},"GB2-03":{"draws":96,"losses":137,"wins":55},"GB2-04":{"draws":187,"losses":66,"wins":97},"GB2-05":{"draws":0,"losses":919,"wins":439},"GB2-06":{"draws":35,"losses":672,"wins":765},"GB2-07":{"draws":0,"losses":799,"wins":379},"GB2-08":{"draws":529,"losses":615,"wins":646}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":90,"losses":462,"wins":66},"GB2-02":{"draws":320,"losses":70,"wins":0},"GB2-04":{"draws":187,"losses":66,"wins":97},"GB2-05":{"draws":0,"losses":348,"wins":350},"GB2-06":{"draws":31,"losses":273,"wins":424},"GB2-07":{"draws":0,"losses":486,"wins":288},"GB2-08":{"draws":203,"losses":328,"wins":319}},"none":{"GB2-01":{"draws":140,"losses":252,"wins":216},"GB2-02":{"draws":631,"losses":157,"wins":10},"GB2-03":{"draws":96,"losses":137,"wins":55},"GB2-05":{"draws":0,"losses":571,"wins":89},"GB2-06":{"draws":4,"losses":399,"wins":341},"GB2-07":{"draws":0,"losses":313,"wins":91},"GB2-08":{"draws":326,"losses":287,"wins":327}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1010.8117187041098,"GB2-02":1403.6682045049267,"GB2-04":1502.4840564508343,"GB2-05":1501.3351282509852,"GB2-06":1605.57771028308,"GB2-07":1207.6284219845277,"GB2-08":1483.55699037846},"none":{"GB2-01":1473.7388340038374,"GB2-02":1404.7207662906474,"GB2-03":1304.4011170314368,"GB2-05":841.4975229595304,"GB2-06":1368.963472024945,"GB2-07":1058.6465105235798,"GB2-08":1504.0189426031811}},"per_game_tracks":{"medium":{"GB2-01":12.888602084214579,"GB2-02":6.617049607884969,"GB2-04":22.208496696988067,"GB2-05":45.96067192505144,"GB2-06":56.7486314206886,"GB2-07":31.979009838468276,"GB2-08":31.632825145949578},"none":{"GB2-01":41.74713756023735,"GB2-02":6.7464866547406,"GB2-03":15.754910620429728,"GB2-05":13.864664598254674,"GB2-06":45.43158965919321,"GB2-07":24.25148109157068,"GB2-08":32.985953807203096}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.65694981223262,"none":24.03383086941349},"reasoning_agg":{"medium":{"max":56.7486314206886,"mean":27.65694981223262,"min":6.617049607884969},"none":{"max":45.43158965919321,"mean":24.03383086941349,"min":6.7464866547406}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":56.7486314206886,"reasoning_variance":3.623118942819133},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":56.7486314206886,"expected_score":28.787115599381302,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1301657871486803},"none":{"ceiling_score":45.43158965919321,"expected_score":28.105495608635504,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.071664739222015}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:c6815a24355772e8","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.058475471099999995},"medium":{"admitted_cell_count":22,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.008042989573333334,"mean":0.0037891845841666666,"median":0.0032265161666666666,"min":0.002126702,"recorded_attempt_count":36,"run_count":24,"total":0.09094043002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.010671596919999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01663094,"mean":0.00499588742,"median":0.0034890575,"min":0.00258188,"recorded_attempt_count":12,"run_count":8,"total":0.03996709936},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.05097333066},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.010671596919999998},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.0584754711}},"codegen_cost_usd":{"admitted_cell_count":36,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.01423672,"mean":0.004144189362222222,"median":0.0032265161666666666,"min":0.0008945895,"recorded_attempt_count":59,"run_count":40,"total":0.16008749803999997},"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":26.585945520349625,"highest":27.329239687008116,"medium":24.987111283488137,"none":26.06231588368078},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:40:50Z","match_totals_all":{"draws":4457,"losses":6491,"wins":3113},"match_totals_tracks":{"highest":{"draws":1090,"losses":1144,"wins":654},"medium":{"draws":2556,"losses":3901,"wins":1770},"none":{"draws":811,"losses":1446,"wins":689}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":75.38882540207108,"mean":25.268451644676833,"min":6.8853043038796375},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":56,"overall_ranking_status":"ranked","per_game":{"GB2-01":20.625063145041924,"GB2-02":8.767313427713924,"GB2-03":17.128541945601327,"GB2-04":10.776243791407634,"GB2-06":75.38882540207108,"GB2-07":40.963444634984995,"GB2-08":17.655245462235943},"per_game_all":{"GB2-01":25.478179460779444,"GB2-02":7.747486786545051,"GB2-03":18.915741203024982,"GB2-06":55.8825494130815,"GB2-07":32.61612688027755,"GB2-08":18.87558937838922},"per_game_match_totals_all":{"GB2-01":{"draws":316,"losses":1055,"wins":355},"GB2-02":{"draws":1644,"losses":381,"wins":41},"GB2-03":{"draws":502,"losses":562,"wins":289},"GB2-04":{"draws":771,"losses":318,"wins":89},"GB2-05":{"draws":0,"losses":874,"wins":566},"GB2-06":{"draws":50,"losses":1142,"wins":922},"GB2-07":{"draws":0,"losses":1369,"wins":625},"GB2-08":{"draws":1174,"losses":790,"wins":226}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":97,"losses":238,"wins":13},"GB2-02":{"draws":330,"losses":65,"wins":21},"GB2-03":{"draws":142,"losses":168,"wins":64},"GB2-04":{"draws":237,"losses":140,"wins":53},"GB2-06":{"draws":24,"losses":74,"wins":282},"GB2-07":{"draws":0,"losses":281,"wins":195},"GB2-08":{"draws":260,"losses":178,"wins":26}},"medium":{"GB2-01":{"draws":126,"losses":564,"wins":304},"GB2-02":{"draws":945,"losses":225,"wins":16},"GB2-03":{"draws":227,"losses":217,"wins":163},"GB2-04":{"draws":534,"losses":178,"wins":36},"GB2-05":{"draws":0,"losses":696,"wins":370},"GB2-06":{"draws":12,"losses":853,"wins":373},"GB2-07":{"draws":0,"losses":767,"wins":351},"GB2-08":{"draws":712,"losses":401,"wins":157}},"none":{"GB2-01":{"draws":93,"losses":253,"wins":38},"GB2-02":{"draws":369,"losses":91,"wins":4},"GB2-03":{"draws":133,"losses":177,"wins":62},"GB2-05":{"draws":0,"losses":178,"wins":196},"GB2-06":{"draws":14,"losses":215,"wins":267},"GB2-07":{"draws":0,"losses":321,"wins":79},"GB2-08":{"draws":202,"losses":211,"wins":43}}},"per_game_raw_elo_all":{"GB2-01":1212.7643348588051,"GB2-02":1412.860742532641,"GB2-03":1341.7109990087472,"GB2-06":1587.46985676289,"GB2-07":1219.911639274557,"GB2-08":1290.642631034756},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1134.9142603765072,"GB2-02":1421.153812999178,"GB2-03":1320.6152168647816,"GB2-04":1414.5644791799214,"GB2-06":1995.302816263947,"GB2-07":1380.842694389363,"GB2-08":1272.188643897328},"medium":{"GB2-01":1353.1675076551965,"GB2-02":1405.849609664448,"GB2-03":1394.102923015199,"GB2-04":1403.1635329950336,"GB2-05":1240.7202800460375,"GB2-06":1187.0192529790775,"GB2-07":1207.5501509270362,"GB2-08":1370.3207390864104},"none":{"GB2-01":1150.211236544712,"GB2-02":1411.5788049342973,"GB2-03":1310.414857146261,"GB2-05":1414.5033424491178,"GB2-06":1580.0875010456457,"GB2-07":1071.3420725072717,"GB2-08":1229.4185101205296}},"per_game_tracks":{"highest":{"GB2-01":20.625063145041924,"GB2-02":8.767313427713924,"GB2-03":17.128541945601327,"GB2-04":10.776243791407634,"GB2-06":75.38882540207108,"GB2-07":40.963444634984995,"GB2-08":17.655245462235943},"medium":{"GB2-01":34.23080986236525,"GB2-02":6.8853043038796375,"GB2-03":23.354297073593216,"GB2-04":9.293769646349727,"GB2-05":33.28377080517167,"GB2-06":36.729364719718525,"GB2-07":31.974950004352273,"GB2-08":24.144623852474773},"none":{"GB2-01":21.578665374931163,"GB2-02":7.589842628041591,"GB2-03":16.2643845898804,"GB2-05":41.73697565350509,"GB2-06":55.52945811745489,"GB2-07":24.909986001495373,"GB2-08":14.826898820456941}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.4319718324022,"medium":24.166739696466166,"none":25.206643405162147},"reasoning_agg":{"highest":{"max":75.38882540207108,"mean":26.4319718324022,"min":8.767313427713924},"medium":{"max":36.729364719718525,"mean":24.166739696466166,"min":6.8853043038796375},"none":{"max":55.52945811745489,"mean":25.206643405162147,"min":7.589842628041591}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":75.38882540207108,"expected_score":22.536972124737158,"reasoning_variance":2.265232135936035,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.7314795199396755},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.38882540207108,"expected_score":18.51278999639399,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.91918183600821},"medium":{"ceiling_score":36.729364719718525,"expected_score":22.184105290651175,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.9826344058149914},"none":{"ceiling_score":55.52945811745489,"expected_score":28.00945205868204,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.802808653519893}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:e75fbb8f582d72f4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000002},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711},"historical-provider-setting-intensive":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000001}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519749},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":25.524719643925252,"highest":26.65866587329135,"medium":21.068299252763083,"none":28.84719380572132},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:44:48Z","match_totals_all":{"draws":6949,"losses":10514,"wins":5555},"match_totals_tracks":{"highest":{"draws":1728,"losses":3215,"wins":1987},"medium":{"draws":2518,"losses":3780,"wins":1237},"none":{"draws":2703,"losses":3519,"wins":2331}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":55.45396738047438,"mean":24.84849772113728,"min":6.860082745117203},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":57,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.59607775363385,"GB2-02":11.37182403705243,"GB2-03":26.33092286591195,"GB2-04":9.667956202157555,"GB2-05":25.27077167736678,"GB2-06":46.111700766488916,"GB2-07":43.295203775843135,"GB2-08":17.624869907876185},"per_game_all":{"GB2-01":35.566739504776905,"GB2-02":9.309396289127221,"GB2-03":25.418255337436573,"GB2-04":12.37017642103593,"GB2-05":20.656031687868282,"GB2-06":41.948802846626194,"GB2-07":41.13513259024565,"GB2-08":17.79322247428525},"per_game_match_totals_all":{"GB2-01":{"draws":513,"losses":1375,"wins":874},"GB2-02":{"draws":1791,"losses":290,"wins":52},"GB2-03":{"draws":732,"losses":1031,"wins":817},"GB2-04":{"draws":1858,"losses":685,"wins":369},"GB2-05":{"draws":0,"losses":2581,"wins":569},"GB2-06":{"draws":67,"losses":2062,"wins":1323},"GB2-07":{"draws":0,"losses":1552,"wins":1431},"GB2-08":{"draws":1988,"losses":938,"wins":120}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":101,"losses":242,"wins":125},"GB2-02":{"draws":404,"losses":76,"wins":42},"GB2-03":{"draws":200,"losses":434,"wins":382},"GB2-04":{"draws":603,"losses":258,"wins":102},"GB2-05":{"draws":0,"losses":798,"wins":242},"GB2-06":{"draws":42,"losses":594,"wins":502},"GB2-07":{"draws":0,"losses":626,"wins":569},"GB2-08":{"draws":378,"losses":187,"wins":23}},"medium":{"GB2-01":{"draws":202,"losses":580,"wins":422},"GB2-02":{"draws":498,"losses":72,"wins":5},"GB2-03":{"draws":396,"losses":368,"wins":202},"GB2-04":{"draws":624,"losses":155,"wins":69},"GB2-05":{"draws":0,"losses":863,"wins":195},"GB2-06":{"draws":13,"losses":916,"wins":153},"GB2-07":{"draws":0,"losses":450,"wins":140},"GB2-08":{"draws":785,"losses":376,"wins":51}},"none":{"GB2-01":{"draws":210,"losses":553,"wins":327},"GB2-02":{"draws":889,"losses":142,"wins":5},"GB2-03":{"draws":136,"losses":229,"wins":233},"GB2-04":{"draws":631,"losses":272,"wins":198},"GB2-05":{"draws":0,"losses":920,"wins":132},"GB2-06":{"draws":12,"losses":552,"wins":668},"GB2-07":{"draws":0,"losses":476,"wins":722},"GB2-08":{"draws":825,"losses":375,"wins":46}}},"per_game_raw_elo_all":{"GB2-01":1374.5974951928126,"GB2-02":1425.5619458983635,"GB2-03":1418.4655192435812,"GB2-04":1426.8225952444136,"GB2-05":981.1161163701978,"GB2-06":1296.146125757405,"GB2-07":1384.1527305713473,"GB2-08":1274.2751262175289},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1342.9856082886372,"GB2-02":1442.3332852174472,"GB2-03":1429.2384844127491,"GB2-04":1406.041209344463,"GB2-05":1075.9870750134296,"GB2-06":1383.1830865651327,"GB2-07":1425.797549330673,"GB2-08":1271.7293060975262},"medium":{"GB2-01":1408.6534265232558,"GB2-02":1428.7080405775102,"GB2-03":1356.0988766638948,"GB2-04":1418.760546835529,"GB2-05":994.0343999874052,"GB2-06":926.7461335080553,"GB2-07":1096.8630915869971,"GB2-08":1275.9646748670248},"none":{"GB2-01":1372.1534507665447,"GB2-02":1405.644511900133,"GB2-03":1470.0591966540994,"GB2-04":1455.666029553249,"GB2-05":873.3268741097588,"GB2-06":1578.5091571990267,"GB2-07":1629.7975507963715,"GB2-08":1275.1313976880358}},"per_game_tracks":{"highest":{"GB2-01":33.59607775363385,"GB2-02":11.37182403705243,"GB2-03":26.33092286591195,"GB2-04":9.667956202157555,"GB2-05":25.27077167736678,"GB2-06":46.111700766488916,"GB2-07":43.295203775843135,"GB2-08":17.624869907876185},"medium":{"GB2-01":37.68976118570018,"GB2-02":9.696282085212031,"GB2-03":20.134658050274354,"GB2-04":11.321861822531904,"GB2-05":21.284406491460118,"GB2-06":24.28074039291529,"GB2-07":26.233733338704127,"GB2-08":17.904950655306656},"none":{"GB2-01":35.41437957499669,"GB2-02":6.860082745117203,"GB2-03":29.78918509612342,"GB2-04":16.12071123841833,"GB2-05":15.412916894777954,"GB2-06":55.45396738047438,"GB2-07":53.87646065618968,"GB2-08":17.849846859672915}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.783414157227135,"medium":20.376589278858876,"none":28.38548972732583},"reasoning_agg":{"highest":{"max":46.111700766488916,"mean":25.783414157227135,"min":9.667956202157555},"medium":{"max":37.68976118570018,"mean":20.376589278858876,"min":9.696282085212031},"none":{"max":55.45396738047438,"mean":28.38548972732583,"min":6.860082745117203}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":55.45396738047438,"expected_score":22.183808187607053,"reasoning_variance":8.008900448466953,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.664689533530229},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":46.111700766488916,"expected_score":16.514603390877408,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.268810766349727},"medium":{"ceiling_score":37.68976118570018,"expected_score":17.103446534477676,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.2731427443812002},"none":{"ceiling_score":55.45396738047438,"expected_score":32.93337463746607,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.547884910140244}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:0fc707ac11e4d94c","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.5164659199999999},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":35.1436081293869,"none":18.362090312035978},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:17:19Z","match_totals_all":{"draws":1441,"losses":2290,"wins":1114},"match_totals_tracks":{"medium":{"draws":785,"losses":947,"wins":792},"none":{"draws":656,"losses":1343,"wins":322}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":67.60641042661422,"mean":24.648417044004063,"min":6.052878333907418},"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":58,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":170,"losses":432,"wins":256},"GB2-02":{"draws":684,"losses":108,"wins":8},"GB2-04":{"draws":235,"losses":61,"wins":33},"GB2-05":{"draws":0,"losses":375,"wins":315},"GB2-06":{"draws":12,"losses":394,"wins":320},"GB2-07":{"draws":0,"losses":782,"wins":182},"GB2-08":{"draws":340,"losses":138,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":100,"losses":224,"wins":220},"GB2-02":{"draws":336,"losses":38,"wins":8},"GB2-05":{"draws":0,"losses":164,"wins":180},"GB2-06":{"draws":9,"losses":89,"wins":266},"GB2-07":{"draws":0,"losses":294,"wins":118},"GB2-08":{"draws":340,"losses":138,"wins":0}},"none":{"GB2-01":{"draws":70,"losses":208,"wins":36},"GB2-02":{"draws":348,"losses":70,"wins":0},"GB2-04":{"draws":235,"losses":61,"wins":33},"GB2-05":{"draws":0,"losses":211,"wins":135},"GB2-06":{"draws":3,"losses":305,"wins":54},"GB2-07":{"draws":0,"losses":488,"wins":64}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1474.9839045569588,"GB2-02":1432.4427040118967,"GB2-05":1469.4754178293008,"GB2-06":1832.5897831202833,"GB2-07":1151.6017721808898,"GB2-08":1274.2419136546662},"none":{"GB2-01":1158.7224200824219,"GB2-02":1399.0804520954298,"GB2-04":1427.989619771122,"GB2-05":1255.7214278331944,"GB2-06":888.9095983909609,"GB2-07":841.801683452831}},"per_game_tracks":{"medium":{"GB2-01":41.82475434166988,"GB2-02":10.15554615170646,"GB2-05":44.41094288426369,"GB2-06":67.60641042661422,"GB2-07":29.072968811712734,"GB2-08":17.791026160354416},"none":{"GB2-01":22.109246289179215,"GB2-02":6.052878333907418,"GB2-04":12.521925553032265,"GB2-05":34.01346087652532,"GB2-06":22.471053659003278,"GB2-07":13.00397716056839}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.7048124915875,"none":16.59202159642063},"reasoning_agg":{"medium":{"max":67.60641042661422,"mean":32.7048124915875,"min":10.15554615170646},"none":{"max":34.01346087652532,"mean":16.59202159642063,"min":6.052878333907418}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":67.60641042661422,"reasoning_variance":16.112790895166867},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":67.60641042661422,"expected_score":34.96672046607467,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2619079744871726},"none":{"ceiling_score":34.01346087652532,"expected_score":17.151769168710157,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5597475722895275}}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:fa20daa18c2e9d41","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176385999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917796},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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":21.467775128439342,"none":29.394682138008438},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:29:14Z","match_totals_all":{"draws":4005,"losses":4652,"wins":2312},"match_totals_tracks":{"medium":{"draws":2598,"losses":2625,"wins":1004},"none":{"draws":1407,"losses":2027,"wins":1308}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":45.0939622391995,"mean":24.247573117731907,"min":6.215828361238643},"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":59,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":214,"losses":563,"wins":469},"GB2-02":{"draws":1320,"losses":236,"wins":16},"GB2-03":{"draws":752,"losses":796,"wins":404},"GB2-04":{"draws":309,"losses":149,"wins":42},"GB2-05":{"draws":0,"losses":1078,"wins":729},"GB2-06":{"draws":29,"losses":719,"wins":232},"GB2-07":{"draws":0,"losses":448,"wins":340},"GB2-08":{"draws":1381,"losses":663,"wins":80}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":90,"losses":297,"wins":203},"GB2-02":{"draws":976,"losses":156,"wins":2},"GB2-03":{"draws":404,"losses":466,"wins":214},"GB2-04":{"draws":309,"losses":149,"wins":42},"GB2-05":{"draws":0,"losses":743,"wins":362},"GB2-06":{"draws":16,"losses":443,"wins":133},"GB2-08":{"draws":803,"losses":371,"wins":48}},"none":{"GB2-01":{"draws":124,"losses":266,"wins":266},"GB2-02":{"draws":344,"losses":80,"wins":14},"GB2-03":{"draws":348,"losses":330,"wins":190},"GB2-05":{"draws":0,"losses":335,"wins":367},"GB2-06":{"draws":13,"losses":276,"wins":99},"GB2-07":{"draws":0,"losses":448,"wins":340},"GB2-08":{"draws":578,"losses":292,"wins":32}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1397.3559484325758,"GB2-02":1422.7149609427386,"GB2-03":1350.283077477093,"GB2-04":1379.4926696152038,"GB2-05":1178.4834139538937,"GB2-06":1054.6728324085202,"GB2-08":1274.6208067091675},"none":{"GB2-01":1483.9143831519655,"GB2-02":1405.106820036278,"GB2-03":1366.8368108068016,"GB2-05":1483.5170975603583,"GB2-06":1051.4051892221767,"GB2-07":1410.687648959715,"GB2-08":1272.7819740272944}},"per_game_tracks":{"medium":{"GB2-01":36.98548472080054,"GB2-02":8.95929301718846,"GB2-03":19.641953304034338,"GB2-04":6.215828361238643,"GB2-05":30.256427570910283,"GB2-06":30.399356941626017,"GB2-08":17.816081983277122},"none":{"GB2-01":42.38147380102795,"GB2-02":6.793960976381263,"GB2-03":21.044357808998704,"GB2-05":45.0939622391995,"GB2-06":30.24306856830686,"GB2-07":42.51146977529004,"GB2-08":17.694481796854745}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":20.21171658716402,"none":28.28342964829979},"reasoning_agg":{"medium":{"max":36.98548472080054,"mean":20.21171658716402,"min":6.215828361238643},"none":{"max":45.0939622391995,"mean":28.28342964829979,"min":6.793960976381263}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":45.0939622391995,"reasoning_variance":8.071713061135771},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":36.98548472080054,"expected_score":17.80188211019584,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.4098344769681788},"none":{"ceiling_score":45.0939622391995,"expected_score":31.753005483044607,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.4695758347448162}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:88185f1d0a66d1cc","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586438999999994}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725612999999995},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":28.646834443088174,"none":23.19107388008071},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T13:07:48Z","match_totals_all":{"draws":1703,"losses":1833,"wins":1162},"match_totals_tracks":{"highest":{"draws":750,"losses":1092,"wins":730},"none":{"draws":953,"losses":741,"wins":432}},"model_slug":"tencent-hy3-preview","overall":{"max":60.81361135675185,"mean":24.242047381734842,"min":2.735663815902644},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":60,"overall_ranking_status":"partial","per_game":{"GB2-01":51.03616201067215,"GB2-02":5.858467386221834,"GB2-04":9.51750020086228,"GB2-05":51.87513864151379,"GB2-06":27.53214946331989,"GB2-07":30.41231581211475,"GB2-08":24.29610758691253},"per_game_match_totals_all":{"GB2-01":{"draws":113,"losses":144,"wins":371},"GB2-02":{"draws":598,"losses":152,"wins":6},"GB2-03":{"draws":88,"losses":172,"wins":56},"GB2-04":{"draws":477,"losses":118,"wins":73},"GB2-05":{"draws":0,"losses":372,"wins":298},"GB2-06":{"draws":1,"losses":278,"wins":77},"GB2-07":{"draws":0,"losses":279,"wins":123},"GB2-08":{"draws":426,"losses":318,"wins":158}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":61,"losses":85,"wins":180},"GB2-02":{"draws":303,"losses":73,"wins":6},"GB2-04":{"draws":267,"losses":62,"wins":9},"GB2-05":{"draws":0,"losses":131,"wins":205},"GB2-06":{"draws":1,"losses":278,"wins":77},"GB2-07":{"draws":0,"losses":279,"wins":123},"GB2-08":{"draws":118,"losses":184,"wins":130}},"none":{"GB2-01":{"draws":52,"losses":59,"wins":191},"GB2-02":{"draws":295,"losses":79,"wins":0},"GB2-03":{"draws":88,"losses":172,"wins":56},"GB2-04":{"draws":210,"losses":56,"wins":64},"GB2-05":{"draws":0,"losses":241,"wins":93},"GB2-08":{"draws":308,"losses":134,"wins":28}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1622.7464403101658,"GB2-02":1397.4995327278255,"GB2-04":1404.8841296208946,"GB2-05":1622.9261883174593,"GB2-06":994.7258844600142,"GB2-07":1177.4235429907997,"GB2-08":1372.61146946974},"none":{"GB2-01":1779.5889947263638,"GB2-02":1372.1053833534502,"GB2-03":1278.352412501324,"GB2-04":1477.785930689806,"GB2-05":1045.9073930960692,"GB2-08":1296.220571544782}},"per_game_tracks":{"highest":{"GB2-01":51.03616201067215,"GB2-02":5.858467386221834,"GB2-04":9.51750020086228,"GB2-05":51.87513864151379,"GB2-06":27.53214946331989,"GB2-07":30.41231581211475,"GB2-08":24.29610758691253},"none":{"GB2-01":60.81361135675185,"GB2-02":2.735663815902644,"GB2-03":13.548108091120207,"GB2-04":18.996979663371487,"GB2-05":23.807627286284553,"GB2-08":19.244453067053513}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.902368722870794,"none":21.58172604059889},"reasoning_agg":{"highest":{"max":51.87513864151379,"mean":26.902368722870794,"min":5.858467386221834},"none":{"max":60.81361135675185,"mean":21.58172604059889,"min":2.735663815902644}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":60.81361135675185,"reasoning_variance":5.320642682271902},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.87513864151379,"expected_score":18.94952243382693,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.952846289043862},"none":{"ceiling_score":60.81361135675185,"expected_score":27.84901849409955,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.267292453500659}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:fff6a7186478d23a","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528459999999995}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528460000000007}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.48528459999999995},"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":24.10934469321998},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:32:43Z","match_totals_all":{"draws":1106,"losses":1538,"wins":716},"match_totals_tracks":{"medium":{"draws":1106,"losses":1538,"wins":716}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":46.92214515417542,"mean":24.10934469321998,"min":9.877186344638275},"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":61,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":116,"losses":261,"wins":167},"GB2-02":{"draws":329,"losses":55,"wins":10},"GB2-03":{"draws":94,"losses":143,"wins":49},"GB2-04":{"draws":279,"losses":58,"wins":15},"GB2-05":{"draws":0,"losses":167,"wins":203},"GB2-06":{"draws":1,"losses":246,"wins":153},"GB2-07":{"draws":0,"losses":465,"wins":103},"GB2-08":{"draws":287,"losses":143,"wins":16}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":116,"losses":261,"wins":167},"GB2-02":{"draws":329,"losses":55,"wins":10},"GB2-03":{"draws":94,"losses":143,"wins":49},"GB2-04":{"draws":279,"losses":58,"wins":15},"GB2-05":{"draws":0,"losses":167,"wins":203},"GB2-06":{"draws":1,"losses":246,"wins":153},"GB2-07":{"draws":0,"losses":465,"wins":103},"GB2-08":{"draws":287,"losses":143,"wins":16}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1379.3812961659582,"GB2-02":1430.179125672325,"GB2-03":1273.8580266316071,"GB2-04":1412.7640713465162,"GB2-05":1521.1013311496038,"GB2-06":1231.9840540925534,"GB2-07":970.6662174527305,"GB2-08":1276.3881085657995}},"per_game_tracks":{"medium":{"GB2-01":35.864958134732014,"GB2-02":9.877186344638275,"GB2-03":13.167351263327935,"GB2-04":10.54213532178598,"GB2-05":46.92214515417542,"GB2-06":38.87998987120831,"GB2-07":19.68803954891284,"GB2-08":17.93295190697904}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.10934469321998},"reasoning_agg":{"medium":{"max":46.92214515417542,"mean":24.10934469321998,"min":9.877186344638275}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":46.92214515417542},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":46.92214515417542,"expected_score":21.390248744296947,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.7190959489230337}}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:ddf14d5cbaf2ef89","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605809999999994},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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},"cost_is_complete":false,"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}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"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},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605809999999994}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"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":37.83152066180169,"highest":26.81968449450334,"medium":23.60193151691687,"none":31.995770406515536},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:26:26Z","match_totals_all":{"draws":1444,"losses":2943,"wins":1382},"match_totals_tracks":{"highest":{"draws":343,"losses":1063,"wins":411},"medium":{"draws":688,"losses":625,"wins":299},"none":{"draws":413,"losses":1255,"wins":672}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":46.60139596151438,"mean":23.532784867972197,"min":9.71546572634645},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":62,"overall_ranking_status":"partial","per_game":{"GB2-01":9.75758349862545,"GB2-05":40.01390573707106,"GB2-06":36.01686499743997,"GB2-07":29.627173888416635,"GB2-08":18.68289435096357},"per_game_all":{"GB2-05":38.863195819117024,"GB2-06":36.799845504486356},"per_game_match_totals_all":{"GB2-01":{"draws":17,"losses":263,"wins":26},"GB2-02":{"draws":423,"losses":62,"wins":9},"GB2-04":{"draws":260,"losses":57,"wins":35},"GB2-05":{"draws":0,"losses":695,"wins":525},"GB2-06":{"draws":50,"losses":888,"wins":464},"GB2-07":{"draws":0,"losses":654,"wins":311},"GB2-08":{"draws":694,"losses":324,"wins":12}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":263,"wins":26},"GB2-05":{"draws":0,"losses":168,"wins":152},"GB2-06":{"draws":8,"losses":242,"wins":110},"GB2-07":{"draws":0,"losses":276,"wins":113},"GB2-08":{"draws":318,"losses":114,"wins":10}},"medium":{"GB2-02":{"draws":423,"losses":62,"wins":9},"GB2-04":{"draws":260,"losses":57,"wins":35},"GB2-05":{"draws":0,"losses":194,"wins":174},"GB2-06":{"draws":5,"losses":312,"wins":81}},"none":{"GB2-05":{"draws":0,"losses":333,"wins":199},"GB2-06":{"draws":37,"losses":334,"wins":273},"GB2-07":{"draws":0,"losses":378,"wins":198},"GB2-08":{"draws":376,"losses":210,"wins":2}}},"per_game_raw_elo_all":{"GB2-05":1355.4234704653416,"GB2-06":1188.492849838675},"per_game_raw_elo_tracks":{"highest":{"GB2-01":960.5862523778344,"GB2-05":1379.0800477123812,"GB2-06":1172.1224643483533,"GB2-07":1162.2864987439398,"GB2-08":1287.728705287686},"medium":{"GB2-02":1428.864038941654,"GB2-04":1438.13838549183,"GB2-05":1441.895795848001,"GB2-06":999.934558381894},"none":{"GB2-05":1245.2945678356423,"GB2-06":1393.421526785778,"GB2-07":1237.6575295665068,"GB2-08":1222.0378681242516}},"per_game_tracks":{"highest":{"GB2-01":9.75758349862545,"GB2-05":40.01390573707106,"GB2-06":36.01686499743997,"GB2-07":29.627173888416635,"GB2-08":18.68289435096357},"medium":{"GB2-02":9.71546572634645,"GB2-04":13.841577671480318,"GB2-05":43.06940711533599,"GB2-06":27.781275554504724},"none":{"GB2-05":33.50627460494401,"GB2-06":46.60139596151438,"GB2-07":33.53658679400525,"GB2-08":14.338824265598523}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.84644636015772,"medium":19.84677960563906,"none":26.9051286381198},"reasoning_agg":{"highest":{"max":40.01390573707106,"mean":23.84644636015772,"min":9.75758349862545},"medium":{"max":43.06940711533599,"mean":19.84677960563906,"min":9.71546572634645},"none":{"max":46.60139596151438,"mean":26.9051286381198,"min":14.338824265598523}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":46.60139596151438,"expected_score":29.631959044350445,"reasoning_variance":7.058349032480738,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.0991741763782485},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":40.01390573707106,"expected_score":14.11122848608333,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.73521787407439},"medium":{"ceiling_score":43.06940711533599,"expected_score":19.617210604674504,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.22956900096455612},"none":{"ceiling_score":46.60139596151438,"expected_score":33.484683745201735,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.579555107081937}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:cb80da4f8c571880","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.06253070000000001},"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":29.00743295558867,"none":21.7712915612621},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:44:44Z","match_totals_all":{"draws":875,"losses":2196,"wins":935},"match_totals_tracks":{"medium":{"draws":276,"losses":903,"wins":537},"none":{"draws":599,"losses":1293,"wins":398}},"model_slug":"google-gemma-4-31b-it","overall":{"max":45.187438536995955,"mean":23.084255476990435,"min":12.211359731633044},"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":63,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":71,"losses":142,"wins":139},"GB2-04":{"draws":531,"losses":123,"wins":54},"GB2-05":{"draws":0,"losses":573,"wins":353},"GB2-06":{"draws":5,"losses":600,"wins":177},"GB2-07":{"draws":0,"losses":593,"wins":193},"GB2-08":{"draws":268,"losses":165,"wins":19}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":275,"losses":55,"wins":24},"GB2-05":{"draws":0,"losses":271,"wins":295},"GB2-06":{"draws":1,"losses":305,"wins":84},"GB2-07":{"draws":0,"losses":272,"wins":134}},"none":{"GB2-01":{"draws":71,"losses":142,"wins":139},"GB2-04":{"draws":256,"losses":68,"wins":30},"GB2-05":{"draws":0,"losses":302,"wins":58},"GB2-06":{"draws":4,"losses":295,"wins":93},"GB2-07":{"draws":0,"losses":321,"wins":59},"GB2-08":{"draws":268,"losses":165,"wins":19}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1425.6012177686712,"GB2-05":1485.4388062595594,"GB2-06":993.8102441355389,"GB2-07":1191.5025466167172},"none":{"GB2-01":1418.4232228015587,"GB2-04":1426.7098402159183,"GB2-05":910.8460978594044,"GB2-06":1012.7949442111656,"GB2-07":911.5589445290392,"GB2-08":1273.1211009813617}},"per_game_tracks":{"medium":{"GB2-04":12.211359731633044,"GB2-05":45.187438536995955,"GB2-06":27.4883552273226,"GB2-07":31.142578326403076},"none":{"GB2-01":38.29880309137549,"GB2-04":12.355514794556967,"GB2-05":17.237937582758356,"GB2-06":28.39637600057353,"GB2-07":16.62220997141898,"GB2-08":17.716907926889274}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":25.22027309467877,"none":20.9482378593021},"reasoning_agg":{"medium":{"max":45.187438536995955,"mean":25.22027309467877,"min":12.211359731633044},"none":{"max":38.29880309137549,"mean":20.9482378593021,"min":12.355514794556967}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":45.187438536995955,"reasoning_variance":4.27203523537667},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":45.187438536995955,"expected_score":24.78989233222291,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.43038076245586154},"none":{"ceiling_score":38.29880309137549,"expected_score":22.200612532540188,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2523746732380872}}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:5d3c00714ad2933d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855891}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855890999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.015120192000000001,"mean":0.0032700552500000003,"median":0.0013951725,"min":0.00046744,"recorded_attempt_count":33,"run_count":24,"total":0.078481326},"codegen_latency_ms":{"attempt_count":33,"max_ms":1105859,"mean_ms":161415.45833333334,"min_ms":22661,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1105859,"mean_ms":300420.375,"min_ms":56038,"run_count":8},"medium":{"attempt_count":10,"max_ms":291211,"mean_ms":111417.625,"min_ms":22661,"run_count":8},"none":{"attempt_count":12,"max_ms":151123,"mean_ms":72408.375,"min_ms":26216,"run_count":8}},"codegen_output_tokens":{"attempt_count":33,"output_max":63626,"output_mean":9305.125,"output_min":1487,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":63626,"output_mean":22255.875,"output_min":2344,"run_count":8},"medium":{"attempt_count":10,"output_max":5420,"output_mean":3175.75,"output_min":2107,"run_count":8},"none":{"attempt_count":12,"output_max":4178,"output_mean":2483.75,"output_min":1487,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":21.612884934213746,"highest":25.655890492430565,"medium":21.298474115195894,"none":22.38374976848203},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:24:45Z","match_totals_all":{"draws":2914,"losses":3982,"wins":1579},"match_totals_tracks":{"highest":{"draws":978,"losses":1220,"wins":623},"medium":{"draws":1124,"losses":1608,"wins":502},"none":{"draws":812,"losses":1154,"wins":454}},"model_slug":"openai-gpt-oss-120b","overall":{"max":52.06572520797038,"mean":22.314154033874832,"min":8.09711601193836},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":64,"overall_ranking_status":"ranked","per_game":{"GB2-02":10.55935198002859,"GB2-03":23.054464623161447,"GB2-04":12.822510299630586,"GB2-05":52.06572520797038,"GB2-06":30.935478878833038,"GB2-07":35.19681962617331,"GB2-08":14.956882831216605},"per_game_all":{"GB2-02":9.144776391002793,"GB2-03":19.64079363138157,"GB2-05":31.840708571295977,"GB2-07":31.244480570804225,"GB2-08":16.19366550658416},"per_game_match_totals_all":{"GB2-01":{"draws":131,"losses":419,"wins":266},"GB2-02":{"draws":1035,"losses":147,"wins":16},"GB2-03":{"draws":363,"losses":507,"wins":261},"GB2-04":{"draws":528,"losses":217,"wins":65},"GB2-05":{"draws":0,"losses":782,"wins":352},"GB2-06":{"draws":6,"losses":581,"wins":203},"GB2-07":{"draws":0,"losses":840,"wins":380},"GB2-08":{"draws":851,"losses":489,"wins":36}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":324,"losses":66,"wins":12},"GB2-03":{"draws":124,"losses":152,"wins":105},"GB2-04":{"draws":237,"losses":85,"wins":42},"GB2-05":{"draws":0,"losses":175,"wins":219},"GB2-06":{"draws":1,"losses":314,"wins":93},"GB2-07":{"draws":0,"losses":259,"wins":145},"GB2-08":{"draws":292,"losses":169,"wins":7}},"medium":{"GB2-01":{"draws":63,"losses":195,"wins":104},"GB2-02":{"draws":359,"losses":36,"wins":3},"GB2-03":{"draws":130,"losses":175,"wins":71},"GB2-04":{"draws":291,"losses":132,"wins":23},"GB2-05":{"draws":0,"losses":321,"wins":67},"GB2-06":{"draws":5,"losses":267,"wins":110},"GB2-07":{"draws":0,"losses":316,"wins":98},"GB2-08":{"draws":276,"losses":166,"wins":26}},"none":{"GB2-01":{"draws":68,"losses":224,"wins":162},"GB2-02":{"draws":352,"losses":45,"wins":1},"GB2-03":{"draws":109,"losses":180,"wins":85},"GB2-05":{"draws":0,"losses":286,"wins":66},"GB2-07":{"draws":0,"losses":265,"wins":137},"GB2-08":{"draws":283,"losses":154,"wins":3}}},"per_game_raw_elo_all":{"GB2-02":1424.223282678333,"GB2-03":1350.2693889073716,"GB2-05":1211.0534520511392,"GB2-07":1193.467158027466,"GB2-08":1250.0866959587986},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1435.7263897422827,"GB2-03":1390.5637541017572,"GB2-04":1430.3012624607366,"GB2-05":1626.8443137818201,"GB2-06":1065.8819528181768,"GB2-07":1269.6657781163324,"GB2-08":1231.3841226260529},"medium":{"GB2-01":1363.1257715094116,"GB2-02":1421.2395856766875,"GB2-03":1326.7028130042586,"GB2-04":1397.026561283536,"GB2-05":994.2539677096646,"GB2-06":1147.1401505404056,"GB2-07":1096.1130093647214,"GB2-08":1282.0351599917187},"none":{"GB2-01":1416.2111309469803,"GB2-02":1415.7038726160288,"GB2-03":1333.5415996160993,"GB2-05":1012.062074661933,"GB2-07":1214.622686601344,"GB2-08":1236.8408052586242}},"per_game_tracks":{"highest":{"GB2-02":10.55935198002859,"GB2-03":23.054464623161447,"GB2-04":12.822510299630586,"GB2-05":52.06572520797038,"GB2-06":30.935478878833038,"GB2-07":35.19681962617331,"GB2-08":14.956882831216605},"medium":{"GB2-01":34.85160069793857,"GB2-02":8.777861181041429,"GB2-03":17.644272873505344,"GB2-04":8.495774309497206,"GB2-05":21.295086766676096,"GB2-06":34.821983866259316,"GB2-07":26.194827394496986,"GB2-08":18.306385832152223},"none":{"GB2-01":38.16090291410841,"GB2-02":8.09711601193836,"GB2-03":18.223643397477918,"GB2-05":22.161313739241447,"GB2-07":32.34179469174238,"GB2-08":15.317727856383653}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.813561686953737,"medium":21.298474115195894,"none":20.830426299474873},"reasoning_agg":{"highest":{"max":52.06572520797038,"mean":24.813561686953737,"min":10.55935198002859},"medium":{"max":34.85160069793857,"mean":21.298474115195894,"min":8.495774309497206},"none":{"max":38.16090291410841,"mean":20.830426299474873,"min":8.09711601193836}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":52.06572520797038,"expected_score":19.321566619173385,"reasoning_variance":3.983135387478864,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.992587414701447},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.06572520797038,"expected_score":14.59901020887956,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.214551478074176},"medium":{"ceiling_score":34.85160069793857,"expected_score":17.901132022938956,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.397342092256938},"none":{"ceiling_score":38.16090291410841,"expected_score":25.09491126519582,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.264484965720946}}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:0df6b86db3976510","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000002}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.6004064599999999},"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":23.182898907772078,"none":23.705911839602066},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T16:17:55Z","match_totals_all":{"draws":3325,"losses":5818,"wins":2735},"match_totals_tracks":{"medium":{"draws":1720,"losses":3371,"wins":1566},"none":{"draws":1605,"losses":2447,"wins":1169}},"model_slug":"meituan-longcat-2-0","overall":{"max":42.61144443631092,"mean":22.25086134757193,"min":6.229273448098161},"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":65,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":221,"losses":280,"wins":231},"GB2-02":{"draws":803,"losses":151,"wins":4},"GB2-03":{"draws":406,"losses":459,"wins":230},"GB2-04":{"draws":784,"losses":379,"wins":153},"GB2-05":{"draws":0,"losses":1285,"wins":527},"GB2-06":{"draws":115,"losses":1222,"wins":567},"GB2-07":{"draws":0,"losses":1230,"wins":754},"GB2-08":{"draws":996,"losses":812,"wins":269}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":456,"losses":77,"wins":3},"GB2-03":{"draws":202,"losses":200,"wins":115},"GB2-04":{"draws":594,"losses":286,"wins":91},"GB2-05":{"draws":0,"losses":710,"wins":412},"GB2-06":{"draws":62,"losses":786,"wins":284},"GB2-07":{"draws":0,"losses":748,"wins":428},"GB2-08":{"draws":406,"losses":564,"wins":233}},"none":{"GB2-01":{"draws":221,"losses":280,"wins":231},"GB2-02":{"draws":347,"losses":74,"wins":1},"GB2-03":{"draws":204,"losses":259,"wins":115},"GB2-04":{"draws":190,"losses":93,"wins":62},"GB2-05":{"draws":0,"losses":575,"wins":115},"GB2-06":{"draws":53,"losses":436,"wins":283},"GB2-07":{"draws":0,"losses":482,"wins":326},"GB2-08":{"draws":590,"losses":248,"wins":36}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1429.1023160129187,"GB2-03":1385.6443037844558,"GB2-04":1384.9384744001463,"GB2-05":1273.2918738463559,"GB2-06":1099.5437908772928,"GB2-07":1297.7730455736682,"GB2-08":1291.0955904828365},"none":{"GB2-01":1396.72667677659,"GB2-02":1400.5148695276514,"GB2-03":1316.803682846049,"GB2-04":1451.3056693866026,"GB2-05":889.6415471417569,"GB2-06":1310.0004914375659,"GB2-07":1297.0630753140495,"GB2-08":1287.6330362627616}},"per_game_tracks":{"medium":{"GB2-02":9.74476745557159,"GB2-03":22.63769704877082,"GB2-04":6.9239507101899305,"GB2-05":34.86812747850601,"GB2-06":32.54549368558406,"GB2-07":36.65471283712351,"GB2-08":18.90554313865863},"none":{"GB2-01":36.946256389151486,"GB2-02":6.229273448098161,"GB2-03":16.80563518056951,"GB2-04":15.55373012076671,"GB2-05":16.206499832413055,"GB2-06":42.61144443631092,"GB2-07":36.61788745653304,"GB2-08":18.676567852973662}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":21.57411837164545,"none":22.92760432349841},"reasoning_agg":{"medium":{"max":36.65471283712351,"mean":21.57411837164545,"min":6.9239507101899305},"none":{"max":42.61144443631092,"mean":22.92760432349841,"min":6.229273448098161}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":42.61144443631092,"reasoning_variance":1.35348595185296},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":36.65471283712351,"expected_score":20.69064195993303,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.8834764117124223},"none":{"ceiling_score":42.61144443631092,"expected_score":26.209893319508733,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.2822889960103225}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:ae76db4acccefa0c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539000000004},"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":24.09315864433969,"highest":25.511461348839653,"medium":21.244654612751585,"none":21.754631738268404},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:08:25Z","match_totals_all":{"draws":3253,"losses":3810,"wins":1578},"match_totals_tracks":{"highest":{"draws":1135,"losses":1109,"wins":663},"medium":{"draws":1195,"losses":1521,"wins":496},"none":{"draws":923,"losses":1180,"wins":419}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":43.86507075936351,"mean":22.05449834233889,"min":8.164999983862401},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":66,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.977016267495298,"GB2-02":8.164999983862401,"GB2-03":18.64358276890487,"GB2-04":17.25406065634394,"GB2-05":43.86507075936351,"GB2-07":42.903037200528765,"GB2-08":17.772461805378814},"per_game_all":{"GB2-01":29.549653707094205,"GB2-03":19.779675483359814,"GB2-04":14.113185014191131,"GB2-05":25.797197365491737,"GB2-07":37.414442430586895,"GB2-08":17.90479786531434},"per_game_match_totals_all":{"GB2-01":{"draws":295,"losses":588,"wins":222},"GB2-02":{"draws":763,"losses":104,"wins":5},"GB2-03":{"draws":432,"losses":460,"wins":246},"GB2-04":{"draws":796,"losses":278,"wins":132},"GB2-05":{"draws":0,"losses":864,"wins":312},"GB2-06":{"draws":3,"losses":330,"wins":83},"GB2-07":{"draws":0,"losses":751,"wins":511},"GB2-08":{"draws":964,"losses":435,"wins":67}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":105,"losses":190,"wins":58},"GB2-02":{"draws":358,"losses":55,"wins":3},"GB2-03":{"draws":155,"losses":144,"wins":65},"GB2-04":{"draws":242,"losses":112,"wins":76},"GB2-05":{"draws":0,"losses":232,"wins":216},"GB2-07":{"draws":0,"losses":236,"wins":220},"GB2-08":{"draws":275,"losses":140,"wins":25}},"medium":{"GB2-01":{"draws":95,"losses":223,"wins":46},"GB2-02":{"draws":405,"losses":49,"wins":2},"GB2-03":{"draws":126,"losses":176,"wins":88},"GB2-04":{"draws":269,"losses":62,"wins":29},"GB2-05":{"draws":0,"losses":311,"wins":65},"GB2-06":{"draws":3,"losses":330,"wins":83},"GB2-07":{"draws":0,"losses":239,"wins":165},"GB2-08":{"draws":297,"losses":131,"wins":18}},"none":{"GB2-01":{"draws":95,"losses":175,"wins":118},"GB2-03":{"draws":151,"losses":140,"wins":93},"GB2-04":{"draws":285,"losses":104,"wins":27},"GB2-05":{"draws":0,"losses":321,"wins":31},"GB2-07":{"draws":0,"losses":276,"wins":126},"GB2-08":{"draws":392,"losses":164,"wins":24}}},"per_game_raw_elo_all":{"GB2-01":1278.0758898900579,"GB2-03":1351.9087255850889,"GB2-04":1440.2271778717777,"GB2-05":1086.8094636638173,"GB2-07":1312.4201560193023,"GB2-08":1275.9623643834673},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1284.9313215330794,"GB2-02":1416.2558944401196,"GB2-03":1338.4984892614473,"GB2-04":1464.382037023274,"GB2-05":1458.253244553288,"GB2-07":1418.236823526206,"GB2-08":1273.9611842935412},"medium":{"GB2-01":1187.4247592349175,"GB2-02":1421.1435818712605,"GB2-03":1339.2362754545613,"GB2-04":1431.7560373558144,"GB2-05":992.7045191874265,"GB2-06":1014.0696899719193,"GB2-07":1322.4657076375934,"GB2-08":1276.8323909204569},"none":{"GB2-01":1361.8715889021769,"GB2-03":1377.9914120392582,"GB2-04":1424.5434592362442,"GB2-05":809.470627250737,"GB2-07":1196.5579368941078,"GB2-08":1277.0935179364033}},"per_game_tracks":{"highest":{"GB2-01":29.977016267495298,"GB2-02":8.164999983862401,"GB2-03":18.64358276890487,"GB2-04":17.25406065634394,"GB2-05":43.86507075936351,"GB2-07":42.903037200528765,"GB2-08":17.772461805378814},"medium":{"GB2-01":23.898528976024714,"GB2-02":8.766055271659237,"GB2-03":18.706086776932278,"GB2-04":13.01167584202136,"GB2-05":21.219718053642104,"GB2-06":28.457345919864693,"GB2-07":37.93549420222519,"GB2-08":17.962331859643076},"none":{"GB2-01":34.773415877762595,"GB2-03":21.989356904242303,"GB2-04":12.073818544208095,"GB2-05":12.306803283469588,"GB2-07":31.404795889006728,"GB2-08":17.979599930921133}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.673874410655753,"medium":21.244654612751585,"none":20.24496600360933},"reasoning_agg":{"highest":{"max":43.86507075936351,"mean":24.673874410655753,"min":8.164999983862401},"medium":{"max":37.93549420222519,"mean":21.244654612751585,"min":8.766055271659237},"none":{"max":34.773415877762595,"mean":20.24496600360933,"min":12.073818544208095}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":43.86507075936351,"expected_score":21.76327624331266,"reasoning_variance":4.428908407046421,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.2912220990262284},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":43.86507075936351,"expected_score":16.75433138952078,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.919543021134974},"medium":{"ceiling_score":37.93549420222519,"expected_score":17.556187340188202,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.6884672725633827},"none":{"ceiling_score":34.773415877762595,"expected_score":25.115673767783978,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.870707764174647}}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:a30c86981748047c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.5047206500000001},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.3891924000000001},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.2116408500000002},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":32.00587375284846,"highest":21.917860131999138,"medium":27.358612655166404,"none":24.540683163192462},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:11:37Z","match_totals_all":{"draws":3034,"losses":3370,"wins":1357},"match_totals_tracks":{"highest":{"draws":1606,"losses":1385,"wins":470},"medium":{"draws":699,"losses":801,"wins":414},"none":{"draws":729,"losses":1184,"wins":473}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":56.043611717699584,"mean":21.88249094315015,"min":4.407553922677234},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":67,"overall_ranking_status":"partial","per_game":{"GB2-01":24.09663938138535,"GB2-02":7.360763226142691,"GB2-04":10.652565595674064,"GB2-05":32.325146934375724,"GB2-06":38.8738059437259,"GB2-08":18.198239710691105},"per_game_all":{"GB2-01":37.428880739482565,"GB2-06":40.36846713906705,"GB2-08":18.220273379995763},"per_game_match_totals_all":{"GB2-01":{"draws":185,"losses":436,"wins":285},"GB2-02":{"draws":948,"losses":177,"wins":11},"GB2-03":{"draws":131,"losses":118,"wins":23},"GB2-04":{"draws":669,"losses":171,"wins":50},"GB2-05":{"draws":0,"losses":558,"wins":434},"GB2-06":{"draws":44,"losses":681,"wins":402},"GB2-07":{"draws":0,"losses":674,"wins":72},"GB2-08":{"draws":1057,"losses":555,"wins":80}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":70,"losses":192,"wins":50},"GB2-02":{"draws":616,"losses":114,"wins":10},"GB2-04":{"draws":388,"losses":106,"wins":24},"GB2-05":{"draws":0,"losses":445,"wins":229},"GB2-06":{"draws":22,"losses":238,"wins":115},"GB2-08":{"draws":510,"losses":290,"wins":42}},"medium":{"GB2-01":{"draws":66,"losses":122,"wins":126},"GB2-02":{"draws":332,"losses":63,"wins":1},"GB2-06":{"draws":19,"losses":150,"wins":215},"GB2-07":{"draws":0,"losses":336,"wins":48},"GB2-08":{"draws":282,"losses":130,"wins":24}},"none":{"GB2-01":{"draws":49,"losses":122,"wins":109},"GB2-03":{"draws":131,"losses":118,"wins":23},"GB2-04":{"draws":281,"losses":65,"wins":26},"GB2-05":{"draws":0,"losses":113,"wins":205},"GB2-06":{"draws":3,"losses":293,"wins":72},"GB2-07":{"draws":0,"losses":338,"wins":24},"GB2-08":{"draws":265,"losses":135,"wins":14}}},"per_game_raw_elo_all":{"GB2-01":1404.468576862192,"GB2-06":1263.1048118242459,"GB2-08":1280.7329712698076},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1190.60269868859,"GB2-02":1409.715967128646,"GB2-04":1413.6133337865915,"GB2-05":1221.0126549560746,"GB2-06":1231.8547618869106,"GB2-08":1280.399779089672},"medium":{"GB2-01":1493.0014316787046,"GB2-02":1406.4232838530888,"GB2-06":1590.8373122625217,"GB2-07":833.0678834889079,"GB2-08":1281.8581810814828},"none":{"GB2-01":1529.801600219282,"GB2-03":1269.267753647597,"GB2-04":1430.269461787624,"GB2-05":1629.2439919380067,"GB2-06":966.6223613233057,"GB2-07":676.0680307346175,"GB2-08":1279.9409536382682}},"per_game_tracks":{"highest":{"GB2-01":24.09663938138535,"GB2-02":7.360763226142691,"GB2-04":10.652565595674064,"GB2-05":32.325146934375724,"GB2-06":38.8738059437259,"GB2-08":18.198239710691105},"medium":{"GB2-01":42.94795371463478,"GB2-02":6.955850939566312,"GB2-06":56.043611717699584,"GB2-07":12.550964512059316,"GB2-08":18.29468239187206},"none":{"GB2-01":45.24204912242757,"GB2-03":12.778471040143533,"GB2-04":12.818375232687885,"GB2-05":52.18245103121123,"GB2-06":26.187983755775672,"GB2-07":4.407553922677234,"GB2-08":18.167898037424134}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":18.981423670905404,"medium":23.61978523437724,"none":23.046263924167807},"reasoning_agg":{"highest":{"max":38.8738059437259,"mean":18.981423670905404,"min":7.360763226142691},"medium":{"max":56.043611717699584,"mean":23.61978523437724,"min":6.955850939566312},"none":{"max":52.18245103121123,"mean":23.046263924167807,"min":4.407553922677234}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":56.043611717699584,"expected_score":26.358174464582913,"reasoning_variance":4.638361563471836,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.475683521432764},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":38.8738059437259,"expected_score":11.781435471708187,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.199988199197216},"medium":{"ceiling_score":56.043611717699584,"expected_score":24.029180998227144,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.40939576384990417},"none":{"ceiling_score":52.18245103121123,"expected_score":26.951508993487465,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.9052450693196583}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:71bb0f56d289472a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761484999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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":0.07206400000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761484999999996}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":false,"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":22.594811245723395,"highest":26.478976615358775,"medium":20.689539861923315,"none":20.6159172598881},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:17:51Z","match_totals_all":{"draws":3689,"losses":4925,"wins":1917},"match_totals_tracks":{"highest":{"draws":1278,"losses":1585,"wins":816},"medium":{"draws":1145,"losses":1757,"wins":612},"none":{"draws":1266,"losses":1583,"wins":489}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":52.6195359963235,"mean":21.71639635582169,"min":5.420841512017856},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":68,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.093049782790228,"GB2-02":8.250907728917404,"GB2-03":25.72054413992679,"GB2-04":12.840827400740329,"GB2-05":38.83123654895427,"GB2-06":52.6195359963235,"GB2-07":24.47073707097078,"GB2-08":18.004974254246914},"per_game_all":{"GB2-01":21.650180264558234,"GB2-02":8.164975353103664,"GB2-03":25.33379357524989,"GB2-04":14.881587343768294,"GB2-05":19.470484782018218,"GB2-06":36.55521122343958,"GB2-07":36.26113535393126,"GB2-08":18.441122069718034},"per_game_match_totals_all":{"GB2-01":{"draws":252,"losses":790,"wins":159},"GB2-02":{"draws":1235,"losses":206,"wins":3},"GB2-03":{"draws":423,"losses":413,"wins":339},"GB2-04":{"draws":796,"losses":320,"wins":165},"GB2-05":{"draws":0,"losses":971,"wins":246},"GB2-06":{"draws":13,"losses":896,"wins":423},"GB2-07":{"draws":0,"losses":821,"wins":518},"GB2-08":{"draws":970,"losses":508,"wins":64}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":138,"losses":189,"wins":73},"GB2-02":{"draws":477,"losses":91,"wins":0},"GB2-03":{"draws":101,"losses":177,"wins":138},"GB2-04":{"draws":250,"losses":125,"wins":52},"GB2-05":{"draws":0,"losses":241,"wins":188},"GB2-06":{"draws":8,"losses":232,"wins":258},"GB2-07":{"draws":0,"losses":332,"wins":88},"GB2-08":{"draws":304,"losses":198,"wins":19}},"medium":{"GB2-01":{"draws":52,"losses":321,"wins":11},"GB2-02":{"draws":371,"losses":59,"wins":0},"GB2-03":{"draws":123,"losses":159,"wins":97},"GB2-04":{"draws":260,"losses":112,"wins":68},"GB2-05":{"draws":0,"losses":353,"wins":41},"GB2-06":{"draws":3,"losses":328,"wins":80},"GB2-07":{"draws":0,"losses":222,"wins":283},"GB2-08":{"draws":336,"losses":203,"wins":32}},"none":{"GB2-01":{"draws":62,"losses":280,"wins":75},"GB2-02":{"draws":387,"losses":56,"wins":3},"GB2-03":{"draws":199,"losses":77,"wins":104},"GB2-04":{"draws":286,"losses":83,"wins":45},"GB2-05":{"draws":0,"losses":377,"wins":17},"GB2-06":{"draws":2,"losses":336,"wins":85},"GB2-07":{"draws":0,"losses":267,"wins":147},"GB2-08":{"draws":330,"losses":107,"wins":13}}},"per_game_raw_elo_all":{"GB2-01":1151.3584250977674,"GB2-02":1416.2556941466485,"GB2-03":1417.4685476260154,"GB2-04":1446.136564984569,"GB2-05":956.7433517658077,"GB2-06":1183.3780897024483,"GB2-07":1290.18511834952,"GB2-08":1284.0726354624223},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1302.833899307428,"GB2-02":1416.9544827634702,"GB2-03":1422.0336824998074,"GB2-04":1430.4421298645368,"GB2-05":1354.7664439362677,"GB2-06":1519.2474846709938,"GB2-07":1062.8736284004797,"GB2-08":1277.4772273400204},"medium":{"GB2-01":957.780053134819,"GB2-02":1413.6098075247762,"GB2-03":1363.0182178358068,"GB2-04":1451.4828445908333,"GB2-05":847.5562782342258,"GB2-06":1013.7499177154542,"GB2-07":1555.2453782415625,"GB2-08":1295.3290824413946},"none":{"GB2-01":1193.4613228510552,"GB2-02":1418.2027921516992,"GB2-03":1467.3537425424324,"GB2-04":1456.4847204983366,"GB2-05":667.9073331269294,"GB2-06":1017.1368667208973,"GB2-07":1252.436348406518,"GB2-08":1279.4115966058525}},"per_game_tracks":{"highest":{"GB2-01":31.093049782790228,"GB2-02":8.250907728917404,"GB2-03":25.72054413992679,"GB2-04":12.840827400740329,"GB2-05":38.83123654895427,"GB2-06":52.6195359963235,"GB2-07":24.47073707097078,"GB2-08":18.004974254246914},"medium":{"GB2-01":9.58264710425392,"GB2-02":7.8396018165606245,"GB2-03":20.720853021378538,"GB2-04":15.576768354186804,"GB2-05":14.159376285082521,"GB2-06":28.442051506446365,"GB2-07":50.00952103303974,"GB2-08":19.185499774438},"none":{"GB2-01":24.274843906630554,"GB2-02":8.404416513832961,"GB2-03":29.55998356444434,"GB2-04":16.22716627637774,"GB2-05":5.420841512017856,"GB2-06":28.604046167548873,"GB2-07":34.303147957783274,"GB2-08":18.13289218046918}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.042269948966876,"medium":20.089202726748884,"none":20.017716391749325},"reasoning_agg":{"highest":{"max":52.6195359963235,"mean":25.042269948966876,"min":8.250907728917404},"medium":{"max":50.00952103303974,"mean":20.089202726748884,"min":7.8396018165606245},"none":{"max":34.303147957783274,"mean":20.017716391749325,"min":5.420841512017856}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":52.6195359963235,"expected_score":18.64911667399289,"reasoning_variance":5.024553557217551,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.0672796818288006},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.6195359963235,"expected_score":16.474559839679102,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.567710109287773},"medium":{"ceiling_score":50.00952103303974,"expected_score":16.936730894675748,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.152471832073136},"none":{"ceiling_score":34.303147957783274,"expected_score":22.53605928762382,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.518342895874497}}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:086325b8dde80f14","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798000000002}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":17.697313002171406,"none":27.370379921641685},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:32:28Z","match_totals_all":{"draws":1401,"losses":2528,"wins":1147},"match_totals_tracks":{"medium":{"draws":890,"losses":1361,"wins":395},"none":{"draws":511,"losses":1167,"wins":752}},"model_slug":"minimax-minimax-m3","overall":{"max":45.312290483103915,"mean":21.293643545519327,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":69,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":87,"losses":360,"wins":211},"GB2-02":{"draws":636,"losses":140,"wins":2},"GB2-03":{"draws":90,"losses":136,"wins":86},"GB2-04":{"draws":245,"losses":80,"wins":25},"GB2-05":{"draws":0,"losses":706,"wins":196},"GB2-06":{"draws":5,"losses":304,"wins":93},"GB2-07":{"draws":0,"losses":498,"wins":298},"GB2-08":{"draws":338,"losses":304,"wins":236}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":19,"losses":241,"wins":62},"GB2-02":{"draws":308,"losses":71,"wins":1},"GB2-04":{"draws":245,"losses":80,"wins":25},"GB2-05":{"draws":0,"losses":335,"wins":9},"GB2-06":{"draws":5,"losses":304,"wins":93},"GB2-07":{"draws":0,"losses":218,"wins":184},"GB2-08":{"draws":313,"losses":112,"wins":21}},"none":{"GB2-01":{"draws":68,"losses":119,"wins":149},"GB2-02":{"draws":328,"losses":69,"wins":1},"GB2-03":{"draws":90,"losses":136,"wins":86},"GB2-05":{"draws":0,"losses":371,"wins":187},"GB2-07":{"draws":0,"losses":280,"wins":114},"GB2-08":{"draws":25,"losses":192,"wins":215}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1154.8321714017297,"GB2-02":1387.3728891882963,"GB2-04":1407.453773824793,"GB2-05":556.4643413075681,"GB2-06":1017.4197831620446,"GB2-07":1374.1821347297148,"GB2-08":1282.1521195836028},"none":{"GB2-01":1530.928359770183,"GB2-02":1403.0184368661035,"GB2-03":1365.5064560699388,"GB2-05":1220.1294411574652,"GB2-07":1134.204870670019,"GB2-08":1473.8119488554914}},"per_game_tracks":{"medium":{"GB2-01":21.86673105113874,"GB2-02":4.613160125309916,"GB2-04":9.851633090580398,"GB2-05":0.0,"GB2-06":28.617577801160813,"GB2-07":40.617968692733776,"GB2-08":18.31412025427621},"none":{"GB2-01":45.312290483103915,"GB2-02":6.537145505862055,"GB2-03":20.931652388474102,"GB2-05":32.28218539910711,"GB2-07":28.17061056423221,"GB2-08":30.98839518907073}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":17.11627854048836,"none":25.471008550550295},"reasoning_agg":{"medium":{"max":40.617968692733776,"mean":17.11627854048836,"min":0.0},"none":{"max":45.312290483103915,"mean":25.471008550550295,"min":6.537145505862055}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":45.312290483103915,"reasoning_variance":8.354730010061935},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.617968692733776,"expected_score":13.388795026549477,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.727483513938882},"none":{"ceiling_score":45.312290483103915,"expected_score":31.530329210882638,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.059320660332343}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:9c0e6813dd98cfc8","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"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},"cost_is_complete":false,"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":1.2552692800000003},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.5884539499999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.5884539500000001},"historical-provider-setting-intensive":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"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},"cost_is_complete":false,"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":6.000973940000001},"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":23.967907915364034,"highest":24.35870355769378,"medium":22.221570545357523,"none":25.63139645842407},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T15:46:47Z","match_totals_all":{"draws":3703,"losses":6068,"wins":2603},"match_totals_tracks":{"highest":{"draws":1559,"losses":2433,"wins":954},"medium":{"draws":927,"losses":1518,"wins":549},"none":{"draws":1217,"losses":2117,"wins":1100}},"model_slug":"thinkingmachines-inkling","overall":{"max":51.23936190977641,"mean":20.77909229225796,"min":8.144514320529337},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":70,"overall_ranking_status":"partial","per_game":{"GB2-01":25.52762746276728,"GB2-02":8.144514320529337,"GB2-03":26.461657048886575,"GB2-04":16.049277918847604,"GB2-05":21.608315813726072,"GB2-06":51.23936190977641,"GB2-07":31.987832842263895,"GB2-08":13.851041144753044},"per_game_all":{"GB2-01":25.584763403691365,"GB2-03":29.993985516427447,"GB2-04":11.205245286505757,"GB2-05":24.46933436495831,"GB2-07":25.508207117943133,"GB2-08":27.045911802658186},"per_game_match_totals_all":{"GB2-01":{"draws":549,"losses":898,"wins":157},"GB2-02":{"draws":800,"losses":111,"wins":11},"GB2-03":{"draws":464,"losses":573,"wins":574},"GB2-04":{"draws":1143,"losses":413,"wins":164},"GB2-05":{"draws":0,"losses":1713,"wins":535},"GB2-06":{"draws":29,"losses":609,"wins":440},"GB2-07":{"draws":0,"losses":1126,"wins":356},"GB2-08":{"draws":718,"losses":625,"wins":366}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":178,"losses":258,"wins":22},"GB2-02":{"draws":449,"losses":66,"wins":7},"GB2-03":{"draws":198,"losses":209,"wins":165},"GB2-04":{"draws":358,"losses":123,"wins":77},"GB2-05":{"draws":0,"losses":845,"wins":193},"GB2-06":{"draws":21,"losses":318,"wins":319},"GB2-07":{"draws":0,"losses":375,"wins":165},"GB2-08":{"draws":355,"losses":239,"wins":6}},"medium":{"GB2-01":{"draws":151,"losses":254,"wins":89},"GB2-03":{"draws":81,"losses":154,"wins":236},"GB2-04":{"draws":353,"losses":100,"wins":17},"GB2-05":{"draws":0,"losses":257,"wins":89},"GB2-07":{"draws":0,"losses":479,"wins":69},"GB2-08":{"draws":342,"losses":274,"wins":49}},"none":{"GB2-01":{"draws":220,"losses":386,"wins":46},"GB2-02":{"draws":351,"losses":45,"wins":4},"GB2-03":{"draws":185,"losses":210,"wins":173},"GB2-04":{"draws":432,"losses":190,"wins":70},"GB2-05":{"draws":0,"losses":611,"wins":253},"GB2-06":{"draws":8,"losses":291,"wins":121},"GB2-07":{"draws":0,"losses":272,"wins":122},"GB2-08":{"draws":21,"losses":112,"wins":311}}},"per_game_raw_elo_all":{"GB2-01":1214.474075024604,"GB2-03":1472.4766243873419,"GB2-04":1417.8637090350628,"GB2-05":1059.5109298148548,"GB2-07":1082.8754007320902,"GB2-08":1414.1938881274018},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1213.5575428487457,"GB2-02":1416.0893082354485,"GB2-03":1430.7816474547806,"GB2-04":1455.1166726319505,"GB2-05":1000.6934074259132,"GB2-06":1490.3911062079346,"GB2-07":1207.7985239684028,"GB2-08":1214.661633180326},"medium":{"GB2-01":1284.5286221506465,"GB2-03":1569.0851674705266,"GB2-04":1399.0056400998824,"GB2-05":1012.3585175457965,"GB2-07":909.599276693091,"GB2-08":1273.6154507831259},"none":{"GB2-01":1145.3360600744195,"GB2-02":1426.6764474573063,"GB2-03":1417.563058236719,"GB2-04":1399.4688143733551,"GB2-05":1165.480864472855,"GB2-06":1108.9953779486996,"GB2-07":1131.2284015347766,"GB2-08":1754.3045804187534}},"per_game_tracks":{"highest":{"GB2-01":25.52762746276728,"GB2-02":8.144514320529337,"GB2-03":26.461657048886575,"GB2-04":16.049277918847604,"GB2-05":21.608315813726072,"GB2-06":51.23936190977641,"GB2-07":31.987832842263895,"GB2-08":13.851041144753044},"medium":{"GB2-01":29.951912284535496,"GB2-03":38.178499144827676,"GB2-04":8.753115509840235,"GB2-05":22.175733397800098,"GB2-07":16.52056414483399,"GB2-08":17.74959879030767},"none":{"GB2-01":21.274750463771312,"GB2-02":9.446450277275563,"GB2-03":25.3418003555681,"GB2-04":8.813342430829435,"GB2-05":29.62395388334876,"GB2-06":32.99755441695402,"GB2-07":28.01622436673152,"GB2-08":49.537095472913855}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":21.095256084217198,"medium":17.389318702774904,"none":23.852702089781786},"reasoning_agg":{"highest":{"max":51.23936190977641,"mean":21.095256084217198,"min":8.144514320529337},"medium":{"max":38.178499144827676,"mean":17.389318702774904,"min":8.753115509840235},"none":{"max":49.537095472913855,"mean":23.852702089781786,"min":8.813342430829435}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":51.23936190977641,"expected_score":21.64661338567562,"reasoning_variance":6.463383387006882,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8675210934176611},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.23936190977641,"expected_score":13.927591364768558,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.16766471944864},"medium":{"ceiling_score":38.178499144827676,"expected_score":21.03912401033558,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.6498053075606762},"none":{"ceiling_score":49.537095472913855,"expected_score":28.591812295535192,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.739110205753406}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:b8830caed32526e1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.03062629,"mean":0.020124273158333334,"median":0.017895481666666668,"min":0.012095886733333333,"recorded_attempt_count":52,"run_count":24,"total":0.486187507},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.00169122,"recorded_attempt_count":37,"run_count":24,"total":0.06890521579999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0265755425,"mean":0.018416099712499998,"median":0.017703669999999998,"min":0.0109615788,"recorded_attempt_count":32,"run_count":15,"total":0.2720731754},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.21411433159999999},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.030685472800000002},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","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}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":16,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.00169122,"recorded_attempt_count":108,"run_count":56,"total":0.7524538071999999},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":20.509812069286223,"highest":21.65607607102175,"medium":22.64636674445,"none":23.46220174278016},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:37:50Z","match_totals_all":{"draws":4749,"losses":6297,"wins":2646},"match_totals_tracks":{"highest":{"draws":995,"losses":613,"wins":210},"medium":{"draws":2111,"losses":2498,"wins":997},"none":{"draws":1643,"losses":3186,"wins":1439}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":48.823825942366724,"mean":20.360931494100146,"min":6.5516845430151545},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":71,"overall_ranking_status":"partial","per_game":{"GB2-01":23.1790783669699,"GB2-02":9.188109957115675,"GB2-04":9.339076197702287,"GB2-06":48.823825942366724,"GB2-08":17.75028989095417},"per_game_all":{"GB2-01":29.526631794739433,"GB2-02":8.144879351534541,"GB2-04":9.63675580139791,"GB2-06":38.81432197445104,"GB2-08":16.426471424308186},"per_game_match_totals_all":{"GB2-01":{"draws":409,"losses":976,"wins":483},"GB2-02":{"draws":1558,"losses":301,"wins":55},"GB2-03":{"draws":186,"losses":176,"wins":108},"GB2-04":{"draws":1377,"losses":519,"wins":156},"GB2-05":{"draws":0,"losses":1107,"wins":579},"GB2-06":{"draws":52,"losses":1148,"wins":642},"GB2-07":{"draws":0,"losses":1188,"wins":510},"GB2-08":{"draws":1167,"losses":882,"wins":113}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":145,"losses":143,"wins":4},"GB2-02":{"draws":303,"losses":54,"wins":15},"GB2-04":{"draws":231,"losses":80,"wins":23},"GB2-06":{"draws":19,"losses":193,"wins":160},"GB2-08":{"draws":297,"losses":143,"wins":8}},"medium":{"GB2-01":{"draws":78,"losses":369,"wins":185},"GB2-02":{"draws":963,"losses":173,"wins":36},"GB2-04":{"draws":659,"losses":288,"wins":71},"GB2-05":{"draws":0,"losses":492,"wins":250},"GB2-06":{"draws":22,"losses":283,"wins":93},"GB2-07":{"draws":0,"losses":514,"wins":260},"GB2-08":{"draws":389,"losses":379,"wins":102}},"none":{"GB2-01":{"draws":186,"losses":464,"wins":294},"GB2-02":{"draws":292,"losses":74,"wins":4},"GB2-03":{"draws":186,"losses":176,"wins":108},"GB2-04":{"draws":487,"losses":151,"wins":62},"GB2-05":{"draws":0,"losses":615,"wins":329},"GB2-06":{"draws":11,"losses":672,"wins":389},"GB2-07":{"draws":0,"losses":674,"wins":250},"GB2-08":{"draws":481,"losses":360,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1277.7065895323203,"GB2-02":1416.0922766103922,"GB2-04":1405.8012631091824,"GB2-06":1230.6110840446652,"GB2-08":1253.6071768284362},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1175.8838688343253,"GB2-02":1424.575664448757,"GB2-04":1403.511962379462,"GB2-06":1439.8876075941548,"GB2-08":1273.625901576769},"medium":{"GB2-01":1276.821352588035,"GB2-02":1420.5644993440642,"GB2-04":1393.4522938295415,"GB2-05":1178.3373983411639,"GB2-06":1068.4950562221422,"GB2-07":1243.7213046118134,"GB2-08":1264.795935992648},"none":{"GB2-01":1380.4145471746006,"GB2-02":1403.1366660383558,"GB2-03":1386.5864243982041,"GB2-04":1420.4395331185433,"GB2-05":1264.356119036047,"GB2-06":1183.4505883176978,"GB2-07":1084.7215212007827,"GB2-08":1222.3996929158916}},"per_game_tracks":{"highest":{"GB2-01":23.1790783669699,"GB2-02":9.188109957115675,"GB2-04":9.339076197702287,"GB2-06":48.823825942366724,"GB2-08":17.75028989095417},"medium":{"GB2-01":29.471446775506323,"GB2-02":8.694843554472795,"GB2-04":8.031009455586002,"GB2-05":30.249325038198577,"GB2-06":31.06046121534619,"GB2-07":33.8511081712505,"GB2-08":17.166373000789573},"none":{"GB2-01":35.92937024174208,"GB2-02":6.5516845430151545,"GB2-03":22.717511925972527,"GB2-04":11.540181750905441,"GB2-05":34.43347196696472,"GB2-06":36.55867876564021,"GB2-07":25.603963366820352,"GB2-08":14.362751381180814}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.255277089667295,"medium":20.463302364768378,"none":21.364215027864766},"reasoning_agg":{"highest":{"max":48.823825942366724,"mean":19.255277089667295,"min":9.188109957115675},"medium":{"max":33.8511081712505,"mean":20.463302364768378,"min":8.031009455586002},"none":{"max":36.55867876564021,"mean":21.364215027864766,"min":6.5516845430151545}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":48.823825942366724,"expected_score":16.05750123035915,"reasoning_variance":2.108937938197471,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.303430263740996},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.823825942366724,"expected_score":12.615311604856107,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.639965484811189},"medium":{"ceiling_score":33.8511081712505,"expected_score":19.225320745683643,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.237981619084735},"none":{"ceiling_score":36.55867876564021,"expected_score":25.8813187621108,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.517103734246035}}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:4f85ca3e446f4344","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"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},"cost_is_complete":false,"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":22.820787817678568,"none":19.116817623724675},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":1190,"losses":2519,"wins":717},"match_totals_tracks":{"medium":{"draws":628,"losses":1174,"wins":470},"none":{"draws":562,"losses":1345,"wins":247}},"model_slug":"cohere-north-mini-code","overall":{"max":43.979924929185685,"mean":17.765145499451098,"min":4.8785978314600325},"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":72,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":232,"losses":580,"wins":84},"GB2-03":{"draws":79,"losses":193,"wins":22},"GB2-04":{"draws":258,"losses":84,"wins":24},"GB2-05":{"draws":0,"losses":166,"wins":188},"GB2-06":{"draws":6,"losses":321,"wins":87},"GB2-07":{"draws":0,"losses":869,"wins":299},"GB2-08":{"draws":615,"losses":306,"wins":13}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":79,"losses":193,"wins":22},"GB2-04":{"draws":258,"losses":84,"wins":24},"GB2-05":{"draws":0,"losses":166,"wins":188},"GB2-06":{"draws":6,"losses":321,"wins":87},"GB2-07":{"draws":0,"losses":267,"wins":149},"GB2-08":{"draws":285,"losses":143,"wins":0}},"none":{"GB2-01":{"draws":232,"losses":580,"wins":84},"GB2-07":{"draws":0,"losses":602,"wins":150},"GB2-08":{"draws":330,"losses":163,"wins":13}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1176.0190554495132,"GB2-04":1412.039426709161,"GB2-05":1460.6144447985885,"GB2-06":1022.295124260716,"GB2-07":1246.973688949272,"GB2-08":1228.2212964883506},"none":{"GB2-01":1141.8146556772917,"GB2-07":951.779254796128,"GB2-08":1271.154078931288}},"per_game_tracks":{"medium":{"GB2-03":4.8785978314600325,"GB2-04":10.447909200391102,"GB2-05":43.979924929185685,"GB2-06":28.850760889471022,"GB2-07":34.019805788412285,"GB2-08":14.747728267151299},"none":{"GB2-01":21.055228706757493,"GB2-07":18.708393460073832,"GB2-08":17.586830704342706}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":21.237136031669674,"none":14.293154967232521},"reasoning_agg":{"medium":{"max":43.979924929185685,"mean":21.237136031669674,"min":4.8785978314600325},"none":{"max":21.055228706757493,"mean":14.293154967232521,"min":17.586830704342706}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":43.979924929185685,"reasoning_variance":6.943981064437153},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.979924929185685,"expected_score":19.59819329915693,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6389427325127457},"none":{"ceiling_score":21.055228706757493,"expected_score":19.048217673838305,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.755062706605784}}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:4c136a759fc9b24c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122239999999998},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.00761251}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122239999999998},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.007612510000000001},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.028312969999999996},"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":15.783411444467092,"highest":17.565279956680516,"medium":16.70273853594702,"none":22.9958144871648},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:06:59Z","match_totals_all":{"draws":2798,"losses":3379,"wins":875},"match_totals_tracks":{"highest":{"draws":1045,"losses":1259,"wins":216},"medium":{"draws":926,"losses":1297,"wins":242},"none":{"draws":827,"losses":823,"wins":417}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":38.82948150198784,"mean":17.445492076946586,"min":8.149181743448631},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":73,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.412884337714427,"GB2-02":8.566817724975147,"GB2-04":9.46471787082586,"GB2-06":25.323241511485644,"GB2-07":20.663469936450927,"GB2-08":13.960548358631083},"per_game_all":{"GB2-02":8.340457475398068,"GB2-04":10.786973106490677,"GB2-06":28.22280375151253},"per_game_match_totals_all":{"GB2-01":{"draws":104,"losses":211,"wins":69},"GB2-02":{"draws":1133,"losses":184,"wins":1},"GB2-03":{"draws":132,"losses":206,"wins":121},"GB2-04":{"draws":828,"losses":224,"wins":61},"GB2-05":{"draws":0,"losses":525,"wins":259},"GB2-06":{"draws":9,"losses":984,"wins":231},"GB2-07":{"draws":0,"losses":740,"wins":108},"GB2-08":{"draws":592,"losses":305,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":104,"losses":211,"wins":69},"GB2-02":{"draws":377,"losses":64,"wins":1},"GB2-04":{"draws":287,"losses":92,"wins":15},"GB2-06":{"draws":3,"losses":345,"wins":60},"GB2-07":{"draws":0,"losses":367,"wins":63},"GB2-08":{"draws":274,"losses":180,"wins":8}},"medium":{"GB2-02":{"draws":349,"losses":45,"wins":0},"GB2-04":{"draws":254,"losses":81,"wins":24},"GB2-05":{"draws":0,"losses":329,"wins":75},"GB2-06":{"draws":5,"losses":344,"wins":81},"GB2-07":{"draws":0,"losses":373,"wins":45},"GB2-08":{"draws":318,"losses":125,"wins":17}},"none":{"GB2-02":{"draws":407,"losses":75,"wins":0},"GB2-03":{"draws":132,"losses":206,"wins":121},"GB2-04":{"draws":287,"losses":51,"wins":22},"GB2-05":{"draws":0,"losses":196,"wins":184},"GB2-06":{"draws":1,"losses":295,"wins":90}}},"per_game_raw_elo_all":{"GB2-02":1417.6826872718104,"GB2-04":1414.6469928239337,"GB2-06":1009.1659335244635},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1243.7994283887579,"GB2-02":1419.5234133567988,"GB2-04":1404.4782078675444,"GB2-06":948.5425192820337,"GB2-07":989.4719040301968,"GB2-08":1216.3175964621612},"medium":{"GB2-02":1416.1272629873683,"GB2-04":1402.4276831171055,"GB2-05":998.9623934561852,"GB2-06":1017.0314453650652,"GB2-07":868.4139110311621,"GB2-08":1282.8719114916082},"none":{"GB2-02":1417.3973854712642,"GB2-03":1394.6416514666143,"GB2-04":1437.0350874871506,"GB2-05":1354.7303632494798,"GB2-06":1061.9238359262918}},"per_game_tracks":{"highest":{"GB2-01":27.412884337714427,"GB2-02":8.566817724975147,"GB2-04":9.46471787082586,"GB2-06":25.323241511485644,"GB2-07":20.663469936450927,"GB2-08":13.960548358631083},"medium":{"GB2-02":8.149181743448631,"GB2-04":9.198086498566921,"GB2-05":21.524115342868342,"GB2-06":28.599003960895175,"GB2-07":14.384324288712468,"GB2-08":18.36171938119059},"none":{"GB2-02":8.305372957770427,"GB2-03":23.399937243829708,"GB2-04":13.69811495007925,"GB2-05":38.82948150198784,"GB2-06":30.74616578215677}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":16.346334879175604,"medium":15.543649641864185,"none":20.446491709799968},"reasoning_agg":{"highest":{"max":27.412884337714427,"mean":16.346334879175604,"min":8.566817724975147},"medium":{"max":28.599003960895175,"mean":15.543649641864185,"min":8.149181743448631},"none":{"max":38.82948150198784,"mean":20.446491709799968,"min":8.305372957770427}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":38.82948150198784,"expected_score":9.61316789910758,"reasoning_variance":4.902842067935783,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.832324177839006},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":27.412884337714427,"expected_score":6.555165376751469,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.791169502424136},"medium":{"ceiling_score":28.599003960895175,"expected_score":13.126295305688435,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.41735433617575},"none":{"ceiling_score":38.82948150198784,"expected_score":26.173288902042763,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.726797192242795}}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:b2e253da0b9fdd77","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167187}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167187},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.27741402547937455,"mean":0.12115799999999999,"median":0.10979066017348882,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":16,"token_priced_attempt_count":25,"total":1.9385279999999998},"codegen_output_tokens":{"attempt_count":25,"output_max":39199,"output_mean":13770.375,"output_min":1490,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":39199,"output_mean":24874.75,"output_min":14259,"run_count":8},"none":{"attempt_count":12,"output_max":5186,"output_mean":2666.0,"output_min":1490,"run_count":8}},"display_name":"Mistral Medium 3.5","economics":{"highest":21.565706231425086,"none":14.278710242029288},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[209715],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":34,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[209715],"total_output_tokens":220326,"total_visible_output_tokens":220326,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":209715,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-10-06T14:30:12Z","match_totals_all":{"draws":1999,"losses":2848,"wins":825},"match_totals_tracks":{"highest":{"draws":1076,"losses":1371,"wins":521},"none":{"draws":923,"losses":1477,"wins":304}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":40.21973759032722,"mean":17.333790061961302,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":74,"overall_ranking_status":"partial","per_game":{"GB2-02":10.959437842954705,"GB2-03":18.880268510400633,"GB2-04":9.886754659027098,"GB2-05":40.21973759032722,"GB2-06":33.94102069850164,"GB2-07":18.907137280777043,"GB2-08":18.16558703798724},"per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":308,"wins":21},"GB2-02":{"draws":719,"losses":155,"wins":20},"GB2-03":{"draws":211,"losses":345,"wins":174},"GB2-04":{"draws":428,"losses":236,"wins":64},"GB2-05":{"draws":0,"losses":519,"wins":251},"GB2-06":{"draws":22,"losses":589,"wins":185},"GB2-07":{"draws":0,"losses":374,"wins":60},"GB2-08":{"draws":584,"losses":322,"wins":50}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":377,"losses":83,"wins":20},"GB2-03":{"draws":115,"losses":160,"wins":81},"GB2-04":{"draws":263,"losses":85,"wins":28},"GB2-05":{"draws":0,"losses":208,"wins":198},"GB2-06":{"draws":19,"losses":274,"wins":107},"GB2-07":{"draws":0,"losses":374,"wins":60},"GB2-08":{"draws":302,"losses":187,"wins":27}},"none":{"GB2-01":{"draws":35,"losses":308,"wins":21},"GB2-02":{"draws":342,"losses":72,"wins":0},"GB2-03":{"draws":96,"losses":185,"wins":93},"GB2-04":{"draws":165,"losses":151,"wins":36},"GB2-05":{"draws":0,"losses":311,"wins":53},"GB2-06":{"draws":3,"losses":315,"wins":78},"GB2-08":{"draws":282,"losses":135,"wins":23}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1438.979825296887,"GB2-03":1341.2922856545676,"GB2-04":1407.7238757440234,"GB2-05":1383.3115895288568,"GB2-06":1128.7211649728456,"GB2-07":955.6109111081545,"GB2-08":1279.9060068062165},"none":{"GB2-01":977.1142547404326,"GB2-02":1400.516462384792,"GB2-03":1318.833677848819,"GB2-04":1331.6899306081011,"GB2-05":952.4159343738606,"GB2-06":1015.8235570020754,"GB2-08":1279.7419984937205}},"per_game_tracks":{"highest":{"GB2-02":10.959437842954705,"GB2-03":18.880268510400633,"GB2-04":9.886754659027098,"GB2-05":40.21973759032722,"GB2-06":33.94102069850164,"GB2-07":18.907137280777043,"GB2-08":18.16558703798724},"none":{"GB2-01":10.787926994966133,"GB2-02":6.2294693270737636,"GB2-03":16.97761295019025,"GB2-04":0.0,"GB2-05":19.2599893219168,"GB2-06":28.54123176955195,"GB2-08":18.154741330506113}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.857665496119484,"none":13.809914627803119},"reasoning_agg":{"highest":{"max":40.21973759032722,"mean":20.857665496119484,"min":9.886754659027098},"none":{"max":28.54123176955195,"mean":13.809914627803119,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":40.21973759032722,"reasoning_variance":7.047750868316365},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":40.21973759032722,"expected_score":9.885299865457954,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.97236563066153},"none":{"ceiling_score":28.54123176955195,"expected_score":13.092637299312287,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.717277328490832}}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:adf7f523552132a5","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":17.74296281010806,"none":22.23274017516591},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:07:06Z","match_totals_all":{"draws":1354,"losses":2433,"wins":807},"match_totals_tracks":{"medium":{"draws":200,"losses":1329,"wins":325},"none":{"draws":1154,"losses":1104,"wins":482}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":56.41590518983862,"mean":16.928799877385778,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":75,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-02":{"draws":315,"losses":110,"wins":9},"GB2-03":{"draws":267,"losses":244,"wins":63},"GB2-04":{"draws":277,"losses":62,"wins":17},"GB2-05":{"draws":0,"losses":494,"wins":194},"GB2-06":{"draws":35,"losses":630,"wins":89},"GB2-07":{"draws":0,"losses":373,"wins":403},"GB2-08":{"draws":460,"losses":520,"wins":32}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":116,"losses":144,"wins":38},"GB2-05":{"draws":0,"losses":283,"wins":67},"GB2-06":{"draws":30,"losses":298,"wins":48},"GB2-07":{"draws":0,"losses":258,"wins":142},"GB2-08":{"draws":54,"losses":346,"wins":30}},"none":{"GB2-02":{"draws":315,"losses":110,"wins":9},"GB2-03":{"draws":151,"losses":100,"wins":25},"GB2-04":{"draws":277,"losses":62,"wins":17},"GB2-05":{"draws":0,"losses":211,"wins":127},"GB2-06":{"draws":5,"losses":332,"wins":41},"GB2-07":{"draws":0,"losses":115,"wins":261},"GB2-08":{"draws":406,"losses":174,"wins":2}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1284.9390256860013,"GB2-05":952.5018695839257,"GB2-06":933.5637801054097,"GB2-07":1183.696892132104,"GB2-08":1005.2067969313983},"none":{"GB2-02":1372.2273227587168,"GB2-03":1292.9868006697534,"GB2-04":1415.6901094849802,"GB2-05":1262.2448257582232,"GB2-06":820.0332190842747,"GB2-07":1678.7564499559462,"GB2-08":1265.9783384889204}},"per_game_tracks":{"medium":{"GB2-03":14.106114905575271,"GB2-05":19.264169406697903,"GB2-06":24.60682216984202,"GB2-07":30.737707568425126,"GB2-08":0.0},"none":{"GB2-02":2.750659112831687,"GB2-03":14.787908895327323,"GB2-04":10.922610399676982,"GB2-05":34.330773842501024,"GB2-06":19.17675967765803,"GB2-07":56.41590518983862,"GB2-08":17.24456410832772}},"provider_color":"#111827","provider_company":"Nex AGI","provider_key":"nex-agi","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":15.775972719150754,"none":18.081627035620798},"reasoning_agg":{"medium":{"max":30.737707568425126,"mean":15.775972719150754,"min":0.0},"none":{"max":56.41590518983862,"mean":18.081627035620798,"min":2.750659112831687}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":56.41590518983862,"reasoning_variance":2.3056543164700436},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":30.737707568425126,"expected_score":12.40621960663757,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.369753112513184},"none":{"ceiling_score":56.41590518983862,"expected_score":23.532327202327508,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.45070016670671}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:5c001adb5b86655b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994024999999998},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706874999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.08108399999999999},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.047068750000000006},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0422995,"mean":0.014503875,"median":0.010566625,"min":0.003432,"recorded_attempt_count":50,"run_count":24,"total":0.348093},"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":20.246679470083343,"highest":21.411671813832474,"medium":20.620020331980847,"none":13.553952687925923},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T14:23:07Z","match_totals_all":{"draws":1468,"losses":3534,"wins":878},"match_totals_tracks":{"highest":{"draws":520,"losses":1072,"wins":299},"medium":{"draws":558,"losses":1313,"wins":396},"none":{"draws":390,"losses":1149,"wins":183}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":35.666530535729535,"mean":16.75947205701339,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":76,"overall_ranking_status":"partial","per_game":{"GB2-04":11.366997288610671,"GB2-05":15.473991714346251,"GB2-06":27.125216573733876,"GB2-07":35.666530535729535,"GB2-08":17.425622956742032},"per_game_all":{"GB2-05":15.727199028913445,"GB2-06":30.57956266642944,"GB2-07":14.433276714907144},"per_game_match_totals_all":{"GB2-01":{"draws":232,"losses":344,"wins":74},"GB2-02":{"draws":325,"losses":49,"wins":4},"GB2-04":{"draws":493,"losses":149,"wins":57},"GB2-05":{"draws":0,"losses":813,"wins":161},"GB2-06":{"draws":6,"losses":846,"wins":293},"GB2-07":{"draws":0,"losses":950,"wins":174},"GB2-08":{"draws":412,"losses":383,"wins":115}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":259,"losses":70,"wins":21},"GB2-05":{"draws":0,"losses":275,"wins":53},"GB2-06":{"draws":0,"losses":300,"wins":81},"GB2-07":{"draws":0,"losses":259,"wins":127},"GB2-08":{"draws":261,"losses":168,"wins":17}},"medium":{"GB2-01":{"draws":172,"losses":116,"wins":50},"GB2-04":{"draws":234,"losses":79,"wins":36},"GB2-05":{"draws":0,"losses":262,"wins":74},"GB2-06":{"draws":1,"losses":292,"wins":105},"GB2-07":{"draws":0,"losses":349,"wins":33},"GB2-08":{"draws":151,"losses":215,"wins":98}},"none":{"GB2-01":{"draws":60,"losses":228,"wins":24},"GB2-02":{"draws":325,"losses":49,"wins":4},"GB2-05":{"draws":0,"losses":276,"wins":34},"GB2-06":{"draws":5,"losses":254,"wins":107},"GB2-07":{"draws":0,"losses":342,"wins":14}}},"per_game_raw_elo_all":{"GB2-05":879.7879634490772,"GB2-06":1058.4405343577337,"GB2-07":869.3576831301093},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1419.107660491109,"GB2-05":874.5824652578175,"GB2-06":986.2178204516993,"GB2-07":1278.7215100885805,"GB2-08":1268.7163024477095},"medium":{"GB2-01":1313.1769981314121,"GB2-04":1424.8067131598355,"GB2-05":983.8290180550625,"GB2-06":1082.9644642677572,"GB2-07":738.2583860182528,"GB2-08":1303.115814121326},"none":{"GB2-01":1055.699971937463,"GB2-02":1417.3723725983562,"GB2-05":780.9524070343515,"GB2-06":1106.1393183537448,"GB2-07":591.0931532834944}},"per_game_tracks":{"highest":{"GB2-04":11.366997288610671,"GB2-05":15.473991714346251,"GB2-06":27.125216573733876,"GB2-07":35.666530535729535,"GB2-08":17.425622956742032},"medium":{"GB2-01":31.737830946992926,"GB2-04":12.10804966230831,"GB2-05":20.787993418536594,"GB2-06":31.75251971665116,"GB2-07":7.633299608991899,"GB2-08":19.700428638404173},"none":{"GB2-01":15.686902735825122,"GB2-02":8.302297041043715,"GB2-05":10.919611953857492,"GB2-06":32.860951708903286,"GB2-07":0.0}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":19.03796756052452,"medium":19.189091115725464,"none":12.05135749479019},"reasoning_agg":{"highest":{"max":35.666530535729535,"mean":19.03796756052452,"min":11.366997288610671},"medium":{"max":31.75251971665116,"mean":19.189091115725464,"min":7.633299608991899},"none":{"max":32.860951708903286,"mean":12.05135749479019,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":35.666530535729535,"expected_score":10.962476877240922,"reasoning_variance":7.137733620935274,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.796995179772468},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":35.666530535729535,"expected_score":8.374939539123933,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.663028021400589},"medium":{"ceiling_score":31.75251971665116,"expected_score":16.206155446348387,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.9829356693770777},"none":{"ceiling_score":32.860951708903286,"expected_score":10.127079807904698,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.9242776868854925}}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:ba2d1a0743a2b288","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":92},"cost_is_complete":false,"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":19.280193720949143,"none":15.889598637016093},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":2657,"losses":3741,"wins":1192},"match_totals_tracks":{"medium":{"draws":926,"losses":1901,"wins":749},"none":{"draws":1731,"losses":1840,"wins":443}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":36.92814018225363,"mean":14.73052337811163,"min":1.8079039272629827},"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":77,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":316,"losses":721,"wins":233},"GB2-02":{"draws":764,"losses":199,"wins":11},"GB2-03":{"draws":219,"losses":356,"wins":79},"GB2-04":{"draws":711,"losses":147,"wins":58},"GB2-06":{"draws":13,"losses":1139,"wins":230},"GB2-07":{"draws":0,"losses":872,"wins":548},"GB2-08":{"draws":634,"losses":307,"wins":33}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":125,"losses":356,"wins":29},"GB2-02":{"draws":409,"losses":121,"wins":6},"GB2-04":{"draws":388,"losses":102,"wins":34},"GB2-06":{"draws":4,"losses":450,"wins":132},"GB2-07":{"draws":0,"losses":872,"wins":548}},"none":{"GB2-01":{"draws":191,"losses":365,"wins":204},"GB2-02":{"draws":355,"losses":78,"wins":5},"GB2-03":{"draws":219,"losses":356,"wins":79},"GB2-04":{"draws":323,"losses":45,"wins":24},"GB2-06":{"draws":9,"losses":689,"wins":98},"GB2-08":{"draws":634,"losses":307,"wins":33}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1125.67512154343,"GB2-02":1364.5609852940931,"GB2-04":1390.435883940974,"GB2-06":1045.8431051619382,"GB2-07":1303.0445534330895},"none":{"GB2-01":1355.588791945279,"GB2-02":1397.1264040612816,"GB2-03":1238.8119816663927,"GB2-04":1437.038553633983,"GB2-06":714.754540138695,"GB2-08":1263.8679535231934}},"per_game_tracks":{"medium":{"GB2-01":20.04910203373474,"GB2-02":1.8079039272629827,"GB2-04":7.638783266796015,"GB2-06":29.977039194698342,"GB2-07":36.92814018225363},"none":{"GB2-01":34.381750942015856,"GB2-02":5.812582504830717,"GB2-03":10.198309152918036,"GB2-04":13.698565655922309,"GB2-06":14.141377128437208,"GB2-08":17.105006437972413}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":15.332973711229139,"none":14.128073044994125},"reasoning_agg":{"medium":{"max":36.92814018225363,"mean":15.332973711229139,"min":1.8079039272629827},"none":{"max":34.381750942015856,"mean":14.128073044994125,"min":5.812582504830717}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":36.92814018225363,"reasoning_variance":1.2049006662350141},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":36.92814018225363,"expected_score":12.689195249389602,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.6437784618395366},"none":{"ceiling_score":34.381750942015856,"expected_score":16.312747782176512,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1846747371823874}}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:65196d7ce2f62e3d","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":true,"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":0.05924464},"medium":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"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},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"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},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.02253992},"historical-provider-setting-intensive":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":true,"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":0.05924464}},"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":24,"cost_basis_counts":{"provider_reported":54},"cost_is_complete":true,"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":0.0961938},"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":15.718857447275008,"medium":9.79279664054907},"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":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","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":"2026-10-06T08:33:29Z","match_totals_all":{"draws":543,"losses":704,"wins":25},"match_totals_tracks":{"highest":{"draws":252,"losses":121,"wins":9},"medium":{"draws":291,"losses":583,"wins":16}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":15.718857447275008,"mean":8.135520734659782,"min":5.058036164457326},"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":78,"overall_ranking_status":"partial","per_game":{"GB2-03":15.718857447275008},"per_game_match_totals_all":{"GB2-03":{"draws":252,"losses":121,"wins":9},"GB2-07":{"draws":0,"losses":410,"wins":16},"GB2-08":{"draws":291,"losses":173,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":252,"losses":121,"wins":9}},"medium":{"GB2-07":{"draws":0,"losses":410,"wins":16},"GB2-08":{"draws":291,"losses":173,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1303.9755517883273},"medium":{"GB2-07":688.6089207042223,"GB2-08":1224.8918780139581}},"per_game_tracks":{"highest":{"GB2-03":15.718857447275008},"medium":{"GB2-07":5.058036164457326,"GB2-08":14.527557116640816}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":9.346488558006474,"medium":6.92455291131309},"reasoning_agg":{"highest":{"max":15.718857447275008,"mean":9.346488558006474,"min":15.718857447275008},"medium":{"max":14.527557116640816,"mean":6.92455291131309,"min":5.058036164457326}},"reasoning_labels":{"highest":"Full","medium":"Low","none":"Setting not tested"},"reasoning_settings":{"balanced":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":15.718857447275008,"reasoning_variance":2.4219356466933837},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":15.718857447275008,"expected_score":0.0,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.346488558006474},"medium":{"ceiling_score":14.527557116640816,"expected_score":8.128185865618262,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2036329543051716}}}],"public_release_id":"gb2-20261006-d1c76bc1df7d","rating_method":{"bootstrap_iterations":0,"first_player_advantage":false,"method":"glicko2_style"},"results_cut_id":"gb2-20261006-d1c76bc1df7d","schema_version":2,"snapshot_id":"20261006_165822","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-10-06 16:58 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":42,"wins":42},"claude-fable-5":{"draws":29,"losses":104,"wins":23},"claude-fable-5-1":{"draws":4,"losses":138,"wins":4},"claude-opus-4-5":{"draws":70,"losses":99,"wins":43},"claude-opus-4-8":{"draws":13,"losses":35,"wins":16},"claude-opus-5":{"draws":11,"losses":92,"wins":21},"claude-opus-5-5":{"draws":3,"losses":53,"wins":2},"claude-sonnet-5":{"draws":61,"losses":91,"wins":32},"claude-sonnet-5-5":{"draws":16,"losses":41,"wins":13},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":15},"deepseek/deepseek-v4-flash":{"draws":71,"losses":72,"wins":59},"deepseek/deepseek-v4-pro":{"draws":50,"losses":82,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":50,"losses":67,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":29,"wins":14},"fireworks/ember-1":{"draws":22,"losses":35,"wins":13},"gemini-3.1-pro-preview":{"draws":21,"losses":28,"wins":19},"google/gemini-3.1-flash-lite":{"draws":17,"losses":10,"wins":27},"google/gemini-3.5-flash":{"draws":56,"losses":87,"wins":37},"google/gemini-3.5-flash-lite":{"draws":121,"losses":101,"wins":102},"google/gemini-3.6-flash":{"draws":79,"losses":124,"wins":67},"google/gemini-3.8-flash":{"draws":42,"losses":88,"wins":30},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":8,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":8,"wins":0},"gpt-5":{"draws":21,"losses":27,"wins":24},"gpt-5.4":{"draws":43,"losses":55,"wins":36},"gpt-5.4-mini":{"draws":24,"losses":12,"wins":18},"gpt-5.4-nano":{"draws":20,"losses":30,"wins":36},"gpt-5.5":{"draws":38,"losses":41,"wins":15},"gpt-5.6-luna":{"draws":59,"losses":62,"wins":71},"gpt-5.6-sol":{"draws":24,"losses":96,"wins":24},"gpt-5.6-terra":{"draws":57,"losses":85,"wins":32},"gpt-6-astra":{"draws":8,"losses":100,"wins":12},"gpt-6-luna":{"draws":21,"losses":40,"wins":31},"gpt-6-sol":{"draws":5,"losses":49,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":63,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":16},"inception/mercury-2.5-preview":{"draws":58,"losses":33,"wins":41},"inclusionai/ling-3.0-flash":{"draws":35,"losses":16,"wins":39},"meituan/longcat-2.0":{"draws":49,"losses":31,"wins":48},"meta/muse-glimmer-30b":{"draws":71,"losses":46,"wins":59},"meta/muse-spark-1.2":{"draws":35,"losses":38,"wins":33},"meta/muse-spark-1.3":{"draws":31,"losses":74,"wins":23},"minimax/minimax-m3":{"draws":11,"losses":11,"wins":30},"mistralai/mistral-medium-3-5":{"draws":42,"losses":25,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":12,"wins":8},"moonshotai/kimi-k3":{"draws":44,"losses":66,"wins":32},"nex-agi/nex-n2-pro":{"draws":11,"losses":4,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":22,"wins":27},"o3":{"draws":38,"losses":99,"wins":61},"openai/gpt-oss-120b":{"draws":63,"losses":45,"wins":56},"poolside/laguna-s-2.1":{"draws":55,"losses":34,"wins":41},"qwen/qwen3.7-max":{"draws":24,"losses":21,"wins":21},"qwen/qwen3.7-plus":{"draws":20,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":66,"wins":36},"qwen/qwen3.8-27b":{"draws":19,"losses":49,"wins":32},"qwen/qwen3.8-flash":{"draws":43,"losses":54,"wins":31},"qwen/qwen3.8-max":{"draws":67,"losses":71,"wins":54},"qwen/qwen3.8-max-0902":{"draws":25,"losses":40,"wins":7},"stealth/ox-alpha":{"draws":129,"losses":271,"wins":112},"stealth/space-bunny-alpha":{"draws":14,"losses":21,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":23,"wins":30},"tencent/hy3-preview":{"draws":15,"losses":17,"wins":16},"tencent/hy4-preview":{"draws":61,"losses":87,"wins":28},"thinkingmachines/inkling":{"draws":55,"losses":42,"wins":77},"thinkingmachines/inkling-small":{"draws":72,"losses":43,"wins":81},"x-ai/grok-4.5":{"draws":40,"losses":94,"wins":26},"x-ai/grok-4.6":{"draws":50,"losses":95,"wins":25},"x-ai/grok-4.7":{"draws":3,"losses":48,"wins":9},"x-ai/grok-build-0.1":{"draws":12,"losses":4,"wins":16},"xiaomi/mimo-v2.5":{"draws":50,"losses":26,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":18,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":26,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":28,"wins":9},"z-ai/glm-5.2":{"draws":99,"losses":75,"wins":74},"z-ai/glm-5.3":{"draws":33,"losses":86,"wins":19},"z-ai/glm-5.3-flash":{"draws":55,"losses":90,"wins":31},"z-ai/glm-5.3-flashx":{"draws":17,"losses":47,"wins":10}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":23,"wins":104},"claude-fable-5":{"draws":22,"losses":51,"wins":51},"claude-fable-5-1":{"draws":11,"losses":190,"wins":39},"claude-opus-4-5":{"draws":45,"losses":32,"wins":181},"claude-opus-4-8":{"draws":15,"losses":24,"wins":51},"claude-opus-5":{"draws":28,"losses":147,"wins":63},"claude-opus-5-5":{"draws":10,"losses":78,"wins":10},"claude-sonnet-5":{"draws":47,"losses":30,"wins":129},"claude-sonnet-5-5":{"draws":13,"losses":19,"wins":18},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":40},"deepseek/deepseek-v4-flash":{"draws":44,"losses":17,"wins":169},"deepseek/deepseek-v4-pro":{"draws":41,"losses":48,"wins":103},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":35,"wins":105},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":19,"wins":52},"fireworks/ember-1":{"draws":13,"losses":11,"wins":38},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":31},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":45},"google/gemini-3.5-flash":{"draws":42,"losses":40,"wins":148},"google/gemini-3.5-flash-lite":{"draws":67,"losses":38,"wins":205},"google/gemini-3.6-flash":{"draws":59,"losses":96,"wins":175},"google/gemini-3.8-flash":{"draws":30,"losses":77,"wins":101},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":31},"gpt-4.1":{"draws":5,"losses":9,"wins":24},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":20,"losses":21,"wins":59},"gpt-5.4":{"draws":55,"losses":69,"wins":94},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":49},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":77},"gpt-5.5":{"draws":17,"losses":31,"wins":50},"gpt-5.6-luna":{"draws":45,"losses":29,"wins":100},"gpt-5.6-sol":{"draws":30,"losses":88,"wins":108},"gpt-5.6-terra":{"draws":60,"losses":31,"wins":131},"gpt-6-astra":{"draws":17,"losses":170,"wins":41},"gpt-6-luna":{"draws":20,"losses":20,"wins":64},"gpt-6-sol":{"draws":12,"losses":42,"wins":28},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":11},"inception/mercury-2.5-preview":{"draws":37,"losses":4,"wins":67},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":59},"meituan/longcat-2.0":{"draws":23,"losses":24,"wins":101},"meta/muse-glimmer-30b":{"draws":39,"losses":9,"wins":86},"meta/muse-spark-1.2":{"draws":24,"losses":34,"wins":88},"meta/muse-spark-1.3":{"draws":37,"losses":54,"wins":99},"minimax/minimax-m3":{"draws":13,"losses":5,"wins":36},"mistralai/mistral-medium-3-5":{"draws":34,"losses":9,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":12},"moonshotai/kimi-k3":{"draws":38,"losses":31,"wins":133},"nex-agi/nex-n2-pro":{"draws":9,"losses":1,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":6,"wins":65},"o3":{"draws":17,"losses":34,"wins":161},"openai/gpt-oss-120b":{"draws":43,"losses":14,"wins":85},"poolside/laguna-s-2.1":{"draws":30,"losses":19,"wins":83},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":32},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":53,"losses":53,"wins":106},"qwen/qwen3.8-27b":{"draws":12,"losses":25,"wins":63},"qwen/qwen3.8-flash":{"draws":38,"losses":21,"wins":73},"qwen/qwen3.8-max":{"draws":33,"losses":56,"wins":109},"qwen/qwen3.8-max-0902":{"draws":16,"losses":16,"wins":54},"stealth/ox-alpha":{"draws":144,"losses":142,"wins":404},"stealth/space-bunny-alpha":{"draws":21,"losses":4,"wins":25},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":63},"tencent/hy3-preview":{"draws":16,"losses":5,"wins":31},"tencent/hy4-preview":{"draws":34,"losses":51,"wins":121},"thinkingmachines/inkling":{"draws":30,"losses":7,"wins":113},"thinkingmachines/inkling-small":{"draws":44,"losses":17,"wins":105},"x-ai/grok-4.5":{"draws":27,"losses":63,"wins":100},"x-ai/grok-4.6":{"draws":57,"losses":81,"wins":104},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":20},"x-ai/grok-build-0.1":{"draws":8,"losses":7,"wins":29},"xiaomi/mimo-v2.5":{"draws":32,"losses":4,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":53},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":11,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":17,"wins":31},"z-ai/glm-5.2":{"draws":64,"losses":48,"wins":166},"z-ai/glm-5.3":{"draws":35,"losses":108,"wins":79},"z-ai/glm-5.3-flash":{"draws":39,"losses":70,"wins":113},"z-ai/glm-5.3-flashx":{"draws":17,"losses":23,"wins":50}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":138},"claude-fable-5":{"draws":11,"losses":39,"wins":190},"claude-fable-5-1":{"draws":10,"losses":97,"wins":97},"claude-opus-4-5":{"draws":9,"losses":5,"wins":216},"claude-opus-4-8":{"draws":4,"losses":7,"wins":61},"claude-opus-5":{"draws":19,"losses":52,"wins":99},"claude-opus-5-5":{"draws":9,"losses":38,"wins":31},"claude-sonnet-5":{"draws":12,"losses":7,"wins":197},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":59},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":38},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":209},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":156},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":4,"wins":159},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":5,"wins":71},"fireworks/ember-1":{"draws":3,"losses":4,"wins":103},"gemini-3.1-pro-preview":{"draws":2,"losses":3,"wins":79},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":52},"google/gemini-3.5-flash":{"draws":17,"losses":12,"wins":183},"google/gemini-3.5-flash-lite":{"draws":24,"losses":1,"wins":229},"google/gemini-3.6-flash":{"draws":22,"losses":25,"wins":257},"google/gemini-3.8-flash":{"draws":20,"losses":20,"wins":184},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":34},"gpt-4.1":{"draws":1,"losses":0,"wins":21},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":1,"wins":77},"gpt-5.4":{"draws":14,"losses":21,"wins":161},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":47},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":67},"gpt-5.5":{"draws":4,"losses":8,"wins":76},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":124},"gpt-5.6-sol":{"draws":22,"losses":35,"wins":181},"gpt-5.6-terra":{"draws":19,"losses":6,"wins":193},"gpt-6-astra":{"draws":21,"losses":135,"wins":82},"gpt-6-luna":{"draws":5,"losses":5,"wins":80},"gpt-6-sol":{"draws":2,"losses":23,"wins":39},"gpt-6.1-sol":{"draws":10,"losses":45,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":84},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":75},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":92},"meta/muse-glimmer-30b":{"draws":10,"losses":1,"wins":102},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":116},"meta/muse-spark-1.3":{"draws":8,"losses":10,"wins":166},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":61},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":60},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k3":{"draws":19,"losses":7,"wins":174},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":49},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":86},"o3":{"draws":0,"losses":9,"wins":157},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":117},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":102},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":57},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":9,"wins":176},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":98},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":127},"qwen/qwen3.8-max":{"draws":6,"losses":7,"wins":173},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":66},"stealth/ox-alpha":{"draws":62,"losses":36,"wins":602},"stealth/space-bunny-alpha":{"draws":3,"losses":1,"wins":68},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":41},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":48},"tencent/hy4-preview":{"draws":6,"losses":16,"wins":180},"thinkingmachines/inkling":{"draws":11,"losses":0,"wins":125},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":148},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":162},"x-ai/grok-4.6":{"draws":15,"losses":34,"wins":193},"x-ai/grok-4.7":{"draws":5,"losses":17,"wins":46},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":40},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":144},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":43},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":8,"wins":41},"z-ai/glm-5.2":{"draws":22,"losses":6,"wins":198},"z-ai/glm-5.3":{"draws":13,"losses":35,"wins":148},"z-ai/glm-5.3-flash":{"draws":21,"losses":25,"wins":208},"z-ai/glm-5.3-flashx":{"draws":10,"losses":9,"wins":85}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":45,"losses":31,"wins":80},"claude-fable-5":{"draws":36,"losses":126,"wins":26},"claude-fable-5-1":{"draws":8,"losses":166,"wins":4},"claude-opus-4-5":{"draws":73,"losses":65,"wins":84},"claude-opus-4-8":{"draws":45,"losses":82,"wins":45},"claude-opus-5":{"draws":52,"losses":258,"wins":38},"claude-opus-5-5":{"draws":5,"losses":61,"wins":2},"claude-sonnet-5":{"draws":86,"losses":51,"wins":117},"claude-sonnet-5-5":{"draws":12,"losses":30,"wins":14},"cohere/north-mini-code":{"draws":13,"losses":11,"wins":48},"deepseek/deepseek-v4-flash":{"draws":64,"losses":47,"wins":103},"deepseek/deepseek-v4-pro":{"draws":36,"losses":52,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":44,"losses":67,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":28,"wins":10},"fireworks/ember-1":{"draws":23,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":27},"google/gemini-3.1-flash-lite":{"draws":29,"losses":7,"wins":68},"google/gemini-3.5-flash":{"draws":49,"losses":75,"wins":62},"google/gemini-3.5-flash-lite":{"draws":181,"losses":126,"wins":245},"google/gemini-3.6-flash":{"draws":134,"losses":224,"wins":166},"google/gemini-3.8-flash":{"draws":42,"losses":93,"wins":35},"google/gemma-4-31b-it":{"draws":18,"losses":17,"wins":41},"gpt-4.1":{"draws":26,"losses":18,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":8},"gpt-5":{"draws":43,"losses":32,"wins":37},"gpt-5.4":{"draws":70,"losses":121,"wins":51},"gpt-5.4-mini":{"draws":48,"losses":25,"wins":35},"gpt-5.4-nano":{"draws":45,"losses":39,"wins":86},"gpt-5.5":{"draws":60,"losses":67,"wins":31},"gpt-5.6-luna":{"draws":81,"losses":61,"wins":96},"gpt-5.6-sol":{"draws":41,"losses":185,"wins":56},"gpt-5.6-terra":{"draws":64,"losses":37,"wins":65},"gpt-6-astra":{"draws":14,"losses":154,"wins":10},"gpt-6-luna":{"draws":30,"losses":28,"wins":32},"gpt-6-sol":{"draws":6,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":50,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":46,"losses":8,"wins":58},"inclusionai/ling-3.0-flash":{"draws":41,"losses":20,"wins":63},"meituan/longcat-2.0":{"draws":66,"losses":43,"wins":127},"meta/muse-glimmer-30b":{"draws":46,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":47,"losses":79,"wins":48},"meta/muse-spark-1.3":{"draws":34,"losses":74,"wins":32},"minimax/minimax-m3":{"draws":28,"losses":11,"wins":45},"mistralai/mistral-medium-3-5":{"draws":23,"losses":9,"wins":70},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":15,"wins":24},"moonshotai/kimi-k3":{"draws":109,"losses":101,"wins":74},"nex-agi/nex-n2-pro":{"draws":23,"losses":11,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":19,"wins":64},"o3":{"draws":56,"losses":100,"wins":220},"openai/gpt-oss-120b":{"draws":38,"losses":15,"wins":67},"poolside/laguna-s-2.1":{"draws":96,"losses":20,"wins":108},"qwen/qwen3.7-max":{"draws":30,"losses":24,"wins":46},"qwen/qwen3.7-plus":{"draws":22,"losses":19,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":65,"wins":49},"qwen/qwen3.8-27b":{"draws":21,"losses":35,"wins":40},"qwen/qwen3.8-flash":{"draws":44,"losses":38,"wins":42},"qwen/qwen3.8-max":{"draws":49,"losses":74,"wins":40},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":7},"stealth/ox-alpha":{"draws":166,"losses":216,"wins":151},"stealth/space-bunny-alpha":{"draws":16,"losses":5,"wins":13},"stepfun/step-3.7-flash":{"draws":26,"losses":20,"wins":66},"tencent/hy3-preview":{"draws":35,"losses":19,"wins":36},"tencent/hy4-preview":{"draws":43,"losses":76,"wins":51},"thinkingmachines/inkling":{"draws":75,"losses":41,"wins":136},"thinkingmachines/inkling-small":{"draws":58,"losses":25,"wins":92},"x-ai/grok-4.5":{"draws":104,"losses":131,"wins":89},"x-ai/grok-4.6":{"draws":48,"losses":98,"wins":34},"x-ai/grok-4.7":{"draws":7,"losses":44,"wins":7},"x-ai/grok-build-0.1":{"draws":22,"losses":4,"wins":32},"xiaomi/mimo-v2.5":{"draws":79,"losses":34,"wins":119},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":42,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":88,"losses":82,"wins":144},"z-ai/glm-5.3":{"draws":42,"losses":93,"wins":23},"z-ai/glm-5.3-flash":{"draws":45,"losses":94,"wins":51},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":6}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":16,"wins":35},"claude-fable-5":{"draws":15,"losses":51,"wins":24},"claude-fable-5-1":{"draws":4,"losses":61,"wins":7},"claude-opus-4-5":{"draws":71,"losses":68,"wins":147},"claude-opus-4-8":{"draws":24,"losses":50,"wins":50},"claude-opus-5":{"draws":65,"losses":215,"wins":68},"claude-opus-5-5":{"draws":8,"losses":72,"wins":6},"claude-sonnet-5":{"draws":22,"losses":18,"wins":34},"claude-sonnet-5-5":{"draws":13,"losses":28,"wins":27},"cohere/north-mini-code":{"draws":15,"losses":5,"wins":70},"deepseek/deepseek-v4-flash":{"draws":51,"losses":15,"wins":90},"deepseek/deepseek-v4-pro":{"draws":17,"losses":27,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":24,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":25,"wins":20},"fireworks/ember-1":{"draws":21,"losses":13,"wins":22},"gemini-3.1-pro-preview":{"draws":19,"losses":9,"wins":42},"google/gemini-3.1-flash-lite":{"draws":32,"losses":8,"wins":96},"google/gemini-3.5-flash":{"draws":39,"losses":30,"wins":63},"google/gemini-3.5-flash-lite":{"draws":50,"losses":24,"wins":112},"google/gemini-3.6-flash":{"draws":57,"losses":85,"wins":72},"google/gemini-3.8-flash":{"draws":19,"losses":36,"wins":35},"google/gemma-4-31b-it":{"draws":30,"losses":10,"wins":50},"gpt-4.1":{"draws":24,"losses":7,"wins":33},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":37,"losses":36,"wins":71},"gpt-5.4":{"draws":9,"losses":31,"wins":24},"gpt-5.4-mini":{"draws":39,"losses":36,"wins":59},"gpt-5.4-nano":{"draws":46,"losses":45,"wins":109},"gpt-5.5":{"draws":54,"losses":72,"wins":52},"gpt-5.6-luna":{"draws":35,"losses":8,"wins":39},"gpt-5.6-sol":{"draws":21,"losses":34,"wins":33},"gpt-5.6-terra":{"draws":34,"losses":26,"wins":46},"gpt-6-astra":{"draws":9,"losses":71,"wins":6},"gpt-6-luna":{"draws":19,"losses":30,"wins":39},"gpt-6-sol":{"draws":8,"losses":43,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":9,"wins":39},"inclusionai/ling-3.0-flash":{"draws":48,"losses":0,"wins":50},"meituan/longcat-2.0":{"draws":27,"losses":27,"wins":71},"meta/muse-glimmer-30b":{"draws":27,"losses":9,"wins":42},"meta/muse-spark-1.2":{"draws":18,"losses":21,"wins":33},"meta/muse-spark-1.3":{"draws":26,"losses":32,"wins":30},"minimax/minimax-m3":{"draws":23,"losses":16,"wins":59},"mistralai/mistral-medium-3-5":{"draws":17,"losses":3,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":10,"wins":22},"moonshotai/kimi-k3":{"draws":30,"losses":38,"wins":32},"nex-agi/nex-n2-pro":{"draws":37,"losses":9,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":21,"wins":94},"o3":{"draws":16,"losses":39,"wins":107},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":40,"losses":16,"wins":78},"qwen/qwen3.7-max":{"draws":38,"losses":26,"wins":54},"qwen/qwen3.7-plus":{"draws":20,"losses":18,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":26,"wins":28},"qwen/qwen3.8-27b":{"draws":12,"losses":18,"wins":22},"qwen/qwen3.8-flash":{"draws":21,"losses":13,"wins":28},"qwen/qwen3.8-max":{"draws":18,"losses":30,"wins":32},"qwen/qwen3.8-max-0902":{"draws":23,"losses":28,"wins":17},"stealth/ox-alpha":{"draws":72,"losses":119,"wins":99},"stealth/space-bunny-alpha":{"draws":17,"losses":8,"wins":27},"stepfun/step-3.7-flash":{"draws":21,"losses":20,"wins":53},"tencent/hy3-preview":{"draws":32,"losses":17,"wins":41},"tencent/hy4-preview":{"draws":20,"losses":37,"wins":29},"thinkingmachines/inkling":{"draws":35,"losses":21,"wins":90},"thinkingmachines/inkling-small":{"draws":25,"losses":6,"wins":49},"x-ai/grok-4.5":{"draws":48,"losses":59,"wins":59},"x-ai/grok-4.6":{"draws":25,"losses":43,"wins":34},"x-ai/grok-4.7":{"draws":13,"losses":32,"wins":11},"x-ai/grok-build-0.1":{"draws":22,"losses":13,"wins":47},"xiaomi/mimo-v2.5":{"draws":92,"losses":28,"wins":158},"xiaomi/mimo-v2.5-pro":{"draws":29,"losses":30,"wins":59},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":26,"wins":22},"z-ai/glm-5.2":{"draws":91,"losses":65,"wins":132},"z-ai/glm-5.3":{"draws":21,"losses":49,"wins":24},"z-ai/glm-5.3-flash":{"draws":15,"losses":39,"wins":40},"z-ai/glm-5.3-flashx":{"draws":13,"losses":28,"wins":33}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":21,"wins":92},"claude-fable-5":{"draws":28,"losses":63,"wins":147},"claude-fable-5-1":{"draws":19,"losses":99,"wins":52},"claude-opus-4-5":{"draws":87,"losses":69,"wins":418},"claude-opus-4-8":{"draws":65,"losses":68,"wins":215},"claude-opus-5":{"draws":90,"losses":343,"wins":343},"claude-opus-5-5":{"draws":11,"losses":70,"wins":39},"claude-sonnet-5":{"draws":20,"losses":28,"wins":106},"claude-sonnet-5-5":{"draws":15,"losses":38,"wins":81},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":89},"deepseek/deepseek-v4-flash":{"draws":33,"losses":15,"wins":208},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":115},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":112},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":13,"wins":77},"fireworks/ember-1":{"draws":16,"losses":16,"wins":74},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":78},"google/gemini-3.1-flash-lite":{"draws":20,"losses":7,"wins":101},"google/gemini-3.5-flash":{"draws":29,"losses":22,"wins":169},"google/gemini-3.5-flash-lite":{"draws":51,"losses":26,"wins":307},"google/gemini-3.6-flash":{"draws":52,"losses":68,"wins":294},"google/gemini-3.8-flash":{"draws":24,"losses":40,"wins":128},"google/gemma-4-31b-it":{"draws":18,"losses":14,"wins":84},"gpt-4.1":{"draws":16,"losses":8,"wins":97},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":31,"losses":20,"wins":211},"gpt-5.4":{"draws":12,"losses":16,"wins":112},"gpt-5.4-mini":{"draws":36,"losses":12,"wins":138},"gpt-5.4-nano":{"draws":34,"losses":27,"wins":231},"gpt-5.5":{"draws":46,"losses":85,"wins":233},"gpt-5.6-luna":{"draws":16,"losses":10,"wins":102},"gpt-5.6-sol":{"draws":27,"losses":39,"wins":126},"gpt-5.6-terra":{"draws":24,"losses":12,"wins":138},"gpt-6-astra":{"draws":20,"losses":95,"wins":33},"gpt-6-luna":{"draws":24,"losses":13,"wins":109},"gpt-6-sol":{"draws":16,"losses":34,"wins":52},"gpt-6.1-sol":{"draws":18,"losses":54,"wins":34},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":18},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":67},"inclusionai/ling-3.0-flash":{"draws":30,"losses":7,"wins":101},"meituan/longcat-2.0":{"draws":28,"losses":27,"wins":214},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":89},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":92},"meta/muse-spark-1.3":{"draws":25,"losses":33,"wins":112},"minimax/minimax-m3":{"draws":22,"losses":10,"wins":120},"mistralai/mistral-medium-3-5":{"draws":13,"losses":9,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":4,"wins":87},"moonshotai/kimi-k3":{"draws":35,"losses":36,"wins":157},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":102},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":6,"wins":194},"o3":{"draws":10,"losses":17,"wins":241},"openai/gpt-oss-120b":{"draws":17,"losses":1,"wins":114},"poolside/laguna-s-2.1":{"draws":24,"losses":22,"wins":242},"qwen/qwen3.7-max":{"draws":20,"losses":20,"wins":136},"qwen/qwen3.7-plus":{"draws":21,"losses":13,"wins":86},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":28,"wins":118},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":56},"qwen/qwen3.8-flash":{"draws":20,"losses":10,"wins":98},"qwen/qwen3.8-max":{"draws":23,"losses":15,"wins":112},"qwen/qwen3.8-max-0902":{"draws":20,"losses":23,"wins":67},"stealth/ox-alpha":{"draws":70,"losses":73,"wins":404},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":77},"stepfun/step-3.7-flash":{"draws":14,"losses":2,"wins":112},"tencent/hy3-preview":{"draws":33,"losses":14,"wins":127},"tencent/hy4-preview":{"draws":18,"losses":17,"wins":131},"thinkingmachines/inkling":{"draws":30,"losses":25,"wins":213},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":116},"x-ai/grok-4.5":{"draws":49,"losses":69,"wins":226},"x-ai/grok-4.6":{"draws":26,"losses":51,"wins":142},"x-ai/grok-4.7":{"draws":12,"losses":51,"wins":39},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":69},"xiaomi/mimo-v2.5":{"draws":63,"losses":24,"wins":307},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":6,"wins":123},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":8,"wins":59},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":19,"wins":41},"z-ai/glm-5.2":{"draws":82,"losses":37,"wins":321},"z-ai/glm-5.3":{"draws":22,"losses":41,"wins":89},"z-ai/glm-5.3-flash":{"draws":24,"losses":54,"wins":160},"z-ai/glm-5.3-flashx":{"draws":17,"losses":13,"wins":76}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":53},"claude-fable-5":{"draws":10,"losses":10,"wins":78},"claude-fable-5-1":{"draws":9,"losses":31,"wins":38},"claude-opus-4-5":{"draws":12,"losses":5,"wins":107},"claude-opus-4-8":{"draws":8,"losses":6,"wins":72},"claude-opus-5":{"draws":11,"losses":39,"wins":70},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":4,"losses":6,"wins":52},"claude-sonnet-5-5":{"draws":14,"losses":22,"wins":96},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":44},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":104},"deepseek/deepseek-v4-pro":{"draws":3,"losses":0,"wins":69},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":124},"fireworks/ember-1":{"draws":8,"losses":10,"wins":102},"gemini-3.1-pro-preview":{"draws":7,"losses":7,"wins":124},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":57},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":72},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":102},"google/gemini-3.6-flash":{"draws":11,"losses":12,"wins":121},"google/gemini-3.8-flash":{"draws":10,"losses":6,"wins":44},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":38},"gpt-4.1":{"draws":4,"losses":1,"wins":33},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":3,"wins":44},"gpt-5.4":{"draws":7,"losses":4,"wins":57},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":44},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":52},"gpt-5.5":{"draws":5,"losses":8,"wins":51},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":66},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":65},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":93},"gpt-6-astra":{"draws":11,"losses":34,"wins":27},"gpt-6-luna":{"draws":16,"losses":1,"wins":133},"gpt-6-sol":{"draws":13,"losses":39,"wins":104},"gpt-6.1-sol":{"draws":15,"losses":52,"wins":59},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":54},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":53},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":90},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":74},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":58},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":51},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":39},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":18},"moonshotai/kimi-k3":{"draws":1,"losses":9,"wins":58},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":70},"o3":{"draws":3,"losses":2,"wins":89},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":80},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":69},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":38},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":5,"wins":53},"qwen/qwen3.8-27b":{"draws":4,"losses":0,"wins":30},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":46},"qwen/qwen3.8-max":{"draws":10,"losses":4,"wins":78},"qwen/qwen3.8-max-0902":{"draws":14,"losses":14,"wins":118},"stealth/ox-alpha":{"draws":22,"losses":12,"wins":184},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":99},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":39},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":39},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":58},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":75},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":61},"x-ai/grok-4.5":{"draws":12,"losses":8,"wins":84},"x-ai/grok-4.6":{"draws":11,"losses":10,"wins":89},"x-ai/grok-4.7":{"draws":10,"losses":28,"wins":90},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":20},"xiaomi/mimo-v2.5":{"draws":6,"losses":3,"wins":143},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":2,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":68},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":124},"z-ai/glm-5.3":{"draws":4,"losses":16,"wins":66},"z-ai/glm-5.3-flash":{"draws":10,"losses":9,"wins":83},"z-ai/glm-5.3-flashx":{"draws":15,"losses":10,"wins":131}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":61,"losses":32,"wins":91},"claude-fable-5":{"draws":47,"losses":129,"wins":30},"claude-fable-5-1":{"draws":12,"losses":197,"wins":7},"claude-opus-4-5":{"draws":101,"losses":135,"wins":78},"claude-opus-4-8":{"draws":22,"losses":34,"wins":18},"claude-opus-5":{"draws":20,"losses":106,"wins":28},"claude-opus-5-5":{"draws":4,"losses":52,"wins":6},"claude-sonnet-5":{"draws":64,"losses":80,"wins":80},"claude-sonnet-5-5":{"draws":12,"losses":50,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-flash":{"draws":79,"losses":44,"wins":111},"deepseek/deepseek-v4-pro":{"draws":56,"losses":56,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":56,"losses":74,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":23,"wins":20},"fireworks/ember-1":{"draws":30,"losses":27,"wins":27},"gemini-3.1-pro-preview":{"draws":25,"losses":20,"wins":31},"google/gemini-3.1-flash-lite":{"draws":24,"losses":5,"wins":41},"google/gemini-3.5-flash":{"draws":68,"losses":80,"wins":64},"google/gemini-3.5-flash-lite":{"draws":169,"losses":137,"wins":286},"google/gemini-3.6-flash":{"draws":131,"losses":221,"wins":172},"google/gemini-3.8-flash":{"draws":52,"losses":101,"wins":47},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":28},"gpt-4.1":{"draws":9,"losses":8,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":8},"gpt-5":{"draws":24,"losses":18,"wins":32},"gpt-5.4":{"draws":102,"losses":164,"wins":66},"gpt-5.4-mini":{"draws":20,"losses":9,"wins":19},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":37},"gpt-5.5":{"draws":30,"losses":42,"wins":14},"gpt-5.6-luna":{"draws":113,"losses":91,"wins":138},"gpt-5.6-sol":{"draws":56,"losses":268,"wins":45},"gpt-5.6-terra":{"draws":77,"losses":65,"wins":58},"gpt-6-astra":{"draws":9,"losses":182,"wins":15},"gpt-6-luna":{"draws":20,"losses":35,"wins":27},"gpt-6-sol":{"draws":5,"losses":53,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":80,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":19},"inception/mercury-2.5-preview":{"draws":63,"losses":11,"wins":70},"inclusionai/ling-3.0-flash":{"draws":40,"losses":14,"wins":80},"meituan/longcat-2.0":{"draws":62,"losses":28,"wins":104},"meta/muse-glimmer-30b":{"draws":60,"losses":27,"wins":77},"meta/muse-spark-1.2":{"draws":77,"losses":81,"wins":84},"meta/muse-spark-1.3":{"draws":55,"losses":66,"wins":43},"minimax/minimax-m3":{"draws":13,"losses":10,"wins":27},"mistralai/mistral-medium-3-5":{"draws":49,"losses":14,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":14,"wins":8},"moonshotai/kimi-k3":{"draws":106,"losses":128,"wins":66},"nex-agi/nex-n2-pro":{"draws":21,"losses":5,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":11,"wins":31},"o3":{"draws":33,"losses":151,"wins":176},"openai/gpt-oss-120b":{"draws":72,"losses":23,"wins":89},"poolside/laguna-s-2.1":{"draws":67,"losses":21,"wins":108},"qwen/qwen3.7-max":{"draws":17,"losses":14,"wins":27},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":71,"losses":62,"wins":43},"qwen/qwen3.8-27b":{"draws":24,"losses":38,"wins":34},"qwen/qwen3.8-flash":{"draws":47,"losses":35,"wins":50},"qwen/qwen3.8-max":{"draws":57,"losses":76,"wins":54},"qwen/qwen3.8-max-0902":{"draws":19,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":152,"losses":293,"wins":166},"stealth/space-bunny-alpha":{"draws":15,"losses":16,"wins":31},"stepfun/step-3.7-flash":{"draws":21,"losses":32,"wins":51},"tencent/hy3-preview":{"draws":22,"losses":16,"wins":24},"tencent/hy4-preview":{"draws":61,"losses":79,"wins":44},"thinkingmachines/inkling":{"draws":76,"losses":34,"wins":128},"thinkingmachines/inkling-small":{"draws":57,"losses":37,"wins":108},"x-ai/grok-4.5":{"draws":95,"losses":135,"wins":54},"x-ai/grok-4.6":{"draws":58,"losses":105,"wins":51},"x-ai/grok-4.7":{"draws":7,"losses":51,"wins":10},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":15},"xiaomi/mimo-v2.5":{"draws":58,"losses":17,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":23,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":20,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":29,"wins":9},"z-ai/glm-5.2":{"draws":94,"losses":83,"wins":115},"z-ai/glm-5.3":{"draws":38,"losses":123,"wins":19},"z-ai/glm-5.3-flash":{"draws":44,"losses":111,"wins":55},"z-ai/glm-5.3-flashx":{"draws":22,"losses":23,"wins":17}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":13,"wins":41},"claude-fable-5":{"draws":13,"losses":18,"wins":19},"claude-fable-5-1":{"draws":8,"losses":59,"wins":21},"claude-opus-4-5":{"draws":21,"losses":25,"wins":60},"claude-opus-4-8":{"draws":13,"losses":27,"wins":28},"claude-opus-5":{"draws":15,"losses":81,"wins":38},"claude-opus-5-5":{"draws":14,"losses":96,"wins":22},"claude-sonnet-5":{"draws":12,"losses":20,"wins":50},"claude-sonnet-5-5":{"draws":10,"losses":43,"wins":43},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":80},"deepseek/deepseek-v4-pro":{"draws":21,"losses":14,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":3,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":27,"wins":63},"fireworks/ember-1":{"draws":30,"losses":42,"wins":72},"gemini-3.1-pro-preview":{"draws":22,"losses":39,"wins":83},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":44},"google/gemini-3.5-flash":{"draws":16,"losses":20,"wins":50},"google/gemini-3.5-flash-lite":{"draws":24,"losses":21,"wins":69},"google/gemini-3.6-flash":{"draws":27,"losses":50,"wins":67},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":21},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":20},"gpt-4.1":{"draws":2,"losses":1,"wins":19},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":14,"losses":12,"wins":34},"gpt-5.4":{"draws":20,"losses":19,"wins":21},"gpt-5.4-mini":{"draws":6,"losses":14,"wins":32},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":42},"gpt-5.5":{"draws":17,"losses":13,"wins":38},"gpt-5.6-luna":{"draws":27,"losses":14,"wins":51},"gpt-5.6-sol":{"draws":5,"losses":46,"wins":29},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":33},"gpt-6-astra":{"draws":9,"losses":53,"wins":18},"gpt-6-luna":{"draws":20,"losses":20,"wins":44},"gpt-6-sol":{"draws":9,"losses":74,"wins":47},"gpt-6.1-sol":{"draws":5,"losses":103,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":39},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":34},"meituan/longcat-2.0":{"draws":13,"losses":12,"wins":57},"meta/muse-glimmer-30b":{"draws":10,"losses":13,"wins":37},"meta/muse-spark-1.2":{"draws":15,"losses":10,"wins":21},"meta/muse-spark-1.3":{"draws":13,"losses":19,"wins":42},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":25},"mistralai/mistral-medium-3-5":{"draws":12,"losses":5,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":34},"nex-agi/nex-n2-pro":{"draws":5,"losses":9,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":11,"wins":42},"o3":{"draws":1,"losses":17,"wins":60},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":48},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":51},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":24},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":30,"wins":38},"qwen/qwen3.8-27b":{"draws":0,"losses":9,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":17,"wins":17},"qwen/qwen3.8-max":{"draws":16,"losses":29,"wins":47},"qwen/qwen3.8-max-0902":{"draws":20,"losses":43,"wins":61},"stealth/ox-alpha":{"draws":31,"losses":75,"wins":120},"stealth/space-bunny-alpha":{"draws":22,"losses":24,"wins":68},"stepfun/step-3.7-flash":{"draws":0,"losses":8,"wins":18},"tencent/hy3-preview":{"draws":14,"losses":0,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":19,"wins":27},"thinkingmachines/inkling":{"draws":20,"losses":9,"wins":45},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":52},"x-ai/grok-4.5":{"draws":8,"losses":19,"wins":27},"x-ai/grok-4.6":{"draws":6,"losses":18,"wins":22},"x-ai/grok-4.7":{"draws":13,"losses":59,"wins":44},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":26,"losses":7,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":34,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":31,"wins":45},"z-ai/glm-5.2":{"draws":31,"losses":37,"wins":88},"z-ai/glm-5.3":{"draws":19,"losses":32,"wins":25},"z-ai/glm-5.3-flash":{"draws":7,"losses":13,"wins":24},"z-ai/glm-5.3-flashx":{"draws":23,"losses":50,"wins":53}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":15,"wins":7},"claude-fable-5":{"draws":2,"losses":40,"wins":4},"claude-fable-5-1":{"draws":0,"losses":38,"wins":0},"claude-opus-4-5":{"draws":24,"losses":70,"wins":14},"claude-opus-4-8":{"draws":15,"losses":70,"wins":5},"claude-opus-5":{"draws":8,"losses":89,"wins":7},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":2,"losses":31,"wins":5},"claude-sonnet-5-5":{"draws":2,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":10,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":33,"losses":35,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":31,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":34,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":3},"fireworks/ember-1":{"draws":6,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":16,"wins":3},"google/gemini-3.1-flash-lite":{"draws":17,"losses":39,"wins":38},"google/gemini-3.5-flash":{"draws":18,"losses":41,"wins":11},"google/gemini-3.5-flash-lite":{"draws":45,"losses":46,"wins":19},"google/gemini-3.6-flash":{"draws":42,"losses":66,"wins":16},"google/gemini-3.8-flash":{"draws":6,"losses":38,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":25,"wins":13},"gpt-4.1":{"draws":11,"losses":21,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":27,"losses":42,"wins":13},"gpt-5.4":{"draws":8,"losses":28,"wins":0},"gpt-5.4-mini":{"draws":23,"losses":32,"wins":11},"gpt-5.4-nano":{"draws":30,"losses":59,"wins":29},"gpt-5.5":{"draws":30,"losses":34,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":24,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":41,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":43,"wins":6},"gpt-6-astra":{"draws":2,"losses":38,"wins":0},"gpt-6-luna":{"draws":11,"losses":22,"wins":7},"gpt-6-sol":{"draws":7,"losses":26,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":15,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":12,"wins":12},"inclusionai/ling-3.0-flash":{"draws":40,"losses":31,"wins":15},"meituan/longcat-2.0":{"draws":49,"losses":49,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":24,"wins":14},"meta/muse-spark-1.2":{"draws":1,"losses":38,"wins":7},"meta/muse-spark-1.3":{"draws":2,"losses":34,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":38,"wins":18},"mistralai/mistral-medium-3-5":{"draws":7,"losses":11,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":10,"losses":37,"wins":7},"nex-agi/nex-n2-pro":{"draws":23,"losses":28,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":19,"wins":21},"o3":{"draws":37,"losses":43,"wins":22},"openai/gpt-oss-120b":{"draws":11,"losses":13,"wins":4},"poolside/laguna-s-2.1":{"draws":52,"losses":11,"wins":27},"qwen/qwen3.7-max":{"draws":23,"losses":36,"wins":11},"qwen/qwen3.7-plus":{"draws":21,"losses":33,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":41,"wins":3},"qwen/qwen3.8-27b":{"draws":15,"losses":25,"wins":4},"qwen/qwen3.8-flash":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":28,"wins":4},"qwen/qwen3.8-max-0902":{"draws":5,"losses":22,"wins":1},"stealth/ox-alpha":{"draws":27,"losses":93,"wins":18},"stealth/space-bunny-alpha":{"draws":4,"losses":14,"wins":6},"stepfun/step-3.7-flash":{"draws":20,"losses":26,"wins":8},"tencent/hy3-preview":{"draws":12,"losses":28,"wins":8},"tencent/hy4-preview":{"draws":13,"losses":26,"wins":3},"thinkingmachines/inkling":{"draws":22,"losses":33,"wins":29},"thinkingmachines/inkling-small":{"draws":21,"losses":18,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":59,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":37,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":16,"losses":23,"wins":7},"xiaomi/mimo-v2.5":{"draws":60,"losses":58,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":38,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":11,"wins":1},"z-ai/glm-5.2":{"draws":38,"losses":67,"wins":21},"z-ai/glm-5.3":{"draws":3,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":15,"losses":34,"wins":3},"z-ai/glm-5.3-flashx":{"draws":3,"losses":21,"wins":2}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":71,"losses":59,"wins":72},"claude-fable-5":{"draws":44,"losses":169,"wins":17},"claude-fable-5-1":{"draws":8,"losses":209,"wins":1},"claude-opus-4-5":{"draws":109,"losses":148,"wins":63},"claude-opus-4-8":{"draws":51,"losses":90,"wins":15},"claude-opus-5":{"draws":33,"losses":208,"wins":15},"claude-opus-5-5":{"draws":4,"losses":104,"wins":4},"claude-sonnet-5":{"draws":79,"losses":111,"wins":44},"claude-sonnet-5-5":{"draws":24,"losses":80,"wins":12},"cohere/north-mini-code":{"draws":33,"losses":30,"wins":35},"deepseek/deepseek-v4-flash":{"draws":78,"losses":83,"wins":83},"deepseek/deepseek-v4-pro":{"draws":75,"losses":86,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":81,"losses":82,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":62,"wins":9},"fireworks/ember-1":{"draws":38,"losses":67,"wins":19},"gemini-3.1-pro-preview":{"draws":38,"losses":47,"wins":25},"google/gemini-3.1-flash-lite":{"draws":40,"losses":41,"wins":81},"google/gemini-3.5-flash":{"draws":78,"losses":112,"wins":56},"google/gemini-3.5-flash-lite":{"draws":151,"losses":111,"wins":130},"google/gemini-3.6-flash":{"draws":114,"losses":209,"wins":69},"google/gemini-3.8-flash":{"draws":53,"losses":129,"wins":32},"google/gemma-4-31b-it":{"draws":21,"losses":28,"wins":41},"gpt-4.1":{"draws":34,"losses":28,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":4},"gpt-5":{"draws":66,"losses":65,"wins":21},"gpt-5.4":{"draws":62,"losses":99,"wins":27},"gpt-5.4-mini":{"draws":60,"losses":33,"wins":29},"gpt-5.4-nano":{"draws":49,"losses":56,"wins":63},"gpt-5.5":{"draws":62,"losses":62,"wins":16},"gpt-5.6-luna":{"draws":97,"losses":80,"wins":67},"gpt-5.6-sol":{"draws":31,"losses":138,"wins":27},"gpt-5.6-terra":{"draws":101,"losses":113,"wins":44},"gpt-6-astra":{"draws":8,"losses":168,"wins":4},"gpt-6-luna":{"draws":36,"losses":72,"wins":22},"gpt-6-sol":{"draws":11,"losses":96,"wins":5},"gpt-6.1-sol":{"draws":10,"losses":104,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":16,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":81,"losses":19,"wins":68},"inclusionai/ling-3.0-flash":{"draws":64,"losses":40,"wins":54},"meituan/longcat-2.0":{"draws":67,"losses":57,"wins":66},"meta/muse-glimmer-30b":{"draws":114,"losses":37,"wins":67},"meta/muse-spark-1.2":{"draws":40,"losses":81,"wins":31},"meta/muse-spark-1.3":{"draws":52,"losses":110,"wins":26},"minimax/minimax-m3":{"draws":45,"losses":42,"wins":43},"mistralai/mistral-medium-3-5":{"draws":55,"losses":23,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":27,"wins":14},"moonshotai/kimi-k3":{"draws":60,"losses":90,"wins":46},"nex-agi/nex-n2-pro":{"draws":30,"losses":35,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":94,"losses":39,"wins":55},"o3":{"draws":43,"losses":142,"wins":99},"openai/gpt-oss-120b":{"draws":83,"losses":53,"wins":50},"poolside/laguna-s-2.1":{"draws":100,"losses":53,"wins":55},"qwen/qwen3.7-max":{"draws":57,"losses":35,"wins":20},"qwen/qwen3.7-plus":{"draws":31,"losses":40,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":72,"losses":99,"wins":39},"qwen/qwen3.8-27b":{"draws":27,"losses":67,"wins":40},"qwen/qwen3.8-flash":{"draws":56,"losses":64,"wins":36},"qwen/qwen3.8-max":{"draws":81,"losses":103,"wins":36},"qwen/qwen3.8-max-0902":{"draws":31,"losses":50,"wins":11},"stealth/ox-alpha":{"draws":215,"losses":333,"wins":133},"stealth/space-bunny-alpha":{"draws":29,"losses":33,"wins":14},"stepfun/step-3.7-flash":{"draws":37,"losses":43,"wins":44},"tencent/hy3-preview":{"draws":38,"losses":46,"wins":34},"tencent/hy4-preview":{"draws":70,"losses":110,"wins":38},"thinkingmachines/inkling":{"draws":86,"losses":91,"wins":85},"thinkingmachines/inkling-small":{"draws":117,"losses":42,"wins":97},"x-ai/grok-4.5":{"draws":50,"losses":130,"wins":50},"x-ai/grok-4.6":{"draws":68,"losses":145,"wins":25},"x-ai/grok-4.7":{"draws":7,"losses":88,"wins":3},"x-ai/grok-build-0.1":{"draws":34,"losses":19,"wins":29},"xiaomi/mimo-v2.5":{"draws":130,"losses":113,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":41,"losses":48,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":46,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":53,"wins":9},"z-ai/glm-5.2":{"draws":139,"losses":166,"wins":79},"z-ai/glm-5.3":{"draws":49,"losses":115,"wins":10},"z-ai/glm-5.3-flash":{"draws":77,"losses":120,"wins":43},"z-ai/glm-5.3-flashx":{"draws":29,"losses":59,"wins":12}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":44,"wins":82},"claude-fable-5":{"draws":41,"losses":103,"wins":48},"claude-fable-5-1":{"draws":10,"losses":156,"wins":4},"claude-opus-4-5":{"draws":52,"losses":66,"wins":72},"claude-opus-4-8":{"draws":17,"losses":30,"wins":27},"claude-opus-5":{"draws":15,"losses":115,"wins":20},"claude-opus-5-5":{"draws":3,"losses":69,"wins":0},"claude-sonnet-5":{"draws":56,"losses":60,"wins":56},"claude-sonnet-5-5":{"draws":21,"losses":29,"wins":14},"cohere/north-mini-code":{"draws":15,"losses":6,"wins":31},"deepseek/deepseek-v4-flash":{"draws":75,"losses":41,"wins":86},"deepseek/deepseek-v4-pro":{"draws":36,"losses":40,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":64,"losses":65,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":25,"wins":14},"fireworks/ember-1":{"draws":16,"losses":23,"wins":15},"gemini-3.1-pro-preview":{"draws":22,"losses":13,"wins":27},"google/gemini-3.1-flash-lite":{"draws":16,"losses":2,"wins":26},"google/gemini-3.5-flash":{"draws":55,"losses":77,"wins":72},"google/gemini-3.5-flash-lite":{"draws":101,"losses":75,"wins":144},"google/gemini-3.6-flash":{"draws":87,"losses":104,"wins":99},"google/gemini-3.8-flash":{"draws":54,"losses":94,"wins":40},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":21},"gpt-4.1":{"draws":9,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":7,"wins":1},"gpt-5":{"draws":32,"losses":15,"wins":35},"gpt-5.4":{"draws":53,"losses":70,"wins":49},"gpt-5.4-mini":{"draws":24,"losses":12,"wins":16},"gpt-5.4-nano":{"draws":21,"losses":22,"wins":43},"gpt-5.5":{"draws":23,"losses":37,"wins":22},"gpt-5.6-luna":{"draws":59,"losses":40,"wins":63},"gpt-5.6-sol":{"draws":20,"losses":96,"wins":46},"gpt-5.6-terra":{"draws":70,"losses":56,"wins":68},"gpt-6-astra":{"draws":9,"losses":134,"wins":13},"gpt-6-luna":{"draws":25,"losses":36,"wins":27},"gpt-6-sol":{"draws":5,"losses":47,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":57,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":55,"losses":13,"wins":56},"inclusionai/ling-3.0-flash":{"draws":30,"losses":11,"wins":39},"meituan/longcat-2.0":{"draws":42,"losses":23,"wins":70},"meta/muse-glimmer-30b":{"draws":64,"losses":32,"wins":58},"meta/muse-spark-1.2":{"draws":17,"losses":59,"wins":56},"meta/muse-spark-1.3":{"draws":30,"losses":80,"wins":50},"minimax/minimax-m3":{"draws":11,"losses":3,"wins":28},"mistralai/mistral-medium-3-5":{"draws":31,"losses":15,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":6,"wins":7},"moonshotai/kimi-k3":{"draws":50,"losses":64,"wins":44},"nex-agi/nex-n2-pro":{"draws":12,"losses":7,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":10,"wins":23},"o3":{"draws":39,"losses":57,"wins":110},"openai/gpt-oss-120b":{"draws":60,"losses":30,"wins":66},"poolside/laguna-s-2.1":{"draws":50,"losses":30,"wins":50},"qwen/qwen3.7-max":{"draws":14,"losses":8,"wins":22},"qwen/qwen3.7-plus":{"draws":14,"losses":7,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":53,"losses":70,"wins":45},"qwen/qwen3.8-27b":{"draws":23,"losses":51,"wins":38},"qwen/qwen3.8-flash":{"draws":41,"losses":39,"wins":42},"qwen/qwen3.8-max":{"draws":54,"losses":66,"wins":46},"qwen/qwen3.8-max-0902":{"draws":14,"losses":28,"wins":8},"stealth/ox-alpha":{"draws":175,"losses":220,"wins":171},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":22},"stepfun/step-3.7-flash":{"draws":23,"losses":5,"wins":48},"tencent/hy3-preview":{"draws":21,"losses":7,"wins":16},"tencent/hy4-preview":{"draws":55,"losses":72,"wins":51},"thinkingmachines/inkling":{"draws":54,"losses":22,"wins":78},"thinkingmachines/inkling-small":{"draws":84,"losses":23,"wins":87},"x-ai/grok-4.5":{"draws":43,"losses":64,"wins":59},"x-ai/grok-4.6":{"draws":51,"losses":104,"wins":43},"x-ai/grok-4.7":{"draws":7,"losses":40,"wins":13},"x-ai/grok-build-0.1":{"draws":12,"losses":9,"wins":15},"xiaomi/mimo-v2.5":{"draws":56,"losses":17,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":19,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":18,"wins":7},"z-ai/glm-5.2":{"draws":87,"losses":79,"wins":94},"z-ai/glm-5.3":{"draws":32,"losses":93,"wins":31},"z-ai/glm-5.3-flash":{"draws":53,"losses":90,"wins":55},"z-ai/glm-5.3-flashx":{"draws":15,"losses":27,"wins":20}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":43,"wins":67},"claude-fable-5":{"draws":38,"losses":105,"wins":35},"claude-fable-5-1":{"draws":7,"losses":159,"wins":4},"claude-opus-4-5":{"draws":54,"losses":67,"wins":81},"claude-opus-4-8":{"draws":22,"losses":40,"wins":24},"claude-opus-5":{"draws":13,"losses":112,"wins":21},"claude-opus-5-5":{"draws":2,"losses":47,"wins":1},"claude-sonnet-5":{"draws":56,"losses":48,"wins":74},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":14,"losses":2,"wins":34},"deepseek/deepseek-v4-flash":{"draws":81,"losses":47,"wins":82},"deepseek/deepseek-v4-pro":{"draws":64,"losses":57,"wins":65},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":41,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":16,"wins":5},"fireworks/ember-1":{"draws":9,"losses":9,"wins":16},"gemini-3.1-pro-preview":{"draws":10,"losses":9,"wins":23},"google/gemini-3.1-flash-lite":{"draws":14,"losses":9,"wins":23},"google/gemini-3.5-flash":{"draws":76,"losses":84,"wins":62},"google/gemini-3.5-flash-lite":{"draws":115,"losses":69,"wins":132},"google/gemini-3.6-flash":{"draws":92,"losses":141,"wins":89},"google/gemini-3.8-flash":{"draws":48,"losses":85,"wins":53},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":20},"gpt-4.1":{"draws":15,"losses":5,"wins":16},"gpt-4.1-nano":{"draws":4,"losses":6,"wins":2},"gpt-5":{"draws":33,"losses":27,"wins":30},"gpt-5.4":{"draws":55,"losses":67,"wins":44},"gpt-5.4-mini":{"draws":24,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":20,"losses":21,"wins":39},"gpt-5.5":{"draws":21,"losses":28,"wins":21},"gpt-5.6-luna":{"draws":52,"losses":45,"wins":55},"gpt-5.6-sol":{"draws":30,"losses":102,"wins":40},"gpt-5.6-terra":{"draws":65,"losses":66,"wins":59},"gpt-6-astra":{"draws":12,"losses":141,"wins":1},"gpt-6-luna":{"draws":22,"losses":29,"wins":21},"gpt-6-sol":{"draws":11,"losses":34,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":48,"losses":16,"wins":68},"inclusionai/ling-3.0-flash":{"draws":36,"losses":12,"wins":30},"meituan/longcat-2.0":{"draws":53,"losses":29,"wins":60},"meta/muse-glimmer-30b":{"draws":66,"losses":27,"wins":69},"meta/muse-spark-1.2":{"draws":40,"losses":51,"wins":45},"meta/muse-spark-1.3":{"draws":40,"losses":76,"wins":38},"minimax/minimax-m3":{"draws":14,"losses":4,"wins":30},"mistralai/mistral-medium-3-5":{"draws":30,"losses":14,"wins":52},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":13,"wins":10},"moonshotai/kimi-k3":{"draws":55,"losses":45,"wins":44},"nex-agi/nex-n2-pro":{"draws":15,"losses":5,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":7,"wins":37},"o3":{"draws":46,"losses":46,"wins":100},"openai/gpt-oss-120b":{"draws":54,"losses":32,"wins":52},"poolside/laguna-s-2.1":{"draws":60,"losses":28,"wins":48},"qwen/qwen3.7-max":{"draws":14,"losses":13,"wins":27},"qwen/qwen3.7-plus":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":66,"wins":63},"qwen/qwen3.8-27b":{"draws":36,"losses":49,"wins":41},"qwen/qwen3.8-flash":{"draws":52,"losses":39,"wins":33},"qwen/qwen3.8-max":{"draws":66,"losses":57,"wins":49},"qwen/qwen3.8-max-0902":{"draws":19,"losses":8,"wins":7},"stealth/ox-alpha":{"draws":173,"losses":212,"wins":199},"stealth/space-bunny-alpha":{"draws":6,"losses":12,"wins":18},"stepfun/step-3.7-flash":{"draws":23,"losses":10,"wins":27},"tencent/hy3-preview":{"draws":28,"losses":12,"wins":18},"tencent/hy4-preview":{"draws":45,"losses":70,"wins":53},"thinkingmachines/inkling":{"draws":49,"losses":36,"wins":59},"thinkingmachines/inkling-small":{"draws":69,"losses":33,"wins":88},"x-ai/grok-4.5":{"draws":41,"losses":57,"wins":58},"x-ai/grok-4.6":{"draws":66,"losses":84,"wins":46},"x-ai/grok-4.7":{"draws":0,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":11,"losses":1,"wins":16},"xiaomi/mimo-v2.5":{"draws":54,"losses":20,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":19,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":4,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":100,"losses":82,"wins":102},"z-ai/glm-5.3":{"draws":30,"losses":94,"wins":34},"z-ai/glm-5.3-flash":{"draws":52,"losses":92,"wins":52},"z-ai/glm-5.3-flashx":{"draws":11,"losses":26,"wins":7}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":14,"wins":29},"claude-fable-5":{"draws":19,"losses":52,"wins":19},"claude-fable-5-1":{"draws":10,"losses":71,"wins":5},"claude-opus-4-5":{"draws":37,"losses":20,"wins":51},"claude-opus-4-8":{"draws":15,"losses":20,"wins":25},"claude-opus-5":{"draws":22,"losses":77,"wins":13},"claude-opus-5-5":{"draws":9,"losses":124,"wins":15},"claude-sonnet-5":{"draws":17,"losses":20,"wins":23},"claude-sonnet-5-5":{"draws":26,"losses":63,"wins":27},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":19},"deepseek/deepseek-v4-flash":{"draws":35,"losses":9,"wins":62},"deepseek/deepseek-v4-pro":{"draws":19,"losses":14,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":5,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":36,"wins":36},"fireworks/ember-1":{"draws":47,"losses":50,"wins":39},"gemini-3.1-pro-preview":{"draws":42,"losses":42,"wins":42},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":24},"google/gemini-3.5-flash":{"draws":24,"losses":26,"wins":26},"google/gemini-3.5-flash-lite":{"draws":37,"losses":26,"wins":53},"google/gemini-3.6-flash":{"draws":27,"losses":35,"wins":34},"google/gemini-3.8-flash":{"draws":9,"losses":16,"wins":13},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":21},"gpt-4.1":{"draws":7,"losses":7,"wins":18},"gpt-5":{"draws":14,"losses":14,"wins":12},"gpt-5.4":{"draws":24,"losses":22,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":13,"wins":28},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":25},"gpt-5.5":{"draws":25,"losses":14,"wins":19},"gpt-5.6-luna":{"draws":34,"losses":8,"wins":30},"gpt-5.6-sol":{"draws":10,"losses":33,"wins":9},"gpt-5.6-terra":{"draws":25,"losses":25,"wins":28},"gpt-6-astra":{"draws":6,"losses":53,"wins":3},"gpt-6-luna":{"draws":42,"losses":38,"wins":58},"gpt-6-sol":{"draws":26,"losses":85,"wins":33},"gpt-6.1-sol":{"draws":14,"losses":95,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":19,"losses":4,"wins":31},"meituan/longcat-2.0":{"draws":29,"losses":19,"wins":48},"meta/muse-glimmer-30b":{"draws":29,"losses":5,"wins":28},"meta/muse-spark-1.2":{"draws":12,"losses":14,"wins":18},"meta/muse-spark-1.3":{"draws":20,"losses":16,"wins":24},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":21},"mistralai/mistral-medium-3-5":{"draws":15,"losses":6,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":23,"wins":26},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":36},"o3":{"draws":22,"losses":18,"wins":34},"openai/gpt-oss-120b":{"draws":23,"losses":13,"wins":36},"poolside/laguna-s-2.1":{"draws":21,"losses":11,"wins":24},"qwen/qwen3.7-max":{"draws":15,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":29,"wins":25},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":12},"qwen/qwen3.8-flash":{"draws":18,"losses":10,"wins":26},"qwen/qwen3.8-max":{"draws":25,"losses":23,"wins":28},"qwen/qwen3.8-max-0902":{"draws":46,"losses":44,"wins":48},"stealth/ox-alpha":{"draws":43,"losses":73,"wins":78},"stealth/space-bunny-alpha":{"draws":32,"losses":21,"wins":47},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":15},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":34,"wins":22},"thinkingmachines/inkling":{"draws":27,"losses":14,"wins":35},"thinkingmachines/inkling-small":{"draws":26,"losses":6,"wins":28},"x-ai/grok-4.5":{"draws":22,"losses":34,"wins":30},"x-ai/grok-4.6":{"draws":25,"losses":42,"wins":23},"x-ai/grok-4.7":{"draws":11,"losses":67,"wins":28},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":22},"xiaomi/mimo-v2.5":{"draws":48,"losses":13,"wins":77},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":10,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":32,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":45,"wins":22},"z-ai/glm-5.2":{"draws":39,"losses":26,"wins":41},"z-ai/glm-5.3":{"draws":22,"losses":30,"wins":10},"z-ai/glm-5.3-flash":{"draws":27,"losses":39,"wins":36},"z-ai/glm-5.3-flashx":{"draws":40,"losses":61,"wins":43}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":13,"wins":35},"claude-fable-5":{"draws":13,"losses":38,"wins":11},"claude-fable-5-1":{"draws":3,"losses":103,"wins":4},"claude-opus-4-5":{"draws":42,"losses":28,"wins":34},"claude-opus-4-8":{"draws":21,"losses":22,"wins":13},"claude-opus-5":{"draws":16,"losses":74,"wins":16},"claude-opus-5-5":{"draws":8,"losses":102,"wins":10},"claude-sonnet-5":{"draws":30,"losses":27,"wins":27},"claude-sonnet-5-5":{"draws":30,"losses":72,"wins":42},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":20},"deepseek/deepseek-v4-flash":{"draws":38,"losses":19,"wins":67},"deepseek/deepseek-v4-pro":{"draws":16,"losses":15,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":47,"losses":39,"wins":50},"fireworks/ember-1":{"draws":30,"losses":33,"wins":33},"gemini-3.1-pro-preview":{"draws":41,"losses":41,"wins":62},"google/gemini-3.1-flash-lite":{"draws":18,"losses":0,"wins":42},"google/gemini-3.5-flash":{"draws":22,"losses":27,"wins":27},"google/gemini-3.5-flash-lite":{"draws":46,"losses":27,"wins":39},"google/gemini-3.6-flash":{"draws":37,"losses":47,"wins":42},"google/gemini-3.8-flash":{"draws":18,"losses":26,"wins":14},"google/gemma-4-31b-it":{"draws":9,"losses":1,"wins":18},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":12,"wins":24},"gpt-5.4":{"draws":24,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":23},"gpt-5.4-nano":{"draws":19,"losses":22,"wins":29},"gpt-5.5":{"draws":33,"losses":16,"wins":23},"gpt-5.6-luna":{"draws":37,"losses":16,"wins":29},"gpt-5.6-sol":{"draws":11,"losses":38,"wins":13},"gpt-5.6-terra":{"draws":13,"losses":22,"wins":17},"gpt-6-astra":{"draws":1,"losses":55,"wins":4},"gpt-6-luna":{"draws":27,"losses":18,"wins":33},"gpt-6-sol":{"draws":17,"losses":88,"wins":21},"gpt-6.1-sol":{"draws":10,"losses":117,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":25,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":25,"losses":2,"wins":33},"meituan/longcat-2.0":{"draws":32,"losses":6,"wins":57},"meta/muse-glimmer-30b":{"draws":26,"losses":4,"wins":30},"meta/muse-spark-1.2":{"draws":15,"losses":11,"wins":16},"meta/muse-spark-1.3":{"draws":16,"losses":18,"wins":24},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":27},"mistralai/mistral-medium-3-5":{"draws":17,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":16,"losses":9,"wins":23},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":10,"wins":39},"o3":{"draws":13,"losses":26,"wins":45},"openai/gpt-oss-120b":{"draws":22,"losses":10,"wins":40},"poolside/laguna-s-2.1":{"draws":26,"losses":13,"wins":21},"qwen/qwen3.7-max":{"draws":15,"losses":10,"wins":23},"qwen/qwen3.7-plus":{"draws":14,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":26,"wins":24},"qwen/qwen3.8-27b":{"draws":2,"losses":11,"wins":15},"qwen/qwen3.8-flash":{"draws":16,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":29,"losses":28,"wins":33},"qwen/qwen3.8-max-0902":{"draws":46,"losses":44,"wins":36},"stealth/ox-alpha":{"draws":67,"losses":93,"wins":84},"stealth/space-bunny-alpha":{"draws":36,"losses":23,"wins":55},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":12},"tencent/hy3-preview":{"draws":12,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":24,"losses":28,"wins":20},"thinkingmachines/inkling":{"draws":32,"losses":10,"wins":38},"thinkingmachines/inkling-small":{"draws":31,"losses":4,"wins":49},"x-ai/grok-4.5":{"draws":12,"losses":31,"wins":11},"x-ai/grok-4.6":{"draws":15,"losses":21,"wins":12},"x-ai/grok-4.7":{"draws":11,"losses":82,"wins":23},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":50,"losses":14,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":32,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":45,"wins":26},"z-ai/glm-5.2":{"draws":54,"losses":31,"wins":63},"z-ai/glm-5.3":{"draws":21,"losses":53,"wins":14},"z-ai/glm-5.3-flash":{"draws":14,"losses":26,"wins":14},"z-ai/glm-5.3-flashx":{"draws":35,"losses":54,"wins":47}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":19,"wins":28},"claude-fable-5":{"draws":11,"losses":31,"wins":12},"claude-fable-5-1":{"draws":2,"losses":79,"wins":3},"claude-opus-4-5":{"draws":30,"losses":53,"wins":27},"claude-opus-4-8":{"draws":19,"losses":42,"wins":9},"claude-opus-5":{"draws":12,"losses":78,"wins":14},"claude-opus-5-5":{"draws":7,"losses":124,"wins":7},"claude-sonnet-5":{"draws":25,"losses":31,"wins":20},"claude-sonnet-5-5":{"draws":22,"losses":83,"wins":39},"cohere/north-mini-code":{"draws":11,"losses":3,"wins":16},"deepseek/deepseek-v4-flash":{"draws":38,"losses":25,"wins":47},"deepseek/deepseek-v4-pro":{"draws":22,"losses":27,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":23,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":42,"wins":42},"fireworks/ember-1":{"draws":41,"losses":62,"wins":41},"gemini-3.1-pro-preview":{"draws":26,"losses":35,"wins":35},"google/gemini-3.1-flash-lite":{"draws":10,"losses":12,"wins":36},"google/gemini-3.5-flash":{"draws":22,"losses":32,"wins":22},"google/gemini-3.5-flash-lite":{"draws":36,"losses":38,"wins":46},"google/gemini-3.6-flash":{"draws":27,"losses":62,"wins":45},"google/gemini-3.8-flash":{"draws":19,"losses":29,"wins":6},"google/gemma-4-31b-it":{"draws":8,"losses":6,"wins":18},"gpt-4.1":{"draws":6,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":13,"wins":14},"gpt-5.4":{"draws":14,"losses":27,"wins":27},"gpt-5.4-mini":{"draws":22,"losses":17,"wins":15},"gpt-5.4-nano":{"draws":21,"losses":24,"wins":25},"gpt-5.5":{"draws":26,"losses":26,"wins":18},"gpt-5.6-luna":{"draws":29,"losses":16,"wins":41},"gpt-5.6-sol":{"draws":5,"losses":45,"wins":10},"gpt-5.6-terra":{"draws":19,"losses":28,"wins":13},"gpt-6-astra":{"draws":7,"losses":67,"wins":2},"gpt-6-luna":{"draws":22,"losses":24,"wins":30},"gpt-6-sol":{"draws":19,"losses":86,"wins":23},"gpt-6.1-sol":{"draws":8,"losses":126,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":24,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":22,"losses":4,"wins":30},"meituan/longcat-2.0":{"draws":23,"losses":20,"wins":43},"meta/muse-glimmer-30b":{"draws":24,"losses":6,"wins":18},"meta/muse-spark-1.2":{"draws":15,"losses":16,"wins":17},"meta/muse-spark-1.3":{"draws":17,"losses":35,"wins":18},"minimax/minimax-m3":{"draws":8,"losses":16,"wins":16},"mistralai/mistral-medium-3-5":{"draws":13,"losses":6,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":16,"losses":19,"wins":19},"nex-agi/nex-n2-pro":{"draws":12,"losses":4,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":17,"wins":25},"o3":{"draws":18,"losses":33,"wins":29},"openai/gpt-oss-120b":{"draws":33,"losses":15,"wins":32},"poolside/laguna-s-2.1":{"draws":27,"losses":21,"wins":28},"qwen/qwen3.7-max":{"draws":16,"losses":16,"wins":20},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":35,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":12,"wins":14},"qwen/qwen3.8-max":{"draws":19,"losses":29,"wins":26},"qwen/qwen3.8-max-0902":{"draws":34,"losses":61,"wins":31},"stealth/ox-alpha":{"draws":51,"losses":123,"wins":66},"stealth/space-bunny-alpha":{"draws":36,"losses":34,"wins":44},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":17},"tencent/hy3-preview":{"draws":13,"losses":12,"wins":15},"tencent/hy4-preview":{"draws":17,"losses":36,"wins":19},"thinkingmachines/inkling":{"draws":24,"losses":17,"wins":33},"thinkingmachines/inkling-small":{"draws":25,"losses":14,"wins":39},"x-ai/grok-4.5":{"draws":13,"losses":31,"wins":12},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":9},"x-ai/grok-4.7":{"draws":12,"losses":79,"wins":23},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":1},"xiaomi/mimo-v2.5":{"draws":50,"losses":27,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":36,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":54,"wins":19},"z-ai/glm-5.2":{"draws":58,"losses":45,"wins":47},"z-ai/glm-5.3":{"draws":14,"losses":46,"wins":18},"z-ai/glm-5.3-flash":{"draws":13,"losses":20,"wins":11},"z-ai/glm-5.3-flashx":{"draws":31,"losses":66,"wins":29}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":27,"wins":10},"claude-fable-5":{"draws":9,"losses":45,"wins":2},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-opus-4-5":{"draws":49,"losses":121,"wins":10},"claude-opus-4-8":{"draws":32,"losses":96,"wins":8},"claude-opus-5":{"draws":20,"losses":101,"wins":7},"claude-opus-5-5":{"draws":1,"losses":57,"wins":0},"claude-sonnet-5":{"draws":24,"losses":41,"wins":5},"claude-sonnet-5-5":{"draws":7,"losses":44,"wins":5},"cohere/north-mini-code":{"draws":17,"losses":38,"wins":39},"deepseek/deepseek-v4-flash":{"draws":40,"losses":81,"wins":41},"deepseek/deepseek-v4-pro":{"draws":16,"losses":26,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":23,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"fireworks/ember-1":{"draws":18,"losses":42,"wins":0},"gemini-3.1-pro-preview":{"draws":10,"losses":36,"wins":12},"google/gemini-3.1-flash-lite":{"draws":0,"losses":36,"wins":36},"google/gemini-3.5-flash":{"draws":22,"losses":44,"wins":12},"google/gemini-3.5-flash-lite":{"draws":51,"losses":57,"wins":24},"google/gemini-3.6-flash":{"draws":27,"losses":78,"wins":11},"google/gemini-3.8-flash":{"draws":13,"losses":42,"wins":3},"google/gemma-4-31b-it":{"draws":24,"losses":43,"wins":29},"gpt-4.1":{"draws":18,"losses":25,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":36,"losses":55,"wins":3},"gpt-5.4":{"draws":11,"losses":39,"wins":4},"gpt-5.4-mini":{"draws":26,"losses":38,"wins":12},"gpt-5.4-nano":{"draws":22,"losses":96,"wins":38},"gpt-5.5":{"draws":32,"losses":55,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":25,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":34,"wins":2},"gpt-5.6-terra":{"draws":23,"losses":49,"wins":8},"gpt-6-astra":{"draws":2,"losses":52,"wins":0},"gpt-6-luna":{"draws":13,"losses":47,"wins":8},"gpt-6-sol":{"draws":6,"losses":46,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":51,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":16,"wins":8},"inclusionai/ling-3.0-flash":{"draws":25,"losses":28,"wins":29},"meituan/longcat-2.0":{"draws":24,"losses":57,"wins":32},"meta/muse-glimmer-30b":{"draws":26,"losses":22,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":5},"meta/muse-spark-1.3":{"draws":10,"losses":34,"wins":0},"minimax/minimax-m3":{"draws":22,"losses":40,"wins":30},"mistralai/mistral-medium-3-5":{"draws":10,"losses":14,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":31,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":31,"wins":2},"nex-agi/nex-n2-pro":{"draws":18,"losses":39,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":55,"wins":33},"o3":{"draws":18,"losses":94,"wins":10},"openai/gpt-oss-120b":{"draws":14,"losses":26,"wins":6},"poolside/laguna-s-2.1":{"draws":20,"losses":41,"wins":25},"qwen/qwen3.7-max":{"draws":29,"losses":39,"wins":14},"qwen/qwen3.7-plus":{"draws":23,"losses":51,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":29,"wins":0},"qwen/qwen3.8-27b":{"draws":13,"losses":33,"wins":6},"qwen/qwen3.8-flash":{"draws":18,"losses":19,"wins":7},"qwen/qwen3.8-max":{"draws":17,"losses":37,"wins":0},"qwen/qwen3.8-max-0902":{"draws":13,"losses":29,"wins":0},"stealth/ox-alpha":{"draws":28,"losses":108,"wins":14},"stealth/space-bunny-alpha":{"draws":15,"losses":20,"wins":7},"stepfun/step-3.7-flash":{"draws":18,"losses":53,"wins":11},"tencent/hy3-preview":{"draws":24,"losses":30,"wins":20},"tencent/hy4-preview":{"draws":10,"losses":41,"wins":1},"thinkingmachines/inkling":{"draws":39,"losses":63,"wins":34},"thinkingmachines/inkling-small":{"draws":18,"losses":27,"wins":17},"x-ai/grok-4.5":{"draws":20,"losses":77,"wins":3},"x-ai/grok-4.6":{"draws":5,"losses":42,"wins":5},"x-ai/grok-4.7":{"draws":1,"losses":50,"wins":1},"x-ai/grok-build-0.1":{"draws":19,"losses":32,"wins":9},"xiaomi/mimo-v2.5":{"draws":81,"losses":94,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":69,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":19,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":29,"wins":1},"z-ai/glm-5.2":{"draws":50,"losses":106,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":43,"wins":7},"z-ai/glm-5.3-flashx":{"draws":11,"losses":39,"wins":2}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":56,"losses":37,"wins":87},"claude-fable-5":{"draws":42,"losses":148,"wins":40},"claude-fable-5-1":{"draws":17,"losses":183,"wins":12},"claude-opus-4-5":{"draws":72,"losses":82,"wins":110},"claude-opus-4-8":{"draws":39,"losses":63,"wins":30},"claude-opus-5":{"draws":29,"losses":169,"wins":22},"claude-opus-5-5":{"draws":5,"losses":72,"wins":7},"claude-sonnet-5":{"draws":68,"losses":64,"wins":80},"claude-sonnet-5-5":{"draws":16,"losses":50,"wins":20},"cohere/north-mini-code":{"draws":18,"losses":11,"wins":41},"deepseek/deepseek-v4-flash":{"draws":78,"losses":56,"wins":112},"deepseek/deepseek-v4-pro":{"draws":55,"losses":72,"wins":77},"deepseek/deepseek-v4-pro-0813":{"draws":76,"losses":62,"wins":84},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":26,"wins":26},"fireworks/ember-1":{"draws":22,"losses":27,"wins":27},"gemini-3.1-pro-preview":{"draws":22,"losses":22,"wins":32},"google/gemini-3.1-flash-lite":{"draws":22,"losses":12,"wins":44},"google/gemini-3.5-flash":{"draws":34,"losses":55,"wins":55},"google/gemini-3.5-flash-lite":{"draws":106,"losses":94,"wins":168},"google/gemini-3.6-flash":{"draws":97,"losses":123,"wins":128},"google/gemini-3.8-flash":{"draws":52,"losses":101,"wins":61},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":27},"gpt-4.1":{"draws":14,"losses":10,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":6},"gpt-5":{"draws":40,"losses":33,"wins":41},"gpt-5.4":{"draws":37,"losses":101,"wins":62},"gpt-5.4-mini":{"draws":34,"losses":18,"wins":38},"gpt-5.4-nano":{"draws":31,"losses":37,"wins":78},"gpt-5.5":{"draws":42,"losses":43,"wins":29},"gpt-5.6-luna":{"draws":65,"losses":47,"wins":78},"gpt-5.6-sol":{"draws":23,"losses":132,"wins":59},"gpt-5.6-terra":{"draws":75,"losses":76,"wins":69},"gpt-6-astra":{"draws":23,"losses":168,"wins":7},"gpt-6-luna":{"draws":27,"losses":45,"wins":50},"gpt-6-sol":{"draws":10,"losses":55,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":64,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":16},"inception/mercury-2.5-preview":{"draws":52,"losses":18,"wins":74},"inclusionai/ling-3.0-flash":{"draws":37,"losses":12,"wins":63},"meituan/longcat-2.0":{"draws":43,"losses":28,"wins":111},"meta/muse-glimmer-30b":{"draws":62,"losses":35,"wins":71},"meta/muse-spark-1.2":{"draws":36,"losses":58,"wins":76},"meta/muse-spark-1.3":{"draws":40,"losses":105,"wins":53},"minimax/minimax-m3":{"draws":18,"losses":17,"wins":25},"mistralai/mistral-medium-3-5":{"draws":37,"losses":16,"wins":65},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":12,"wins":6},"moonshotai/kimi-k3":{"draws":68,"losses":53,"wins":71},"nex-agi/nex-n2-pro":{"draws":23,"losses":14,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":17,"wins":50},"o3":{"draws":38,"losses":66,"wins":136},"openai/gpt-oss-120b":{"draws":55,"losses":35,"wins":78},"poolside/laguna-s-2.1":{"draws":64,"losses":30,"wins":78},"qwen/qwen3.7-max":{"draws":23,"losses":19,"wins":22},"qwen/qwen3.7-plus":{"draws":20,"losses":11,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":52,"losses":87,"wins":75},"qwen/qwen3.8-27b":{"draws":28,"losses":55,"wins":33},"qwen/qwen3.8-flash":{"draws":51,"losses":45,"wins":64},"qwen/qwen3.8-max":{"draws":57,"losses":47,"wins":72},"qwen/qwen3.8-max-0902":{"draws":24,"losses":32,"wins":16},"stealth/ox-alpha":{"draws":163,"losses":277,"wins":235},"stealth/space-bunny-alpha":{"draws":17,"losses":18,"wins":25},"stepfun/step-3.7-flash":{"draws":23,"losses":20,"wins":45},"tencent/hy3-preview":{"draws":22,"losses":15,"wins":19},"tencent/hy4-preview":{"draws":41,"losses":97,"wins":62},"thinkingmachines/inkling":{"draws":50,"losses":41,"wins":85},"thinkingmachines/inkling-small":{"draws":63,"losses":35,"wins":94},"x-ai/grok-4.5":{"draws":43,"losses":82,"wins":69},"x-ai/grok-4.6":{"draws":64,"losses":132,"wins":44},"x-ai/grok-4.7":{"draws":7,"losses":55,"wins":10},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":31},"xiaomi/mimo-v2.5":{"draws":61,"losses":36,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":34,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":22,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":24,"wins":21},"z-ai/glm-5.2":{"draws":100,"losses":112,"wins":124},"z-ai/glm-5.3":{"draws":38,"losses":125,"wins":41},"z-ai/glm-5.3-flash":{"draws":58,"losses":100,"wins":82},"z-ai/glm-5.3-flashx":{"draws":34,"losses":30,"wins":26}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":121,"losses":102,"wins":101},"claude-fable-5":{"draws":67,"losses":205,"wins":38},"claude-fable-5-1":{"draws":24,"losses":229,"wins":1},"claude-opus-4-5":{"draws":222,"losses":287,"wins":157},"claude-opus-4-8":{"draws":50,"losses":112,"wins":24},"claude-opus-5":{"draws":51,"losses":307,"wins":26},"claude-opus-5-5":{"draws":6,"losses":102,"wins":2},"claude-sonnet-5":{"draws":169,"losses":286,"wins":137},"claude-sonnet-5-5":{"draws":24,"losses":69,"wins":21},"cohere/north-mini-code":{"draws":45,"losses":19,"wins":46},"deepseek/deepseek-v4-flash":{"draws":151,"losses":130,"wins":111},"deepseek/deepseek-v4-pro":{"draws":101,"losses":144,"wins":75},"deepseek/deepseek-v4-pro-0813":{"draws":115,"losses":132,"wins":69},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":53,"wins":26},"fireworks/ember-1":{"draws":46,"losses":39,"wins":27},"gemini-3.1-pro-preview":{"draws":36,"losses":46,"wins":38},"google/gemini-3.1-flash-lite":{"draws":51,"losses":24,"wins":57},"google/gemini-3.5-flash":{"draws":106,"losses":168,"wins":94},"google/gemini-3.5-flash-lite":{"draws":364,"losses":364,"wins":364},"google/gemini-3.6-flash":{"draws":380,"losses":543,"wins":226},"google/gemini-3.8-flash":{"draws":67,"losses":193,"wins":16},"google/gemma-4-31b-it":{"draws":30,"losses":37,"wins":33},"gpt-4.1":{"draws":27,"losses":27,"wins":34},"gpt-4.1-nano":{"draws":3,"losses":18,"wins":15},"gpt-5":{"draws":79,"losses":56,"wins":41},"gpt-5.4":{"draws":149,"losses":302,"wins":77},"gpt-5.4-mini":{"draws":53,"losses":56,"wins":39},"gpt-5.4-nano":{"draws":56,"losses":61,"wins":87},"gpt-5.5":{"draws":82,"losses":77,"wins":15},"gpt-5.6-luna":{"draws":194,"losses":208,"wins":184},"gpt-5.6-sol":{"draws":77,"losses":417,"wins":44},"gpt-5.6-terra":{"draws":120,"losses":150,"wins":80},"gpt-6-astra":{"draws":14,"losses":236,"wins":2},"gpt-6-luna":{"draws":40,"losses":76,"wins":36},"gpt-6-sol":{"draws":13,"losses":91,"wins":10},"gpt-6.1-sol":{"draws":10,"losses":110,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":30,"losses":0,"wins":16},"inception/mercury-2.5-preview":{"draws":117,"losses":46,"wins":107},"inclusionai/ling-3.0-flash":{"draws":119,"losses":56,"wins":141},"meituan/longcat-2.0":{"draws":127,"losses":184,"wins":214},"meta/muse-glimmer-30b":{"draws":137,"losses":69,"wins":108},"meta/muse-spark-1.2":{"draws":105,"losses":211,"wins":90},"meta/muse-spark-1.3":{"draws":67,"losses":153,"wins":56},"minimax/minimax-m3":{"draws":35,"losses":36,"wins":33},"mistralai/mistral-medium-3-5":{"draws":84,"losses":48,"wins":92},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":18,"wins":15},"moonshotai/kimi-k3":{"draws":205,"losses":298,"wins":121},"nex-agi/nex-n2-pro":{"draws":46,"losses":26,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":79,"losses":43,"wins":52},"o3":{"draws":129,"losses":427,"wins":256},"openai/gpt-oss-120b":{"draws":116,"losses":89,"wins":101},"poolside/laguna-s-2.1":{"draws":224,"losses":165,"wins":139},"qwen/qwen3.7-max":{"draws":32,"losses":27,"wins":39},"qwen/qwen3.7-plus":{"draws":41,"losses":31,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":101,"losses":148,"wins":61},"qwen/qwen3.8-27b":{"draws":37,"losses":110,"wins":47},"qwen/qwen3.8-flash":{"draws":88,"losses":99,"wins":41},"qwen/qwen3.8-max":{"draws":105,"losses":118,"wins":76},"qwen/qwen3.8-max-0902":{"draws":43,"losses":51,"wins":10},"stealth/ox-alpha":{"draws":263,"losses":539,"wins":207},"stealth/space-bunny-alpha":{"draws":33,"losses":33,"wins":24},"stepfun/step-3.7-flash":{"draws":57,"losses":85,"wins":68},"tencent/hy3-preview":{"draws":46,"losses":33,"wins":19},"tencent/hy4-preview":{"draws":101,"losses":154,"wins":67},"thinkingmachines/inkling":{"draws":209,"losses":162,"wins":223},"thinkingmachines/inkling-small":{"draws":140,"losses":107,"wins":131},"x-ai/grok-4.5":{"draws":157,"losses":321,"wins":116},"x-ai/grok-4.6":{"draws":97,"losses":195,"wins":44},"x-ai/grok-4.7":{"draws":7,"losses":82,"wins":15},"x-ai/grok-build-0.1":{"draws":30,"losses":29,"wins":23},"xiaomi/mimo-v2.5":{"draws":115,"losses":82,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":53,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":40,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":39,"wins":8},"z-ai/glm-5.2":{"draws":193,"losses":179,"wins":150},"z-ai/glm-5.3":{"draws":62,"losses":191,"wins":21},"z-ai/glm-5.3-flash":{"draws":101,"losses":206,"wins":59},"z-ai/glm-5.3-flashx":{"draws":27,"losses":55,"wins":18}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":79,"losses":67,"wins":124},"claude-fable-5":{"draws":59,"losses":175,"wins":96},"claude-fable-5-1":{"draws":22,"losses":257,"wins":25},"claude-opus-4-5":{"draws":174,"losses":196,"wins":252},"claude-opus-4-8":{"draws":57,"losses":72,"wins":85},"claude-opus-5":{"draws":52,"losses":294,"wins":68},"claude-opus-5-5":{"draws":11,"losses":121,"wins":12},"claude-sonnet-5":{"draws":131,"losses":172,"wins":221},"claude-sonnet-5-5":{"draws":27,"losses":67,"wins":50},"cohere/north-mini-code":{"draws":42,"losses":16,"wins":66},"deepseek/deepseek-v4-flash":{"draws":114,"losses":69,"wins":209},"deepseek/deepseek-v4-pro":{"draws":87,"losses":99,"wins":104},"deepseek/deepseek-v4-pro-0813":{"draws":92,"losses":89,"wins":141},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":34,"wins":35},"fireworks/ember-1":{"draws":37,"losses":42,"wins":47},"gemini-3.1-pro-preview":{"draws":27,"losses":45,"wins":62},"google/gemini-3.1-flash-lite":{"draws":27,"losses":11,"wins":78},"google/gemini-3.5-flash":{"draws":97,"losses":128,"wins":123},"google/gemini-3.5-flash-lite":{"draws":380,"losses":226,"wins":543},"google/gemini-3.6-flash":{"draws":200,"losses":350,"wins":350},"google/gemini-3.8-flash":{"draws":62,"losses":143,"wins":106},"google/gemma-4-31b-it":{"draws":24,"losses":21,"wins":39},"gpt-4.1":{"draws":24,"losses":16,"wins":38},"gpt-4.1-nano":{"draws":18,"losses":10,"wins":4},"gpt-5":{"draws":45,"losses":57,"wins":80},"gpt-5.4":{"draws":130,"losses":232,"wins":152},"gpt-5.4-mini":{"draws":52,"losses":26,"wins":63},"gpt-5.4-nano":{"draws":52,"losses":50,"wins":88},"gpt-5.5":{"draws":66,"losses":74,"wins":66},"gpt-5.6-luna":{"draws":152,"losses":122,"wins":250},"gpt-5.6-sol":{"draws":72,"losses":292,"wins":150},"gpt-5.6-terra":{"draws":105,"losses":88,"wins":127},"gpt-6-astra":{"draws":24,"losses":237,"wins":19},"gpt-6-luna":{"draws":38,"losses":44,"wins":82},"gpt-6-sol":{"draws":13,"losses":80,"wins":27},"gpt-6.1-sol":{"draws":11,"losses":106,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":30},"inception/mercury-2.5-preview":{"draws":86,"losses":21,"wins":101},"inclusionai/ling-3.0-flash":{"draws":142,"losses":46,"wins":130},"meituan/longcat-2.0":{"draws":141,"losses":79,"wins":250},"meta/muse-glimmer-30b":{"draws":112,"losses":37,"wins":135},"meta/muse-spark-1.2":{"draws":76,"losses":175,"wins":145},"meta/muse-spark-1.3":{"draws":52,"losses":124,"wins":88},"minimax/minimax-m3":{"draws":27,"losses":12,"wins":69},"mistralai/mistral-medium-3-5":{"draws":63,"losses":19,"wins":84},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":13,"wins":26},"moonshotai/kimi-k3":{"draws":175,"losses":207,"wins":236},"nex-agi/nex-n2-pro":{"draws":29,"losses":19,"wins":70},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":66,"losses":16,"wins":74},"o3":{"draws":134,"losses":249,"wins":375},"openai/gpt-oss-120b":{"draws":100,"losses":36,"wins":118},"poolside/laguna-s-2.1":{"draws":195,"losses":66,"wins":185},"qwen/qwen3.7-max":{"draws":26,"losses":21,"wins":63},"qwen/qwen3.7-plus":{"draws":41,"losses":21,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":83,"losses":106,"wins":117},"qwen/qwen3.8-27b":{"draws":48,"losses":59,"wins":95},"qwen/qwen3.8-flash":{"draws":95,"losses":52,"wins":85},"qwen/qwen3.8-max":{"draws":94,"losses":122,"wins":117},"qwen/qwen3.8-max-0902":{"draws":27,"losses":32,"wins":31},"stealth/ox-alpha":{"draws":237,"losses":368,"wins":374},"stealth/space-bunny-alpha":{"draws":29,"losses":21,"wins":60},"stepfun/step-3.7-flash":{"draws":40,"losses":21,"wins":130},"tencent/hy3-preview":{"draws":42,"losses":26,"wins":46},"tencent/hy4-preview":{"draws":84,"losses":132,"wins":130},"thinkingmachines/inkling":{"draws":193,"losses":83,"wins":284},"thinkingmachines/inkling-small":{"draws":114,"losses":54,"wins":140},"x-ai/grok-4.5":{"draws":122,"losses":238,"wins":252},"x-ai/grok-4.6":{"draws":88,"losses":141,"wins":99},"x-ai/grok-4.7":{"draws":2,"losses":79,"wins":31},"x-ai/grok-build-0.1":{"draws":23,"losses":2,"wins":41},"xiaomi/mimo-v2.5":{"draws":113,"losses":38,"wins":143},"xiaomi/mimo-v2.5-pro":{"draws":32,"losses":33,"wins":71},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":32,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":34,"wins":31},"z-ai/glm-5.2":{"draws":138,"losses":122,"wins":186},"z-ai/glm-5.3":{"draws":48,"losses":174,"wins":56},"z-ai/glm-5.3-flash":{"draws":84,"losses":157,"wins":111},"z-ai/glm-5.3-flashx":{"draws":29,"losses":44,"wins":47}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":42,"losses":30,"wins":88},"claude-fable-5":{"draws":30,"losses":101,"wins":77},"claude-fable-5-1":{"draws":20,"losses":184,"wins":20},"claude-opus-4-5":{"draws":62,"losses":44,"wins":116},"claude-opus-4-8":{"draws":19,"losses":35,"wins":36},"claude-opus-5":{"draws":24,"losses":128,"wins":40},"claude-opus-5-5":{"draws":10,"losses":44,"wins":6},"claude-sonnet-5":{"draws":52,"losses":47,"wins":101},"claude-sonnet-5-5":{"draws":9,"losses":21,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":38},"deepseek/deepseek-v4-flash":{"draws":53,"losses":32,"wins":129},"deepseek/deepseek-v4-pro":{"draws":54,"losses":40,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":48,"losses":53,"wins":85},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":13,"wins":16},"fireworks/ember-1":{"draws":18,"losses":14,"wins":26},"gemini-3.1-pro-preview":{"draws":19,"losses":6,"wins":29},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":42},"google/gemini-3.5-flash":{"draws":52,"losses":61,"wins":101},"google/gemini-3.5-flash-lite":{"draws":67,"losses":16,"wins":193},"google/gemini-3.6-flash":{"draws":62,"losses":106,"wins":143},"google/gemini-3.8-flash":{"draws":38,"losses":51,"wins":51},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":29},"gpt-4.1":{"draws":11,"losses":4,"wins":17},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":18,"losses":25,"wins":41},"gpt-5.4":{"draws":51,"losses":78,"wins":75},"gpt-5.4-mini":{"draws":17,"losses":14,"wins":29},"gpt-5.4-nano":{"draws":18,"losses":17,"wins":65},"gpt-5.5":{"draws":21,"losses":31,"wins":26},"gpt-5.6-luna":{"draws":39,"losses":35,"wins":90},"gpt-5.6-sol":{"draws":27,"losses":103,"wins":76},"gpt-5.6-terra":{"draws":70,"losses":48,"wins":80},"gpt-6-astra":{"draws":22,"losses":168,"wins":14},"gpt-6-luna":{"draws":23,"losses":24,"wins":33},"gpt-6-sol":{"draws":10,"losses":33,"wins":7},"gpt-6.1-sol":{"draws":7,"losses":38,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":15},"inception/mercury-2.5-preview":{"draws":51,"losses":5,"wins":66},"inclusionai/ling-3.0-flash":{"draws":21,"losses":3,"wins":50},"meituan/longcat-2.0":{"draws":32,"losses":14,"wins":71},"meta/muse-glimmer-30b":{"draws":49,"losses":18,"wins":77},"meta/muse-spark-1.2":{"draws":23,"losses":56,"wins":59},"meta/muse-spark-1.3":{"draws":30,"losses":76,"wins":64},"minimax/minimax-m3":{"draws":16,"losses":2,"wins":40},"mistralai/mistral-medium-3-5":{"draws":25,"losses":5,"wins":52},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":9},"moonshotai/kimi-k3":{"draws":56,"losses":43,"wins":83},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":10,"wins":43},"o3":{"draws":29,"losses":50,"wins":123},"openai/gpt-oss-120b":{"draws":36,"losses":11,"wins":79},"poolside/laguna-s-2.1":{"draws":33,"losses":15,"wins":80},"qwen/qwen3.7-max":{"draws":15,"losses":18,"wins":31},"qwen/qwen3.7-plus":{"draws":14,"losses":6,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":66,"wins":92},"qwen/qwen3.8-27b":{"draws":24,"losses":34,"wins":72},"qwen/qwen3.8-flash":{"draws":35,"losses":30,"wins":65},"qwen/qwen3.8-max":{"draws":48,"losses":57,"wins":71},"qwen/qwen3.8-max-0902":{"draws":16,"losses":12,"wins":18},"stealth/ox-alpha":{"draws":147,"losses":204,"wins":289},"stealth/space-bunny-alpha":{"draws":20,"losses":5,"wins":29},"stepfun/step-3.7-flash":{"draws":17,"losses":2,"wins":51},"tencent/hy3-preview":{"draws":28,"losses":6,"wins":28},"tencent/hy4-preview":{"draws":40,"losses":66,"wins":62},"thinkingmachines/inkling":{"draws":42,"losses":13,"wins":79},"thinkingmachines/inkling-small":{"draws":59,"losses":21,"wins":92},"x-ai/grok-4.5":{"draws":34,"losses":82,"wins":60},"x-ai/grok-4.6":{"draws":58,"losses":81,"wins":73},"x-ai/grok-4.7":{"draws":5,"losses":44,"wins":13},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":23},"xiaomi/mimo-v2.5":{"draws":41,"losses":12,"wins":77},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":9,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":21,"wins":7},"z-ai/glm-5.2":{"draws":70,"losses":66,"wins":142},"z-ai/glm-5.3":{"draws":32,"losses":107,"wins":49},"z-ai/glm-5.3-flash":{"draws":49,"losses":75,"wins":98},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":22}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":12,"wins":8},"claude-fable-5":{"draws":2,"losses":31,"wins":1},"claude-fable-5-1":{"draws":4,"losses":34,"wins":0},"claude-opus-4-5":{"draws":32,"losses":65,"wins":29},"claude-opus-4-8":{"draws":30,"losses":50,"wins":10},"claude-opus-5":{"draws":18,"losses":84,"wins":14},"claude-opus-5-5":{"draws":0,"losses":38,"wins":0},"claude-sonnet-5":{"draws":9,"losses":28,"wins":7},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":12,"losses":13,"wins":25},"deepseek/deepseek-v4-flash":{"draws":21,"losses":41,"wins":28},"deepseek/deepseek-v4-pro":{"draws":7,"losses":21,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":21,"wins":5},"fireworks/ember-1":{"draws":9,"losses":18,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":18,"wins":6},"google/gemini-3.1-flash-lite":{"draws":24,"losses":29,"wins":43},"google/gemini-3.5-flash":{"draws":17,"losses":27,"wins":12},"google/gemini-3.5-flash-lite":{"draws":30,"losses":33,"wins":37},"google/gemini-3.6-flash":{"draws":24,"losses":39,"wins":21},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":12,"wins":12},"gpt-4.1":{"draws":10,"losses":19,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":41,"wins":10},"gpt-5.4":{"draws":7,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":21,"wins":24},"gpt-5.4-nano":{"draws":9,"losses":47,"wins":36},"gpt-5.5":{"draws":26,"losses":35,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":17,"wins":9},"gpt-5.6-sol":{"draws":1,"losses":31,"wins":2},"gpt-5.6-terra":{"draws":9,"losses":33,"wins":4},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":7,"losses":24,"wins":7},"gpt-6-sol":{"draws":1,"losses":28,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":26,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":13,"wins":19},"inclusionai/ling-3.0-flash":{"draws":20,"losses":17,"wins":29},"meituan/longcat-2.0":{"draws":19,"losses":43,"wins":32},"meta/muse-glimmer-30b":{"draws":9,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":3},"meta/muse-spark-1.3":{"draws":6,"losses":23,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":26,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":5,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":26,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":37,"wins":6},"nex-agi/nex-n2-pro":{"draws":12,"losses":22,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":15,"wins":28},"o3":{"draws":17,"losses":54,"wins":15},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":9},"poolside/laguna-s-2.1":{"draws":8,"losses":30,"wins":30},"qwen/qwen3.7-max":{"draws":8,"losses":39,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":22,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":26,"wins":4},"qwen/qwen3.8-27b":{"draws":6,"losses":21,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":2,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":8,"losses":23,"wins":5},"stealth/ox-alpha":{"draws":20,"losses":83,"wins":17},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":39,"wins":8},"tencent/hy3-preview":{"draws":20,"losses":25,"wins":11},"tencent/hy4-preview":{"draws":6,"losses":25,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":32,"wins":28},"thinkingmachines/inkling-small":{"draws":8,"losses":13,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":43,"wins":6},"x-ai/grok-4.6":{"draws":8,"losses":32,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":24,"wins":3},"x-ai/grok-build-0.1":{"draws":15,"losses":22,"wins":9},"xiaomi/mimo-v2.5":{"draws":48,"losses":58,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":30,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":12,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":2},"z-ai/glm-5.2":{"draws":38,"losses":48,"wins":20},"z-ai/glm-5.3":{"draws":3,"losses":31,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":35,"wins":5},"z-ai/glm-5.3-flashx":{"draws":4,"losses":26,"wins":6}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":10},"claude-fable-5":{"draws":5,"losses":24,"wins":9},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-opus-4-5":{"draws":46,"losses":22,"wins":22},"claude-opus-4-8":{"draws":24,"losses":33,"wins":7},"claude-opus-5":{"draws":16,"losses":97,"wins":8},"claude-opus-5-5":{"draws":4,"losses":33,"wins":1},"claude-sonnet-5":{"draws":9,"losses":11,"wins":8},"claude-sonnet-5-5":{"draws":2,"losses":19,"wins":1},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":34,"losses":12,"wins":28},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":7},"fireworks/ember-1":{"draws":4,"losses":6,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":6},"google/gemini-3.1-flash-lite":{"draws":18,"losses":7,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":10},"google/gemini-3.5-flash-lite":{"draws":27,"losses":34,"wins":27},"google/gemini-3.6-flash":{"draws":24,"losses":38,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":17,"wins":4},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":21,"losses":13,"wins":18},"gpt-5.4":{"draws":6,"losses":15,"wins":3},"gpt-5.4-mini":{"draws":23,"losses":26,"wins":11},"gpt-5.4-nano":{"draws":14,"losses":29,"wins":25},"gpt-5.5":{"draws":21,"losses":21,"wins":14},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":7},"gpt-5.6-sol":{"draws":10,"losses":21,"wins":5},"gpt-5.6-terra":{"draws":17,"losses":6,"wins":11},"gpt-6-astra":{"draws":4,"losses":30,"wins":0},"gpt-6-luna":{"draws":11,"losses":12,"wins":15},"gpt-6-sol":{"draws":6,"losses":26,"wins":6},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":9,"losses":9,"wins":12},"inclusionai/ling-3.0-flash":{"draws":20,"losses":1,"wins":25},"meituan/longcat-2.0":{"draws":22,"losses":13,"wins":35},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":9},"meta/muse-spark-1.2":{"draws":6,"losses":11,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":1},"minimax/minimax-m3":{"draws":14,"losses":14,"wins":24},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":9,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":5},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":11,"wins":25},"o3":{"draws":12,"losses":20,"wins":26},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":18,"losses":16,"wins":20},"qwen/qwen3.7-max":{"draws":19,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":12,"wins":6},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":6,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":5},"stealth/ox-alpha":{"draws":30,"losses":50,"wins":20},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":12,"losses":8,"wins":16},"tencent/hy3-preview":{"draws":27,"losses":6,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":14,"losses":29,"wins":17},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":8},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":11},"x-ai/grok-4.6":{"draws":17,"losses":22,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":0},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":11},"xiaomi/mimo-v2.5":{"draws":48,"losses":26,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":12,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":29,"losses":44,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":21,"wins":9},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":6}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":8},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":8,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":5,"wins":1},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":8,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":6},"fireworks/ember-1":{"draws":2,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":15,"wins":18},"google/gemini-3.6-flash":{"draws":18,"losses":4,"wins":10},"google/gemini-3.8-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":4},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":6,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":8,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":0,"losses":1,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":6},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":4},"meta/muse-spark-1.2":{"draws":3,"losses":10,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":8,"wins":16},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":8,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":4},"stealth/ox-alpha":{"draws":2,"losses":23,"wins":1},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":14},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":4,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":5,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":24,"wins":27},"claude-fable-5":{"draws":20,"losses":59,"wins":21},"claude-fable-5-1":{"draws":2,"losses":77,"wins":1},"claude-opus-4-5":{"draws":77,"losses":65,"wins":66},"claude-opus-4-8":{"draws":37,"losses":71,"wins":36},"claude-opus-5":{"draws":31,"losses":211,"wins":20},"claude-opus-5-5":{"draws":1,"losses":44,"wins":3},"claude-sonnet-5":{"draws":24,"losses":32,"wins":18},"claude-sonnet-5-5":{"draws":14,"losses":34,"wins":12},"cohere/north-mini-code":{"draws":27,"losses":13,"wins":42},"deepseek/deepseek-v4-flash":{"draws":66,"losses":21,"wins":65},"deepseek/deepseek-v4-pro":{"draws":32,"losses":35,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":30,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":12,"wins":14},"fireworks/ember-1":{"draws":12,"losses":24,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":13},"google/gemini-3.1-flash-lite":{"draws":36,"losses":3,"wins":55},"google/gemini-3.5-flash":{"draws":40,"losses":41,"wins":33},"google/gemini-3.5-flash-lite":{"draws":79,"losses":41,"wins":56},"google/gemini-3.6-flash":{"draws":45,"losses":80,"wins":57},"google/gemini-3.8-flash":{"draws":18,"losses":41,"wins":25},"google/gemma-4-31b-it":{"draws":9,"losses":10,"wins":41},"gpt-4.1":{"draws":21,"losses":18,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":26,"losses":29,"wins":29},"gpt-5.4":{"draws":23,"losses":32,"wins":19},"gpt-5.4-mini":{"draws":46,"losses":30,"wins":26},"gpt-5.4-nano":{"draws":30,"losses":43,"wins":67},"gpt-5.5":{"draws":52,"losses":79,"wins":39},"gpt-5.6-luna":{"draws":21,"losses":17,"wins":34},"gpt-5.6-sol":{"draws":15,"losses":46,"wins":11},"gpt-5.6-terra":{"draws":30,"losses":44,"wins":20},"gpt-6-astra":{"draws":4,"losses":69,"wins":1},"gpt-6-luna":{"draws":22,"losses":23,"wins":17},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":20,"losses":5,"wins":23},"inclusionai/ling-3.0-flash":{"draws":29,"losses":28,"wins":33},"meituan/longcat-2.0":{"draws":48,"losses":36,"wins":62},"meta/muse-glimmer-30b":{"draws":28,"losses":16,"wins":34},"meta/muse-spark-1.2":{"draws":19,"losses":34,"wins":13},"meta/muse-spark-1.3":{"draws":24,"losses":45,"wins":19},"minimax/minimax-m3":{"draws":32,"losses":15,"wins":45},"mistralai/mistral-medium-3-5":{"draws":15,"losses":11,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":18,"wins":16},"moonshotai/kimi-k3":{"draws":28,"losses":34,"wins":22},"nex-agi/nex-n2-pro":{"draws":25,"losses":9,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":66,"losses":24,"wins":54},"o3":{"draws":33,"losses":45,"wins":74},"openai/gpt-oss-120b":{"draws":23,"losses":8,"wins":29},"poolside/laguna-s-2.1":{"draws":49,"losses":39,"wins":30},"qwen/qwen3.7-max":{"draws":40,"losses":18,"wins":38},"qwen/qwen3.7-plus":{"draws":22,"losses":13,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":37,"wins":23},"qwen/qwen3.8-27b":{"draws":10,"losses":26,"wins":20},"qwen/qwen3.8-flash":{"draws":19,"losses":22,"wins":25},"qwen/qwen3.8-max":{"draws":29,"losses":25,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":10,"wins":5},"stealth/ox-alpha":{"draws":75,"losses":124,"wins":63},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":17},"stepfun/step-3.7-flash":{"draws":33,"losses":7,"wins":42},"tencent/hy3-preview":{"draws":36,"losses":29,"wins":35},"tencent/hy4-preview":{"draws":28,"losses":27,"wins":19},"thinkingmachines/inkling":{"draws":45,"losses":29,"wins":62},"thinkingmachines/inkling-small":{"draws":41,"losses":11,"wins":40},"x-ai/grok-4.5":{"draws":23,"losses":67,"wins":34},"x-ai/grok-4.6":{"draws":28,"losses":56,"wins":18},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":21,"losses":13,"wins":30},"xiaomi/mimo-v2.5":{"draws":104,"losses":44,"wins":88},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":25,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":8,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":89,"losses":69,"wins":78},"z-ai/glm-5.3":{"draws":11,"losses":47,"wins":8},"z-ai/glm-5.3-flash":{"draws":36,"losses":59,"wins":21},"z-ai/glm-5.3-flashx":{"draws":19,"losses":10,"wins":7}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":36,"wins":55},"claude-fable-5":{"draws":55,"losses":94,"wins":69},"claude-fable-5-1":{"draws":14,"losses":161,"wins":21},"claude-opus-4-5":{"draws":78,"losses":60,"wins":146},"claude-opus-4-8":{"draws":9,"losses":24,"wins":31},"claude-opus-5":{"draws":12,"losses":112,"wins":16},"claude-opus-5-5":{"draws":7,"losses":57,"wins":4},"claude-sonnet-5":{"draws":102,"losses":66,"wins":164},"claude-sonnet-5-5":{"draws":20,"losses":21,"wins":19},"cohere/north-mini-code":{"draws":8,"losses":0,"wins":28},"deepseek/deepseek-v4-flash":{"draws":62,"losses":27,"wins":99},"deepseek/deepseek-v4-pro":{"draws":53,"losses":49,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":55,"losses":44,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":12,"wins":22},"fireworks/ember-1":{"draws":24,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":14,"losses":27,"wins":27},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":39},"google/gemini-3.5-flash":{"draws":37,"losses":62,"wins":101},"google/gemini-3.5-flash-lite":{"draws":149,"losses":77,"wins":302},"google/gemini-3.6-flash":{"draws":130,"losses":152,"wins":232},"google/gemini-3.8-flash":{"draws":51,"losses":75,"wins":78},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":26},"gpt-4.1":{"draws":6,"losses":3,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":12},"gpt-5":{"draws":23,"losses":19,"wins":32},"gpt-5.4":{"draws":62,"losses":99,"wins":99},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":53},"gpt-5.5":{"draws":30,"losses":32,"wins":30},"gpt-5.6-luna":{"draws":122,"losses":53,"wins":172},"gpt-5.6-sol":{"draws":66,"losses":162,"wins":114},"gpt-5.6-terra":{"draws":67,"losses":33,"wins":94},"gpt-6-astra":{"draws":16,"losses":152,"wins":24},"gpt-6-luna":{"draws":32,"losses":22,"wins":40},"gpt-6-sol":{"draws":7,"losses":44,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":55,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":13,"losses":2,"wins":11},"inception/mercury-2.5-preview":{"draws":55,"losses":3,"wins":42},"inclusionai/ling-3.0-flash":{"draws":26,"losses":17,"wins":53},"meituan/longcat-2.0":{"draws":61,"losses":26,"wins":103},"meta/muse-glimmer-30b":{"draws":50,"losses":19,"wins":53},"meta/muse-spark-1.2":{"draws":44,"losses":75,"wins":109},"meta/muse-spark-1.3":{"draws":30,"losses":60,"wins":58},"minimax/minimax-m3":{"draws":10,"losses":9,"wins":19},"mistralai/mistral-medium-3-5":{"draws":38,"losses":15,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":10},"moonshotai/kimi-k3":{"draws":69,"losses":71,"wins":148},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":5,"wins":23},"o3":{"draws":35,"losses":68,"wins":219},"openai/gpt-oss-120b":{"draws":64,"losses":17,"wins":55},"poolside/laguna-s-2.1":{"draws":80,"losses":13,"wins":87},"qwen/qwen3.7-max":{"draws":11,"losses":11,"wins":26},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":46,"losses":75,"wins":59},"qwen/qwen3.8-27b":{"draws":26,"losses":29,"wins":57},"qwen/qwen3.8-flash":{"draws":33,"losses":33,"wins":50},"qwen/qwen3.8-max":{"draws":58,"losses":65,"wins":55},"qwen/qwen3.8-max-0902":{"draws":22,"losses":18,"wins":24},"stealth/ox-alpha":{"draws":178,"losses":172,"wins":213},"stealth/space-bunny-alpha":{"draws":23,"losses":5,"wins":22},"stepfun/step-3.7-flash":{"draws":19,"losses":9,"wins":60},"tencent/hy3-preview":{"draws":19,"losses":11,"wins":20},"tencent/hy4-preview":{"draws":43,"losses":56,"wins":63},"thinkingmachines/inkling":{"draws":54,"losses":39,"wins":121},"thinkingmachines/inkling-small":{"draws":77,"losses":18,"wins":72},"x-ai/grok-4.5":{"draws":63,"losses":88,"wins":130},"x-ai/grok-4.6":{"draws":66,"losses":73,"wins":77},"x-ai/grok-4.7":{"draws":10,"losses":32,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.5":{"draws":36,"losses":6,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":10,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":18,"wins":11},"z-ai/glm-5.2":{"draws":91,"losses":58,"wins":107},"z-ai/glm-5.3":{"draws":34,"losses":95,"wins":65},"z-ai/glm-5.3-flash":{"draws":47,"losses":79,"wins":76},"z-ai/glm-5.3-flashx":{"draws":21,"losses":15,"wins":16}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":18,"wins":12},"claude-fable-5":{"draws":15,"losses":49,"wins":6},"claude-fable-5-1":{"draws":3,"losses":47,"wins":0},"claude-opus-4-5":{"draws":73,"losses":79,"wins":54},"claude-opus-4-8":{"draws":39,"losses":59,"wins":36},"claude-opus-5":{"draws":36,"losses":138,"wins":12},"claude-opus-5-5":{"draws":2,"losses":44,"wins":2},"claude-sonnet-5":{"draws":20,"losses":19,"wins":9},"claude-sonnet-5-5":{"draws":6,"losses":32,"wins":14},"cohere/north-mini-code":{"draws":23,"losses":11,"wins":32},"deepseek/deepseek-v4-flash":{"draws":60,"losses":29,"wins":33},"deepseek/deepseek-v4-pro":{"draws":24,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":16,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":28,"wins":13},"fireworks/ember-1":{"draws":19,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":22,"losses":15,"wins":17},"google/gemini-3.1-flash-lite":{"draws":26,"losses":12,"wins":38},"google/gemini-3.5-flash":{"draws":34,"losses":38,"wins":18},"google/gemini-3.5-flash-lite":{"draws":53,"losses":39,"wins":56},"google/gemini-3.6-flash":{"draws":52,"losses":63,"wins":26},"google/gemini-3.8-flash":{"draws":17,"losses":29,"wins":14},"google/gemma-4-31b-it":{"draws":7,"losses":24,"wins":21},"gpt-4.1":{"draws":23,"losses":11,"wins":26},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":46,"losses":26,"wins":30},"gpt-5.4":{"draws":10,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":24,"losses":16,"wins":16},"gpt-5.4-nano":{"draws":49,"losses":68,"wins":39},"gpt-5.5":{"draws":55,"losses":43,"wins":12},"gpt-5.6-luna":{"draws":19,"losses":15,"wins":12},"gpt-5.6-sol":{"draws":15,"losses":46,"wins":5},"gpt-5.6-terra":{"draws":33,"losses":27,"wins":14},"gpt-6-astra":{"draws":2,"losses":44,"wins":0},"gpt-6-luna":{"draws":20,"losses":31,"wins":11},"gpt-6-sol":{"draws":5,"losses":26,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":52,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":45,"losses":12,"wins":27},"meituan/longcat-2.0":{"draws":45,"losses":35,"wins":50},"meta/muse-glimmer-30b":{"draws":26,"losses":3,"wins":17},"meta/muse-spark-1.2":{"draws":8,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":18,"losses":35,"wins":5},"minimax/minimax-m3":{"draws":32,"losses":32,"wins":36},"mistralai/mistral-medium-3-5":{"draws":11,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":19,"wins":6},"moonshotai/kimi-k3":{"draws":35,"losses":29,"wins":22},"nex-agi/nex-n2-pro":{"draws":33,"losses":15,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":72,"losses":29,"wins":29},"o3":{"draws":21,"losses":36,"wins":29},"openai/gpt-oss-120b":{"draws":18,"losses":10,"wins":12},"poolside/laguna-s-2.1":{"draws":54,"losses":23,"wins":35},"qwen/qwen3.7-max":{"draws":31,"losses":29,"wins":14},"qwen/qwen3.7-plus":{"draws":24,"losses":29,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":31,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":15,"wins":6},"qwen/qwen3.8-flash":{"draws":17,"losses":21,"wins":8},"qwen/qwen3.8-max":{"draws":31,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":11,"losses":24,"wins":9},"stealth/ox-alpha":{"draws":66,"losses":95,"wins":35},"stealth/space-bunny-alpha":{"draws":19,"losses":21,"wins":10},"stepfun/step-3.7-flash":{"draws":25,"losses":16,"wins":17},"tencent/hy3-preview":{"draws":26,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":30,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":44,"losses":27,"wins":35},"thinkingmachines/inkling-small":{"draws":32,"losses":15,"wins":13},"x-ai/grok-4.5":{"draws":34,"losses":49,"wins":9},"x-ai/grok-4.6":{"draws":24,"losses":45,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":4},"x-ai/grok-build-0.1":{"draws":26,"losses":16,"wins":20},"xiaomi/mimo-v2.5":{"draws":99,"losses":60,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":17,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":97,"losses":60,"wins":25},"z-ai/glm-5.3":{"draws":11,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":30,"losses":36,"wins":8},"z-ai/glm-5.3-flashx":{"draws":8,"losses":35,"wins":9}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":36,"wins":30},"claude-fable-5":{"draws":11,"losses":77,"wins":10},"claude-fable-5-1":{"draws":1,"losses":67,"wins":0},"claude-opus-4-5":{"draws":83,"losses":134,"wins":91},"claude-opus-4-8":{"draws":46,"losses":109,"wins":45},"claude-opus-5":{"draws":34,"losses":231,"wins":27},"claude-opus-5-5":{"draws":0,"losses":52,"wins":2},"claude-sonnet-5":{"draws":20,"losses":37,"wins":23},"claude-sonnet-5-5":{"draws":13,"losses":42,"wins":13},"cohere/north-mini-code":{"draws":30,"losses":29,"wins":59},"deepseek/deepseek-v4-flash":{"draws":49,"losses":63,"wins":56},"deepseek/deepseek-v4-pro":{"draws":21,"losses":43,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":39,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":25,"wins":11},"fireworks/ember-1":{"draws":19,"losses":29,"wins":22},"gemini-3.1-pro-preview":{"draws":21,"losses":25,"wins":24},"google/gemini-3.1-flash-lite":{"draws":22,"losses":38,"wins":96},"google/gemini-3.5-flash":{"draws":31,"losses":78,"wins":37},"google/gemini-3.5-flash-lite":{"draws":56,"losses":87,"wins":61},"google/gemini-3.6-flash":{"draws":52,"losses":88,"wins":50},"google/gemini-3.8-flash":{"draws":18,"losses":65,"wins":17},"google/gemma-4-31b-it":{"draws":9,"losses":36,"wins":47},"gpt-4.1":{"draws":14,"losses":25,"wins":29},"gpt-4.1-nano":{"draws":3,"losses":4,"wins":1},"gpt-5":{"draws":30,"losses":67,"wins":43},"gpt-5.4":{"draws":20,"losses":53,"wins":23},"gpt-5.4-mini":{"draws":49,"losses":39,"wins":68},"gpt-5.4-nano":{"draws":50,"losses":79,"wins":79},"gpt-5.5":{"draws":53,"losses":90,"wins":55},"gpt-5.6-luna":{"draws":27,"losses":34,"wins":33},"gpt-5.6-sol":{"draws":17,"losses":62,"wins":9},"gpt-5.6-terra":{"draws":19,"losses":42,"wins":33},"gpt-6-astra":{"draws":3,"losses":87,"wins":0},"gpt-6-luna":{"draws":23,"losses":42,"wins":23},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":6,"losses":56,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":15,"losses":14,"wins":35},"inclusionai/ling-3.0-flash":{"draws":55,"losses":26,"wins":43},"meituan/longcat-2.0":{"draws":39,"losses":68,"wins":85},"meta/muse-glimmer-30b":{"draws":19,"losses":18,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":35,"wins":20},"meta/muse-spark-1.3":{"draws":17,"losses":53,"wins":10},"minimax/minimax-m3":{"draws":35,"losses":42,"wins":51},"mistralai/mistral-medium-3-5":{"draws":11,"losses":14,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":19,"wins":25},"moonshotai/kimi-k3":{"draws":37,"losses":66,"wins":21},"nex-agi/nex-n2-pro":{"draws":26,"losses":32,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":49,"wins":53},"o3":{"draws":15,"losses":93,"wins":82},"openai/gpt-oss-120b":{"draws":13,"losses":25,"wins":20},"poolside/laguna-s-2.1":{"draws":62,"losses":62,"wins":50},"qwen/qwen3.7-max":{"draws":37,"losses":52,"wins":45},"qwen/qwen3.7-plus":{"draws":28,"losses":53,"wins":57},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":56,"wins":19},"qwen/qwen3.8-27b":{"draws":10,"losses":31,"wins":19},"qwen/qwen3.8-flash":{"draws":23,"losses":28,"wins":13},"qwen/qwen3.8-max":{"draws":16,"losses":46,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":28,"wins":11},"stealth/ox-alpha":{"draws":50,"losses":152,"wins":62},"stealth/space-bunny-alpha":{"draws":14,"losses":19,"wins":25},"stepfun/step-3.7-flash":{"draws":32,"losses":22,"wins":64},"tencent/hy3-preview":{"draws":25,"losses":39,"wins":22},"tencent/hy4-preview":{"draws":17,"losses":48,"wins":15},"thinkingmachines/inkling":{"draws":24,"losses":50,"wins":68},"thinkingmachines/inkling-small":{"draws":34,"losses":27,"wins":29},"x-ai/grok-4.5":{"draws":26,"losses":90,"wins":44},"x-ai/grok-4.6":{"draws":17,"losses":69,"wins":16},"x-ai/grok-4.7":{"draws":15,"losses":52,"wins":5},"x-ai/grok-build-0.1":{"draws":18,"losses":25,"wins":49},"xiaomi/mimo-v2.5":{"draws":84,"losses":120,"wins":144},"xiaomi/mimo-v2.5-pro":{"draws":35,"losses":62,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":18,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":26,"wins":2},"z-ai/glm-5.2":{"draws":85,"losses":104,"wins":89},"z-ai/glm-5.3":{"draws":12,"losses":73,"wins":19},"z-ai/glm-5.3-flash":{"draws":22,"losses":58,"wins":22},"z-ai/glm-5.3-flashx":{"draws":14,"losses":35,"wins":17}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":15,"wins":41},"claude-fable-5":{"draws":17,"losses":50,"wins":31},"claude-fable-5-1":{"draws":4,"losses":76,"wins":8},"claude-opus-4-5":{"draws":100,"losses":68,"wins":104},"claude-opus-4-8":{"draws":54,"losses":52,"wins":72},"claude-opus-5":{"draws":46,"losses":233,"wins":85},"claude-opus-5-5":{"draws":5,"losses":51,"wins":8},"claude-sonnet-5":{"draws":30,"losses":14,"wins":42},"claude-sonnet-5-5":{"draws":17,"losses":38,"wins":13},"cohere/north-mini-code":{"draws":30,"losses":8,"wins":34},"deepseek/deepseek-v4-flash":{"draws":62,"losses":16,"wins":62},"deepseek/deepseek-v4-pro":{"draws":23,"losses":22,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":21,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":19,"wins":14},"fireworks/ember-1":{"draws":33,"losses":23,"wins":16},"gemini-3.1-pro-preview":{"draws":26,"losses":18,"wins":26},"google/gemini-3.1-flash-lite":{"draws":32,"losses":7,"wins":55},"google/gemini-3.5-flash":{"draws":42,"losses":29,"wins":43},"google/gemini-3.5-flash-lite":{"draws":82,"losses":15,"wins":77},"google/gemini-3.6-flash":{"draws":66,"losses":66,"wins":74},"google/gemini-3.8-flash":{"draws":21,"losses":26,"wins":31},"google/gemma-4-31b-it":{"draws":26,"losses":7,"wins":35},"gpt-4.1":{"draws":21,"losses":14,"wins":21},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":52,"losses":39,"wins":79},"gpt-5.4":{"draws":30,"losses":30,"wins":32},"gpt-5.4-mini":{"draws":55,"losses":12,"wins":43},"gpt-5.4-nano":{"draws":53,"losses":55,"wins":90},"gpt-5.5":{"draws":52,"losses":38,"wins":38},"gpt-5.6-luna":{"draws":26,"losses":18,"wins":44},"gpt-5.6-sol":{"draws":23,"losses":25,"wins":34},"gpt-5.6-terra":{"draws":37,"losses":21,"wins":30},"gpt-6-astra":{"draws":2,"losses":56,"wins":4},"gpt-6-luna":{"draws":32,"losses":21,"wins":35},"gpt-6-sol":{"draws":15,"losses":41,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":43,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":21,"losses":5,"wins":20},"inclusionai/ling-3.0-flash":{"draws":57,"losses":8,"wins":47},"meituan/longcat-2.0":{"draws":65,"losses":32,"wins":58},"meta/muse-glimmer-30b":{"draws":31,"losses":6,"wins":39},"meta/muse-spark-1.2":{"draws":17,"losses":22,"wins":21},"meta/muse-spark-1.3":{"draws":15,"losses":24,"wins":31},"minimax/minimax-m3":{"draws":26,"losses":11,"wins":55},"mistralai/mistral-medium-3-5":{"draws":19,"losses":4,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":25,"losses":17,"wins":12},"moonshotai/kimi-k3":{"draws":39,"losses":40,"wins":23},"nex-agi/nex-n2-pro":{"draws":28,"losses":9,"wins":63},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":71,"losses":11,"wins":76},"o3":{"draws":40,"losses":31,"wins":79},"openai/gpt-oss-120b":{"draws":23,"losses":6,"wins":37},"poolside/laguna-s-2.1":{"draws":54,"losses":29,"wins":51},"qwen/qwen3.7-max":{"draws":42,"losses":23,"wins":43},"qwen/qwen3.7-plus":{"draws":47,"losses":12,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":24,"wins":29},"qwen/qwen3.8-27b":{"draws":11,"losses":20,"wins":29},"qwen/qwen3.8-flash":{"draws":25,"losses":11,"wins":36},"qwen/qwen3.8-max":{"draws":23,"losses":28,"wins":27},"qwen/qwen3.8-max-0902":{"draws":36,"losses":24,"wins":16},"stealth/ox-alpha":{"draws":59,"losses":89,"wins":74},"stealth/space-bunny-alpha":{"draws":18,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":16,"losses":14,"wins":52},"tencent/hy3-preview":{"draws":49,"losses":13,"wins":40},"tencent/hy4-preview":{"draws":25,"losses":30,"wins":27},"thinkingmachines/inkling":{"draws":45,"losses":32,"wins":91},"thinkingmachines/inkling-small":{"draws":24,"losses":6,"wins":42},"x-ai/grok-4.5":{"draws":51,"losses":63,"wins":56},"x-ai/grok-4.6":{"draws":28,"losses":44,"wins":22},"x-ai/grok-4.7":{"draws":8,"losses":49,"wins":19},"x-ai/grok-build-0.1":{"draws":43,"losses":8,"wins":19},"xiaomi/mimo-v2.5":{"draws":119,"losses":26,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":26,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":13},"z-ai/glm-5.2":{"draws":96,"losses":59,"wins":103},"z-ai/glm-5.3":{"draws":20,"losses":51,"wins":15},"z-ai/glm-5.3-flash":{"draws":18,"losses":45,"wins":35},"z-ai/glm-5.3-flashx":{"draws":25,"losses":21,"wins":18}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":59,"losses":71,"wins":62},"claude-fable-5":{"draws":45,"losses":100,"wins":29},"claude-fable-5-1":{"draws":14,"losses":124,"wins":6},"claude-opus-4-5":{"draws":101,"losses":115,"wins":74},"claude-opus-4-8":{"draws":35,"losses":39,"wins":8},"claude-opus-5":{"draws":16,"losses":102,"wins":10},"claude-opus-5-5":{"draws":6,"losses":66,"wins":0},"claude-sonnet-5":{"draws":113,"losses":138,"wins":91},"claude-sonnet-5-5":{"draws":27,"losses":51,"wins":14},"cohere/north-mini-code":{"draws":9,"losses":7,"wins":24},"deepseek/deepseek-v4-flash":{"draws":97,"losses":67,"wins":80},"deepseek/deepseek-v4-pro":{"draws":59,"losses":63,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":52,"losses":55,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":30,"wins":8},"fireworks/ember-1":{"draws":37,"losses":29,"wins":16},"gemini-3.1-pro-preview":{"draws":29,"losses":41,"wins":16},"google/gemini-3.1-flash-lite":{"draws":19,"losses":10,"wins":25},"google/gemini-3.5-flash":{"draws":65,"losses":78,"wins":47},"google/gemini-3.5-flash-lite":{"draws":194,"losses":184,"wins":208},"google/gemini-3.6-flash":{"draws":152,"losses":250,"wins":122},"google/gemini-3.8-flash":{"draws":39,"losses":90,"wins":35},"google/gemma-4-31b-it":{"draws":14,"losses":9,"wins":17},"gpt-4.1":{"draws":11,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":6},"gpt-5":{"draws":21,"losses":34,"wins":17},"gpt-5.4":{"draws":122,"losses":172,"wins":53},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":15},"gpt-5.4-nano":{"draws":27,"losses":33,"wins":34},"gpt-5.5":{"draws":26,"losses":44,"wins":18},"gpt-5.6-luna":{"draws":110,"losses":66,"wins":66},"gpt-5.6-sol":{"draws":51,"losses":207,"wins":50},"gpt-5.6-terra":{"draws":74,"losses":62,"wins":74},"gpt-6-astra":{"draws":19,"losses":123,"wins":0},"gpt-6-luna":{"draws":34,"losses":41,"wins":15},"gpt-6-sol":{"draws":13,"losses":49,"wins":2},"gpt-6.1-sol":{"draws":7,"losses":66,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":15,"losses":1,"wins":12},"inception/mercury-2.5-preview":{"draws":76,"losses":22,"wins":48},"inclusionai/ling-3.0-flash":{"draws":45,"losses":32,"wins":37},"meituan/longcat-2.0":{"draws":66,"losses":60,"wins":74},"meta/muse-glimmer-30b":{"draws":86,"losses":53,"wins":53},"meta/muse-spark-1.2":{"draws":55,"losses":117,"wins":58},"meta/muse-spark-1.3":{"draws":44,"losses":66,"wins":30},"minimax/minimax-m3":{"draws":9,"losses":14,"wins":21},"mistralai/mistral-medium-3-5":{"draws":51,"losses":18,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":13,"wins":9},"moonshotai/kimi-k3":{"draws":95,"losses":121,"wins":66},"nex-agi/nex-n2-pro":{"draws":16,"losses":7,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":17,"wins":19},"o3":{"draws":47,"losses":155,"wins":136},"openai/gpt-oss-120b":{"draws":77,"losses":39,"wins":54},"poolside/laguna-s-2.1":{"draws":83,"losses":49,"wins":62},"qwen/qwen3.7-max":{"draws":16,"losses":18,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":20,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":62,"wins":39},"qwen/qwen3.8-27b":{"draws":19,"losses":48,"wins":29},"qwen/qwen3.8-flash":{"draws":42,"losses":47,"wins":41},"qwen/qwen3.8-max":{"draws":63,"losses":79,"wins":38},"qwen/qwen3.8-max-0902":{"draws":34,"losses":29,"wins":3},"stealth/ox-alpha":{"draws":181,"losses":221,"wins":125},"stealth/space-bunny-alpha":{"draws":31,"losses":14,"wins":15},"stepfun/step-3.7-flash":{"draws":25,"losses":30,"wins":31},"tencent/hy3-preview":{"draws":14,"losses":17,"wins":15},"tencent/hy4-preview":{"draws":60,"losses":92,"wins":32},"thinkingmachines/inkling":{"draws":88,"losses":55,"wins":107},"thinkingmachines/inkling-small":{"draws":73,"losses":57,"wins":60},"x-ai/grok-4.5":{"draws":72,"losses":108,"wins":88},"x-ai/grok-4.6":{"draws":54,"losses":103,"wins":37},"x-ai/grok-4.7":{"draws":12,"losses":51,"wins":9},"x-ai/grok-build-0.1":{"draws":14,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":57,"losses":21,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":25,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":15,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":38,"wins":6},"z-ai/glm-5.2":{"draws":108,"losses":88,"wins":56},"z-ai/glm-5.3":{"draws":39,"losses":91,"wins":22},"z-ai/glm-5.3-flash":{"draws":58,"losses":86,"wins":42},"z-ai/glm-5.3-flashx":{"draws":29,"losses":26,"wins":9}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":24,"wins":96},"claude-fable-5":{"draws":30,"losses":108,"wins":88},"claude-fable-5-1":{"draws":22,"losses":181,"wins":35},"claude-opus-4-5":{"draws":56,"losses":66,"wins":214},"claude-opus-4-8":{"draws":21,"losses":33,"wins":34},"claude-opus-5":{"draws":27,"losses":126,"wins":39},"claude-opus-5-5":{"draws":5,"losses":65,"wins":10},"claude-sonnet-5":{"draws":56,"losses":45,"wins":268},"claude-sonnet-5-5":{"draws":5,"losses":29,"wins":46},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":41},"deepseek/deepseek-v4-flash":{"draws":31,"losses":27,"wins":138},"deepseek/deepseek-v4-pro":{"draws":20,"losses":46,"wins":96},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":40,"wins":102},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":9,"wins":33},"fireworks/ember-1":{"draws":11,"losses":13,"wins":38},"gemini-3.1-pro-preview":{"draws":5,"losses":10,"wins":45},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":34},"google/gemini-3.5-flash":{"draws":23,"losses":59,"wins":132},"google/gemini-3.5-flash-lite":{"draws":77,"losses":44,"wins":417},"google/gemini-3.6-flash":{"draws":72,"losses":150,"wins":292},"google/gemini-3.8-flash":{"draws":27,"losses":76,"wins":103},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":31},"gpt-4.1":{"draws":10,"losses":5,"wins":21},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":15,"losses":11,"wins":46},"gpt-5.4":{"draws":66,"losses":114,"wins":162},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":46},"gpt-5.4-nano":{"draws":17,"losses":9,"wins":62},"gpt-5.5":{"draws":23,"losses":34,"wins":25},"gpt-5.6-luna":{"draws":51,"losses":50,"wins":207},"gpt-5.6-sol":{"draws":36,"losses":110,"wins":110},"gpt-5.6-terra":{"draws":58,"losses":34,"wins":114},"gpt-6-astra":{"draws":21,"losses":177,"wins":20},"gpt-6-luna":{"draws":20,"losses":12,"wins":52},"gpt-6-sol":{"draws":6,"losses":30,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":51,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":24,"losses":1,"wins":79},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":76},"meituan/longcat-2.0":{"draws":34,"losses":23,"wins":155},"meta/muse-glimmer-30b":{"draws":24,"losses":10,"wins":72},"meta/muse-spark-1.2":{"draws":25,"losses":50,"wins":169},"meta/muse-spark-1.3":{"draws":36,"losses":51,"wins":77},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":40},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":16},"moonshotai/kimi-k3":{"draws":66,"losses":63,"wins":165},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":43},"o3":{"draws":17,"losses":59,"wins":268},"openai/gpt-oss-120b":{"draws":15,"losses":11,"wins":90},"poolside/laguna-s-2.1":{"draws":40,"losses":5,"wins":155},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":25},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":50,"wins":110},"qwen/qwen3.8-27b":{"draws":17,"losses":28,"wins":61},"qwen/qwen3.8-flash":{"draws":28,"losses":30,"wins":78},"qwen/qwen3.8-max":{"draws":37,"losses":43,"wins":101},"qwen/qwen3.8-max-0902":{"draws":10,"losses":5,"wins":27},"stealth/ox-alpha":{"draws":103,"losses":169,"wins":367},"stealth/space-bunny-alpha":{"draws":11,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":56},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":36},"tencent/hy4-preview":{"draws":30,"losses":65,"wins":105},"thinkingmachines/inkling":{"draws":33,"losses":15,"wins":162},"thinkingmachines/inkling-small":{"draws":28,"losses":23,"wins":116},"x-ai/grok-4.5":{"draws":32,"losses":91,"wins":157},"x-ai/grok-4.6":{"draws":43,"losses":90,"wins":101},"x-ai/grok-4.7":{"draws":9,"losses":42,"wins":15},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":20},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":80},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":12},"z-ai/glm-5.2":{"draws":25,"losses":42,"wins":183},"z-ai/glm-5.3":{"draws":33,"losses":79,"wins":86},"z-ai/glm-5.3-flash":{"draws":39,"losses":79,"wins":116},"z-ai/glm-5.3-flashx":{"draws":14,"losses":11,"wins":27}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":32,"wins":85},"claude-fable-5":{"draws":60,"losses":131,"wins":31},"claude-fable-5-1":{"draws":19,"losses":193,"wins":6},"claude-opus-4-5":{"draws":86,"losses":89,"wins":55},"claude-opus-4-8":{"draws":34,"losses":46,"wins":26},"claude-opus-5":{"draws":24,"losses":138,"wins":12},"claude-opus-5-5":{"draws":5,"losses":93,"wins":2},"claude-sonnet-5":{"draws":77,"losses":58,"wins":65},"claude-sonnet-5-5":{"draws":13,"losses":33,"wins":16},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":43},"deepseek/deepseek-v4-flash":{"draws":101,"losses":44,"wins":113},"deepseek/deepseek-v4-pro":{"draws":70,"losses":68,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":65,"losses":59,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":28,"wins":25},"fireworks/ember-1":{"draws":13,"losses":17,"wins":22},"gemini-3.1-pro-preview":{"draws":19,"losses":13,"wins":28},"google/gemini-3.1-flash-lite":{"draws":23,"losses":8,"wins":49},"google/gemini-3.5-flash":{"draws":75,"losses":69,"wins":76},"google/gemini-3.5-flash-lite":{"draws":120,"losses":80,"wins":150},"google/gemini-3.6-flash":{"draws":105,"losses":127,"wins":88},"google/gemini-3.8-flash":{"draws":70,"losses":80,"wins":48},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":33},"gpt-4.1":{"draws":17,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":8},"gpt-5":{"draws":30,"losses":20,"wins":44},"gpt-5.4":{"draws":67,"losses":94,"wins":33},"gpt-5.4-mini":{"draws":33,"losses":14,"wins":27},"gpt-5.4-nano":{"draws":19,"losses":33,"wins":42},"gpt-5.5":{"draws":37,"losses":30,"wins":21},"gpt-5.6-luna":{"draws":74,"losses":74,"wins":62},"gpt-5.6-sol":{"draws":58,"losses":114,"wins":34},"gpt-5.6-terra":{"draws":32,"losses":34,"wins":34},"gpt-6-astra":{"draws":16,"losses":183,"wins":9},"gpt-6-luna":{"draws":28,"losses":38,"wins":36},"gpt-6-sol":{"draws":14,"losses":63,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":13},"inception/mercury-2.5-preview":{"draws":65,"losses":12,"wins":65},"inclusionai/ling-3.0-flash":{"draws":30,"losses":11,"wins":59},"meituan/longcat-2.0":{"draws":58,"losses":38,"wins":78},"meta/muse-glimmer-30b":{"draws":79,"losses":22,"wins":77},"meta/muse-spark-1.2":{"draws":51,"losses":64,"wins":49},"meta/muse-spark-1.3":{"draws":53,"losses":93,"wins":48},"minimax/minimax-m3":{"draws":17,"losses":12,"wins":25},"mistralai/mistral-medium-3-5":{"draws":42,"losses":14,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":9,"wins":15},"moonshotai/kimi-k3":{"draws":67,"losses":86,"wins":45},"nex-agi/nex-n2-pro":{"draws":18,"losses":5,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":14,"wins":44},"o3":{"draws":38,"losses":77,"wins":99},"openai/gpt-oss-120b":{"draws":70,"losses":18,"wins":90},"poolside/laguna-s-2.1":{"draws":61,"losses":15,"wins":60},"qwen/qwen3.7-max":{"draws":20,"losses":12,"wins":30},"qwen/qwen3.7-plus":{"draws":17,"losses":8,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":77,"losses":80,"wins":33},"qwen/qwen3.8-27b":{"draws":36,"losses":37,"wins":35},"qwen/qwen3.8-flash":{"draws":43,"losses":37,"wins":44},"qwen/qwen3.8-max":{"draws":88,"losses":68,"wins":54},"qwen/qwen3.8-max-0902":{"draws":29,"losses":30,"wins":13},"stealth/ox-alpha":{"draws":213,"losses":255,"wins":176},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":30},"stepfun/step-3.7-flash":{"draws":22,"losses":14,"wins":42},"tencent/hy3-preview":{"draws":23,"losses":9,"wins":16},"tencent/hy4-preview":{"draws":57,"losses":86,"wins":47},"thinkingmachines/inkling":{"draws":54,"losses":29,"wins":83},"thinkingmachines/inkling-small":{"draws":70,"losses":36,"wins":102},"x-ai/grok-4.5":{"draws":51,"losses":99,"wins":46},"x-ai/grok-4.6":{"draws":68,"losses":122,"wins":36},"x-ai/grok-4.7":{"draws":11,"losses":41,"wins":10},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5":{"draws":66,"losses":13,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":10,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":19,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":24,"wins":16},"z-ai/glm-5.2":{"draws":141,"losses":67,"wins":108},"z-ai/glm-5.3":{"draws":60,"losses":110,"wins":26},"z-ai/glm-5.3-flash":{"draws":61,"losses":92,"wins":61},"z-ai/glm-5.3-flashx":{"draws":23,"losses":44,"wins":23}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":12,"wins":100},"claude-fable-5":{"draws":17,"losses":41,"wins":170},"claude-fable-5-1":{"draws":21,"losses":82,"wins":135},"claude-opus-4-5":{"draws":18,"losses":14,"wins":202},"claude-opus-4-8":{"draws":9,"losses":6,"wins":71},"claude-opus-5":{"draws":20,"losses":33,"wins":95},"claude-opus-5-5":{"draws":11,"losses":27,"wins":34},"claude-sonnet-5":{"draws":9,"losses":15,"wins":182},"claude-sonnet-5-5":{"draws":9,"losses":18,"wins":53},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":38},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":168},"deepseek/deepseek-v4-pro":{"draws":9,"losses":13,"wins":134},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":1,"wins":141},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":3,"wins":53},"fireworks/ember-1":{"draws":1,"losses":4,"wins":55},"gemini-3.1-pro-preview":{"draws":7,"losses":2,"wins":67},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":52},"google/gemini-3.5-flash":{"draws":23,"losses":7,"wins":168},"google/gemini-3.5-flash-lite":{"draws":14,"losses":2,"wins":236},"google/gemini-3.6-flash":{"draws":24,"losses":19,"wins":237},"google/gemini-3.8-flash":{"draws":22,"losses":14,"wins":168},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":36},"gpt-4.1":{"draws":4,"losses":0,"wins":30},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":1,"wins":69},"gpt-5.4":{"draws":16,"losses":24,"wins":152},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":44},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":87},"gpt-5.5":{"draws":2,"losses":4,"wins":56},"gpt-5.6-luna":{"draws":19,"losses":0,"wins":123},"gpt-5.6-sol":{"draws":21,"losses":20,"wins":177},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":183},"gpt-6-astra":{"draws":10,"losses":63,"wins":63},"gpt-6-luna":{"draws":16,"losses":4,"wins":70},"gpt-6-sol":{"draws":6,"losses":8,"wins":40},"gpt-6.1-sol":{"draws":9,"losses":21,"wins":38},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":13},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":78},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":59},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":106},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":96},"meta/muse-spark-1.2":{"draws":13,"losses":2,"wins":111},"meta/muse-spark-1.3":{"draws":17,"losses":16,"wins":135},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":35},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":19},"moonshotai/kimi-k3":{"draws":19,"losses":15,"wins":134},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":58},"o3":{"draws":4,"losses":2,"wins":166},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":83},"poolside/laguna-s-2.1":{"draws":17,"losses":0,"wins":99},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":48},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":8,"wins":155},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":96},"qwen/qwen3.8-flash":{"draws":17,"losses":3,"wins":96},"qwen/qwen3.8-max":{"draws":20,"losses":4,"wins":142},"qwen/qwen3.8-max-0902":{"draws":7,"losses":6,"wins":41},"stealth/ox-alpha":{"draws":76,"losses":37,"wins":489},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":51},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":42},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":36},"tencent/hy4-preview":{"draws":18,"losses":12,"wins":150},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":116},"thinkingmachines/inkling-small":{"draws":14,"losses":0,"wins":134},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":151},"x-ai/grok-4.6":{"draws":20,"losses":21,"wins":191},"x-ai/grok-4.7":{"draws":6,"losses":9,"wins":35},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":29},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":102},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":31},"z-ai/glm-5.2":{"draws":19,"losses":6,"wins":205},"z-ai/glm-5.3":{"draws":26,"losses":16,"wins":160},"z-ai/glm-5.3-flash":{"draws":30,"losses":14,"wins":178},"z-ai/glm-5.3-flashx":{"draws":6,"losses":3,"wins":55}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":31,"wins":40},"claude-fable-5":{"draws":20,"losses":64,"wins":20},"claude-fable-5-1":{"draws":5,"losses":80,"wins":5},"claude-opus-4-5":{"draws":58,"losses":53,"wins":43},"claude-opus-4-8":{"draws":19,"losses":39,"wins":30},"claude-opus-5":{"draws":24,"losses":109,"wins":13},"claude-opus-5-5":{"draws":16,"losses":133,"wins":1},"claude-sonnet-5":{"draws":20,"losses":27,"wins":35},"claude-sonnet-5-5":{"draws":20,"losses":44,"wins":20},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":22},"deepseek/deepseek-v4-flash":{"draws":36,"losses":22,"wins":72},"deepseek/deepseek-v4-pro":{"draws":25,"losses":27,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":21,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":58,"wins":38},"fireworks/ember-1":{"draws":27,"losses":33,"wins":18},"gemini-3.1-pro-preview":{"draws":22,"losses":30,"wins":24},"google/gemini-3.1-flash-lite":{"draws":13,"losses":8,"wins":47},"google/gemini-3.5-flash":{"draws":27,"losses":50,"wins":45},"google/gemini-3.5-flash-lite":{"draws":40,"losses":36,"wins":76},"google/gemini-3.6-flash":{"draws":38,"losses":82,"wins":44},"google/gemini-3.8-flash":{"draws":23,"losses":33,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":24},"gpt-4.1":{"draws":11,"losses":15,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":22,"losses":17,"wins":23},"gpt-5.4":{"draws":32,"losses":40,"wins":22},"gpt-5.4-mini":{"draws":20,"losses":11,"wins":31},"gpt-5.4-nano":{"draws":23,"losses":23,"wins":42},"gpt-5.5":{"draws":32,"losses":35,"wins":21},"gpt-5.6-luna":{"draws":34,"losses":15,"wins":41},"gpt-5.6-sol":{"draws":20,"losses":52,"wins":12},"gpt-5.6-terra":{"draws":28,"losses":36,"wins":38},"gpt-6-astra":{"draws":16,"losses":70,"wins":4},"gpt-6-luna":{"draws":20,"losses":34,"wins":34},"gpt-6-sol":{"draws":21,"losses":101,"wins":16},"gpt-6.1-sol":{"draws":5,"losses":69,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":5},"inception/mercury-2.5-preview":{"draws":25,"losses":6,"wins":31},"inclusionai/ling-3.0-flash":{"draws":23,"losses":8,"wins":41},"meituan/longcat-2.0":{"draws":27,"losses":17,"wins":54},"meta/muse-glimmer-30b":{"draws":24,"losses":11,"wins":37},"meta/muse-spark-1.2":{"draws":15,"losses":26,"wins":21},"meta/muse-spark-1.3":{"draws":18,"losses":39,"wins":23},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":29},"mistralai/mistral-medium-3-5":{"draws":18,"losses":2,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":8},"moonshotai/kimi-k3":{"draws":17,"losses":29,"wins":30},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":20,"wins":43},"o3":{"draws":20,"losses":38,"wins":54},"openai/gpt-oss-120b":{"draws":29,"losses":16,"wins":45},"poolside/laguna-s-2.1":{"draws":32,"losses":30,"wins":36},"qwen/qwen3.7-max":{"draws":13,"losses":18,"wins":23},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":34,"wins":30},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":22},"qwen/qwen3.8-flash":{"draws":15,"losses":22,"wins":31},"qwen/qwen3.8-max":{"draws":27,"losses":39,"wins":38},"qwen/qwen3.8-max-0902":{"draws":44,"losses":51,"wins":39},"stealth/ox-alpha":{"draws":63,"losses":116,"wins":99},"stealth/space-bunny-alpha":{"draws":21,"losses":16,"wins":23},"stepfun/step-3.7-flash":{"draws":13,"losses":10,"wins":31},"tencent/hy3-preview":{"draws":14,"losses":11,"wins":23},"tencent/hy4-preview":{"draws":16,"losses":38,"wins":24},"thinkingmachines/inkling":{"draws":27,"losses":23,"wins":48},"thinkingmachines/inkling-small":{"draws":19,"losses":14,"wins":45},"x-ai/grok-4.5":{"draws":29,"losses":42,"wins":31},"x-ai/grok-4.6":{"draws":31,"losses":58,"wins":15},"x-ai/grok-4.7":{"draws":8,"losses":56,"wins":18},"x-ai/grok-build-0.1":{"draws":12,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":58,"losses":35,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":37,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":40,"wins":16},"z-ai/glm-5.2":{"draws":56,"losses":59,"wins":75},"z-ai/glm-5.3":{"draws":17,"losses":53,"wins":18},"z-ai/glm-5.3-flash":{"draws":29,"losses":55,"wins":24},"z-ai/glm-5.3-flashx":{"draws":35,"losses":64,"wins":39}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":49},"claude-fable-5":{"draws":12,"losses":28,"wins":42},"claude-fable-5-1":{"draws":2,"losses":39,"wins":23},"claude-opus-4-5":{"draws":13,"losses":16,"wins":67},"claude-opus-4-8":{"draws":8,"losses":9,"wins":43},"claude-opus-5":{"draws":16,"losses":52,"wins":34},"claude-opus-5-5":{"draws":13,"losses":104,"wins":39},"claude-sonnet-5":{"draws":5,"losses":4,"wins":53},"claude-sonnet-5-5":{"draws":9,"losses":47,"wins":74},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":26},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":96},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":5,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":33,"wins":85},"fireworks/ember-1":{"draws":17,"losses":21,"wins":88},"gemini-3.1-pro-preview":{"draws":19,"losses":23,"wins":86},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":46},"google/gemini-3.5-flash":{"draws":10,"losses":15,"wins":55},"google/gemini-3.5-flash-lite":{"draws":13,"losses":10,"wins":91},"google/gemini-3.6-flash":{"draws":13,"losses":27,"wins":80},"google/gemini-3.8-flash":{"draws":10,"losses":7,"wins":33},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":28},"gpt-4.1":{"draws":6,"losses":6,"wins":26},"gpt-5":{"draws":3,"losses":0,"wins":27},"gpt-5.4":{"draws":7,"losses":7,"wins":44},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":26},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":38},"gpt-5.5":{"draws":15,"losses":8,"wins":41},"gpt-5.6-luna":{"draws":13,"losses":2,"wins":49},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":30},"gpt-5.6-terra":{"draws":14,"losses":5,"wins":63},"gpt-6-astra":{"draws":6,"losses":40,"wins":8},"gpt-6-luna":{"draws":21,"losses":16,"wins":101},"gpt-6-sol":{"draws":14,"losses":41,"wins":41},"gpt-6.1-sol":{"draws":15,"losses":84,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":29},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":51},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":72},"meta/muse-glimmer-30b":{"draws":4,"losses":6,"wins":44},"meta/muse-spark-1.2":{"draws":5,"losses":4,"wins":39},"meta/muse-spark-1.3":{"draws":4,"losses":3,"wins":35},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":42},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":13},"moonshotai/kimi-k3":{"draws":9,"losses":12,"wins":45},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":51},"o3":{"draws":4,"losses":4,"wins":64},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":57},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":47},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":27},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":12,"wins":34},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":33},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":47},"qwen/qwen3.8-max-0902":{"draws":17,"losses":26,"wins":95},"stealth/ox-alpha":{"draws":27,"losses":21,"wins":124},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":76},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":36},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":6,"losses":16,"wins":36},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":59},"thinkingmachines/inkling-small":{"draws":13,"losses":2,"wins":47},"x-ai/grok-4.5":{"draws":18,"losses":18,"wins":56},"x-ai/grok-4.6":{"draws":19,"losses":22,"wins":59},"x-ai/grok-4.7":{"draws":13,"losses":59,"wins":50},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":15},"xiaomi/mimo-v2.5":{"draws":20,"losses":13,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":18,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":19,"wins":53},"z-ai/glm-5.2":{"draws":19,"losses":7,"wins":96},"z-ai/glm-5.3":{"draws":18,"losses":27,"wins":29},"z-ai/glm-5.3-flash":{"draws":14,"losses":25,"wins":59},"z-ai/glm-5.3-flashx":{"draws":20,"losses":37,"wins":87}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":63},"claude-fable-5":{"draws":2,"losses":9,"wins":41},"claude-fable-5-1":{"draws":10,"losses":33,"wins":45},"claude-opus-4-5":{"draws":10,"losses":7,"wins":99},"claude-opus-4-8":{"draws":5,"losses":8,"wins":49},"claude-opus-5":{"draws":18,"losses":34,"wins":54},"claude-opus-5-5":{"draws":15,"losses":59,"wins":52},"claude-sonnet-5":{"draws":4,"losses":6,"wins":80},"claude-sonnet-5-5":{"draws":5,"losses":36,"wins":103},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":104},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":57},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":13,"wins":95},"fireworks/ember-1":{"draws":10,"losses":17,"wins":117},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":126},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":51},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":64},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":110},"google/gemini-3.6-flash":{"draws":11,"losses":23,"wins":106},"google/gemini-3.8-flash":{"draws":7,"losses":9,"wins":38},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":0,"wins":40},"gpt-5.4":{"draws":6,"losses":7,"wins":55},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":52},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":56},"gpt-5.5":{"draws":6,"losses":7,"wins":43},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":66},"gpt-5.6-sol":{"draws":9,"losses":8,"wins":51},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":38},"gpt-6-astra":{"draws":9,"losses":38,"wins":21},"gpt-6-luna":{"draws":5,"losses":0,"wins":69},"gpt-6-sol":{"draws":15,"losses":27,"wins":84},"gpt-6.1-sol":{"draws":6,"losses":45,"wins":45},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":13},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":53},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":59},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":81},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":63},"meta/muse-spark-1.2":{"draws":3,"losses":0,"wins":49},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":50},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":34},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":20},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":47},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":77},"o3":{"draws":0,"losses":1,"wins":75},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":73},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":64},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":50},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":13,"wins":50},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":25},"qwen/qwen3.8-flash":{"draws":3,"losses":6,"wins":41},"qwen/qwen3.8-max":{"draws":3,"losses":5,"wins":74},"qwen/qwen3.8-max-0902":{"draws":15,"losses":15,"wins":90},"stealth/ox-alpha":{"draws":27,"losses":12,"wins":181},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":100},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":36},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":33},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":52},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":76},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":73},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":47},"x-ai/grok-4.6":{"draws":8,"losses":3,"wins":43},"x-ai/grok-4.7":{"draws":5,"losses":40,"wins":65},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":11,"losses":0,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":6,"wins":70},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":21,"wins":54},"z-ai/glm-5.2":{"draws":16,"losses":5,"wins":123},"z-ai/glm-5.3":{"draws":10,"losses":14,"wins":54},"z-ai/glm-5.3-flash":{"draws":4,"losses":1,"wins":35},"z-ai/glm-5.3-flashx":{"draws":17,"losses":18,"wins":89}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":16,"wins":0},"claude-fable-5":{"draws":7,"losses":11,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-opus-4-5":{"draws":8,"losses":18,"wins":0},"claude-opus-4-8":{"draws":6,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":12,"wins":0},"claude-sonnet-5":{"draws":9,"losses":19,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":16,"losses":12,"wins":0},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":8,"wins":0},"gemini-3.1-pro-preview":{"draws":5,"losses":7,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":8,"losses":16,"wins":0},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":0},"google/gemini-3.6-flash":{"draws":10,"losses":30,"wins":0},"google/gemini-3.8-flash":{"draws":3,"losses":15,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":0},"gpt-4.1":{"draws":4,"losses":6,"wins":0},"gpt-5":{"draws":2,"losses":10,"wins":0},"gpt-5.4":{"draws":13,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":2},"gpt-5.5":{"draws":2,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":0},"gpt-6-astra":{"draws":1,"losses":13,"wins":0},"gpt-6-luna":{"draws":4,"losses":5,"wins":1},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":13,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":6,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":3},"meta/muse-glimmer-30b":{"draws":20,"losses":8,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":11,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":18,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":0},"o3":{"draws":10,"losses":20,"wins":0},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":0},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":10,"wins":1},"qwen/qwen3.8-27b":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.8-flash":{"draws":7,"losses":3,"wins":2},"qwen/qwen3.8-max":{"draws":6,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":41,"losses":37,"wins":4},"stealth/space-bunny-alpha":{"draws":5,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":0},"tencent/hy4-preview":{"draws":8,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":10,"losses":14,"wins":0},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":11,"wins":0},"x-ai/grok-4.6":{"draws":6,"losses":17,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":4,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":10,"wins":2},"z-ai/glm-5.3":{"draws":6,"losses":12,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":0},"z-ai/glm-5.3-flashx":{"draws":5,"losses":5,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":58,"losses":41,"wins":33},"claude-fable-5":{"draws":37,"losses":67,"wins":4},"claude-fable-5-1":{"draws":8,"losses":84,"wins":0},"claude-opus-4-5":{"draws":65,"losses":77,"wins":8},"claude-opus-4-8":{"draws":16,"losses":39,"wins":9},"claude-opus-5":{"draws":14,"losses":67,"wins":5},"claude-opus-5-5":{"draws":6,"losses":54,"wins":0},"claude-sonnet-5":{"draws":63,"losses":70,"wins":11},"claude-sonnet-5-5":{"draws":17,"losses":39,"wins":4},"cohere/north-mini-code":{"draws":10,"losses":12,"wins":12},"deepseek/deepseek-v4-flash":{"draws":81,"losses":68,"wins":19},"deepseek/deepseek-v4-pro":{"draws":55,"losses":56,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":48,"losses":68,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":16,"wins":2},"fireworks/ember-1":{"draws":25,"losses":23,"wins":0},"gemini-3.1-pro-preview":{"draws":24,"losses":11,"wins":7},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":16},"google/gemini-3.5-flash":{"draws":52,"losses":74,"wins":18},"google/gemini-3.5-flash-lite":{"draws":117,"losses":107,"wins":46},"google/gemini-3.6-flash":{"draws":86,"losses":101,"wins":21},"google/gemini-3.8-flash":{"draws":51,"losses":66,"wins":5},"google/gemma-4-31b-it":{"draws":12,"losses":19,"wins":13},"gpt-4.1":{"draws":9,"losses":12,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":20,"losses":23,"wins":5},"gpt-5.4":{"draws":55,"losses":42,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":13,"wins":8},"gpt-5.4-nano":{"draws":15,"losses":35,"wins":14},"gpt-5.5":{"draws":21,"losses":20,"wins":5},"gpt-5.6-luna":{"draws":76,"losses":48,"wins":22},"gpt-5.6-sol":{"draws":24,"losses":79,"wins":1},"gpt-5.6-terra":{"draws":65,"losses":65,"wins":12},"gpt-6-astra":{"draws":10,"losses":78,"wins":0},"gpt-6-luna":{"draws":25,"losses":31,"wins":6},"gpt-6-sol":{"draws":3,"losses":29,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":53,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":48,"losses":12,"wins":12},"inclusionai/ling-3.0-flash":{"draws":29,"losses":22,"wins":13},"meituan/longcat-2.0":{"draws":47,"losses":48,"wins":24},"meta/muse-glimmer-30b":{"draws":72,"losses":36,"wins":24},"meta/muse-spark-1.2":{"draws":36,"losses":51,"wins":9},"meta/muse-spark-1.3":{"draws":39,"losses":47,"wins":8},"minimax/minimax-m3":{"draws":14,"losses":15,"wins":7},"mistralai/mistral-medium-3-5":{"draws":46,"losses":26,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":14,"wins":1},"moonshotai/kimi-k3":{"draws":56,"losses":64,"wins":8},"nex-agi/nex-n2-pro":{"draws":19,"losses":10,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":14,"wins":12},"o3":{"draws":30,"losses":85,"wins":25},"openai/gpt-oss-120b":{"draws":64,"losses":39,"wins":31},"poolside/laguna-s-2.1":{"draws":41,"losses":30,"wins":21},"qwen/qwen3.7-max":{"draws":20,"losses":14,"wins":12},"qwen/qwen3.7-plus":{"draws":16,"losses":20,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":53,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":49,"wins":7},"qwen/qwen3.8-flash":{"draws":44,"losses":37,"wins":11},"qwen/qwen3.8-max":{"draws":61,"losses":53,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":1},"stealth/ox-alpha":{"draws":122,"losses":202,"wins":43},"stealth/space-bunny-alpha":{"draws":21,"losses":16,"wins":3},"stepfun/step-3.7-flash":{"draws":19,"losses":34,"wins":7},"tencent/hy3-preview":{"draws":20,"losses":9,"wins":13},"tencent/hy4-preview":{"draws":50,"losses":57,"wins":9},"thinkingmachines/inkling":{"draws":57,"losses":36,"wins":25},"thinkingmachines/inkling-small":{"draws":76,"losses":49,"wins":35},"x-ai/grok-4.5":{"draws":51,"losses":62,"wins":5},"x-ai/grok-4.6":{"draws":43,"losses":72,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":40,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":52,"losses":36,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":19,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":12,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":89,"losses":95,"wins":24},"z-ai/glm-5.3":{"draws":42,"losses":58,"wins":4},"z-ai/glm-5.3-flash":{"draws":47,"losses":69,"wins":16},"z-ai/glm-5.3-flashx":{"draws":20,"losses":27,"wins":3}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":39,"wins":16},"claude-fable-5":{"draws":15,"losses":59,"wins":2},"claude-fable-5-1":{"draws":5,"losses":75,"wins":0},"claude-opus-4-5":{"draws":67,"losses":87,"wins":32},"claude-opus-4-8":{"draws":48,"losses":50,"wins":0},"claude-opus-5":{"draws":30,"losses":101,"wins":7},"claude-opus-5-5":{"draws":7,"losses":53,"wins":0},"claude-sonnet-5":{"draws":40,"losses":80,"wins":14},"claude-sonnet-5-5":{"draws":16,"losses":34,"wins":4},"cohere/north-mini-code":{"draws":40,"losses":15,"wins":31},"deepseek/deepseek-v4-flash":{"draws":64,"losses":54,"wins":40},"deepseek/deepseek-v4-pro":{"draws":30,"losses":39,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":30,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":31,"wins":4},"fireworks/ember-1":{"draws":25,"losses":33,"wins":2},"gemini-3.1-pro-preview":{"draws":22,"losses":30,"wins":4},"google/gemini-3.1-flash-lite":{"draws":25,"losses":29,"wins":28},"google/gemini-3.5-flash":{"draws":37,"losses":63,"wins":12},"google/gemini-3.5-flash-lite":{"draws":119,"losses":141,"wins":56},"google/gemini-3.6-flash":{"draws":142,"losses":130,"wins":46},"google/gemini-3.8-flash":{"draws":21,"losses":50,"wins":3},"google/gemma-4-31b-it":{"draws":20,"losses":29,"wins":17},"gpt-4.1":{"draws":20,"losses":25,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":11,"wins":1},"gpt-5":{"draws":29,"losses":33,"wins":28},"gpt-5.4":{"draws":26,"losses":53,"wins":17},"gpt-5.4-mini":{"draws":45,"losses":27,"wins":12},"gpt-5.4-nano":{"draws":55,"losses":43,"wins":26},"gpt-5.5":{"draws":57,"losses":47,"wins":8},"gpt-5.6-luna":{"draws":45,"losses":37,"wins":32},"gpt-5.6-sol":{"draws":16,"losses":76,"wins":10},"gpt-5.6-terra":{"draws":30,"losses":59,"wins":11},"gpt-6-astra":{"draws":3,"losses":59,"wins":0},"gpt-6-luna":{"draws":23,"losses":41,"wins":8},"gpt-6-sol":{"draws":6,"losses":51,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":59,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":29,"losses":13,"wins":22},"inclusionai/ling-3.0-flash":{"draws":30,"losses":35,"wins":35},"meituan/longcat-2.0":{"draws":89,"losses":84,"wins":51},"meta/muse-glimmer-30b":{"draws":35,"losses":28,"wins":15},"meta/muse-spark-1.2":{"draws":28,"losses":38,"wins":14},"meta/muse-spark-1.3":{"draws":12,"losses":46,"wins":8},"minimax/minimax-m3":{"draws":41,"losses":31,"wins":22},"mistralai/mistral-medium-3-5":{"draws":22,"losses":21,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":17,"wins":7},"moonshotai/kimi-k3":{"draws":58,"losses":80,"wins":22},"nex-agi/nex-n2-pro":{"draws":42,"losses":24,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":27,"wins":25},"o3":{"draws":33,"losses":114,"wins":45},"openai/gpt-oss-120b":{"draws":24,"losses":44,"wins":10},"poolside/laguna-s-2.1":{"draws":99,"losses":58,"wins":23},"qwen/qwen3.7-max":{"draws":46,"losses":34,"wins":8},"qwen/qwen3.7-plus":{"draws":33,"losses":25,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":46,"wins":4},"qwen/qwen3.8-27b":{"draws":13,"losses":35,"wins":8},"qwen/qwen3.8-flash":{"draws":26,"losses":38,"wins":10},"qwen/qwen3.8-max":{"draws":33,"losses":43,"wins":15},"qwen/qwen3.8-max-0902":{"draws":15,"losses":28,"wins":7},"stealth/ox-alpha":{"draws":67,"losses":139,"wins":32},"stealth/space-bunny-alpha":{"draws":18,"losses":20,"wins":8},"stepfun/step-3.7-flash":{"draws":26,"losses":37,"wins":17},"tencent/hy3-preview":{"draws":26,"losses":27,"wins":7},"tencent/hy4-preview":{"draws":27,"losses":42,"wins":7},"thinkingmachines/inkling":{"draws":69,"losses":62,"wins":55},"thinkingmachines/inkling-small":{"draws":37,"losses":36,"wins":18},"x-ai/grok-4.5":{"draws":55,"losses":122,"wins":19},"x-ai/grok-4.6":{"draws":27,"losses":53,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":47,"wins":2},"x-ai/grok-build-0.1":{"draws":20,"losses":32,"wins":4},"xiaomi/mimo-v2.5":{"draws":76,"losses":66,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":37,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":20,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":21,"wins":2},"z-ai/glm-5.2":{"draws":82,"losses":59,"wins":29},"z-ai/glm-5.3":{"draws":18,"losses":46,"wins":0},"z-ai/glm-5.3-flash":{"draws":30,"losses":56,"wins":8},"z-ai/glm-5.3-flashx":{"draws":16,"losses":37,"wins":3}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":48,"wins":31},"claude-fable-5":{"draws":23,"losses":101,"wins":24},"claude-fable-5-1":{"draws":2,"losses":92,"wins":4},"claude-opus-4-5":{"draws":96,"losses":188,"wins":60},"claude-opus-4-8":{"draws":27,"losses":71,"wins":27},"claude-opus-5":{"draws":28,"losses":214,"wins":27},"claude-opus-5-5":{"draws":5,"losses":90,"wins":3},"claude-sonnet-5":{"draws":62,"losses":104,"wins":28},"claude-sonnet-5-5":{"draws":13,"losses":57,"wins":12},"cohere/north-mini-code":{"draws":49,"losses":12,"wins":49},"deepseek/deepseek-v4-flash":{"draws":67,"losses":66,"wins":57},"deepseek/deepseek-v4-pro":{"draws":42,"losses":70,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":60,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":48,"wins":19},"fireworks/ember-1":{"draws":32,"losses":57,"wins":6},"gemini-3.1-pro-preview":{"draws":23,"losses":43,"wins":20},"google/gemini-3.1-flash-lite":{"draws":24,"losses":32,"wins":57},"google/gemini-3.5-flash":{"draws":43,"losses":111,"wins":28},"google/gemini-3.5-flash-lite":{"draws":127,"losses":214,"wins":184},"google/gemini-3.6-flash":{"draws":141,"losses":250,"wins":79},"google/gemini-3.8-flash":{"draws":32,"losses":71,"wins":14},"google/gemma-4-31b-it":{"draws":19,"losses":32,"wins":43},"gpt-4.1":{"draws":22,"losses":35,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":6,"wins":0},"gpt-5":{"draws":48,"losses":62,"wins":36},"gpt-5.4":{"draws":61,"losses":103,"wins":26},"gpt-5.4-mini":{"draws":45,"losses":50,"wins":35},"gpt-5.4-nano":{"draws":39,"losses":85,"wins":68},"gpt-5.5":{"draws":65,"losses":58,"wins":32},"gpt-5.6-luna":{"draws":66,"losses":74,"wins":60},"gpt-5.6-sol":{"draws":34,"losses":155,"wins":23},"gpt-5.6-terra":{"draws":58,"losses":78,"wins":38},"gpt-6-astra":{"draws":8,"losses":106,"wins":2},"gpt-6-luna":{"draws":27,"losses":54,"wins":17},"gpt-6-sol":{"draws":11,"losses":72,"wins":4},"gpt-6.1-sol":{"draws":5,"losses":81,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":3,"wins":9},"inception/mercury-2.5-preview":{"draws":47,"losses":24,"wins":48},"inclusionai/ling-3.0-flash":{"draws":89,"losses":51,"wins":84},"meituan/longcat-2.0":{"draws":58,"losses":60,"wins":60},"meta/muse-glimmer-30b":{"draws":52,"losses":40,"wins":36},"meta/muse-spark-1.2":{"draws":42,"losses":70,"wins":48},"meta/muse-spark-1.3":{"draws":31,"losses":73,"wins":14},"minimax/minimax-m3":{"draws":22,"losses":33,"wins":35},"mistralai/mistral-medium-3-5":{"draws":35,"losses":25,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":20,"wins":4},"moonshotai/kimi-k3":{"draws":85,"losses":137,"wins":30},"nex-agi/nex-n2-pro":{"draws":27,"losses":26,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":42,"wins":34},"o3":{"draws":45,"losses":195,"wins":100},"openai/gpt-oss-120b":{"draws":46,"losses":34,"wins":48},"poolside/laguna-s-2.1":{"draws":108,"losses":78,"wins":84},"qwen/qwen3.7-max":{"draws":41,"losses":37,"wins":13},"qwen/qwen3.7-plus":{"draws":23,"losses":23,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":81,"wins":20},"qwen/qwen3.8-27b":{"draws":18,"losses":46,"wins":20},"qwen/qwen3.8-flash":{"draws":37,"losses":40,"wins":19},"qwen/qwen3.8-max":{"draws":49,"losses":65,"wins":21},"qwen/qwen3.8-max-0902":{"draws":27,"losses":57,"wins":13},"stealth/ox-alpha":{"draws":106,"losses":265,"wins":71},"stealth/space-bunny-alpha":{"draws":28,"losses":31,"wins":14},"stepfun/step-3.7-flash":{"draws":31,"losses":53,"wins":50},"tencent/hy3-preview":{"draws":34,"losses":28,"wins":26},"tencent/hy4-preview":{"draws":36,"losses":76,"wins":16},"thinkingmachines/inkling":{"draws":69,"losses":110,"wins":87},"thinkingmachines/inkling-small":{"draws":47,"losses":50,"wins":52},"x-ai/grok-4.5":{"draws":71,"losses":167,"wins":54},"x-ai/grok-4.6":{"draws":46,"losses":91,"wins":20},"x-ai/grok-4.7":{"draws":5,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":21,"losses":26,"wins":25},"xiaomi/mimo-v2.5":{"draws":95,"losses":81,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":40,"losses":46,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":17,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":40,"wins":6},"z-ai/glm-5.2":{"draws":90,"losses":132,"wins":79},"z-ai/glm-5.3":{"draws":30,"losses":93,"wins":11},"z-ai/glm-5.3-flash":{"draws":42,"losses":93,"wins":33},"z-ai/glm-5.3-flashx":{"draws":32,"losses":47,"wins":10}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":71,"losses":59,"wins":46},"claude-fable-5":{"draws":39,"losses":86,"wins":9},"claude-fable-5-1":{"draws":10,"losses":102,"wins":1},"claude-opus-4-5":{"draws":67,"losses":91,"wins":22},"claude-opus-4-8":{"draws":27,"losses":42,"wins":9},"claude-opus-5":{"draws":7,"losses":89,"wins":10},"claude-opus-5-5":{"draws":4,"losses":74,"wins":0},"claude-sonnet-5":{"draws":60,"losses":77,"wins":27},"claude-sonnet-5-5":{"draws":10,"losses":37,"wins":13},"cohere/north-mini-code":{"draws":14,"losses":14,"wins":24},"deepseek/deepseek-v4-flash":{"draws":114,"losses":67,"wins":37},"deepseek/deepseek-v4-pro":{"draws":64,"losses":58,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":66,"losses":69,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":28,"wins":5},"fireworks/ember-1":{"draws":26,"losses":30,"wins":4},"gemini-3.1-pro-preview":{"draws":24,"losses":18,"wins":6},"google/gemini-3.1-flash-lite":{"draws":26,"losses":10,"wins":22},"google/gemini-3.5-flash":{"draws":62,"losses":71,"wins":35},"google/gemini-3.5-flash-lite":{"draws":137,"losses":108,"wins":69},"google/gemini-3.6-flash":{"draws":112,"losses":135,"wins":37},"google/gemini-3.8-flash":{"draws":49,"losses":77,"wins":18},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":10},"gpt-4.1":{"draws":11,"losses":9,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":4,"wins":2},"gpt-5":{"draws":28,"losses":34,"wins":16},"gpt-5.4":{"draws":50,"losses":53,"wins":19},"gpt-5.4-mini":{"draws":26,"losses":17,"wins":3},"gpt-5.4-nano":{"draws":19,"losses":21,"wins":18},"gpt-5.5":{"draws":31,"losses":39,"wins":6},"gpt-5.6-luna":{"draws":86,"losses":53,"wins":53},"gpt-5.6-sol":{"draws":24,"losses":72,"wins":10},"gpt-5.6-terra":{"draws":79,"losses":77,"wins":22},"gpt-6-astra":{"draws":8,"losses":96,"wins":0},"gpt-6-luna":{"draws":24,"losses":37,"wins":11},"gpt-6-sol":{"draws":4,"losses":44,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":63,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":20,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":72,"losses":24,"wins":36},"inclusionai/ling-3.0-flash":{"draws":35,"losses":15,"wins":28},"meituan/longcat-2.0":{"draws":52,"losses":36,"wins":40},"meta/muse-glimmer-30b":{"draws":40,"losses":24,"wins":24},"meta/muse-spark-1.2":{"draws":27,"losses":57,"wins":26},"meta/muse-spark-1.3":{"draws":48,"losses":51,"wins":11},"minimax/minimax-m3":{"draws":17,"losses":20,"wins":13},"mistralai/mistral-medium-3-5":{"draws":54,"losses":12,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":15,"wins":3},"moonshotai/kimi-k3":{"draws":56,"losses":63,"wins":19},"nex-agi/nex-n2-pro":{"draws":15,"losses":11,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":14,"wins":13},"o3":{"draws":49,"losses":90,"wins":33},"openai/gpt-oss-120b":{"draws":75,"losses":41,"wins":38},"poolside/laguna-s-2.1":{"draws":74,"losses":33,"wins":31},"qwen/qwen3.7-max":{"draws":18,"losses":21,"wins":15},"qwen/qwen3.7-plus":{"draws":21,"losses":13,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":68,"losses":66,"wins":22},"qwen/qwen3.8-27b":{"draws":37,"losses":58,"wins":11},"qwen/qwen3.8-flash":{"draws":55,"losses":32,"wins":31},"qwen/qwen3.8-max":{"draws":56,"losses":63,"wins":35},"qwen/qwen3.8-max-0902":{"draws":26,"losses":31,"wins":1},"stealth/ox-alpha":{"draws":159,"losses":264,"wins":65},"stealth/space-bunny-alpha":{"draws":17,"losses":14,"wins":13},"stepfun/step-3.7-flash":{"draws":24,"losses":9,"wins":21},"tencent/hy3-preview":{"draws":20,"losses":22,"wins":6},"tencent/hy4-preview":{"draws":61,"losses":76,"wins":15},"thinkingmachines/inkling":{"draws":68,"losses":43,"wins":51},"thinkingmachines/inkling-small":{"draws":99,"losses":40,"wins":67},"x-ai/grok-4.5":{"draws":43,"losses":75,"wins":18},"x-ai/grok-4.6":{"draws":55,"losses":78,"wins":15},"x-ai/grok-4.7":{"draws":2,"losses":51,"wins":7},"x-ai/grok-build-0.1":{"draws":13,"losses":10,"wins":7},"xiaomi/mimo-v2.5":{"draws":49,"losses":26,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":21,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":21,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":26,"wins":3},"z-ai/glm-5.2":{"draws":117,"losses":78,"wins":41},"z-ai/glm-5.3":{"draws":24,"losses":64,"wins":14},"z-ai/glm-5.3-flash":{"draws":59,"losses":95,"wins":18},"z-ai/glm-5.3-flashx":{"draws":18,"losses":33,"wins":9}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":33,"wins":38},"claude-fable-5":{"draws":24,"losses":88,"wins":34},"claude-fable-5-1":{"draws":11,"losses":116,"wins":9},"claude-opus-4-5":{"draws":57,"losses":60,"wins":95},"claude-opus-4-8":{"draws":18,"losses":33,"wins":21},"claude-opus-5":{"draws":9,"losses":92,"wins":21},"claude-opus-5-5":{"draws":5,"losses":58,"wins":5},"claude-sonnet-5":{"draws":77,"losses":84,"wins":81},"claude-sonnet-5-5":{"draws":15,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":7,"wins":38},"deepseek/deepseek-v4-flash":{"draws":40,"losses":31,"wins":81},"deepseek/deepseek-v4-pro":{"draws":17,"losses":56,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":45,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":18,"wins":14},"fireworks/ember-1":{"draws":15,"losses":16,"wins":11},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"google/gemini-3.1-flash-lite":{"draws":13,"losses":5,"wins":24},"google/gemini-3.5-flash":{"draws":36,"losses":76,"wins":58},"google/gemini-3.5-flash-lite":{"draws":105,"losses":90,"wins":211},"google/gemini-3.6-flash":{"draws":76,"losses":145,"wins":175},"google/gemini-3.8-flash":{"draws":23,"losses":59,"wins":56},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":26},"gpt-4.1":{"draws":6,"losses":7,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":3,"wins":10},"gpt-5":{"draws":19,"losses":13,"wins":34},"gpt-5.4":{"draws":44,"losses":109,"wins":75},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":23},"gpt-5.4-nano":{"draws":9,"losses":20,"wins":35},"gpt-5.5":{"draws":17,"losses":21,"wins":22},"gpt-5.6-luna":{"draws":55,"losses":58,"wins":117},"gpt-5.6-sol":{"draws":25,"losses":169,"wins":50},"gpt-5.6-terra":{"draws":51,"losses":49,"wins":64},"gpt-6-astra":{"draws":13,"losses":111,"wins":2},"gpt-6-luna":{"draws":15,"losses":21,"wins":26},"gpt-6-sol":{"draws":5,"losses":39,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":49,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":11},"inception/mercury-2.5-preview":{"draws":36,"losses":9,"wins":51},"inclusionai/ling-3.0-flash":{"draws":28,"losses":14,"wins":38},"meituan/longcat-2.0":{"draws":42,"losses":48,"wins":70},"meta/muse-glimmer-30b":{"draws":27,"losses":26,"wins":57},"meta/muse-spark-1.2":{"draws":24,"losses":44,"wins":44},"meta/muse-spark-1.3":{"draws":28,"losses":57,"wins":41},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":25,"losses":10,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":5},"moonshotai/kimi-k3":{"draws":48,"losses":95,"wins":77},"nex-agi/nex-n2-pro":{"draws":10,"losses":7,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":4,"wins":28},"o3":{"draws":18,"losses":112,"wins":116},"openai/gpt-oss-120b":{"draws":35,"losses":13,"wins":60},"poolside/laguna-s-2.1":{"draws":40,"losses":25,"wins":87},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":24},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":63,"wins":33},"qwen/qwen3.8-27b":{"draws":14,"losses":39,"wins":35},"qwen/qwen3.8-flash":{"draws":31,"losses":31,"wins":36},"qwen/qwen3.8-max":{"draws":38,"losses":47,"wins":40},"qwen/qwen3.8-max-0902":{"draws":10,"losses":25,"wins":13},"stealth/ox-alpha":{"draws":108,"losses":235,"wins":136},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":4,"losses":12,"wins":44},"tencent/hy3-preview":{"draws":13,"losses":9,"wins":20},"tencent/hy4-preview":{"draws":27,"losses":62,"wins":39},"thinkingmachines/inkling":{"draws":56,"losses":24,"wins":90},"thinkingmachines/inkling-small":{"draws":37,"losses":27,"wins":74},"x-ai/grok-4.5":{"draws":45,"losses":97,"wins":52},"x-ai/grok-4.6":{"draws":30,"losses":88,"wins":32},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":8,"wins":22},"xiaomi/mimo-v2.5":{"draws":23,"losses":15,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":26,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":18,"wins":6},"z-ai/glm-5.2":{"draws":44,"losses":62,"wins":96},"z-ai/glm-5.3":{"draws":22,"losses":77,"wins":35},"z-ai/glm-5.3-flash":{"draws":25,"losses":61,"wins":54},"z-ai/glm-5.3-flashx":{"draws":8,"losses":19,"wins":19}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":23,"wins":74},"claude-fable-5":{"draws":37,"losses":99,"wins":54},"claude-fable-5-1":{"draws":8,"losses":166,"wins":10},"claude-opus-4-5":{"draws":46,"losses":45,"wins":107},"claude-opus-4-8":{"draws":26,"losses":30,"wins":32},"claude-opus-5":{"draws":25,"losses":112,"wins":33},"claude-opus-5-5":{"draws":2,"losses":51,"wins":5},"claude-sonnet-5":{"draws":55,"losses":43,"wins":66},"claude-sonnet-5-5":{"draws":13,"losses":42,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":34},"deepseek/deepseek-v4-flash":{"draws":52,"losses":26,"wins":110},"deepseek/deepseek-v4-pro":{"draws":30,"losses":50,"wins":80},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":38,"wins":76},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":24,"wins":16},"fireworks/ember-1":{"draws":16,"losses":24,"wins":18},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":35},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":34},"google/gemini-3.5-flash":{"draws":40,"losses":53,"wins":105},"google/gemini-3.5-flash-lite":{"draws":67,"losses":56,"wins":153},"google/gemini-3.6-flash":{"draws":52,"losses":88,"wins":124},"google/gemini-3.8-flash":{"draws":30,"losses":64,"wins":76},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":23},"gpt-4.1":{"draws":12,"losses":1,"wins":19},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":24,"losses":19,"wins":45},"gpt-5.4":{"draws":30,"losses":58,"wins":60},"gpt-5.4-mini":{"draws":18,"losses":5,"wins":35},"gpt-5.4-nano":{"draws":17,"losses":10,"wins":53},"gpt-5.5":{"draws":15,"losses":31,"wins":24},"gpt-5.6-luna":{"draws":44,"losses":30,"wins":66},"gpt-5.6-sol":{"draws":36,"losses":77,"wins":51},"gpt-5.6-terra":{"draws":53,"losses":48,"wins":93},"gpt-6-astra":{"draws":17,"losses":135,"wins":16},"gpt-6-luna":{"draws":18,"losses":23,"wins":39},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":7,"losses":50,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":18},"inception/mercury-2.5-preview":{"draws":39,"losses":8,"wins":47},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":46},"meituan/longcat-2.0":{"draws":31,"losses":14,"wins":73},"meta/muse-glimmer-30b":{"draws":48,"losses":11,"wins":51},"meta/muse-spark-1.2":{"draws":28,"losses":41,"wins":57},"meta/muse-spark-1.3":{"draws":18,"losses":33,"wins":33},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":33},"mistralai/mistral-medium-3-5":{"draws":24,"losses":4,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":45,"losses":57,"wins":72},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":8,"wins":47},"o3":{"draws":16,"losses":51,"wins":121},"openai/gpt-oss-120b":{"draws":38,"losses":17,"wins":65},"poolside/laguna-s-2.1":{"draws":35,"losses":17,"wins":64},"qwen/qwen3.7-max":{"draws":13,"losses":10,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":9,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":60,"wins":66},"qwen/qwen3.8-27b":{"draws":14,"losses":32,"wins":48},"qwen/qwen3.8-flash":{"draws":41,"losses":32,"wins":59},"qwen/qwen3.8-max":{"draws":43,"losses":37,"wins":88},"qwen/qwen3.8-max-0902":{"draws":19,"losses":19,"wins":20},"stealth/ox-alpha":{"draws":131,"losses":218,"wins":224},"stealth/space-bunny-alpha":{"draws":14,"losses":14,"wins":34},"stepfun/step-3.7-flash":{"draws":13,"losses":8,"wins":55},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":29},"tencent/hy4-preview":{"draws":39,"losses":75,"wins":62},"thinkingmachines/inkling":{"draws":39,"losses":16,"wins":67},"thinkingmachines/inkling-small":{"draws":59,"losses":16,"wins":87},"x-ai/grok-4.5":{"draws":23,"losses":61,"wins":74},"x-ai/grok-4.6":{"draws":43,"losses":84,"wins":69},"x-ai/grok-4.7":{"draws":7,"losses":39,"wins":10},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":32,"losses":10,"wins":78},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":10,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":12},"z-ai/glm-5.2":{"draws":56,"losses":56,"wins":102},"z-ai/glm-5.3":{"draws":33,"losses":99,"wins":42},"z-ai/glm-5.3-flash":{"draws":44,"losses":83,"wins":71},"z-ai/glm-5.3-flashx":{"draws":17,"losses":14,"wins":21}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":30,"wins":11},"claude-fable-5":{"draws":13,"losses":36,"wins":5},"claude-fable-5-1":{"draws":2,"losses":61,"wins":1},"claude-opus-4-5":{"draws":49,"losses":86,"wins":17},"claude-opus-4-8":{"draws":23,"losses":59,"wins":16},"claude-opus-5":{"draws":22,"losses":120,"wins":10},"claude-opus-5-5":{"draws":2,"losses":39,"wins":1},"claude-sonnet-5":{"draws":13,"losses":27,"wins":10},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":7},"cohere/north-mini-code":{"draws":10,"losses":18,"wins":38},"deepseek/deepseek-v4-flash":{"draws":45,"losses":43,"wins":42},"deepseek/deepseek-v4-pro":{"draws":11,"losses":28,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":30,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":21,"wins":5},"fireworks/ember-1":{"draws":11,"losses":27,"wins":4},"gemini-3.1-pro-preview":{"draws":8,"losses":16,"wins":16},"google/gemini-3.1-flash-lite":{"draws":22,"losses":30,"wins":40},"google/gemini-3.5-flash":{"draws":18,"losses":25,"wins":17},"google/gemini-3.5-flash-lite":{"draws":35,"losses":33,"wins":36},"google/gemini-3.6-flash":{"draws":27,"losses":69,"wins":12},"google/gemini-3.8-flash":{"draws":16,"losses":40,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":16,"wins":26},"gpt-4.1":{"draws":14,"losses":24,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":32,"losses":45,"wins":15},"gpt-5.4":{"draws":10,"losses":19,"wins":9},"gpt-5.4-mini":{"draws":32,"losses":36,"wins":32},"gpt-5.4-nano":{"draws":35,"losses":51,"wins":42},"gpt-5.5":{"draws":26,"losses":55,"wins":11},"gpt-5.6-luna":{"draws":9,"losses":21,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":40,"wins":0},"gpt-5.6-terra":{"draws":17,"losses":25,"wins":12},"gpt-6-astra":{"draws":0,"losses":35,"wins":1},"gpt-6-luna":{"draws":13,"losses":29,"wins":12},"gpt-6-sol":{"draws":2,"losses":42,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":7,"wins":15},"inclusionai/ling-3.0-flash":{"draws":41,"losses":22,"wins":31},"meituan/longcat-2.0":{"draws":22,"losses":35,"wins":33},"meta/muse-glimmer-30b":{"draws":17,"losses":13,"wins":20},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":33,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":21,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":37,"wins":7},"nex-agi/nex-n2-pro":{"draws":24,"losses":17,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":31,"wins":43},"o3":{"draws":14,"losses":50,"wins":18},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":15},"poolside/laguna-s-2.1":{"draws":45,"losses":32,"wins":29},"qwen/qwen3.7-max":{"draws":34,"losses":40,"wins":14},"qwen/qwen3.7-plus":{"draws":22,"losses":28,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":30,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":15,"wins":4},"qwen/qwen3.8-flash":{"draws":15,"losses":19,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":28,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":19,"wins":6},"stealth/ox-alpha":{"draws":43,"losses":80,"wins":19},"stealth/space-bunny-alpha":{"draws":15,"losses":18,"wins":9},"stepfun/step-3.7-flash":{"draws":19,"losses":14,"wins":21},"tencent/hy3-preview":{"draws":32,"losses":32,"wins":16},"tencent/hy4-preview":{"draws":13,"losses":34,"wins":7},"thinkingmachines/inkling":{"draws":23,"losses":42,"wins":41},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":14},"x-ai/grok-4.5":{"draws":16,"losses":63,"wins":7},"x-ai/grok-4.6":{"draws":20,"losses":43,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":30,"wins":3},"x-ai/grok-build-0.1":{"draws":18,"losses":21,"wins":15},"xiaomi/mimo-v2.5":{"draws":76,"losses":67,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":30,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":21,"wins":5},"z-ai/glm-5.2":{"draws":56,"losses":50,"wins":34},"z-ai/glm-5.3":{"draws":6,"losses":28,"wins":2},"z-ai/glm-5.3-flash":{"draws":16,"losses":36,"wins":8},"z-ai/glm-5.3-flashx":{"draws":4,"losses":28,"wins":4}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":42,"losses":31,"wins":25},"claude-fable-5":{"draws":34,"losses":49,"wins":9},"claude-fable-5-1":{"draws":5,"losses":60,"wins":1},"claude-opus-4-5":{"draws":30,"losses":82,"wins":12},"claude-opus-4-8":{"draws":17,"losses":24,"wins":3},"claude-opus-5":{"draws":13,"losses":66,"wins":9},"claude-opus-5-5":{"draws":2,"losses":42,"wins":0},"claude-sonnet-5":{"draws":49,"losses":51,"wins":14},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":12,"wins":11},"deepseek/deepseek-v4-flash":{"draws":55,"losses":50,"wins":23},"deepseek/deepseek-v4-pro":{"draws":31,"losses":54,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":52,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":15,"wins":6},"fireworks/ember-1":{"draws":17,"losses":23,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":12,"wins":14},"google/gemini-3.5-flash":{"draws":37,"losses":65,"wins":16},"google/gemini-3.5-flash-lite":{"draws":84,"losses":92,"wins":48},"google/gemini-3.6-flash":{"draws":63,"losses":84,"wins":19},"google/gemini-3.8-flash":{"draws":25,"losses":52,"wins":5},"google/gemma-4-31b-it":{"draws":7,"losses":14,"wins":5},"gpt-4.1":{"draws":9,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":15,"losses":18,"wins":11},"gpt-5.4":{"draws":38,"losses":35,"wins":15},"gpt-5.4-mini":{"draws":11,"losses":12,"wins":3},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":14},"gpt-5.5":{"draws":19,"losses":25,"wins":4},"gpt-5.6-luna":{"draws":51,"losses":43,"wins":18},"gpt-5.6-sol":{"draws":18,"losses":64,"wins":4},"gpt-5.6-terra":{"draws":42,"losses":64,"wins":14},"gpt-6-astra":{"draws":3,"losses":55,"wins":0},"gpt-6-luna":{"draws":18,"losses":26,"wins":2},"gpt-6-sol":{"draws":4,"losses":22,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":46,"losses":28,"wins":26},"inclusionai/ling-3.0-flash":{"draws":22,"losses":13,"wins":21},"meituan/longcat-2.0":{"draws":35,"losses":36,"wins":25},"meta/muse-glimmer-30b":{"draws":54,"losses":40,"wins":12},"meta/muse-spark-1.2":{"draws":25,"losses":47,"wins":10},"meta/muse-spark-1.3":{"draws":24,"losses":54,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":8},"mistralai/mistral-medium-3-5":{"draws":16,"losses":12,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":36,"losses":54,"wins":8},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":14,"wins":7},"o3":{"draws":22,"losses":73,"wins":13},"openai/gpt-oss-120b":{"draws":57,"losses":27,"wins":20},"poolside/laguna-s-2.1":{"draws":39,"losses":36,"wins":19},"qwen/qwen3.7-max":{"draws":16,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":71,"wins":4},"qwen/qwen3.8-27b":{"draws":10,"losses":37,"wins":7},"qwen/qwen3.8-flash":{"draws":29,"losses":40,"wins":9},"qwen/qwen3.8-max":{"draws":37,"losses":60,"wins":13},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":1},"stealth/ox-alpha":{"draws":93,"losses":170,"wins":57},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"wins":3},"stepfun/step-3.7-flash":{"draws":12,"losses":10,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":40,"losses":57,"wins":7},"thinkingmachines/inkling":{"draws":37,"losses":40,"wins":17},"thinkingmachines/inkling-small":{"draws":58,"losses":46,"wins":24},"x-ai/grok-4.5":{"draws":29,"losses":59,"wins":14},"x-ai/grok-4.6":{"draws":37,"losses":50,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":35,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":11,"wins":3},"xiaomi/mimo-v2.5":{"draws":32,"losses":15,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":18,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":5,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":77,"losses":71,"wins":24},"z-ai/glm-5.3":{"draws":25,"losses":50,"wins":7},"z-ai/glm-5.3-flash":{"draws":37,"losses":55,"wins":20},"z-ai/glm-5.3-flashx":{"draws":15,"losses":16,"wins":5}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":8,"wins":12},"claude-fable-5":{"draws":7,"losses":12,"wins":5},"claude-fable-5-1":{"draws":3,"losses":25,"wins":0},"claude-opus-4-5":{"draws":19,"losses":39,"wins":28},"claude-opus-4-8":{"draws":14,"losses":22,"wins":10},"claude-opus-5":{"draws":11,"losses":87,"wins":4},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":6,"losses":8,"wins":14},"claude-sonnet-5-5":{"draws":4,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":9,"wins":17},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":27},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":10,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":8},"fireworks/ember-1":{"draws":4,"losses":9,"wins":5},"gemini-3.1-pro-preview":{"draws":2,"losses":8,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":31},"google/gemini-3.5-flash":{"draws":10,"losses":6,"wins":12},"google/gemini-3.5-flash-lite":{"draws":15,"losses":15,"wins":18},"google/gemini-3.6-flash":{"draws":13,"losses":26,"wins":13},"google/gemini-3.8-flash":{"draws":6,"losses":9,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":26},"gpt-4.1":{"draws":11,"losses":6,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":10,"losses":16,"wins":18},"gpt-5.4":{"draws":3,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":19},"gpt-5.4-nano":{"draws":12,"losses":25,"wins":19},"gpt-5.5":{"draws":25,"losses":12,"wins":17},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":16,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":9},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":3,"losses":8,"wins":7},"gpt-6-sol":{"draws":4,"losses":13,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":20,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":14},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":17},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":20},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":5,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":14,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":10},"nex-agi/nex-n2-pro":{"draws":12,"losses":0,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":30},"o3":{"draws":2,"losses":17,"wins":27},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":22,"wins":12},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.7-plus":{"draws":20,"losses":2,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":4},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":6},"stealth/ox-alpha":{"draws":16,"losses":22,"wins":18},"stealth/space-bunny-alpha":{"draws":1,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":5,"wins":14},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":12},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":26,"wins":4},"x-ai/grok-4.6":{"draws":6,"losses":13,"wins":5},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":21},"xiaomi/mimo-v2.5":{"draws":44,"losses":16,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":28,"wins":37},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":10},"z-ai/glm-5.3-flashx":{"draws":9,"losses":4,"wins":9}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":44,"losses":32,"wins":66},"claude-fable-5":{"draws":38,"losses":133,"wins":31},"claude-fable-5-1":{"draws":19,"losses":174,"wins":7},"claude-opus-4-5":{"draws":129,"losses":88,"wins":127},"claude-opus-4-8":{"draws":30,"losses":32,"wins":38},"claude-opus-5":{"draws":35,"losses":157,"wins":36},"claude-opus-5-5":{"draws":1,"losses":58,"wins":9},"claude-sonnet-5":{"draws":106,"losses":66,"wins":128},"claude-sonnet-5-5":{"draws":14,"losses":34,"wins":14},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":37},"deepseek/deepseek-v4-flash":{"draws":60,"losses":46,"wins":90},"deepseek/deepseek-v4-pro":{"draws":50,"losses":44,"wins":64},"deepseek/deepseek-v4-pro-0813":{"draws":55,"losses":44,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":26,"wins":23},"fireworks/ember-1":{"draws":16,"losses":23,"wins":9},"gemini-3.1-pro-preview":{"draws":16,"losses":19,"wins":19},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":31},"google/gemini-3.5-flash":{"draws":68,"losses":71,"wins":53},"google/gemini-3.5-flash-lite":{"draws":205,"losses":121,"wins":298},"google/gemini-3.6-flash":{"draws":175,"losses":236,"wins":207},"google/gemini-3.8-flash":{"draws":56,"losses":83,"wins":43},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":37},"gpt-4.1":{"draws":8,"losses":5,"wins":15},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":6},"gpt-5":{"draws":28,"losses":22,"wins":34},"gpt-5.4":{"draws":69,"losses":148,"wins":71},"gpt-5.4-mini":{"draws":35,"losses":22,"wins":29},"gpt-5.4-nano":{"draws":37,"losses":21,"wins":66},"gpt-5.5":{"draws":39,"losses":23,"wins":40},"gpt-5.6-luna":{"draws":95,"losses":66,"wins":121},"gpt-5.6-sol":{"draws":66,"losses":165,"wins":63},"gpt-5.6-terra":{"draws":67,"losses":45,"wins":86},"gpt-6-astra":{"draws":19,"losses":134,"wins":15},"gpt-6-luna":{"draws":17,"losses":30,"wins":29},"gpt-6-sol":{"draws":9,"losses":45,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":47,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":14},"inception/mercury-2.5-preview":{"draws":56,"losses":8,"wins":64},"inclusionai/ling-3.0-flash":{"draws":58,"losses":22,"wins":80},"meituan/longcat-2.0":{"draws":85,"losses":30,"wins":137},"meta/muse-glimmer-30b":{"draws":56,"losses":19,"wins":63},"meta/muse-spark-1.2":{"draws":48,"losses":77,"wins":95},"meta/muse-spark-1.3":{"draws":45,"losses":72,"wins":57},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":37},"mistralai/mistral-medium-3-5":{"draws":36,"losses":8,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":6},"moonshotai/kimi-k3":{"draws":92,"losses":64,"wins":64},"nex-agi/nex-n2-pro":{"draws":17,"losses":8,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":9,"wins":39},"o3":{"draws":44,"losses":154,"wins":164},"openai/gpt-oss-120b":{"draws":48,"losses":22,"wins":74},"poolside/laguna-s-2.1":{"draws":103,"losses":25,"wins":120},"qwen/qwen3.7-max":{"draws":16,"losses":14,"wins":28},"qwen/qwen3.7-plus":{"draws":25,"losses":13,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":61,"losses":55,"wins":66},"qwen/qwen3.8-27b":{"draws":28,"losses":28,"wins":36},"qwen/qwen3.8-flash":{"draws":48,"losses":27,"wins":43},"qwen/qwen3.8-max":{"draws":44,"losses":52,"wins":61},"qwen/qwen3.8-max-0902":{"draws":18,"losses":26,"wins":16},"stealth/ox-alpha":{"draws":171,"losses":237,"wins":197},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":21},"stepfun/step-3.7-flash":{"draws":29,"losses":14,"wins":69},"tencent/hy3-preview":{"draws":23,"losses":5,"wins":26},"tencent/hy4-preview":{"draws":55,"losses":48,"wins":67},"thinkingmachines/inkling":{"draws":111,"losses":32,"wins":137},"thinkingmachines/inkling-small":{"draws":68,"losses":24,"wins":86},"x-ai/grok-4.5":{"draws":109,"losses":124,"wins":101},"x-ai/grok-4.6":{"draws":70,"losses":84,"wins":48},"x-ai/grok-4.7":{"draws":6,"losses":44,"wins":6},"x-ai/grok-build-0.1":{"draws":15,"losses":4,"wins":29},"xiaomi/mimo-v2.5":{"draws":54,"losses":21,"wins":93},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":27,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":13,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":9},"z-ai/glm-5.2":{"draws":96,"losses":49,"wins":89},"z-ai/glm-5.3":{"draws":45,"losses":89,"wins":40},"z-ai/glm-5.3-flash":{"draws":60,"losses":88,"wins":52},"z-ai/glm-5.3-flashx":{"draws":20,"losses":26,"wins":22}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":27,"wins":4},"claude-fable-5":{"draws":9,"losses":42,"wins":1},"claude-fable-5-1":{"draws":3,"losses":49,"wins":0},"claude-opus-4-5":{"draws":33,"losses":77,"wins":20},"claude-opus-4-8":{"draws":37,"losses":50,"wins":9},"claude-opus-5":{"draws":2,"losses":102,"wins":6},"claude-opus-5-5":{"draws":2,"losses":28,"wins":0},"claude-sonnet-5":{"draws":21,"losses":26,"wins":5},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":23,"losses":17,"wins":28},"deepseek/deepseek-v4-flash":{"draws":30,"losses":53,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":21,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":32,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":2},"fireworks/ember-1":{"draws":6,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":24,"wins":4},"google/gemini-3.1-flash-lite":{"draws":18,"losses":27,"wins":39},"google/gemini-3.5-flash":{"draws":23,"losses":27,"wins":14},"google/gemini-3.5-flash-lite":{"draws":46,"losses":30,"wins":26},"google/gemini-3.6-flash":{"draws":29,"losses":70,"wins":19},"google/gemini-3.8-flash":{"draws":10,"losses":36,"wins":4},"google/gemma-4-31b-it":{"draws":12,"losses":24,"wins":22},"gpt-4.1":{"draws":10,"losses":12,"wins":8},"gpt-5":{"draws":25,"losses":38,"wins":9},"gpt-5.4":{"draws":14,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":33,"losses":26,"wins":15},"gpt-5.4-nano":{"draws":26,"losses":50,"wins":32},"gpt-5.5":{"draws":28,"losses":63,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":29,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":23,"wins":5},"gpt-6-astra":{"draws":2,"losses":32,"wins":0},"gpt-6-luna":{"draws":6,"losses":29,"wins":5},"gpt-6-sol":{"draws":0,"losses":16,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":7,"wins":10},"inclusionai/ling-3.0-flash":{"draws":42,"losses":24,"wins":24},"meituan/longcat-2.0":{"draws":27,"losses":43,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":18,"wins":11},"meta/muse-spark-1.2":{"draws":10,"losses":19,"wins":7},"meta/muse-spark-1.3":{"draws":8,"losses":27,"wins":3},"minimax/minimax-m3":{"draws":24,"losses":35,"wins":17},"mistralai/mistral-medium-3-5":{"draws":16,"losses":16,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":16,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":35,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":46,"wins":22},"o3":{"draws":14,"losses":56,"wins":14},"openai/gpt-oss-120b":{"draws":14,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":38,"losses":27,"wins":11},"qwen/qwen3.7-max":{"draws":23,"losses":42,"wins":7},"qwen/qwen3.7-plus":{"draws":22,"losses":21,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":33,"wins":9},"qwen/qwen3.8-27b":{"draws":7,"losses":23,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":30,"wins":4},"qwen/qwen3.8-max":{"draws":11,"losses":31,"wins":2},"qwen/qwen3.8-max-0902":{"draws":4,"losses":18,"wins":4},"stealth/ox-alpha":{"draws":37,"losses":86,"wins":19},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":18,"losses":20,"wins":22},"tencent/hy3-preview":{"draws":32,"losses":14,"wins":16},"tencent/hy4-preview":{"draws":13,"losses":34,"wins":3},"thinkingmachines/inkling":{"draws":26,"losses":30,"wins":28},"thinkingmachines/inkling-small":{"draws":19,"losses":18,"wins":13},"x-ai/grok-4.5":{"draws":23,"losses":59,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":38,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":22,"wins":0},"x-ai/grok-build-0.1":{"draws":18,"losses":16,"wins":10},"xiaomi/mimo-v2.5":{"draws":47,"losses":67,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":29,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":9,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":1},"z-ai/glm-5.2":{"draws":72,"losses":48,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":35,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":37,"wins":4},"z-ai/glm-5.3-flashx":{"draws":5,"losses":20,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":27,"wins":22},"claude-fable-5":{"draws":25,"losses":65,"wins":6},"claude-fable-5-1":{"draws":6,"losses":86,"wins":0},"claude-opus-4-5":{"draws":103,"losses":109,"wins":38},"claude-opus-4-8":{"draws":41,"losses":94,"wins":21},"claude-opus-5":{"draws":42,"losses":194,"wins":6},"claude-opus-5-5":{"draws":2,"losses":70,"wins":0},"claude-sonnet-5":{"draws":34,"losses":31,"wins":11},"claude-sonnet-5-5":{"draws":9,"losses":42,"wins":11},"cohere/north-mini-code":{"draws":34,"losses":21,"wins":19},"deepseek/deepseek-v4-flash":{"draws":94,"losses":55,"wins":39},"deepseek/deepseek-v4-pro":{"draws":31,"losses":23,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":37,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":36,"wins":11},"fireworks/ember-1":{"draws":23,"losses":39,"wins":10},"gemini-3.1-pro-preview":{"draws":24,"losses":25,"wins":17},"google/gemini-3.1-flash-lite":{"draws":53,"losses":33,"wins":55},"google/gemini-3.5-flash":{"draws":45,"losses":50,"wins":17},"google/gemini-3.5-flash-lite":{"draws":79,"losses":52,"wins":43},"google/gemini-3.6-flash":{"draws":66,"losses":74,"wins":16},"google/gemini-3.8-flash":{"draws":31,"losses":43,"wins":10},"google/gemma-4-31b-it":{"draws":25,"losses":28,"wins":15},"gpt-4.1":{"draws":24,"losses":25,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":66,"losses":54,"wins":24},"gpt-5.4":{"draws":20,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":72,"losses":29,"wins":29},"gpt-5.4-nano":{"draws":56,"losses":53,"wins":49},"gpt-5.5":{"draws":71,"losses":76,"wins":11},"gpt-5.6-luna":{"draws":30,"losses":19,"wins":17},"gpt-5.6-sol":{"draws":15,"losses":43,"wins":8},"gpt-5.6-terra":{"draws":38,"losses":44,"wins":14},"gpt-6-astra":{"draws":4,"losses":58,"wins":0},"gpt-6-luna":{"draws":21,"losses":43,"wins":20},"gpt-6-sol":{"draws":5,"losses":51,"wins":0},"gpt-6.1-sol":{"draws":5,"losses":77,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":12,"wins":14},"inclusionai/ling-3.0-flash":{"draws":50,"losses":25,"wins":27},"meituan/longcat-2.0":{"draws":58,"losses":34,"wins":42},"meta/muse-glimmer-30b":{"draws":39,"losses":13,"wins":14},"meta/muse-spark-1.2":{"draws":18,"losses":28,"wins":4},"meta/muse-spark-1.3":{"draws":23,"losses":47,"wins":8},"minimax/minimax-m3":{"draws":46,"losses":43,"wins":31},"mistralai/mistral-medium-3-5":{"draws":25,"losses":7,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":22,"losses":30,"wins":4},"moonshotai/kimi-k3":{"draws":40,"losses":39,"wins":9},"nex-agi/nex-n2-pro":{"draws":52,"losses":22,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":74,"losses":29,"wins":29},"o3":{"draws":55,"losses":82,"wins":31},"openai/gpt-oss-120b":{"draws":34,"losses":22,"wins":16},"poolside/laguna-s-2.1":{"draws":58,"losses":34,"wins":20},"qwen/qwen3.7-max":{"draws":62,"losses":32,"wins":16},"qwen/qwen3.7-plus":{"draws":45,"losses":27,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":28,"wins":6},"qwen/qwen3.8-27b":{"draws":21,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":32,"losses":26,"wins":16},"qwen/qwen3.8-max":{"draws":33,"losses":34,"wins":11},"qwen/qwen3.8-max-0902":{"draws":18,"losses":37,"wins":3},"stealth/ox-alpha":{"draws":84,"losses":116,"wins":24},"stealth/space-bunny-alpha":{"draws":20,"losses":21,"wins":13},"stepfun/step-3.7-flash":{"draws":44,"losses":30,"wins":32},"tencent/hy3-preview":{"draws":65,"losses":27,"wins":18},"tencent/hy4-preview":{"draws":30,"losses":43,"wins":7},"thinkingmachines/inkling":{"draws":65,"losses":50,"wins":55},"thinkingmachines/inkling-small":{"draws":52,"losses":18,"wins":14},"x-ai/grok-4.5":{"draws":39,"losses":77,"wins":10},"x-ai/grok-4.6":{"draws":36,"losses":49,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":60,"wins":3},"x-ai/grok-build-0.1":{"draws":50,"losses":16,"wins":14},"xiaomi/mimo-v2.5":{"draws":139,"losses":76,"wins":89},"xiaomi/mimo-v2.5-pro":{"draws":40,"losses":39,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":23,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":34,"wins":3},"z-ai/glm-5.2":{"draws":135,"losses":73,"wins":44},"z-ai/glm-5.3":{"draws":19,"losses":45,"wins":10},"z-ai/glm-5.3-flash":{"draws":35,"losses":41,"wins":18},"z-ai/glm-5.3-flashx":{"draws":13,"losses":34,"wins":7}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":61,"wins":99},"claude-fable-5":{"draws":17,"losses":161,"wins":34},"claude-fable-5-1":{"draws":0,"losses":157,"wins":9},"claude-opus-4-5":{"draws":78,"losses":272,"wins":130},"claude-opus-4-8":{"draws":16,"losses":107,"wins":39},"claude-opus-5":{"draws":10,"losses":241,"wins":17},"claude-opus-5-5":{"draws":3,"losses":89,"wins":2},"claude-sonnet-5":{"draws":33,"losses":176,"wins":151},"claude-sonnet-5-5":{"draws":1,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":37,"losses":22,"wins":43},"deepseek/deepseek-v4-flash":{"draws":43,"losses":99,"wins":142},"deepseek/deepseek-v4-pro":{"draws":39,"losses":110,"wins":57},"deepseek/deepseek-v4-pro-0813":{"draws":46,"losses":100,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":34,"wins":18},"fireworks/ember-1":{"draws":13,"losses":45,"wins":26},"gemini-3.1-pro-preview":{"draws":18,"losses":29,"wins":33},"google/gemini-3.1-flash-lite":{"draws":18,"losses":10,"wins":94},"google/gemini-3.5-flash":{"draws":38,"losses":136,"wins":66},"google/gemini-3.5-flash-lite":{"draws":129,"losses":256,"wins":427},"google/gemini-3.6-flash":{"draws":134,"losses":375,"wins":249},"google/gemini-3.8-flash":{"draws":29,"losses":123,"wins":50},"google/gemma-4-31b-it":{"draws":17,"losses":15,"wins":54},"gpt-4.1":{"draws":12,"losses":26,"wins":20},"gpt-4.1-nano":{"draws":0,"losses":16,"wins":8},"gpt-5":{"draws":33,"losses":74,"wins":45},"gpt-5.4":{"draws":35,"losses":219,"wins":68},"gpt-5.4-mini":{"draws":21,"losses":29,"wins":36},"gpt-5.4-nano":{"draws":15,"losses":82,"wins":93},"gpt-5.5":{"draws":40,"losses":79,"wins":31},"gpt-5.6-luna":{"draws":47,"losses":136,"wins":155},"gpt-5.6-sol":{"draws":17,"losses":268,"wins":59},"gpt-5.6-terra":{"draws":38,"losses":99,"wins":77},"gpt-6-astra":{"draws":4,"losses":166,"wins":2},"gpt-6-luna":{"draws":20,"losses":54,"wins":38},"gpt-6-sol":{"draws":4,"losses":64,"wins":4},"gpt-6.1-sol":{"draws":0,"losses":75,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":20},"inception/mercury-2.5-preview":{"draws":30,"losses":25,"wins":85},"inclusionai/ling-3.0-flash":{"draws":33,"losses":45,"wins":114},"meituan/longcat-2.0":{"draws":45,"losses":100,"wins":195},"meta/muse-glimmer-30b":{"draws":49,"losses":33,"wins":90},"meta/muse-spark-1.2":{"draws":18,"losses":116,"wins":112},"meta/muse-spark-1.3":{"draws":16,"losses":121,"wins":51},"minimax/minimax-m3":{"draws":14,"losses":18,"wins":50},"mistralai/mistral-medium-3-5":{"draws":22,"losses":13,"wins":73},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":27,"wins":17},"moonshotai/kimi-k3":{"draws":44,"losses":164,"wins":154},"nex-agi/nex-n2-pro":{"draws":14,"losses":14,"wins":56},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":31,"wins":82},"o3":{"draws":58,"losses":229,"wins":229},"openai/gpt-oss-120b":{"draws":37,"losses":38,"wins":105},"poolside/laguna-s-2.1":{"draws":66,"losses":84,"wins":108},"qwen/qwen3.7-max":{"draws":26,"losses":25,"wins":35},"qwen/qwen3.7-plus":{"draws":12,"losses":31,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":113,"wins":64},"qwen/qwen3.8-27b":{"draws":30,"losses":73,"wins":43},"qwen/qwen3.8-flash":{"draws":37,"losses":56,"wins":61},"qwen/qwen3.8-max":{"draws":37,"losses":104,"wins":71},"qwen/qwen3.8-max-0902":{"draws":16,"losses":38,"wins":16},"stealth/ox-alpha":{"draws":70,"losses":290,"wins":224},"stealth/space-bunny-alpha":{"draws":11,"losses":30,"wins":25},"stepfun/step-3.7-flash":{"draws":45,"losses":56,"wins":125},"tencent/hy3-preview":{"draws":26,"losses":36,"wins":38},"tencent/hy4-preview":{"draws":37,"losses":111,"wins":64},"thinkingmachines/inkling":{"draws":69,"losses":76,"wins":202},"thinkingmachines/inkling-small":{"draws":68,"losses":57,"wins":108},"x-ai/grok-4.5":{"draws":31,"losses":220,"wins":107},"x-ai/grok-4.6":{"draws":43,"losses":134,"wins":49},"x-ai/grok-4.7":{"draws":5,"losses":65,"wins":6},"x-ai/grok-build-0.1":{"draws":11,"losses":9,"wins":38},"xiaomi/mimo-v2.5":{"draws":54,"losses":35,"wins":139},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":53,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":32,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":32,"wins":17},"z-ai/glm-5.2":{"draws":61,"losses":142,"wins":143},"z-ai/glm-5.3":{"draws":13,"losses":136,"wins":33},"z-ai/glm-5.3-flash":{"draws":42,"losses":96,"wins":96},"z-ai/glm-5.3-flashx":{"draws":6,"losses":60,"wins":18}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":63,"losses":56,"wins":45},"claude-fable-5":{"draws":43,"losses":85,"wins":14},"claude-fable-5-1":{"draws":8,"losses":117,"wins":1},"claude-opus-4-5":{"draws":50,"losses":93,"wins":25},"claude-opus-4-8":{"draws":14,"losses":27,"wins":5},"claude-opus-5":{"draws":17,"losses":114,"wins":1},"claude-opus-5-5":{"draws":8,"losses":80,"wins":0},"claude-sonnet-5":{"draws":72,"losses":89,"wins":23},"claude-sonnet-5-5":{"draws":14,"losses":48,"wins":6},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":83,"losses":50,"wins":53},"deepseek/deepseek-v4-pro":{"draws":60,"losses":66,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":54,"losses":52,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":36,"wins":13},"fireworks/ember-1":{"draws":22,"losses":40,"wins":10},"gemini-3.1-pro-preview":{"draws":33,"losses":32,"wins":15},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":26},"google/gemini-3.5-flash":{"draws":55,"losses":78,"wins":35},"google/gemini-3.5-flash-lite":{"draws":116,"losses":101,"wins":89},"google/gemini-3.6-flash":{"draws":100,"losses":118,"wins":36},"google/gemini-3.8-flash":{"draws":36,"losses":79,"wins":11},"google/gemma-4-31b-it":{"draws":9,"losses":9,"wins":12},"gpt-4.1":{"draws":5,"losses":11,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":23,"losses":29,"wins":8},"gpt-5.4":{"draws":64,"losses":55,"wins":17},"gpt-5.4-mini":{"draws":18,"losses":12,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":20,"wins":25},"gpt-5.5":{"draws":23,"losses":37,"wins":6},"gpt-5.6-luna":{"draws":77,"losses":54,"wins":39},"gpt-5.6-sol":{"draws":15,"losses":90,"wins":11},"gpt-5.6-terra":{"draws":70,"losses":90,"wins":18},"gpt-6-astra":{"draws":7,"losses":83,"wins":0},"gpt-6-luna":{"draws":29,"losses":45,"wins":16},"gpt-6-sol":{"draws":6,"losses":57,"wins":1},"gpt-6.1-sol":{"draws":5,"losses":73,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":15,"losses":0,"wins":13},"inception/mercury-2.5-preview":{"draws":64,"losses":31,"wins":39},"inclusionai/ling-3.0-flash":{"draws":24,"losses":10,"wins":44},"meituan/longcat-2.0":{"draws":46,"losses":48,"wins":34},"meta/muse-glimmer-30b":{"draws":75,"losses":38,"wins":41},"meta/muse-spark-1.2":{"draws":35,"losses":60,"wins":13},"meta/muse-spark-1.3":{"draws":38,"losses":65,"wins":17},"minimax/minimax-m3":{"draws":15,"losses":15,"wins":18},"mistralai/mistral-medium-3-5":{"draws":57,"losses":20,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":11,"wins":5},"moonshotai/kimi-k3":{"draws":48,"losses":74,"wins":22},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":16,"wins":22},"o3":{"draws":37,"losses":105,"wins":38},"openai/gpt-oss-120b":{"draws":58,"losses":27,"wins":27},"poolside/laguna-s-2.1":{"draws":59,"losses":39,"wins":24},"qwen/qwen3.7-max":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":9,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":57,"losses":71,"wins":10},"qwen/qwen3.8-27b":{"draws":16,"losses":51,"wins":23},"qwen/qwen3.8-flash":{"draws":40,"losses":36,"wins":32},"qwen/qwen3.8-max":{"draws":61,"losses":73,"wins":10},"qwen/qwen3.8-max-0902":{"draws":25,"losses":41,"wins":6},"stealth/ox-alpha":{"draws":147,"losses":256,"wins":72},"stealth/space-bunny-alpha":{"draws":18,"losses":26,"wins":18},"stepfun/step-3.7-flash":{"draws":18,"losses":25,"wins":21},"tencent/hy3-preview":{"draws":24,"losses":13,"wins":9},"tencent/hy4-preview":{"draws":50,"losses":59,"wins":25},"thinkingmachines/inkling":{"draws":48,"losses":45,"wins":41},"thinkingmachines/inkling-small":{"draws":83,"losses":39,"wins":56},"x-ai/grok-4.5":{"draws":51,"losses":75,"wins":16},"x-ai/grok-4.6":{"draws":50,"losses":83,"wins":19},"x-ai/grok-4.7":{"draws":2,"losses":55,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":7},"xiaomi/mimo-v2.5":{"draws":50,"losses":36,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":18,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":22,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":34,"wins":4},"z-ai/glm-5.2":{"draws":96,"losses":86,"wins":46},"z-ai/glm-5.3":{"draws":44,"losses":68,"wins":8},"z-ai/glm-5.3-flash":{"draws":47,"losses":92,"wins":15},"z-ai/glm-5.3-flashx":{"draws":16,"losses":35,"wins":9}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":55,"losses":41,"wins":34},"claude-fable-5":{"draws":30,"losses":83,"wins":19},"claude-fable-5-1":{"draws":8,"losses":102,"wins":0},"claude-opus-4-5":{"draws":120,"losses":146,"wins":30},"claude-opus-4-8":{"draws":40,"losses":78,"wins":16},"claude-opus-5":{"draws":24,"losses":242,"wins":22},"claude-opus-5-5":{"draws":3,"losses":69,"wins":0},"claude-sonnet-5":{"draws":67,"losses":108,"wins":21},"claude-sonnet-5-5":{"draws":18,"losses":51,"wins":11},"cohere/north-mini-code":{"draws":52,"losses":27,"wins":11},"deepseek/deepseek-v4-flash":{"draws":100,"losses":55,"wins":53},"deepseek/deepseek-v4-pro":{"draws":50,"losses":50,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":60,"losses":48,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":24,"wins":11},"fireworks/ember-1":{"draws":26,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":27,"losses":28,"wins":21},"google/gemini-3.1-flash-lite":{"draws":20,"losses":25,"wins":41},"google/gemini-3.5-flash":{"draws":64,"losses":78,"wins":30},"google/gemini-3.5-flash-lite":{"draws":224,"losses":139,"wins":165},"google/gemini-3.6-flash":{"draws":195,"losses":185,"wins":66},"google/gemini-3.8-flash":{"draws":33,"losses":80,"wins":15},"google/gemma-4-31b-it":{"draws":8,"losses":30,"wins":30},"gpt-4.1":{"draws":18,"losses":20,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":8},"gpt-5":{"draws":49,"losses":30,"wins":39},"gpt-5.4":{"draws":80,"losses":87,"wins":13},"gpt-5.4-mini":{"draws":54,"losses":35,"wins":23},"gpt-5.4-nano":{"draws":62,"losses":50,"wins":62},"gpt-5.5":{"draws":54,"losses":51,"wins":29},"gpt-5.6-luna":{"draws":83,"losses":62,"wins":49},"gpt-5.6-sol":{"draws":40,"losses":155,"wins":5},"gpt-5.6-terra":{"draws":61,"losses":60,"wins":15},"gpt-6-astra":{"draws":17,"losses":99,"wins":0},"gpt-6-luna":{"draws":32,"losses":36,"wins":30},"gpt-6-sol":{"draws":13,"losses":47,"wins":6},"gpt-6.1-sol":{"draws":9,"losses":64,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":14,"losses":2,"wins":4},"inception/mercury-2.5-preview":{"draws":41,"losses":21,"wins":30},"inclusionai/ling-3.0-flash":{"draws":99,"losses":23,"wins":58},"meituan/longcat-2.0":{"draws":108,"losses":84,"wins":78},"meta/muse-glimmer-30b":{"draws":74,"losses":31,"wins":33},"meta/muse-spark-1.2":{"draws":40,"losses":87,"wins":25},"meta/muse-spark-1.3":{"draws":35,"losses":64,"wins":17},"minimax/minimax-m3":{"draws":45,"losses":29,"wins":32},"mistralai/mistral-medium-3-5":{"draws":39,"losses":19,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":12,"wins":22},"moonshotai/kimi-k3":{"draws":103,"losses":120,"wins":25},"nex-agi/nex-n2-pro":{"draws":38,"losses":11,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":20,"wins":34},"o3":{"draws":66,"losses":108,"wins":84},"openai/gpt-oss-120b":{"draws":59,"losses":24,"wins":39},"poolside/laguna-s-2.1":{"draws":92,"losses":54,"wins":54},"qwen/qwen3.7-max":{"draws":39,"losses":27,"wins":26},"qwen/qwen3.7-plus":{"draws":40,"losses":11,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":61,"wins":9},"qwen/qwen3.8-27b":{"draws":18,"losses":41,"wins":19},"qwen/qwen3.8-flash":{"draws":49,"losses":34,"wins":21},"qwen/qwen3.8-max":{"draws":55,"losses":39,"wins":25},"qwen/qwen3.8-max-0902":{"draws":15,"losses":26,"wins":11},"stealth/ox-alpha":{"draws":141,"losses":226,"wins":74},"stealth/space-bunny-alpha":{"draws":20,"losses":20,"wins":16},"stepfun/step-3.7-flash":{"draws":36,"losses":40,"wins":28},"tencent/hy3-preview":{"draws":23,"losses":24,"wins":19},"tencent/hy4-preview":{"draws":53,"losses":54,"wins":21},"thinkingmachines/inkling":{"draws":97,"losses":69,"wins":96},"thinkingmachines/inkling-small":{"draws":78,"losses":24,"wins":59},"x-ai/grok-4.5":{"draws":84,"losses":154,"wins":44},"x-ai/grok-4.6":{"draws":43,"losses":90,"wins":17},"x-ai/grok-4.7":{"draws":8,"losses":46,"wins":8},"x-ai/grok-build-0.1":{"draws":27,"losses":24,"wins":15},"xiaomi/mimo-v2.5":{"draws":79,"losses":61,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":37,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":24,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":27,"wins":6},"z-ai/glm-5.2":{"draws":151,"losses":89,"wins":62},"z-ai/glm-5.3":{"draws":29,"losses":78,"wins":9},"z-ai/glm-5.3-flash":{"draws":59,"losses":77,"wins":22},"z-ai/glm-5.3-flashx":{"draws":17,"losses":28,"wins":13}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":21,"wins":21},"claude-fable-5":{"draws":11,"losses":32,"wins":7},"claude-fable-5-1":{"draws":1,"losses":57,"wins":0},"claude-opus-4-5":{"draws":70,"losses":79,"wins":37},"claude-opus-4-8":{"draws":38,"losses":54,"wins":26},"claude-opus-5":{"draws":20,"losses":136,"wins":20},"claude-opus-5-5":{"draws":4,"losses":38,"wins":0},"claude-sonnet-5":{"draws":17,"losses":27,"wins":14},"claude-sonnet-5-5":{"draws":4,"losses":24,"wins":10},"cohere/north-mini-code":{"draws":23,"losses":11,"wins":36},"deepseek/deepseek-v4-flash":{"draws":57,"losses":20,"wins":35},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":27,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":7,"wins":10},"fireworks/ember-1":{"draws":15,"losses":23,"wins":10},"gemini-3.1-pro-preview":{"draws":16,"losses":20,"wins":16},"google/gemini-3.1-flash-lite":{"draws":29,"losses":14,"wins":39},"google/gemini-3.5-flash":{"draws":23,"losses":22,"wins":19},"google/gemini-3.5-flash-lite":{"draws":32,"losses":39,"wins":27},"google/gemini-3.6-flash":{"draws":26,"losses":63,"wins":21},"google/gemini-3.8-flash":{"draws":15,"losses":31,"wins":18},"google/gemma-4-31b-it":{"draws":8,"losses":17,"wins":39},"gpt-4.1":{"draws":19,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":40,"losses":38,"wins":18},"gpt-5.4":{"draws":11,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":31,"losses":14,"wins":29},"gpt-5.4-nano":{"draws":37,"losses":45,"wins":52},"gpt-5.5":{"draws":42,"losses":43,"wins":23},"gpt-5.6-luna":{"draws":16,"losses":16,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":20,"losses":30,"wins":12},"gpt-6-astra":{"draws":5,"losses":48,"wins":1},"gpt-6-luna":{"draws":13,"losses":23,"wins":18},"gpt-6-sol":{"draws":11,"losses":27,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":50,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":12,"wins":14},"inclusionai/ling-3.0-flash":{"draws":46,"losses":8,"wins":34},"meituan/longcat-2.0":{"draws":41,"losses":13,"wins":37},"meta/muse-glimmer-30b":{"draws":18,"losses":15,"wins":21},"meta/muse-spark-1.2":{"draws":7,"losses":24,"wins":3},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":10},"minimax/minimax-m3":{"draws":34,"losses":14,"wins":40},"mistralai/mistral-medium-3-5":{"draws":16,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":9,"wins":13},"moonshotai/kimi-k3":{"draws":16,"losses":28,"wins":14},"nex-agi/nex-n2-pro":{"draws":23,"losses":7,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":62,"losses":16,"wins":32},"o3":{"draws":26,"losses":35,"wins":25},"openai/gpt-oss-120b":{"draws":16,"losses":9,"wins":17},"poolside/laguna-s-2.1":{"draws":39,"losses":26,"wins":27},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":10},"qwen/qwen3.7-plus":{"draws":30,"losses":18,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":2,"losses":28,"wins":12},"qwen/qwen3.8-flash":{"draws":21,"losses":12,"wins":21},"qwen/qwen3.8-max":{"draws":25,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":13,"wins":9},"stealth/ox-alpha":{"draws":41,"losses":82,"wins":35},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":15},"stepfun/step-3.7-flash":{"draws":24,"losses":11,"wins":29},"tencent/hy3-preview":{"draws":32,"losses":15,"wins":29},"tencent/hy4-preview":{"draws":11,"losses":28,"wins":11},"thinkingmachines/inkling":{"draws":40,"losses":14,"wins":54},"thinkingmachines/inkling-small":{"draws":24,"losses":13,"wins":21},"x-ai/grok-4.5":{"draws":30,"losses":50,"wins":22},"x-ai/grok-4.6":{"draws":13,"losses":33,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":22,"losses":18,"wins":14},"xiaomi/mimo-v2.5":{"draws":77,"losses":32,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":19,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":8},"z-ai/glm-5.2":{"draws":60,"losses":59,"wins":43},"z-ai/glm-5.3":{"draws":16,"losses":18,"wins":10},"z-ai/glm-5.3-flash":{"draws":18,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":26,"wins":8}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":18,"wins":14},"claude-fable-5":{"draws":10,"losses":39,"wins":3},"claude-fable-5-1":{"draws":4,"losses":42,"wins":0},"claude-opus-4-5":{"draws":60,"losses":59,"wins":33},"claude-opus-4-8":{"draws":20,"losses":60,"wins":18},"claude-opus-5":{"draws":21,"losses":86,"wins":13},"claude-opus-5-5":{"draws":2,"losses":36,"wins":0},"claude-sonnet-5":{"draws":16,"losses":29,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":8,"wins":2},"cohere/north-mini-code":{"draws":21,"losses":22,"wins":33},"deepseek/deepseek-v4-flash":{"draws":31,"losses":49,"wins":40},"deepseek/deepseek-v4-pro":{"draws":14,"losses":25,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":18,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":22,"wins":2},"fireworks/ember-1":{"draws":14,"losses":8,"wins":0},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":4},"google/gemini-3.1-flash-lite":{"draws":23,"losses":22,"wins":51},"google/gemini-3.5-flash":{"draws":20,"losses":31,"wins":11},"google/gemini-3.5-flash-lite":{"draws":41,"losses":30,"wins":31},"google/gemini-3.6-flash":{"draws":41,"losses":66,"wins":21},"google/gemini-3.8-flash":{"draws":14,"losses":38,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":32,"wins":22},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":22,"losses":29,"wins":13},"gpt-5.4":{"draws":12,"losses":42,"wins":6},"gpt-5.4-mini":{"draws":24,"losses":19,"wins":29},"gpt-5.4-nano":{"draws":28,"losses":57,"wins":53},"gpt-5.5":{"draws":47,"losses":45,"wins":12},"gpt-5.6-luna":{"draws":9,"losses":25,"wins":20},"gpt-5.6-sol":{"draws":9,"losses":34,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":23,"wins":8},"gpt-6-astra":{"draws":2,"losses":38,"wins":0},"gpt-6-luna":{"draws":10,"losses":26,"wins":8},"gpt-6-sol":{"draws":1,"losses":27,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":8,"wins":20},"inclusionai/ling-3.0-flash":{"draws":33,"losses":22,"wins":25},"meituan/longcat-2.0":{"draws":23,"losses":32,"wins":23},"meta/muse-glimmer-30b":{"draws":21,"losses":16,"wins":13},"meta/muse-spark-1.2":{"draws":8,"losses":35,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":29,"wins":9},"minimax/minimax-m3":{"draws":22,"losses":28,"wins":28},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":20,"losses":26,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":22,"losses":21,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":28,"wins":27},"o3":{"draws":12,"losses":55,"wins":31},"openai/gpt-oss-120b":{"draws":15,"losses":14,"wins":9},"poolside/laguna-s-2.1":{"draws":40,"losses":33,"wins":11},"qwen/qwen3.7-max":{"draws":30,"losses":32,"wins":18},"qwen/qwen3.7-plus":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":31,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":25,"wins":11},"qwen/qwen3.8-flash":{"draws":17,"losses":17,"wins":16},"qwen/qwen3.8-max":{"draws":12,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":5},"stealth/ox-alpha":{"draws":24,"losses":84,"wins":16},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":20,"losses":21,"wins":29},"tencent/hy3-preview":{"draws":28,"losses":27,"wins":15},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":26,"losses":31,"wins":43},"thinkingmachines/inkling-small":{"draws":15,"losses":12,"wins":13},"x-ai/grok-4.5":{"draws":24,"losses":61,"wins":11},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":2},"x-ai/grok-build-0.1":{"draws":14,"losses":10,"wins":20},"xiaomi/mimo-v2.5":{"draws":69,"losses":56,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":29,"losses":38,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":2},"z-ai/glm-5.2":{"draws":65,"losses":77,"wins":30},"z-ai/glm-5.3":{"draws":9,"losses":37,"wins":5},"z-ai/glm-5.3-flash":{"draws":18,"losses":33,"wins":5},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":4}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":36,"wins":66},"claude-fable-5":{"draws":53,"losses":106,"wins":53},"claude-fable-5-1":{"draws":23,"losses":176,"wins":9},"claude-opus-4-5":{"draws":83,"losses":59,"wins":78},"claude-opus-4-8":{"draws":30,"losses":28,"wins":26},"claude-opus-5":{"draws":26,"losses":118,"wins":28},"claude-opus-5-5":{"draws":8,"losses":53,"wins":5},"claude-sonnet-5":{"draws":71,"losses":43,"wins":62},"claude-sonnet-5-5":{"draws":18,"losses":38,"wins":30},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":41},"deepseek/deepseek-v4-flash":{"draws":72,"losses":39,"wins":99},"deepseek/deepseek-v4-pro":{"draws":53,"losses":45,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":47,"losses":63,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":25,"wins":29},"fireworks/ember-1":{"draws":26,"losses":24,"wins":26},"gemini-3.1-pro-preview":{"draws":21,"losses":24,"wins":35},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":52,"losses":75,"wins":87},"google/gemini-3.5-flash-lite":{"draws":101,"losses":61,"wins":148},"google/gemini-3.6-flash":{"draws":83,"losses":117,"wins":106},"google/gemini-3.8-flash":{"draws":38,"losses":92,"wins":66},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":26},"gpt-4.1":{"draws":8,"losses":6,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":23,"wins":37},"gpt-5.4":{"draws":46,"losses":59,"wins":75},"gpt-5.4-mini":{"draws":17,"losses":4,"wins":31},"gpt-5.4-nano":{"draws":27,"losses":19,"wins":56},"gpt-5.5":{"draws":29,"losses":29,"wins":24},"gpt-5.6-luna":{"draws":67,"losses":39,"wins":62},"gpt-5.6-sol":{"draws":40,"losses":110,"wins":50},"gpt-5.6-terra":{"draws":77,"losses":33,"wins":80},"gpt-6-astra":{"draws":11,"losses":155,"wins":8},"gpt-6-luna":{"draws":24,"losses":30,"wins":34},"gpt-6-sol":{"draws":6,"losses":34,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":50,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":10},"inception/mercury-2.5-preview":{"draws":45,"losses":10,"wins":53},"inclusionai/ling-3.0-flash":{"draws":28,"losses":4,"wins":46},"meituan/longcat-2.0":{"draws":35,"losses":20,"wins":81},"meta/muse-glimmer-30b":{"draws":68,"losses":22,"wins":66},"meta/muse-spark-1.2":{"draws":38,"losses":33,"wins":63},"meta/muse-spark-1.3":{"draws":48,"losses":66,"wins":60},"minimax/minimax-m3":{"draws":17,"losses":3,"wins":30},"mistralai/mistral-medium-3-5":{"draws":39,"losses":4,"wins":71},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":7,"wins":9},"moonshotai/kimi-k3":{"draws":61,"losses":66,"wins":55},"nex-agi/nex-n2-pro":{"draws":14,"losses":9,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":6,"wins":28},"o3":{"draws":27,"losses":64,"wins":113},"openai/gpt-oss-120b":{"draws":57,"losses":10,"wins":71},"poolside/laguna-s-2.1":{"draws":54,"losses":9,"wins":61},"qwen/qwen3.7-max":{"draws":17,"losses":10,"wins":21},"qwen/qwen3.7-plus":{"draws":20,"losses":9,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":41,"wins":41},"qwen/qwen3.8-27b":{"draws":34,"losses":29,"wins":41},"qwen/qwen3.8-flash":{"draws":42,"losses":43,"wins":57},"qwen/qwen3.8-max":{"draws":63,"losses":55,"wins":66},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":19},"stealth/ox-alpha":{"draws":160,"losses":234,"wins":200},"stealth/space-bunny-alpha":{"draws":26,"losses":17,"wins":27},"stepfun/step-3.7-flash":{"draws":16,"losses":12,"wins":32},"tencent/hy3-preview":{"draws":15,"losses":9,"wins":22},"tencent/hy4-preview":{"draws":56,"losses":72,"wins":58},"thinkingmachines/inkling":{"draws":59,"losses":24,"wins":63},"thinkingmachines/inkling-small":{"draws":64,"losses":19,"wins":99},"x-ai/grok-4.5":{"draws":48,"losses":72,"wins":62},"x-ai/grok-4.6":{"draws":59,"losses":86,"wins":69},"x-ai/grok-4.7":{"draws":7,"losses":50,"wins":13},"x-ai/grok-build-0.1":{"draws":10,"losses":2,"wins":18},"xiaomi/mimo-v2.5":{"draws":56,"losses":21,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":10,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":22,"wins":9},"z-ai/glm-5.2":{"draws":96,"losses":66,"wins":96},"z-ai/glm-5.3":{"draws":44,"losses":96,"wins":34},"z-ai/glm-5.3-flash":{"draws":49,"losses":81,"wins":78},"z-ai/glm-5.3-flashx":{"draws":19,"losses":22,"wins":21}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":32,"wins":49},"claude-fable-5":{"draws":12,"losses":63,"wins":25},"claude-fable-5-1":{"draws":5,"losses":98,"wins":1},"claude-opus-4-5":{"draws":31,"losses":42,"wins":49},"claude-opus-4-8":{"draws":12,"losses":22,"wins":18},"claude-opus-5":{"draws":7,"losses":56,"wins":7},"claude-opus-5-5":{"draws":4,"losses":30,"wins":0},"claude-sonnet-5":{"draws":24,"losses":34,"wins":38},"claude-sonnet-5-5":{"draws":0,"losses":11,"wins":9},"cohere/north-mini-code":{"draws":15,"losses":4,"wins":25},"deepseek/deepseek-v4-flash":{"draws":27,"losses":40,"wins":67},"deepseek/deepseek-v4-pro":{"draws":23,"losses":38,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":41,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":12,"wins":13},"fireworks/ember-1":{"draws":2,"losses":15,"wins":11},"gemini-3.1-pro-preview":{"draws":3,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":13,"losses":6,"wins":33},"google/gemini-3.5-flash":{"draws":28,"losses":33,"wins":55},"google/gemini-3.5-flash-lite":{"draws":37,"losses":47,"wins":110},"google/gemini-3.6-flash":{"draws":48,"losses":95,"wins":59},"google/gemini-3.8-flash":{"draws":24,"losses":72,"wins":34},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":21},"gpt-4.1":{"draws":5,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":10,"losses":20,"wins":26},"gpt-5.4":{"draws":26,"losses":57,"wins":29},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":19,"wins":31},"gpt-5.5":{"draws":11,"losses":29,"wins":20},"gpt-5.6-luna":{"draws":19,"losses":29,"wins":48},"gpt-5.6-sol":{"draws":17,"losses":61,"wins":28},"gpt-5.6-terra":{"draws":36,"losses":35,"wins":37},"gpt-6-astra":{"draws":0,"losses":96,"wins":2},"gpt-6-luna":{"draws":7,"losses":22,"wins":15},"gpt-6-sol":{"draws":3,"losses":25,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":14,"losses":7,"wins":49},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":35},"meituan/longcat-2.0":{"draws":18,"losses":20,"wins":46},"meta/muse-glimmer-30b":{"draws":37,"losses":11,"wins":58},"meta/muse-spark-1.2":{"draws":14,"losses":35,"wins":39},"meta/muse-spark-1.3":{"draws":14,"losses":48,"wins":32},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":10,"losses":7,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":28,"losses":36,"wins":28},"nex-agi/nex-n2-pro":{"draws":7,"losses":10,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":14},"o3":{"draws":30,"losses":43,"wins":73},"openai/gpt-oss-120b":{"draws":16,"losses":23,"wins":51},"poolside/laguna-s-2.1":{"draws":18,"losses":19,"wins":41},"qwen/qwen3.7-max":{"draws":2,"losses":12,"wins":28},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":41,"wins":29},"qwen/qwen3.8-27b":{"draws":0,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":22,"losses":22,"wins":30},"qwen/qwen3.8-max":{"draws":25,"losses":44,"wins":33},"qwen/qwen3.8-max-0902":{"draws":6,"losses":9,"wins":9},"stealth/ox-alpha":{"draws":83,"losses":153,"wins":119},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":7},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":27},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":26},"tencent/hy4-preview":{"draws":27,"losses":49,"wins":26},"thinkingmachines/inkling":{"draws":24,"losses":14,"wins":58},"thinkingmachines/inkling-small":{"draws":29,"losses":14,"wins":79},"x-ai/grok-4.5":{"draws":10,"losses":54,"wins":44},"x-ai/grok-4.6":{"draws":26,"losses":47,"wins":35},"x-ai/grok-4.7":{"draws":1,"losses":12,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":16,"losses":13,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":12,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":49,"losses":51,"wins":74},"z-ai/glm-5.3":{"draws":15,"losses":62,"wins":19},"z-ai/glm-5.3-flash":{"draws":35,"losses":47,"wins":38},"z-ai/glm-5.3-flashx":{"draws":7,"losses":16,"wins":6}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":31,"wins":54},"claude-fable-5":{"draws":38,"losses":73,"wins":21},"claude-fable-5-1":{"draws":9,"losses":127,"wins":4},"claude-opus-4-5":{"draws":59,"losses":54,"wins":47},"claude-opus-4-8":{"draws":21,"losses":28,"wins":13},"claude-opus-5":{"draws":20,"losses":98,"wins":10},"claude-opus-5-5":{"draws":6,"losses":46,"wins":2},"claude-sonnet-5":{"draws":47,"losses":50,"wins":35},"claude-sonnet-5-5":{"draws":6,"losses":17,"wins":17},"cohere/north-mini-code":{"draws":16,"losses":5,"wins":15},"deepseek/deepseek-v4-flash":{"draws":56,"losses":36,"wins":64},"deepseek/deepseek-v4-pro":{"draws":41,"losses":42,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":52,"losses":33,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":26,"wins":10},"fireworks/ember-1":{"draws":16,"losses":11,"wins":11},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"wins":12},"google/gemini-3.1-flash-lite":{"draws":18,"losses":7,"wins":19},"google/gemini-3.5-flash":{"draws":51,"losses":64,"wins":45},"google/gemini-3.5-flash-lite":{"draws":88,"losses":41,"wins":99},"google/gemini-3.6-flash":{"draws":95,"losses":85,"wins":52},"google/gemini-3.8-flash":{"draws":35,"losses":65,"wins":30},"google/gemma-4-31b-it":{"draws":16,"losses":7,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":17},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":19,"losses":25,"wins":22},"gpt-5.4":{"draws":33,"losses":50,"wins":33},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":21},"gpt-5.4-nano":{"draws":23,"losses":13,"wins":28},"gpt-5.5":{"draws":25,"losses":36,"wins":11},"gpt-5.6-luna":{"draws":42,"losses":41,"wins":47},"gpt-5.6-sol":{"draws":28,"losses":78,"wins":30},"gpt-5.6-terra":{"draws":43,"losses":44,"wins":37},"gpt-6-astra":{"draws":17,"losses":96,"wins":3},"gpt-6-luna":{"draws":15,"losses":31,"wins":22},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":2,"wins":3},"inception/mercury-2.5-preview":{"draws":44,"losses":11,"wins":37},"inclusionai/ling-3.0-flash":{"draws":26,"losses":10,"wins":38},"meituan/longcat-2.0":{"draws":37,"losses":19,"wins":40},"meta/muse-glimmer-30b":{"draws":55,"losses":31,"wins":32},"meta/muse-spark-1.2":{"draws":31,"losses":36,"wins":31},"meta/muse-spark-1.3":{"draws":41,"losses":59,"wins":32},"minimax/minimax-m3":{"draws":15,"losses":18,"wins":19},"mistralai/mistral-medium-3-5":{"draws":29,"losses":9,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":9},"moonshotai/kimi-k3":{"draws":48,"losses":43,"wins":27},"nex-agi/nex-n2-pro":{"draws":22,"losses":4,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":16,"wins":26},"o3":{"draws":37,"losses":61,"wins":56},"openai/gpt-oss-120b":{"draws":40,"losses":32,"wins":36},"poolside/laguna-s-2.1":{"draws":49,"losses":21,"wins":34},"qwen/qwen3.7-max":{"draws":21,"losses":21,"wins":12},"qwen/qwen3.7-plus":{"draws":17,"losses":16,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":57,"wins":43},"qwen/qwen3.8-27b":{"draws":22,"losses":30,"wins":22},"qwen/qwen3.8-flash":{"draws":22,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":51,"losses":37,"wins":38},"qwen/qwen3.8-max-0902":{"draws":19,"losses":22,"wins":15},"stealth/ox-alpha":{"draws":121,"losses":166,"wins":138},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":17,"losses":13,"wins":22},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":37,"losses":52,"wins":41},"thinkingmachines/inkling":{"draws":41,"losses":23,"wins":56},"thinkingmachines/inkling-small":{"draws":63,"losses":24,"wins":47},"x-ai/grok-4.5":{"draws":29,"losses":55,"wins":28},"x-ai/grok-4.6":{"draws":53,"losses":64,"wins":25},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":7},"x-ai/grok-build-0.1":{"draws":15,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":38,"losses":23,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":13,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":15,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":76,"losses":48,"wins":70},"z-ai/glm-5.3":{"draws":28,"losses":84,"wins":18},"z-ai/glm-5.3-flash":{"draws":49,"losses":53,"wins":48},"z-ai/glm-5.3-flashx":{"draws":16,"losses":28,"wins":12}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":67,"losses":54,"wins":71},"claude-fable-5":{"draws":33,"losses":109,"wins":56},"claude-fable-5-1":{"draws":6,"losses":173,"wins":7},"claude-opus-4-5":{"draws":67,"losses":59,"wins":93},"claude-opus-4-8":{"draws":18,"losses":32,"wins":30},"claude-opus-5":{"draws":23,"losses":112,"wins":15},"claude-opus-5-5":{"draws":10,"losses":78,"wins":4},"claude-sonnet-5":{"draws":57,"losses":54,"wins":76},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":29},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":28},"deepseek/deepseek-v4-flash":{"draws":81,"losses":36,"wins":103},"deepseek/deepseek-v4-pro":{"draws":54,"losses":46,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":66,"losses":49,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":28,"wins":23},"fireworks/ember-1":{"draws":29,"losses":33,"wins":28},"gemini-3.1-pro-preview":{"draws":19,"losses":26,"wins":29},"google/gemini-3.1-flash-lite":{"draws":17,"losses":0,"wins":37},"google/gemini-3.5-flash":{"draws":57,"losses":72,"wins":47},"google/gemini-3.5-flash-lite":{"draws":105,"losses":76,"wins":118},"google/gemini-3.6-flash":{"draws":94,"losses":117,"wins":122},"google/gemini-3.8-flash":{"draws":48,"losses":71,"wins":57},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":19},"gpt-4.1":{"draws":13,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":29,"losses":8,"wins":25},"gpt-5.4":{"draws":58,"losses":55,"wins":65},"gpt-5.4-mini":{"draws":31,"losses":9,"wins":20},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":46},"gpt-5.5":{"draws":23,"losses":27,"wins":28},"gpt-5.6-luna":{"draws":63,"losses":38,"wins":79},"gpt-5.6-sol":{"draws":37,"losses":101,"wins":43},"gpt-5.6-terra":{"draws":88,"losses":54,"wins":68},"gpt-6-astra":{"draws":20,"losses":142,"wins":4},"gpt-6-luna":{"draws":27,"losses":38,"wins":39},"gpt-6-sol":{"draws":10,"losses":47,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":74,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":1,"wins":7},"inception/mercury-2.5-preview":{"draws":61,"losses":12,"wins":53},"inclusionai/ling-3.0-flash":{"draws":33,"losses":15,"wins":43},"meituan/longcat-2.0":{"draws":49,"losses":21,"wins":65},"meta/muse-glimmer-30b":{"draws":56,"losses":35,"wins":63},"meta/muse-spark-1.2":{"draws":38,"losses":40,"wins":47},"meta/muse-spark-1.3":{"draws":43,"losses":88,"wins":37},"minimax/minimax-m3":{"draws":12,"losses":6,"wins":28},"mistralai/mistral-medium-3-5":{"draws":37,"losses":13,"wins":60},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":44,"losses":61,"wins":52},"nex-agi/nex-n2-pro":{"draws":11,"losses":2,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":11,"wins":34},"o3":{"draws":37,"losses":71,"wins":104},"openai/gpt-oss-120b":{"draws":61,"losses":10,"wins":73},"poolside/laguna-s-2.1":{"draws":55,"losses":25,"wins":39},"qwen/qwen3.7-max":{"draws":25,"losses":14,"wins":21},"qwen/qwen3.7-plus":{"draws":12,"losses":12,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":63,"losses":66,"wins":55},"qwen/qwen3.8-27b":{"draws":25,"losses":33,"wins":44},"qwen/qwen3.8-flash":{"draws":51,"losses":38,"wins":37},"qwen/qwen3.8-max":{"draws":58,"losses":63,"wins":63},"qwen/qwen3.8-max-0902":{"draws":21,"losses":38,"wins":13},"stealth/ox-alpha":{"draws":165,"losses":226,"wins":191},"stealth/space-bunny-alpha":{"draws":17,"losses":18,"wins":25},"stepfun/step-3.7-flash":{"draws":14,"losses":5,"wins":33},"tencent/hy3-preview":{"draws":16,"losses":9,"wins":17},"tencent/hy4-preview":{"draws":50,"losses":83,"wins":61},"thinkingmachines/inkling":{"draws":51,"losses":30,"wins":73},"thinkingmachines/inkling-small":{"draws":118,"losses":80,"wins":121},"x-ai/grok-4.5":{"draws":51,"losses":72,"wins":62},"x-ai/grok-4.6":{"draws":57,"losses":98,"wins":59},"x-ai/grok-4.7":{"draws":11,"losses":53,"wins":12},"x-ai/grok-build-0.1":{"draws":15,"losses":7,"wins":16},"xiaomi/mimo-v2.5":{"draws":53,"losses":21,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":13,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":27,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":20,"wins":13},"z-ai/glm-5.2":{"draws":84,"losses":65,"wins":87},"z-ai/glm-5.3":{"draws":45,"losses":97,"wins":34},"z-ai/glm-5.3-flash":{"draws":58,"losses":74,"wins":72},"z-ai/glm-5.3-flashx":{"draws":28,"losses":29,"wins":23}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":7,"wins":40},"claude-fable-5":{"draws":16,"losses":54,"wins":16},"claude-fable-5-1":{"draws":4,"losses":66,"wins":6},"claude-opus-4-5":{"draws":32,"losses":17,"wins":39},"claude-opus-4-8":{"draws":23,"losses":17,"wins":28},"claude-opus-5":{"draws":20,"losses":67,"wins":23},"claude-opus-5-5":{"draws":14,"losses":118,"wins":14},"claude-sonnet-5":{"draws":19,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":20,"losses":61,"wins":43},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":22},"deepseek/deepseek-v4-flash":{"draws":31,"losses":11,"wins":50},"deepseek/deepseek-v4-pro":{"draws":14,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":7,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":48,"wins":44},"fireworks/ember-1":{"draws":46,"losses":36,"wins":44},"gemini-3.1-pro-preview":{"draws":34,"losses":31,"wins":61},"google/gemini-3.1-flash-lite":{"draws":13,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":24,"losses":16,"wins":32},"google/gemini-3.5-flash-lite":{"draws":43,"losses":10,"wins":51},"google/gemini-3.6-flash":{"draws":27,"losses":31,"wins":32},"google/gemini-3.8-flash":{"draws":16,"losses":18,"wins":12},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":23},"gpt-4.1":{"draws":10,"losses":5,"wins":15},"gpt-5":{"draws":15,"losses":5,"wins":10},"gpt-5.4":{"draws":22,"losses":24,"wins":18},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":24},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":28},"gpt-5.5":{"draws":36,"losses":16,"wins":24},"gpt-5.6-luna":{"draws":34,"losses":3,"wins":29},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":5},"gpt-5.6-terra":{"draws":29,"losses":13,"wins":30},"gpt-6-astra":{"draws":7,"losses":41,"wins":6},"gpt-6-luna":{"draws":44,"losses":39,"wins":51},"gpt-6-sol":{"draws":17,"losses":95,"wins":26},"gpt-6.1-sol":{"draws":15,"losses":90,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":15,"losses":7,"wins":28},"meituan/longcat-2.0":{"draws":27,"losses":13,"wins":57},"meta/muse-glimmer-30b":{"draws":26,"losses":1,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":25},"meta/muse-spark-1.3":{"draws":19,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":17,"losses":1,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":26},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":3,"wins":37},"o3":{"draws":16,"losses":16,"wins":38},"openai/gpt-oss-120b":{"draws":25,"losses":6,"wins":41},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":26},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":19,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":9},"qwen/qwen3.8-flash":{"draws":19,"losses":15,"wins":22},"qwen/qwen3.8-max":{"draws":21,"losses":13,"wins":38},"qwen/qwen3.8-max-0902":{"draws":20,"losses":34,"wins":34},"stealth/ox-alpha":{"draws":52,"losses":57,"wins":81},"stealth/space-bunny-alpha":{"draws":37,"losses":14,"wins":49},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":13},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":10,"losses":24,"wins":30},"thinkingmachines/inkling":{"draws":22,"losses":5,"wins":31},"thinkingmachines/inkling-small":{"draws":20,"losses":7,"wins":25},"x-ai/grok-4.5":{"draws":23,"losses":27,"wins":30},"x-ai/grok-4.6":{"draws":20,"losses":48,"wins":18},"x-ai/grok-4.7":{"draws":16,"losses":69,"wins":25},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":10},"xiaomi/mimo-v2.5":{"draws":55,"losses":14,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":13,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":35,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":45,"wins":25},"z-ai/glm-5.2":{"draws":35,"losses":18,"wins":57},"z-ai/glm-5.3":{"draws":26,"losses":25,"wins":11},"z-ai/glm-5.3-flash":{"draws":29,"losses":34,"wins":23},"z-ai/glm-5.3-flashx":{"draws":36,"losses":52,"wins":50}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":129,"losses":112,"wins":271},"claude-fable-5":{"draws":144,"losses":404,"wins":142},"claude-fable-5-1":{"draws":62,"losses":602,"wins":36},"claude-opus-4-5":{"draws":214,"losses":189,"wins":296},"claude-opus-4-8":{"draws":72,"losses":99,"wins":119},"claude-opus-5":{"draws":70,"losses":404,"wins":73},"claude-opus-5-5":{"draws":22,"losses":184,"wins":12},"claude-sonnet-5":{"draws":152,"losses":166,"wins":293},"claude-sonnet-5-5":{"draws":31,"losses":120,"wins":75},"cohere/north-mini-code":{"draws":27,"losses":18,"wins":93},"deepseek/deepseek-v4-flash":{"draws":215,"losses":133,"wins":333},"deepseek/deepseek-v4-pro":{"draws":175,"losses":171,"wins":220},"deepseek/deepseek-v4-pro-0813":{"draws":173,"losses":199,"wins":212},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":78,"wins":73},"fireworks/ember-1":{"draws":67,"losses":84,"wins":93},"gemini-3.1-pro-preview":{"draws":51,"losses":66,"wins":123},"google/gemini-3.1-flash-lite":{"draws":28,"losses":14,"wins":108},"google/gemini-3.5-flash":{"draws":163,"losses":235,"wins":277},"google/gemini-3.5-flash-lite":{"draws":263,"losses":207,"wins":539},"google/gemini-3.6-flash":{"draws":237,"losses":374,"wins":368},"google/gemini-3.8-flash":{"draws":147,"losses":289,"wins":204},"google/gemma-4-31b-it":{"draws":20,"losses":17,"wins":83},"gpt-4.1":{"draws":30,"losses":20,"wins":50},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":23},"gpt-5":{"draws":75,"losses":63,"wins":124},"gpt-5.4":{"draws":178,"losses":213,"wins":172},"gpt-5.4-mini":{"draws":66,"losses":35,"wins":95},"gpt-5.4-nano":{"draws":50,"losses":62,"wins":152},"gpt-5.5":{"draws":59,"losses":74,"wins":89},"gpt-5.6-luna":{"draws":181,"losses":125,"wins":221},"gpt-5.6-sol":{"draws":103,"losses":367,"wins":169},"gpt-5.6-terra":{"draws":213,"losses":176,"wins":255},"gpt-6-astra":{"draws":76,"losses":489,"wins":37},"gpt-6-luna":{"draws":63,"losses":99,"wins":116},"gpt-6-sol":{"draws":27,"losses":124,"wins":21},"gpt-6.1-sol":{"draws":27,"losses":181,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":41,"losses":4,"wins":37},"inception/mercury-2.5-preview":{"draws":122,"losses":43,"wins":202},"inclusionai/ling-3.0-flash":{"draws":67,"losses":32,"wins":139},"meituan/longcat-2.0":{"draws":106,"losses":71,"wins":265},"meta/muse-glimmer-30b":{"draws":159,"losses":65,"wins":264},"meta/muse-spark-1.2":{"draws":108,"losses":136,"wins":235},"meta/muse-spark-1.3":{"draws":131,"losses":224,"wins":218},"minimax/minimax-m3":{"draws":43,"losses":19,"wins":80},"mistralai/mistral-medium-3-5":{"draws":93,"losses":57,"wins":170},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":18,"wins":22},"moonshotai/kimi-k3":{"draws":171,"losses":197,"wins":237},"nex-agi/nex-n2-pro":{"draws":37,"losses":19,"wins":86},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":84,"losses":24,"wins":116},"o3":{"draws":70,"losses":224,"wins":290},"openai/gpt-oss-120b":{"draws":147,"losses":72,"wins":256},"poolside/laguna-s-2.1":{"draws":141,"losses":74,"wins":226},"qwen/qwen3.7-max":{"draws":41,"losses":35,"wins":82},"qwen/qwen3.7-plus":{"draws":24,"losses":16,"wins":84},"qwen/qwen3.8-2.4t-a95b":{"draws":160,"losses":200,"wins":234},"qwen/qwen3.8-27b":{"draws":83,"losses":119,"wins":153},"qwen/qwen3.8-flash":{"draws":121,"losses":138,"wins":166},"qwen/qwen3.8-max":{"draws":165,"losses":191,"wins":226},"qwen/qwen3.8-max-0902":{"draws":52,"losses":81,"wins":57},"stealth/ox-alpha":{"draws":508,"losses":883,"wins":883},"stealth/space-bunny-alpha":{"draws":51,"losses":45,"wins":96},"stepfun/step-3.7-flash":{"draws":38,"losses":37,"wins":95},"tencent/hy3-preview":{"draws":56,"losses":24,"wins":54},"tencent/hy4-preview":{"draws":162,"losses":257,"wins":198},"thinkingmachines/inkling":{"draws":120,"losses":82,"wins":291},"thinkingmachines/inkling-small":{"draws":210,"losses":94,"wins":304},"x-ai/grok-4.5":{"draws":116,"losses":229,"wins":193},"x-ai/grok-4.6":{"draws":196,"losses":307,"wins":219},"x-ai/grok-4.7":{"draws":22,"losses":148,"wins":28},"x-ai/grok-build-0.1":{"draws":35,"losses":13,"wins":84},"xiaomi/mimo-v2.5":{"draws":108,"losses":62,"wins":218},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":46,"wins":94},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":56,"wins":61},"xiaomi/mimo-v2.6-pro":{"draws":23,"losses":70,"wins":31},"z-ai/glm-5.2":{"draws":241,"losses":197,"wins":380},"z-ai/glm-5.3":{"draws":115,"losses":316,"wins":151},"z-ai/glm-5.3-flash":{"draws":162,"losses":295,"wins":256},"z-ai/glm-5.3-flashx":{"draws":35,"losses":107,"wins":66}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":15,"wins":21},"claude-fable-5":{"draws":21,"losses":25,"wins":4},"claude-fable-5-1":{"draws":3,"losses":68,"wins":1},"claude-opus-4-5":{"draws":29,"losses":28,"wins":13},"claude-opus-4-8":{"draws":17,"losses":27,"wins":8},"claude-opus-5":{"draws":14,"losses":77,"wins":7},"claude-opus-5-5":{"draws":3,"losses":99,"wins":0},"claude-sonnet-5":{"draws":15,"losses":31,"wins":16},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":24},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":29,"losses":14,"wins":33},"deepseek/deepseek-v4-pro":{"draws":10,"losses":22,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":18,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":47,"wins":21},"fireworks/ember-1":{"draws":36,"losses":55,"wins":23},"gemini-3.1-pro-preview":{"draws":36,"losses":44,"wins":34},"google/gemini-3.1-flash-lite":{"draws":15,"losses":7,"wins":20},"google/gemini-3.5-flash":{"draws":17,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":33,"losses":24,"wins":33},"google/gemini-3.6-flash":{"draws":29,"losses":60,"wins":21},"google/gemini-3.8-flash":{"draws":20,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":15},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":9,"losses":17,"wins":6},"gpt-5.4":{"draws":23,"losses":22,"wins":5},"gpt-5.4-mini":{"draws":19,"losses":10,"wins":21},"gpt-5.4-nano":{"draws":14,"losses":25,"wins":19},"gpt-5.5":{"draws":18,"losses":25,"wins":5},"gpt-5.6-luna":{"draws":31,"losses":15,"wins":14},"gpt-5.6-sol":{"draws":11,"losses":29,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":30,"wins":10},"gpt-6-astra":{"draws":5,"losses":51,"wins":0},"gpt-6-luna":{"draws":21,"losses":23,"wins":16},"gpt-6-sol":{"draws":13,"losses":76,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":100,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":21,"losses":3,"wins":16},"inclusionai/ling-3.0-flash":{"draws":18,"losses":8,"wins":20},"meituan/longcat-2.0":{"draws":28,"losses":14,"wins":31},"meta/muse-glimmer-30b":{"draws":17,"losses":13,"wins":14},"meta/muse-spark-1.2":{"draws":18,"losses":15,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":34,"wins":14},"minimax/minimax-m3":{"draws":15,"losses":9,"wins":18},"mistralai/mistral-medium-3-5":{"draws":15,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":21,"wins":11},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":13,"wins":21},"o3":{"draws":11,"losses":25,"wins":30},"openai/gpt-oss-120b":{"draws":18,"losses":18,"wins":26},"poolside/laguna-s-2.1":{"draws":20,"losses":16,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":15,"wins":13},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":27,"wins":17},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-flash":{"draws":14,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":18},"qwen/qwen3.8-max-0902":{"draws":37,"losses":49,"wins":14},"stealth/ox-alpha":{"draws":51,"losses":96,"wins":45},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":18},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":28,"wins":10},"thinkingmachines/inkling":{"draws":29,"losses":22,"wins":21},"thinkingmachines/inkling-small":{"draws":18,"losses":20,"wins":22},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":5},"x-ai/grok-4.7":{"draws":10,"losses":64,"wins":16},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":52,"losses":17,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":0,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":35,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":36,"wins":17},"z-ai/glm-5.2":{"draws":62,"losses":37,"wins":29},"z-ai/glm-5.3":{"draws":14,"losses":39,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":22,"wins":5},"z-ai/glm-5.3-flashx":{"draws":29,"losses":46,"wins":21}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":30,"wins":23},"claude-fable-5":{"draws":8,"losses":63,"wins":5},"claude-fable-5-1":{"draws":1,"losses":41,"wins":0},"claude-opus-4-5":{"draws":48,"losses":107,"wins":33},"claude-opus-4-8":{"draws":21,"losses":53,"wins":20},"claude-opus-5":{"draws":14,"losses":112,"wins":2},"claude-opus-5-5":{"draws":2,"losses":39,"wins":1},"claude-sonnet-5":{"draws":21,"losses":51,"wins":32},"claude-sonnet-5-5":{"draws":0,"losses":18,"wins":8},"cohere/north-mini-code":{"draws":20,"losses":8,"wins":26},"deepseek/deepseek-v4-flash":{"draws":37,"losses":44,"wins":43},"deepseek/deepseek-v4-pro":{"draws":23,"losses":48,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":27,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":6},"fireworks/ember-1":{"draws":0,"losses":12,"wins":4},"gemini-3.1-pro-preview":{"draws":4,"losses":17,"wins":9},"google/gemini-3.1-flash-lite":{"draws":18,"losses":11,"wins":53},"google/gemini-3.5-flash":{"draws":23,"losses":45,"wins":20},"google/gemini-3.5-flash-lite":{"draws":57,"losses":68,"wins":85},"google/gemini-3.6-flash":{"draws":40,"losses":130,"wins":21},"google/gemini-3.8-flash":{"draws":17,"losses":51,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":39},"gpt-4.1":{"draws":12,"losses":16,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":33,"losses":42,"wins":7},"gpt-5.4":{"draws":19,"losses":60,"wins":9},"gpt-5.4-mini":{"draws":25,"losses":17,"wins":16},"gpt-5.4-nano":{"draws":32,"losses":64,"wins":22},"gpt-5.5":{"draws":16,"losses":52,"wins":14},"gpt-5.6-luna":{"draws":25,"losses":31,"wins":30},"gpt-5.6-sol":{"draws":7,"losses":56,"wins":15},"gpt-5.6-terra":{"draws":22,"losses":42,"wins":14},"gpt-6-astra":{"draws":2,"losses":42,"wins":0},"gpt-6-luna":{"draws":13,"losses":31,"wins":10},"gpt-6-sol":{"draws":5,"losses":36,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":7,"wins":34},"inclusionai/ling-3.0-flash":{"draws":26,"losses":17,"wins":37},"meituan/longcat-2.0":{"draws":31,"losses":50,"wins":53},"meta/muse-glimmer-30b":{"draws":24,"losses":21,"wins":9},"meta/muse-spark-1.2":{"draws":4,"losses":44,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":55,"wins":8},"minimax/minimax-m3":{"draws":19,"losses":21,"wins":14},"mistralai/mistral-medium-3-5":{"draws":12,"losses":10,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":14,"wins":5},"moonshotai/kimi-k3":{"draws":29,"losses":69,"wins":14},"nex-agi/nex-n2-pro":{"draws":18,"losses":22,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":32,"wins":30},"o3":{"draws":45,"losses":125,"wins":56},"openai/gpt-oss-120b":{"draws":18,"losses":21,"wins":25},"poolside/laguna-s-2.1":{"draws":36,"losses":28,"wins":40},"qwen/qwen3.7-max":{"draws":24,"losses":29,"wins":11},"qwen/qwen3.7-plus":{"draws":20,"losses":29,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":32,"wins":12},"qwen/qwen3.8-27b":{"draws":7,"losses":27,"wins":14},"qwen/qwen3.8-flash":{"draws":17,"losses":22,"wins":13},"qwen/qwen3.8-max":{"draws":14,"losses":33,"wins":5},"qwen/qwen3.8-max-0902":{"draws":9,"losses":13,"wins":4},"stealth/ox-alpha":{"draws":38,"losses":95,"wins":37},"stealth/space-bunny-alpha":{"draws":2,"losses":10,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":12,"wins":12},"tencent/hy3-preview":{"draws":20,"losses":13,"wins":15},"tencent/hy4-preview":{"draws":15,"losses":35,"wins":10},"thinkingmachines/inkling":{"draws":32,"losses":39,"wins":63},"thinkingmachines/inkling-small":{"draws":26,"losses":22,"wins":22},"x-ai/grok-4.5":{"draws":20,"losses":83,"wins":19},"x-ai/grok-4.6":{"draws":13,"losses":52,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":18,"losses":21,"wins":5},"xiaomi/mimo-v2.5":{"draws":66,"losses":54,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":31,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":4},"z-ai/glm-5.2":{"draws":44,"losses":66,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":43,"wins":4},"z-ai/glm-5.3-flash":{"draws":29,"losses":40,"wins":9},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":6}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":16,"wins":17},"claude-fable-5":{"draws":16,"losses":31,"wins":5},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-opus-4-5":{"draws":57,"losses":53,"wins":24},"claude-opus-4-8":{"draws":32,"losses":41,"wins":17},"claude-opus-5":{"draws":33,"losses":127,"wins":14},"claude-opus-5-5":{"draws":3,"losses":39,"wins":0},"claude-sonnet-5":{"draws":22,"losses":24,"wins":16},"claude-sonnet-5-5":{"draws":14,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":12,"losses":8,"wins":28},"deepseek/deepseek-v4-flash":{"draws":38,"losses":34,"wins":46},"deepseek/deepseek-v4-pro":{"draws":21,"losses":16,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":18,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":7,"wins":4},"fireworks/ember-1":{"draws":12,"losses":12,"wins":4},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":12},"google/gemini-3.1-flash-lite":{"draws":24,"losses":20,"wins":30},"google/gemini-3.5-flash":{"draws":22,"losses":19,"wins":15},"google/gemini-3.5-flash-lite":{"draws":46,"losses":19,"wins":33},"google/gemini-3.6-flash":{"draws":42,"losses":46,"wins":26},"google/gemini-3.8-flash":{"draws":28,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":20,"losses":11,"wins":25},"gpt-4.1":{"draws":27,"losses":17,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":36,"losses":35,"wins":29},"gpt-5.4":{"draws":19,"losses":20,"wins":11},"gpt-5.4-mini":{"draws":26,"losses":14,"wins":16},"gpt-5.4-nano":{"draws":25,"losses":22,"wins":39},"gpt-5.5":{"draws":49,"losses":40,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":4},"gpt-5.6-terra":{"draws":23,"losses":16,"wins":9},"gpt-6-astra":{"draws":4,"losses":36,"wins":0},"gpt-6-luna":{"draws":14,"losses":23,"wins":11},"gpt-6-sol":{"draws":6,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":20,"losses":13,"wins":9},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":27},"meituan/longcat-2.0":{"draws":34,"losses":26,"wins":28},"meta/muse-glimmer-30b":{"draws":20,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":9},"meta/muse-spark-1.3":{"draws":7,"losses":29,"wins":6},"minimax/minimax-m3":{"draws":32,"losses":16,"wins":32},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":8},"moonshotai/kimi-k3":{"draws":23,"losses":26,"wins":5},"nex-agi/nex-n2-pro":{"draws":32,"losses":16,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":65,"losses":18,"wins":27},"o3":{"draws":26,"losses":38,"wins":36},"openai/gpt-oss-120b":{"draws":24,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":23,"losses":19,"wins":24},"qwen/qwen3.7-max":{"draws":32,"losses":29,"wins":15},"qwen/qwen3.7-plus":{"draws":28,"losses":15,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":22,"wins":9},"qwen/qwen3.8-27b":{"draws":14,"losses":26,"wins":8},"qwen/qwen3.8-flash":{"draws":20,"losses":14,"wins":14},"qwen/qwen3.8-max":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.8-max-0902":{"draws":8,"losses":9,"wins":5},"stealth/ox-alpha":{"draws":56,"losses":54,"wins":24},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":8},"stepfun/step-3.7-flash":{"draws":20,"losses":15,"wins":13},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":32,"losses":31,"wins":35},"thinkingmachines/inkling-small":{"draws":26,"losses":10,"wins":20},"x-ai/grok-4.5":{"draws":24,"losses":51,"wins":11},"x-ai/grok-4.6":{"draws":26,"losses":37,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":6,"wins":15},"xiaomi/mimo-v2.5":{"draws":71,"losses":38,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":22,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":0},"z-ai/glm-5.2":{"draws":64,"losses":48,"wins":46},"z-ai/glm-5.3":{"draws":10,"losses":22,"wins":4},"z-ai/glm-5.3-flash":{"draws":19,"losses":38,"wins":7},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":6}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":61,"losses":28,"wins":87},"claude-fable-5":{"draws":34,"losses":121,"wins":51},"claude-fable-5-1":{"draws":6,"losses":180,"wins":16},"claude-opus-4-5":{"draws":64,"losses":64,"wins":104},"claude-opus-4-8":{"draws":20,"losses":29,"wins":37},"claude-opus-5":{"draws":18,"losses":131,"wins":17},"claude-opus-5-5":{"draws":5,"losses":58,"wins":9},"claude-sonnet-5":{"draws":61,"losses":44,"wins":79},"claude-sonnet-5-5":{"draws":6,"losses":27,"wins":19},"cohere/north-mini-code":{"draws":13,"losses":3,"wins":26},"deepseek/deepseek-v4-flash":{"draws":70,"losses":38,"wins":110},"deepseek/deepseek-v4-pro":{"draws":55,"losses":51,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":45,"losses":53,"wins":70},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":22,"wins":34},"fireworks/ember-1":{"draws":24,"losses":20,"wins":28},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":36},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":41},"google/gemini-3.5-flash":{"draws":41,"losses":62,"wins":97},"google/gemini-3.5-flash-lite":{"draws":101,"losses":67,"wins":154},"google/gemini-3.6-flash":{"draws":84,"losses":130,"wins":132},"google/gemini-3.8-flash":{"draws":40,"losses":62,"wins":66},"google/gemma-4-31b-it":{"draws":6,"losses":3,"wins":25},"gpt-4.1":{"draws":6,"losses":11,"wins":19},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":28,"losses":19,"wins":27},"gpt-5.4":{"draws":43,"losses":63,"wins":56},"gpt-5.4-mini":{"draws":30,"losses":8,"wins":26},"gpt-5.4-nano":{"draws":17,"losses":15,"wins":48},"gpt-5.5":{"draws":25,"losses":27,"wins":30},"gpt-5.6-luna":{"draws":60,"losses":32,"wins":92},"gpt-5.6-sol":{"draws":30,"losses":105,"wins":65},"gpt-5.6-terra":{"draws":57,"losses":47,"wins":86},"gpt-6-astra":{"draws":18,"losses":150,"wins":12},"gpt-6-luna":{"draws":16,"losses":24,"wins":38},"gpt-6-sol":{"draws":6,"losses":36,"wins":16},"gpt-6.1-sol":{"draws":2,"losses":52,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":50,"losses":9,"wins":57},"inclusionai/ling-3.0-flash":{"draws":27,"losses":7,"wins":42},"meituan/longcat-2.0":{"draws":36,"losses":16,"wins":76},"meta/muse-glimmer-30b":{"draws":61,"losses":15,"wins":76},"meta/muse-spark-1.2":{"draws":27,"losses":39,"wins":62},"meta/muse-spark-1.3":{"draws":39,"losses":62,"wins":75},"minimax/minimax-m3":{"draws":13,"losses":7,"wins":34},"mistralai/mistral-medium-3-5":{"draws":40,"losses":7,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":5,"wins":11},"moonshotai/kimi-k3":{"draws":55,"losses":67,"wins":48},"nex-agi/nex-n2-pro":{"draws":13,"losses":3,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":7,"wins":43},"o3":{"draws":37,"losses":64,"wins":111},"openai/gpt-oss-120b":{"draws":50,"losses":25,"wins":59},"poolside/laguna-s-2.1":{"draws":53,"losses":21,"wins":54},"qwen/qwen3.7-max":{"draws":11,"losses":11,"wins":28},"qwen/qwen3.7-plus":{"draws":13,"losses":6,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":56,"losses":58,"wins":72},"qwen/qwen3.8-27b":{"draws":27,"losses":26,"wins":49},"qwen/qwen3.8-flash":{"draws":37,"losses":41,"wins":52},"qwen/qwen3.8-max":{"draws":50,"losses":61,"wins":83},"qwen/qwen3.8-max-0902":{"draws":10,"losses":30,"wins":24},"stealth/ox-alpha":{"draws":162,"losses":198,"wins":257},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":28},"stepfun/step-3.7-flash":{"draws":15,"losses":10,"wins":35},"tencent/hy3-preview":{"draws":16,"losses":10,"wins":22},"tencent/hy4-preview":{"draws":20,"losses":34,"wins":34},"thinkingmachines/inkling":{"draws":64,"losses":23,"wins":83},"thinkingmachines/inkling-small":{"draws":71,"losses":20,"wins":97},"x-ai/grok-4.5":{"draws":35,"losses":61,"wins":72},"x-ai/grok-4.6":{"draws":61,"losses":86,"wins":53},"x-ai/grok-4.7":{"draws":3,"losses":48,"wins":19},"x-ai/grok-build-0.1":{"draws":17,"losses":2,"wins":23},"xiaomi/mimo-v2.5":{"draws":46,"losses":7,"wins":91},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":15,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":15},"z-ai/glm-5.2":{"draws":78,"losses":50,"wins":110},"z-ai/glm-5.3":{"draws":28,"losses":116,"wins":34},"z-ai/glm-5.3-flash":{"draws":47,"losses":89,"wins":62},"z-ai/glm-5.3-flashx":{"draws":9,"losses":23,"wins":30}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":55,"losses":77,"wins":42},"claude-fable-5":{"draws":30,"losses":113,"wins":7},"claude-fable-5-1":{"draws":11,"losses":125,"wins":0},"claude-opus-4-5":{"draws":126,"losses":181,"wins":57},"claude-opus-4-8":{"draws":35,"losses":90,"wins":21},"claude-opus-5":{"draws":30,"losses":213,"wins":25},"claude-opus-5-5":{"draws":3,"losses":75,"wins":0},"claude-sonnet-5":{"draws":76,"losses":128,"wins":34},"claude-sonnet-5-5":{"draws":20,"losses":45,"wins":9},"cohere/north-mini-code":{"draws":22,"losses":29,"wins":33},"deepseek/deepseek-v4-flash":{"draws":86,"losses":85,"wins":91},"deepseek/deepseek-v4-pro":{"draws":54,"losses":78,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":59,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":35,"wins":14},"fireworks/ember-1":{"draws":32,"losses":38,"wins":10},"gemini-3.1-pro-preview":{"draws":24,"losses":33,"wins":17},"google/gemini-3.1-flash-lite":{"draws":39,"losses":34,"wins":63},"google/gemini-3.5-flash":{"draws":50,"losses":85,"wins":41},"google/gemini-3.5-flash-lite":{"draws":209,"losses":223,"wins":162},"google/gemini-3.6-flash":{"draws":193,"losses":284,"wins":83},"google/gemini-3.8-flash":{"draws":42,"losses":79,"wins":13},"google/gemma-4-31b-it":{"draws":20,"losses":28,"wins":32},"gpt-4.1":{"draws":14,"losses":17,"wins":29},"gpt-4.1-nano":{"draws":0,"losses":14,"wins":0},"gpt-5":{"draws":45,"losses":62,"wins":29},"gpt-5.4":{"draws":54,"losses":121,"wins":39},"gpt-5.4-mini":{"draws":44,"losses":35,"wins":27},"gpt-5.4-nano":{"draws":24,"losses":68,"wins":50},"gpt-5.5":{"draws":45,"losses":91,"wins":32},"gpt-5.6-luna":{"draws":88,"losses":107,"wins":55},"gpt-5.6-sol":{"draws":33,"losses":162,"wins":15},"gpt-5.6-terra":{"draws":54,"losses":83,"wins":29},"gpt-6-astra":{"draws":6,"losses":116,"wins":2},"gpt-6-luna":{"draws":27,"losses":48,"wins":23},"gpt-6-sol":{"draws":6,"losses":59,"wins":1},"gpt-6.1-sol":{"draws":7,"losses":76,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":14},"inception/mercury-2.5-preview":{"draws":57,"losses":25,"wins":36},"inclusionai/ling-3.0-flash":{"draws":69,"losses":55,"wins":62},"meituan/longcat-2.0":{"draws":69,"losses":87,"wins":110},"meta/muse-glimmer-30b":{"draws":68,"losses":51,"wins":43},"meta/muse-spark-1.2":{"draws":56,"losses":90,"wins":24},"meta/muse-spark-1.3":{"draws":39,"losses":67,"wins":16},"minimax/minimax-m3":{"draws":23,"losses":41,"wins":42},"mistralai/mistral-medium-3-5":{"draws":37,"losses":17,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":32,"wins":14},"moonshotai/kimi-k3":{"draws":111,"losses":137,"wins":32},"nex-agi/nex-n2-pro":{"draws":26,"losses":28,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":65,"losses":55,"wins":50},"o3":{"draws":69,"losses":202,"wins":76},"openai/gpt-oss-120b":{"draws":48,"losses":41,"wins":45},"poolside/laguna-s-2.1":{"draws":97,"losses":96,"wins":69},"qwen/qwen3.7-max":{"draws":40,"losses":54,"wins":14},"qwen/qwen3.7-plus":{"draws":26,"losses":43,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":63,"wins":24},"qwen/qwen3.8-27b":{"draws":24,"losses":58,"wins":14},"qwen/qwen3.8-flash":{"draws":41,"losses":56,"wins":23},"qwen/qwen3.8-max":{"draws":51,"losses":73,"wins":30},"qwen/qwen3.8-max-0902":{"draws":22,"losses":31,"wins":5},"stealth/ox-alpha":{"draws":120,"losses":291,"wins":82},"stealth/space-bunny-alpha":{"draws":29,"losses":21,"wins":22},"stepfun/step-3.7-flash":{"draws":32,"losses":63,"wins":39},"tencent/hy3-preview":{"draws":32,"losses":35,"wins":31},"tencent/hy4-preview":{"draws":64,"losses":83,"wins":23},"thinkingmachines/inkling":{"draws":58,"losses":63,"wins":63},"thinkingmachines/inkling-small":{"draws":58,"losses":38,"wins":62},"x-ai/grok-4.5":{"draws":91,"losses":154,"wins":45},"x-ai/grok-4.6":{"draws":53,"losses":79,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":49,"wins":2},"x-ai/grok-build-0.1":{"draws":24,"losses":23,"wins":15},"xiaomi/mimo-v2.5":{"draws":88,"losses":113,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":52,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":29,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":2},"z-ai/glm-5.2":{"draws":105,"losses":108,"wins":71},"z-ai/glm-5.3":{"draws":33,"losses":85,"wins":12},"z-ai/glm-5.3-flash":{"draws":51,"losses":97,"wins":24},"z-ai/glm-5.3-flashx":{"draws":20,"losses":51,"wins":7}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":72,"losses":81,"wins":43},"claude-fable-5":{"draws":44,"losses":105,"wins":17},"claude-fable-5-1":{"draws":9,"losses":148,"wins":1},"claude-opus-4-5":{"draws":77,"losses":117,"wins":33},"claude-opus-4-8":{"draws":25,"losses":49,"wins":6},"claude-opus-5":{"draws":17,"losses":116,"wins":9},"claude-opus-5-5":{"draws":7,"losses":61,"wins":0},"claude-sonnet-5":{"draws":57,"losses":108,"wins":37},"claude-sonnet-5-5":{"draws":17,"losses":52,"wins":7},"cohere/north-mini-code":{"draws":21,"losses":9,"wins":18},"deepseek/deepseek-v4-flash":{"draws":117,"losses":97,"wins":42},"deepseek/deepseek-v4-pro":{"draws":84,"losses":87,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":69,"losses":88,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":28,"wins":6},"fireworks/ember-1":{"draws":31,"losses":49,"wins":4},"gemini-3.1-pro-preview":{"draws":25,"losses":39,"wins":14},"google/gemini-3.1-flash-lite":{"draws":18,"losses":17,"wins":27},"google/gemini-3.5-flash":{"draws":63,"losses":94,"wins":35},"google/gemini-3.5-flash-lite":{"draws":140,"losses":131,"wins":107},"google/gemini-3.6-flash":{"draws":114,"losses":140,"wins":54},"google/gemini-3.8-flash":{"draws":59,"losses":92,"wins":21},"google/gemma-4-31b-it":{"draws":8,"losses":11,"wins":13},"gpt-4.1":{"draws":14,"losses":8,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":10,"wins":0},"gpt-5":{"draws":41,"losses":40,"wins":11},"gpt-5.4":{"draws":77,"losses":72,"wins":18},"gpt-5.4-mini":{"draws":32,"losses":13,"wins":15},"gpt-5.4-nano":{"draws":34,"losses":29,"wins":27},"gpt-5.5":{"draws":24,"losses":42,"wins":6},"gpt-5.6-luna":{"draws":73,"losses":60,"wins":57},"gpt-5.6-sol":{"draws":28,"losses":116,"wins":23},"gpt-5.6-terra":{"draws":70,"losses":102,"wins":36},"gpt-6-astra":{"draws":14,"losses":134,"wins":0},"gpt-6-luna":{"draws":19,"losses":45,"wins":14},"gpt-6-sol":{"draws":13,"losses":47,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":73,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":18,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":76,"losses":35,"wins":49},"inclusionai/ling-3.0-flash":{"draws":37,"losses":18,"wins":36},"meituan/longcat-2.0":{"draws":47,"losses":52,"wins":50},"meta/muse-glimmer-30b":{"draws":99,"losses":67,"wins":40},"meta/muse-spark-1.2":{"draws":37,"losses":74,"wins":27},"meta/muse-spark-1.3":{"draws":59,"losses":87,"wins":16},"minimax/minimax-m3":{"draws":17,"losses":14,"wins":13},"mistralai/mistral-medium-3-5":{"draws":58,"losses":24,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":68,"losses":86,"wins":24},"nex-agi/nex-n2-pro":{"draws":19,"losses":13,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":14,"wins":18},"o3":{"draws":68,"losses":108,"wins":57},"openai/gpt-oss-120b":{"draws":83,"losses":56,"wins":39},"poolside/laguna-s-2.1":{"draws":78,"losses":59,"wins":24},"qwen/qwen3.7-max":{"draws":24,"losses":21,"wins":13},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":64,"losses":99,"wins":19},"qwen/qwen3.8-27b":{"draws":29,"losses":79,"wins":14},"qwen/qwen3.8-flash":{"draws":63,"losses":47,"wins":24},"qwen/qwen3.8-max":{"draws":118,"losses":121,"wins":80},"qwen/qwen3.8-max-0902":{"draws":20,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":210,"losses":304,"wins":94},"stealth/space-bunny-alpha":{"draws":18,"losses":22,"wins":20},"stepfun/step-3.7-flash":{"draws":26,"losses":22,"wins":22},"tencent/hy3-preview":{"draws":26,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":71,"losses":97,"wins":20},"thinkingmachines/inkling":{"draws":58,"losses":62,"wins":38},"thinkingmachines/inkling-small":{"draws":96,"losses":70,"wins":70},"x-ai/grok-4.5":{"draws":45,"losses":101,"wins":27},"x-ai/grok-4.6":{"draws":70,"losses":105,"wins":25},"x-ai/grok-4.7":{"draws":7,"losses":47,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":9,"wins":9},"xiaomi/mimo-v2.5":{"draws":63,"losses":27,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":23,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":118,"losses":114,"wins":62},"z-ai/glm-5.3":{"draws":32,"losses":90,"wins":14},"z-ai/glm-5.3-flash":{"draws":73,"losses":108,"wins":37},"z-ai/glm-5.3-flashx":{"draws":22,"losses":26,"wins":10}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":26,"wins":94},"claude-fable-5":{"draws":27,"losses":100,"wins":63},"claude-fable-5-1":{"draws":5,"losses":162,"wins":13},"claude-opus-4-5":{"draws":127,"losses":103,"wins":166},"claude-opus-4-8":{"draws":48,"losses":59,"wins":59},"claude-opus-5":{"draws":49,"losses":226,"wins":69},"claude-opus-5-5":{"draws":12,"losses":84,"wins":8},"claude-sonnet-5":{"draws":95,"losses":54,"wins":135},"claude-sonnet-5-5":{"draws":8,"losses":27,"wins":19},"cohere/north-mini-code":{"draws":13,"losses":4,"wins":59},"deepseek/deepseek-v4-flash":{"draws":50,"losses":50,"wins":130},"deepseek/deepseek-v4-pro":{"draws":43,"losses":59,"wins":64},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":58,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":30,"wins":34},"fireworks/ember-1":{"draws":12,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":13,"losses":12,"wins":31},"google/gemini-3.1-flash-lite":{"draws":20,"losses":3,"wins":77},"google/gemini-3.5-flash":{"draws":43,"losses":69,"wins":82},"google/gemini-3.5-flash-lite":{"draws":157,"losses":116,"wins":321},"google/gemini-3.6-flash":{"draws":122,"losses":252,"wins":238},"google/gemini-3.8-flash":{"draws":34,"losses":60,"wins":82},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":43},"gpt-4.1":{"draws":15,"losses":11,"wins":24},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":23,"losses":34,"wins":67},"gpt-5.4":{"draws":63,"losses":130,"wins":88},"gpt-5.4-mini":{"draws":34,"losses":9,"wins":49},"gpt-5.4-nano":{"draws":26,"losses":44,"wins":90},"gpt-5.5":{"draws":51,"losses":56,"wins":63},"gpt-5.6-luna":{"draws":72,"losses":88,"wins":108},"gpt-5.6-sol":{"draws":32,"losses":157,"wins":91},"gpt-5.6-terra":{"draws":51,"losses":46,"wins":99},"gpt-6-astra":{"draws":9,"losses":151,"wins":16},"gpt-6-luna":{"draws":29,"losses":31,"wins":42},"gpt-6-sol":{"draws":18,"losses":56,"wins":18},"gpt-6.1-sol":{"draws":3,"losses":47,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":11},"inception/mercury-2.5-preview":{"draws":51,"losses":5,"wins":62},"inclusionai/ling-3.0-flash":{"draws":55,"losses":19,"wins":122},"meituan/longcat-2.0":{"draws":71,"losses":54,"wins":167},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":75},"meta/muse-spark-1.2":{"draws":45,"losses":52,"wins":97},"meta/muse-spark-1.3":{"draws":23,"losses":74,"wins":61},"minimax/minimax-m3":{"draws":16,"losses":7,"wins":63},"mistralai/mistral-medium-3-5":{"draws":29,"losses":14,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":4,"wins":26},"moonshotai/kimi-k3":{"draws":109,"losses":101,"wins":124},"nex-agi/nex-n2-pro":{"draws":23,"losses":4,"wins":59},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":10,"wins":77},"o3":{"draws":31,"losses":107,"wins":220},"openai/gpt-oss-120b":{"draws":51,"losses":16,"wins":75},"poolside/laguna-s-2.1":{"draws":84,"losses":44,"wins":154},"qwen/qwen3.7-max":{"draws":30,"losses":22,"wins":50},"qwen/qwen3.7-plus":{"draws":24,"losses":11,"wins":61},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":62,"wins":72},"qwen/qwen3.8-27b":{"draws":10,"losses":44,"wins":54},"qwen/qwen3.8-flash":{"draws":29,"losses":28,"wins":55},"qwen/qwen3.8-max":{"draws":51,"losses":62,"wins":72},"qwen/qwen3.8-max-0902":{"draws":23,"losses":30,"wins":27},"stealth/ox-alpha":{"draws":116,"losses":193,"wins":229},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":20,"losses":19,"wins":83},"tencent/hy3-preview":{"draws":24,"losses":11,"wins":51},"tencent/hy4-preview":{"draws":35,"losses":72,"wins":61},"thinkingmachines/inkling":{"draws":91,"losses":45,"wins":154},"thinkingmachines/inkling-small":{"draws":45,"losses":27,"wins":101},"x-ai/grok-4.5":{"draws":54,"losses":53,"wins":53},"x-ai/grok-4.6":{"draws":55,"losses":72,"wins":65},"x-ai/grok-4.7":{"draws":12,"losses":32,"wins":14},"x-ai/grok-build-0.1":{"draws":19,"losses":5,"wins":38},"xiaomi/mimo-v2.5":{"draws":75,"losses":23,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":38,"wins":57},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":22,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":22,"wins":13},"z-ai/glm-5.2":{"draws":83,"losses":77,"wins":142},"z-ai/glm-5.3":{"draws":38,"losses":104,"wins":34},"z-ai/glm-5.3-flash":{"draws":29,"losses":82,"wins":67},"z-ai/glm-5.3-flashx":{"draws":24,"losses":46,"wins":26}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":25,"wins":95},"claude-fable-5":{"draws":57,"losses":104,"wins":81},"claude-fable-5-1":{"draws":15,"losses":193,"wins":34},"claude-opus-4-5":{"draws":70,"losses":48,"wins":138},"claude-opus-4-8":{"draws":25,"losses":34,"wins":43},"claude-opus-5":{"draws":26,"losses":142,"wins":51},"claude-opus-5-5":{"draws":11,"losses":89,"wins":10},"claude-sonnet-5":{"draws":58,"losses":51,"wins":105},"claude-sonnet-5-5":{"draws":6,"losses":22,"wins":18},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":37},"deepseek/deepseek-v4-flash":{"draws":68,"losses":25,"wins":145},"deepseek/deepseek-v4-pro":{"draws":51,"losses":43,"wins":104},"deepseek/deepseek-v4-pro-0813":{"draws":66,"losses":46,"wins":84},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":23,"wins":42},"fireworks/ember-1":{"draws":15,"losses":12,"wins":21},"gemini-3.1-pro-preview":{"draws":12,"losses":9,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":42},"google/gemini-3.5-flash":{"draws":64,"losses":44,"wins":132},"google/gemini-3.5-flash-lite":{"draws":97,"losses":44,"wins":195},"google/gemini-3.6-flash":{"draws":88,"losses":99,"wins":141},"google/gemini-3.8-flash":{"draws":58,"losses":73,"wins":81},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":32},"gpt-4.1":{"draws":17,"losses":5,"wins":22},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":6},"gpt-5":{"draws":28,"losses":18,"wins":56},"gpt-5.4":{"draws":66,"losses":77,"wins":73},"gpt-5.4-mini":{"draws":24,"losses":7,"wins":45},"gpt-5.4-nano":{"draws":17,"losses":16,"wins":69},"gpt-5.5":{"draws":28,"losses":22,"wins":44},"gpt-5.6-luna":{"draws":54,"losses":37,"wins":103},"gpt-5.6-sol":{"draws":43,"losses":101,"wins":90},"gpt-5.6-terra":{"draws":68,"losses":36,"wins":122},"gpt-6-astra":{"draws":20,"losses":191,"wins":21},"gpt-6-luna":{"draws":31,"losses":15,"wins":58},"gpt-6-sol":{"draws":19,"losses":59,"wins":22},"gpt-6.1-sol":{"draws":8,"losses":43,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":1,"wins":17},"inception/mercury-2.5-preview":{"draws":43,"losses":15,"wins":72},"inclusionai/ling-3.0-flash":{"draws":27,"losses":6,"wins":53},"meituan/longcat-2.0":{"draws":46,"losses":20,"wins":91},"meta/muse-glimmer-30b":{"draws":55,"losses":15,"wins":78},"meta/muse-spark-1.2":{"draws":30,"losses":32,"wins":88},"meta/muse-spark-1.3":{"draws":43,"losses":69,"wins":84},"minimax/minimax-m3":{"draws":20,"losses":3,"wins":43},"mistralai/mistral-medium-3-5":{"draws":37,"losses":5,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":5,"wins":13},"moonshotai/kimi-k3":{"draws":70,"losses":48,"wins":84},"nex-agi/nex-n2-pro":{"draws":14,"losses":2,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":5,"wins":49},"o3":{"draws":43,"losses":49,"wins":134},"openai/gpt-oss-120b":{"draws":50,"losses":19,"wins":83},"poolside/laguna-s-2.1":{"draws":43,"losses":17,"wins":90},"qwen/qwen3.7-max":{"draws":13,"losses":8,"wins":33},"qwen/qwen3.7-plus":{"draws":16,"losses":3,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":69,"wins":86},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":47},"qwen/qwen3.8-flash":{"draws":53,"losses":25,"wins":64},"qwen/qwen3.8-max":{"draws":57,"losses":59,"wins":98},"qwen/qwen3.8-max-0902":{"draws":20,"losses":18,"wins":48},"stealth/ox-alpha":{"draws":196,"losses":219,"wins":307},"stealth/space-bunny-alpha":{"draws":14,"losses":5,"wins":17},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":52},"tencent/hy3-preview":{"draws":26,"losses":5,"wins":37},"tencent/hy4-preview":{"draws":61,"losses":53,"wins":86},"thinkingmachines/inkling":{"draws":53,"losses":18,"wins":79},"thinkingmachines/inkling-small":{"draws":70,"losses":25,"wins":105},"x-ai/grok-4.5":{"draws":55,"losses":65,"wins":72},"x-ai/grok-4.6":{"draws":46,"losses":37,"wins":37},"x-ai/grok-4.7":{"draws":8,"losses":39,"wins":15},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":59,"losses":11,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":8,"wins":47},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":18,"wins":25},"z-ai/glm-5.2":{"draws":86,"losses":48,"wins":166},"z-ai/glm-5.3":{"draws":41,"losses":106,"wins":69},"z-ai/glm-5.3-flash":{"draws":58,"losses":90,"wins":86},"z-ai/glm-5.3-flashx":{"draws":23,"losses":25,"wins":42}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":48},"claude-fable-5":{"draws":3,"losses":20,"wins":27},"claude-fable-5-1":{"draws":5,"losses":46,"wins":17},"claude-opus-4-5":{"draws":11,"losses":9,"wins":80},"claude-opus-4-8":{"draws":13,"losses":11,"wins":32},"claude-opus-5":{"draws":12,"losses":39,"wins":51},"claude-opus-5-5":{"draws":10,"losses":90,"wins":28},"claude-sonnet-5":{"draws":7,"losses":10,"wins":51},"claude-sonnet-5-5":{"draws":13,"losses":44,"wins":59},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":27},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":88},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":4,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":28,"wins":67},"fireworks/ember-1":{"draws":11,"losses":23,"wins":82},"gemini-3.1-pro-preview":{"draws":12,"losses":23,"wins":79},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":50},"google/gemini-3.5-flash":{"draws":7,"losses":10,"wins":55},"google/gemini-3.5-flash-lite":{"draws":7,"losses":15,"wins":82},"google/gemini-3.6-flash":{"draws":2,"losses":31,"wins":79},"google/gemini-3.8-flash":{"draws":5,"losses":13,"wins":44},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":24},"gpt-4.1":{"draws":4,"losses":0,"wins":20},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":7,"wins":31},"gpt-5.4":{"draws":10,"losses":10,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":39},"gpt-5.4-nano":{"draws":15,"losses":5,"wins":52},"gpt-5.5":{"draws":8,"losses":19,"wins":49},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":51},"gpt-5.6-sol":{"draws":9,"losses":15,"wins":42},"gpt-5.6-terra":{"draws":11,"losses":10,"wins":41},"gpt-6-astra":{"draws":6,"losses":35,"wins":9},"gpt-6-luna":{"draws":8,"losses":18,"wins":56},"gpt-6-sol":{"draws":13,"losses":50,"wins":59},"gpt-6.1-sol":{"draws":5,"losses":65,"wins":40},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":13},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":40},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":47},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":62},"meta/muse-glimmer-30b":{"draws":2,"losses":7,"wins":51},"meta/muse-spark-1.2":{"draws":1,"losses":11,"wins":38},"meta/muse-spark-1.3":{"draws":7,"losses":10,"wins":39},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":30},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":44},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":60},"o3":{"draws":5,"losses":6,"wins":65},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":55},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":46},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":31},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":50},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":12},"qwen/qwen3.8-flash":{"draws":2,"losses":7,"wins":29},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":53},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":69},"stealth/ox-alpha":{"draws":22,"losses":28,"wins":148},"stealth/space-bunny-alpha":{"draws":10,"losses":16,"wins":64},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":35},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":3,"losses":19,"wins":48},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":49},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":47},"x-ai/grok-4.5":{"draws":12,"losses":14,"wins":32},"x-ai/grok-4.6":{"draws":8,"losses":15,"wins":39},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":29},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":49},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":18,"wins":50},"z-ai/glm-5.2":{"draws":13,"losses":15,"wins":106},"z-ai/glm-5.3":{"draws":13,"losses":23,"wins":42},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":30},"z-ai/glm-5.3-flashx":{"draws":14,"losses":27,"wins":77}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":16,"wins":4},"claude-fable-5":{"draws":8,"losses":29,"wins":7},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-opus-4-5":{"draws":38,"losses":55,"wins":13},"claude-opus-4-8":{"draws":22,"losses":47,"wins":13},"claude-opus-5":{"draws":16,"losses":69,"wins":7},"claude-opus-5-5":{"draws":0,"losses":20,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":16,"losses":7,"wins":23},"deepseek/deepseek-v4-flash":{"draws":34,"losses":29,"wins":19},"deepseek/deepseek-v4-pro":{"draws":12,"losses":15,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":22,"wins":2},"fireworks/ember-1":{"draws":6,"losses":7,"wins":3},"gemini-3.1-pro-preview":{"draws":11,"losses":1,"wins":8},"google/gemini-3.1-flash-lite":{"draws":19,"losses":9,"wins":32},"google/gemini-3.5-flash":{"draws":15,"losses":31,"wins":6},"google/gemini-3.5-flash-lite":{"draws":30,"losses":23,"wins":29},"google/gemini-3.6-flash":{"draws":23,"losses":41,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":23,"wins":1},"google/gemma-4-31b-it":{"draws":15,"losses":9,"wins":22},"gpt-4.1":{"draws":11,"losses":11,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":21,"losses":30,"wins":13},"gpt-5.4":{"draws":4,"losses":20,"wins":2},"gpt-5.4-mini":{"draws":26,"losses":20,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":49,"wins":25},"gpt-5.5":{"draws":43,"losses":19,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":2},"gpt-5.6-sol":{"draws":7,"losses":20,"wins":3},"gpt-5.6-terra":{"draws":14,"losses":22,"wins":6},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":12,"losses":13,"wins":3},"gpt-6-sol":{"draws":5,"losses":15,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":32},"meituan/longcat-2.0":{"draws":21,"losses":25,"wins":26},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":24,"wins":6},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":21},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":21,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":14,"wins":16},"o3":{"draws":11,"losses":38,"wins":9},"openai/gpt-oss-120b":{"draws":10,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":27,"losses":15,"wins":24},"qwen/qwen3.7-max":{"draws":22,"losses":14,"wins":18},"qwen/qwen3.7-plus":{"draws":14,"losses":20,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":2},"qwen/qwen3.8-flash":{"draws":15,"losses":6,"wins":3},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":7},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":6},"stealth/ox-alpha":{"draws":35,"losses":84,"wins":13},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":21},"tencent/hy3-preview":{"draws":7,"losses":15,"wins":6},"tencent/hy4-preview":{"draws":17,"losses":23,"wins":2},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":23},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":9},"x-ai/grok-4.5":{"draws":19,"losses":38,"wins":5},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":1},"xiaomi/mimo-v2.5":{"draws":53,"losses":31,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":20,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":33,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":22,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":4},"z-ai/glm-5.3-flashx":{"draws":2,"losses":21,"wins":3}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":46,"wins":26},"claude-fable-5":{"draws":32,"losses":134,"wins":4},"claude-fable-5-1":{"draws":4,"losses":144,"wins":0},"claude-opus-4-5":{"draws":197,"losses":206,"wins":73},"claude-opus-4-8":{"draws":92,"losses":158,"wins":28},"claude-opus-5":{"draws":63,"losses":307,"wins":24},"claude-opus-5-5":{"draws":6,"losses":143,"wins":3},"claude-sonnet-5":{"draws":58,"losses":59,"wins":17},"claude-sonnet-5-5":{"draws":26,"losses":85,"wins":7},"cohere/north-mini-code":{"draws":60,"losses":30,"wins":58},"deepseek/deepseek-v4-flash":{"draws":130,"losses":85,"wins":113},"deepseek/deepseek-v4-pro":{"draws":56,"losses":51,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":54,"losses":48,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":48,"losses":77,"wins":13},"fireworks/ember-1":{"draws":50,"losses":62,"wins":14},"gemini-3.1-pro-preview":{"draws":50,"losses":53,"wins":27},"google/gemini-3.1-flash-lite":{"draws":81,"losses":59,"wins":94},"google/gemini-3.5-flash":{"draws":61,"losses":79,"wins":36},"google/gemini-3.5-flash-lite":{"draws":115,"losses":87,"wins":82},"google/gemini-3.6-flash":{"draws":113,"losses":143,"wins":38},"google/gemini-3.8-flash":{"draws":41,"losses":77,"wins":12},"google/gemma-4-31b-it":{"draws":48,"losses":62,"wins":58},"gpt-4.1":{"draws":48,"losses":44,"wins":26},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":2},"gpt-5":{"draws":104,"losses":88,"wins":44},"gpt-5.4":{"draws":36,"losses":66,"wins":6},"gpt-5.4-mini":{"draws":99,"losses":63,"wins":60},"gpt-5.4-nano":{"draws":84,"losses":144,"wins":120},"gpt-5.5":{"draws":119,"losses":109,"wins":26},"gpt-5.6-luna":{"draws":57,"losses":44,"wins":21},"gpt-5.6-sol":{"draws":24,"losses":80,"wins":10},"gpt-5.6-terra":{"draws":66,"losses":85,"wins":13},"gpt-6-astra":{"draws":6,"losses":102,"wins":0},"gpt-6-luna":{"draws":58,"losses":73,"wins":35},"gpt-6-sol":{"draws":20,"losses":103,"wins":13},"gpt-6.1-sol":{"draws":11,"losses":117,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":52,"losses":12,"wins":36},"inclusionai/ling-3.0-flash":{"draws":76,"losses":38,"wins":66},"meituan/longcat-2.0":{"draws":95,"losses":98,"wins":81},"meta/muse-glimmer-30b":{"draws":49,"losses":39,"wins":26},"meta/muse-spark-1.2":{"draws":23,"losses":50,"wins":15},"meta/muse-spark-1.3":{"draws":32,"losses":78,"wins":10},"minimax/minimax-m3":{"draws":76,"losses":73,"wins":67},"mistralai/mistral-medium-3-5":{"draws":32,"losses":17,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":44,"losses":48,"wins":16},"moonshotai/kimi-k3":{"draws":54,"losses":93,"wins":21},"nex-agi/nex-n2-pro":{"draws":47,"losses":40,"wins":67},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":139,"losses":89,"wins":76},"o3":{"draws":54,"losses":139,"wins":35},"openai/gpt-oss-120b":{"draws":50,"losses":40,"wins":36},"poolside/laguna-s-2.1":{"draws":79,"losses":64,"wins":61},"qwen/qwen3.7-max":{"draws":77,"losses":79,"wins":32},"qwen/qwen3.7-plus":{"draws":69,"losses":59,"wins":56},"qwen/qwen3.8-2.4t-a95b":{"draws":56,"losses":57,"wins":21},"qwen/qwen3.8-27b":{"draws":16,"losses":41,"wins":13},"qwen/qwen3.8-flash":{"draws":38,"losses":29,"wins":23},"qwen/qwen3.8-max":{"draws":53,"losses":64,"wins":21},"qwen/qwen3.8-max-0902":{"draws":55,"losses":61,"wins":14},"stealth/ox-alpha":{"draws":108,"losses":218,"wins":62},"stealth/space-bunny-alpha":{"draws":52,"losses":41,"wins":17},"stepfun/step-3.7-flash":{"draws":66,"losses":54,"wins":54},"tencent/hy3-preview":{"draws":71,"losses":57,"wins":38},"tencent/hy4-preview":{"draws":46,"losses":91,"wins":7},"thinkingmachines/inkling":{"draws":88,"losses":63,"wins":113},"thinkingmachines/inkling-small":{"draws":63,"losses":30,"wins":27},"x-ai/grok-4.5":{"draws":75,"losses":114,"wins":23},"x-ai/grok-4.6":{"draws":59,"losses":92,"wins":11},"x-ai/grok-4.7":{"draws":12,"losses":100,"wins":6},"x-ai/grok-build-0.1":{"draws":53,"losses":44,"wins":31},"xiaomi/mimo-v2.5":{"draws":224,"losses":134,"wins":134},"xiaomi/mimo-v2.5-pro":{"draws":60,"losses":79,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":31,"losses":54,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":54,"wins":4},"z-ai/glm-5.2":{"draws":168,"losses":163,"wins":81},"z-ai/glm-5.3":{"draws":31,"losses":80,"wins":1},"z-ai/glm-5.3-flash":{"draws":38,"losses":110,"wins":28},"z-ai/glm-5.3-flashx":{"draws":43,"losses":90,"wins":9}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":18,"wins":18},"claude-fable-5":{"draws":5,"losses":53,"wins":2},"claude-fable-5-1":{"draws":1,"losses":51,"wins":0},"claude-opus-4-5":{"draws":38,"losses":70,"wins":56},"claude-opus-4-8":{"draws":29,"losses":59,"wins":30},"claude-opus-5":{"draws":21,"losses":123,"wins":6},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":10,"losses":31,"wins":23},"claude-sonnet-5-5":{"draws":5,"losses":15,"wins":6},"cohere/north-mini-code":{"draws":21,"losses":15,"wins":38},"deepseek/deepseek-v4-flash":{"draws":41,"losses":37,"wins":48},"deepseek/deepseek-v4-pro":{"draws":13,"losses":28,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":35,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":10},"fireworks/ember-1":{"draws":6,"losses":12,"wins":2},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":9},"google/gemini-3.1-flash-lite":{"draws":21,"losses":6,"wins":69},"google/gemini-3.5-flash":{"draws":17,"losses":25,"wins":34},"google/gemini-3.5-flash-lite":{"draws":30,"losses":39,"wins":53},"google/gemini-3.6-flash":{"draws":32,"losses":71,"wins":33},"google/gemini-3.8-flash":{"draws":17,"losses":36,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":14,"wins":30},"gpt-4.1":{"draws":9,"losses":21,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":23,"losses":36,"wins":25},"gpt-5.4":{"draws":10,"losses":50,"wins":10},"gpt-5.4-mini":{"draws":19,"losses":25,"wins":22},"gpt-5.4-nano":{"draws":35,"losses":43,"wins":62},"gpt-5.5":{"draws":30,"losses":48,"wins":26},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":25},"gpt-5.6-sol":{"draws":7,"losses":42,"wins":13},"gpt-5.6-terra":{"draws":15,"losses":39,"wins":10},"gpt-6-astra":{"draws":3,"losses":51,"wins":2},"gpt-6-luna":{"draws":15,"losses":28,"wins":13},"gpt-6-sol":{"draws":4,"losses":43,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":27,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":15,"losses":12,"wins":19},"inclusionai/ling-3.0-flash":{"draws":26,"losses":17,"wins":37},"meituan/longcat-2.0":{"draws":40,"losses":32,"wins":46},"meta/muse-glimmer-30b":{"draws":19,"losses":16,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":33,"wins":26},"meta/muse-spark-1.3":{"draws":5,"losses":43,"wins":6},"minimax/minimax-m3":{"draws":18,"losses":22,"wins":30},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":19,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":30,"wins":27},"nex-agi/nex-n2-pro":{"draws":18,"losses":19,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":17,"wins":39},"o3":{"draws":18,"losses":49,"wins":53},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":18},"poolside/laguna-s-2.1":{"draws":28,"losses":29,"wins":37},"qwen/qwen3.7-max":{"draws":24,"losses":41,"wins":19},"qwen/qwen3.7-plus":{"draws":29,"losses":13,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":33,"wins":16},"qwen/qwen3.8-27b":{"draws":13,"losses":33,"wins":12},"qwen/qwen3.8-flash":{"draws":13,"losses":26,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":27,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":29,"wins":13},"stealth/ox-alpha":{"draws":26,"losses":94,"wins":46},"stealth/space-bunny-alpha":{"draws":11,"losses":7,"wins":0},"stepfun/step-3.7-flash":{"draws":14,"losses":19,"wins":31},"tencent/hy3-preview":{"draws":21,"losses":27,"wins":22},"tencent/hy4-preview":{"draws":11,"losses":29,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":25,"wins":52},"thinkingmachines/inkling-small":{"draws":18,"losses":13,"wins":23},"x-ai/grok-4.5":{"draws":15,"losses":57,"wins":38},"x-ai/grok-4.6":{"draws":15,"losses":47,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":20,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":6,"wins":20},"xiaomi/mimo-v2.5":{"draws":60,"losses":41,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":19,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":4},"z-ai/glm-5.2":{"draws":57,"losses":69,"wins":46},"z-ai/glm-5.3":{"draws":14,"losses":42,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":35,"wins":13},"z-ai/glm-5.3-flashx":{"draws":21,"losses":21,"wins":4}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":26},"claude-fable-5":{"draws":12,"losses":35,"wins":11},"claude-fable-5-1":{"draws":3,"losses":43,"wins":6},"claude-opus-4-5":{"draws":20,"losses":21,"wins":19},"claude-opus-4-8":{"draws":13,"losses":14,"wins":17},"claude-opus-5":{"draws":9,"losses":59,"wins":8},"claude-opus-5-5":{"draws":9,"losses":87,"wins":2},"claude-sonnet-5":{"draws":13,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":6,"losses":40,"wins":34},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":28,"losses":10,"wins":46},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":11,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":33,"wins":32},"fireworks/ember-1":{"draws":13,"losses":35,"wins":32},"gemini-3.1-pro-preview":{"draws":11,"losses":29,"wins":36},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":22},"google/gemini-3.5-flash-lite":{"draws":12,"losses":8,"wins":40},"google/gemini-3.6-flash":{"draws":16,"losses":36,"wins":32},"google/gemini-3.8-flash":{"draws":9,"losses":9,"wins":14},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":12},"gpt-4.1":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":14,"losses":8,"wins":8},"gpt-5.4":{"draws":9,"losses":12,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":18},"gpt-5.5":{"draws":12,"losses":11,"wins":11},"gpt-5.6-luna":{"draws":22,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":18,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":20,"wins":19},"gpt-6-astra":{"draws":2,"losses":32,"wins":2},"gpt-6-luna":{"draws":20,"losses":29,"wins":37},"gpt-6-sol":{"draws":10,"losses":62,"wins":18},"gpt-6.1-sol":{"draws":2,"losses":70,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":20},"meituan/longcat-2.0":{"draws":20,"losses":13,"wins":17},"meta/muse-glimmer-30b":{"draws":12,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":7,"losses":21,"wins":6},"meta/muse-spark-1.3":{"draws":10,"losses":20,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":9,"wins":13},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":23},"o3":{"draws":7,"losses":9,"wins":32},"openai/gpt-oss-120b":{"draws":16,"losses":2,"wins":22},"poolside/laguna-s-2.1":{"draws":11,"losses":5,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":1,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":15,"wins":10},"qwen/qwen3.8-27b":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":15},"qwen/qwen3.8-max":{"draws":17,"losses":12,"wins":27},"qwen/qwen3.8-max-0902":{"draws":20,"losses":31,"wins":35},"stealth/ox-alpha":{"draws":27,"losses":61,"wins":56},"stealth/space-bunny-alpha":{"draws":14,"losses":15,"wins":35},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":7},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":29},"thinkingmachines/inkling-small":{"draws":16,"losses":1,"wins":21},"x-ai/grok-4.5":{"draws":9,"losses":21,"wins":22},"x-ai/grok-4.6":{"draws":13,"losses":26,"wins":17},"x-ai/grok-4.7":{"draws":7,"losses":49,"wins":18},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":31,"losses":7,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":27,"wins":17},"z-ai/glm-5.2":{"draws":21,"losses":25,"wins":34},"z-ai/glm-5.3":{"draws":13,"losses":18,"wins":9},"z-ai/glm-5.3-flash":{"draws":18,"losses":24,"wins":18},"z-ai/glm-5.3-flashx":{"draws":21,"losses":35,"wins":34}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":28},"claude-fable-5":{"draws":4,"losses":31,"wins":17},"claude-fable-5-1":{"draws":3,"losses":41,"wins":8},"claude-opus-4-5":{"draws":20,"losses":12,"wins":36},"claude-opus-4-8":{"draws":2,"losses":22,"wins":26},"claude-opus-5":{"draws":12,"losses":41,"wins":19},"claude-opus-5-5":{"draws":10,"losses":68,"wins":12},"claude-sonnet-5":{"draws":10,"losses":9,"wins":29},"claude-sonnet-5-5":{"draws":14,"losses":45,"wins":31},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":12,"losses":9,"wins":53},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":3,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":22,"wins":45},"fireworks/ember-1":{"draws":17,"losses":26,"wins":45},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":54},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":7,"losses":21,"wins":24},"google/gemini-3.5-flash-lite":{"draws":7,"losses":8,"wins":39},"google/gemini-3.6-flash":{"draws":15,"losses":31,"wins":34},"google/gemini-3.8-flash":{"draws":12,"losses":7,"wins":21},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":14},"gpt-4.1":{"draws":4,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":4,"wins":20},"gpt-5.4":{"draws":11,"losses":11,"wins":18},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":26},"gpt-5.5":{"draws":11,"losses":13,"wins":16},"gpt-5.6-luna":{"draws":8,"losses":6,"wins":38},"gpt-5.6-sol":{"draws":7,"losses":12,"wins":19},"gpt-5.6-terra":{"draws":8,"losses":16,"wins":24},"gpt-6-astra":{"draws":4,"losses":31,"wins":3},"gpt-6-luna":{"draws":12,"losses":16,"wins":40},"gpt-6-sol":{"draws":14,"losses":53,"wins":19},"gpt-6.1-sol":{"draws":13,"losses":54,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":21},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":40},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":26},"meta/muse-spark-1.2":{"draws":8,"losses":6,"wins":18},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":22},"minimax/minimax-m3":{"draws":2,"losses":5,"wins":21},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":9,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":34},"o3":{"draws":3,"losses":17,"wins":32},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":34},"poolside/laguna-s-2.1":{"draws":9,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":7},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":9,"wins":22},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":15,"losses":13,"wins":20},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":45},"stealth/ox-alpha":{"draws":23,"losses":31,"wins":70},"stealth/space-bunny-alpha":{"draws":11,"losses":17,"wins":36},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":14},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":13},"tencent/hy4-preview":{"draws":3,"losses":15,"wins":14},"thinkingmachines/inkling":{"draws":10,"losses":2,"wins":36},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":24},"x-ai/grok-4.5":{"draws":11,"losses":13,"wins":22},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":18},"x-ai/grok-4.7":{"draws":8,"losses":50,"wins":18},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":4,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":11,"wins":11},"z-ai/glm-5.2":{"draws":14,"losses":9,"wins":51},"z-ai/glm-5.3":{"draws":7,"losses":16,"wins":13},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":36,"wins":37}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":99,"losses":74,"wins":75},"claude-fable-5":{"draws":64,"losses":166,"wins":48},"claude-fable-5-1":{"draws":22,"losses":198,"wins":6},"claude-opus-4-5":{"draws":156,"losses":212,"wins":142},"claude-opus-4-8":{"draws":91,"losses":132,"wins":65},"claude-opus-5":{"draws":82,"losses":321,"wins":37},"claude-opus-5-5":{"draws":6,"losses":124,"wins":8},"claude-sonnet-5":{"draws":94,"losses":115,"wins":83},"claude-sonnet-5-5":{"draws":31,"losses":88,"wins":37},"cohere/north-mini-code":{"draws":38,"losses":21,"wins":67},"deepseek/deepseek-v4-flash":{"draws":139,"losses":79,"wins":166},"deepseek/deepseek-v4-pro":{"draws":87,"losses":94,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":100,"losses":102,"wins":82},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":41,"wins":26},"fireworks/ember-1":{"draws":54,"losses":63,"wins":31},"gemini-3.1-pro-preview":{"draws":58,"losses":47,"wins":45},"google/gemini-3.1-flash-lite":{"draws":50,"losses":28,"wins":106},"google/gemini-3.5-flash":{"draws":100,"losses":124,"wins":112},"google/gemini-3.5-flash-lite":{"draws":193,"losses":150,"wins":179},"google/gemini-3.6-flash":{"draws":138,"losses":186,"wins":122},"google/gemini-3.8-flash":{"draws":70,"losses":142,"wins":66},"google/gemma-4-31b-it":{"draws":38,"losses":20,"wins":48},"gpt-4.1":{"draws":29,"losses":25,"wins":44},"gpt-4.1-nano":{"draws":3,"losses":6,"wins":5},"gpt-5":{"draws":89,"losses":78,"wins":69},"gpt-5.4":{"draws":91,"losses":107,"wins":58},"gpt-5.4-mini":{"draws":97,"losses":25,"wins":60},"gpt-5.4-nano":{"draws":85,"losses":89,"wins":104},"gpt-5.5":{"draws":96,"losses":103,"wins":59},"gpt-5.6-luna":{"draws":108,"losses":56,"wins":88},"gpt-5.6-sol":{"draws":25,"losses":183,"wins":42},"gpt-5.6-terra":{"draws":141,"losses":108,"wins":67},"gpt-6-astra":{"draws":19,"losses":205,"wins":6},"gpt-6-luna":{"draws":56,"losses":75,"wins":59},"gpt-6-sol":{"draws":19,"losses":96,"wins":7},"gpt-6.1-sol":{"draws":16,"losses":123,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":22,"losses":2,"wins":10},"inception/mercury-2.5-preview":{"draws":89,"losses":24,"wins":95},"inclusionai/ling-3.0-flash":{"draws":82,"losses":29,"wins":59},"meituan/longcat-2.0":{"draws":90,"losses":79,"wins":132},"meta/muse-glimmer-30b":{"draws":117,"losses":41,"wins":78},"meta/muse-spark-1.2":{"draws":44,"losses":96,"wins":62},"meta/muse-spark-1.3":{"draws":56,"losses":102,"wins":56},"minimax/minimax-m3":{"draws":56,"losses":34,"wins":50},"mistralai/mistral-medium-3-5":{"draws":77,"losses":24,"wins":71},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":37,"wins":28},"moonshotai/kimi-k3":{"draws":96,"losses":89,"wins":49},"nex-agi/nex-n2-pro":{"draws":72,"losses":20,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":135,"losses":44,"wins":73},"o3":{"draws":61,"losses":143,"wins":142},"openai/gpt-oss-120b":{"draws":96,"losses":46,"wins":86},"poolside/laguna-s-2.1":{"draws":151,"losses":62,"wins":89},"qwen/qwen3.7-max":{"draws":60,"losses":43,"wins":59},"qwen/qwen3.7-plus":{"draws":65,"losses":30,"wins":77},"qwen/qwen3.8-2.4t-a95b":{"draws":96,"losses":96,"wins":66},"qwen/qwen3.8-27b":{"draws":49,"losses":74,"wins":51},"qwen/qwen3.8-flash":{"draws":76,"losses":70,"wins":48},"qwen/qwen3.8-max":{"draws":84,"losses":87,"wins":65},"qwen/qwen3.8-max-0902":{"draws":35,"losses":57,"wins":18},"stealth/ox-alpha":{"draws":241,"losses":380,"wins":197},"stealth/space-bunny-alpha":{"draws":62,"losses":29,"wins":37},"stepfun/step-3.7-flash":{"draws":44,"losses":38,"wins":66},"tencent/hy3-preview":{"draws":64,"losses":46,"wins":48},"tencent/hy4-preview":{"draws":78,"losses":110,"wins":50},"thinkingmachines/inkling":{"draws":105,"losses":71,"wins":108},"thinkingmachines/inkling-small":{"draws":118,"losses":62,"wins":114},"x-ai/grok-4.5":{"draws":83,"losses":142,"wins":77},"x-ai/grok-4.6":{"draws":86,"losses":166,"wins":48},"x-ai/grok-4.7":{"draws":13,"losses":106,"wins":15},"x-ai/grok-build-0.1":{"draws":27,"losses":18,"wins":33},"xiaomi/mimo-v2.5":{"draws":168,"losses":81,"wins":163},"xiaomi/mimo-v2.5-pro":{"draws":57,"losses":46,"wins":69},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":34,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":51,"wins":9},"z-ai/glm-5.2":{"draws":182,"losses":135,"wins":135},"z-ai/glm-5.3":{"draws":68,"losses":140,"wins":40},"z-ai/glm-5.3-flash":{"draws":100,"losses":148,"wins":66},"z-ai/glm-5.3-flashx":{"draws":35,"losses":59,"wins":26}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":19,"wins":86},"claude-fable-5":{"draws":35,"losses":79,"wins":108},"claude-fable-5-1":{"draws":13,"losses":148,"wins":35},"claude-opus-4-5":{"draws":49,"losses":30,"wins":129},"claude-opus-4-8":{"draws":21,"losses":24,"wins":49},"claude-opus-5":{"draws":22,"losses":89,"wins":41},"claude-opus-5-5":{"draws":4,"losses":66,"wins":16},"claude-sonnet-5":{"draws":38,"losses":19,"wins":123},"claude-sonnet-5-5":{"draws":19,"losses":25,"wins":32},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":25},"deepseek/deepseek-v4-flash":{"draws":49,"losses":10,"wins":115},"deepseek/deepseek-v4-pro":{"draws":32,"losses":31,"wins":93},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":34,"wins":94},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":10,"wins":30},"fireworks/ember-1":{"draws":21,"losses":14,"wins":53},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":46},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":36},"google/gemini-3.5-flash":{"draws":38,"losses":41,"wins":125},"google/gemini-3.5-flash-lite":{"draws":62,"losses":21,"wins":191},"google/gemini-3.6-flash":{"draws":48,"losses":56,"wins":174},"google/gemini-3.8-flash":{"draws":32,"losses":49,"wins":107},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":31},"gpt-4.1":{"draws":7,"losses":3,"wins":22},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":8,"wins":47},"gpt-5.4":{"draws":34,"losses":65,"wins":95},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":34},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":73},"gpt-5.5":{"draws":20,"losses":15,"wins":51},"gpt-5.6-luna":{"draws":39,"losses":22,"wins":91},"gpt-5.6-sol":{"draws":33,"losses":86,"wins":79},"gpt-5.6-terra":{"draws":60,"losses":26,"wins":110},"gpt-6-astra":{"draws":26,"losses":160,"wins":16},"gpt-6-luna":{"draws":17,"losses":18,"wins":53},"gpt-6-sol":{"draws":18,"losses":29,"wins":27},"gpt-6.1-sol":{"draws":10,"losses":54,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":42,"losses":4,"wins":58},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":46},"meituan/longcat-2.0":{"draws":30,"losses":11,"wins":93},"meta/muse-glimmer-30b":{"draws":24,"losses":14,"wins":64},"meta/muse-spark-1.2":{"draws":22,"losses":35,"wins":77},"meta/muse-spark-1.3":{"draws":33,"losses":42,"wins":99},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":28},"mistralai/mistral-medium-3-5":{"draws":25,"losses":7,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":45,"losses":40,"wins":89},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":10,"wins":45},"o3":{"draws":13,"losses":33,"wins":136},"openai/gpt-oss-120b":{"draws":44,"losses":8,"wins":68},"poolside/laguna-s-2.1":{"draws":29,"losses":9,"wins":78},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":18},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":34,"wins":96},"qwen/qwen3.8-27b":{"draws":15,"losses":19,"wins":62},"qwen/qwen3.8-flash":{"draws":28,"losses":18,"wins":84},"qwen/qwen3.8-max":{"draws":45,"losses":34,"wins":97},"qwen/qwen3.8-max-0902":{"draws":26,"losses":11,"wins":25},"stealth/ox-alpha":{"draws":115,"losses":151,"wins":316},"stealth/space-bunny-alpha":{"draws":14,"losses":5,"wins":39},"stepfun/step-3.7-flash":{"draws":13,"losses":4,"wins":43},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":22},"tencent/hy4-preview":{"draws":28,"losses":34,"wins":116},"thinkingmachines/inkling":{"draws":33,"losses":12,"wins":85},"thinkingmachines/inkling-small":{"draws":32,"losses":14,"wins":90},"x-ai/grok-4.5":{"draws":38,"losses":34,"wins":104},"x-ai/grok-4.6":{"draws":41,"losses":69,"wins":106},"x-ai/grok-4.7":{"draws":13,"losses":42,"wins":23},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":22},"xiaomi/mimo-v2.5":{"draws":31,"losses":1,"wins":80},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":6,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":16},"z-ai/glm-5.2":{"draws":68,"losses":40,"wins":140},"z-ai/glm-5.3":{"draws":22,"losses":45,"wins":45},"z-ai/glm-5.3-flash":{"draws":43,"losses":43,"wins":112},"z-ai/glm-5.3-flashx":{"draws":23,"losses":10,"wins":33}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":55,"losses":31,"wins":90},"claude-fable-5":{"draws":39,"losses":113,"wins":70},"claude-fable-5-1":{"draws":21,"losses":208,"wins":25},"claude-opus-4-5":{"draws":60,"losses":65,"wins":137},"claude-opus-4-8":{"draws":15,"losses":40,"wins":39},"claude-opus-5":{"draws":24,"losses":160,"wins":54},"claude-opus-5-5":{"draws":10,"losses":83,"wins":9},"claude-sonnet-5":{"draws":44,"losses":55,"wins":111},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":15,"losses":3,"wins":34},"deepseek/deepseek-v4-flash":{"draws":77,"losses":43,"wins":120},"deepseek/deepseek-v4-pro":{"draws":53,"losses":55,"wins":90},"deepseek/deepseek-v4-pro-0813":{"draws":52,"losses":52,"wins":92},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":36,"wins":39},"fireworks/ember-1":{"draws":14,"losses":14,"wins":26},"gemini-3.1-pro-preview":{"draws":13,"losses":11,"wins":20},"google/gemini-3.1-flash-lite":{"draws":14,"losses":7,"wins":43},"google/gemini-3.5-flash":{"draws":58,"losses":82,"wins":100},"google/gemini-3.5-flash-lite":{"draws":101,"losses":59,"wins":206},"google/gemini-3.6-flash":{"draws":84,"losses":111,"wins":157},"google/gemini-3.8-flash":{"draws":49,"losses":98,"wins":75},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":35},"gpt-4.1":{"draws":6,"losses":9,"wins":21},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":36,"losses":21,"wins":59},"gpt-5.4":{"draws":47,"losses":76,"wins":79},"gpt-5.4-mini":{"draws":30,"losses":8,"wins":36},"gpt-5.4-nano":{"draws":22,"losses":22,"wins":58},"gpt-5.5":{"draws":18,"losses":35,"wins":45},"gpt-5.6-luna":{"draws":58,"losses":42,"wins":86},"gpt-5.6-sol":{"draws":39,"losses":116,"wins":79},"gpt-5.6-terra":{"draws":61,"losses":61,"wins":92},"gpt-6-astra":{"draws":30,"losses":178,"wins":14},"gpt-6-luna":{"draws":29,"losses":24,"wins":55},"gpt-6-sol":{"draws":14,"losses":59,"wins":25},"gpt-6.1-sol":{"draws":4,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":11},"inception/mercury-2.5-preview":{"draws":47,"losses":16,"wins":69},"inclusionai/ling-3.0-flash":{"draws":30,"losses":8,"wins":56},"meituan/longcat-2.0":{"draws":42,"losses":33,"wins":93},"meta/muse-glimmer-30b":{"draws":59,"losses":18,"wins":95},"meta/muse-spark-1.2":{"draws":25,"losses":54,"wins":61},"meta/muse-spark-1.3":{"draws":44,"losses":71,"wins":83},"minimax/minimax-m3":{"draws":16,"losses":8,"wins":36},"mistralai/mistral-medium-3-5":{"draws":37,"losses":20,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":10,"wins":12},"moonshotai/kimi-k3":{"draws":60,"losses":52,"wins":88},"nex-agi/nex-n2-pro":{"draws":19,"losses":4,"wins":37},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":18,"wins":41},"o3":{"draws":42,"losses":96,"wins":96},"openai/gpt-oss-120b":{"draws":47,"losses":15,"wins":92},"poolside/laguna-s-2.1":{"draws":59,"losses":22,"wins":77},"qwen/qwen3.7-max":{"draws":18,"losses":12,"wins":28},"qwen/qwen3.7-plus":{"draws":18,"losses":5,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":49,"losses":78,"wins":81},"qwen/qwen3.8-27b":{"draws":35,"losses":38,"wins":47},"qwen/qwen3.8-flash":{"draws":49,"losses":48,"wins":53},"qwen/qwen3.8-max":{"draws":58,"losses":72,"wins":74},"qwen/qwen3.8-max-0902":{"draws":29,"losses":23,"wins":34},"stealth/ox-alpha":{"draws":162,"losses":256,"wins":295},"stealth/space-bunny-alpha":{"draws":11,"losses":5,"wins":22},"stepfun/step-3.7-flash":{"draws":29,"losses":9,"wins":40},"tencent/hy3-preview":{"draws":19,"losses":7,"wins":38},"tencent/hy4-preview":{"draws":47,"losses":62,"wins":89},"thinkingmachines/inkling":{"draws":51,"losses":24,"wins":97},"thinkingmachines/inkling-small":{"draws":73,"losses":37,"wins":108},"x-ai/grok-4.5":{"draws":29,"losses":67,"wins":82},"x-ai/grok-4.6":{"draws":58,"losses":86,"wins":90},"x-ai/grok-4.7":{"draws":7,"losses":30,"wins":21},"x-ai/grok-build-0.1":{"draws":12,"losses":4,"wins":26},"xiaomi/mimo-v2.5":{"draws":38,"losses":28,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":13,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":18,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":20,"wins":21},"z-ai/glm-5.2":{"draws":100,"losses":66,"wins":148},"z-ai/glm-5.3":{"draws":43,"losses":112,"wins":43},"z-ai/glm-5.3-flash":{"draws":44,"losses":40,"wins":40},"z-ai/glm-5.3-flashx":{"draws":24,"losses":29,"wins":43}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":10,"wins":47},"claude-fable-5":{"draws":17,"losses":50,"wins":23},"claude-fable-5-1":{"draws":10,"losses":85,"wins":9},"claude-opus-4-5":{"draws":23,"losses":17,"wins":48},"claude-opus-4-8":{"draws":13,"losses":33,"wins":28},"claude-opus-5":{"draws":17,"losses":76,"wins":13},"claude-opus-5-5":{"draws":15,"losses":131,"wins":10},"claude-sonnet-5":{"draws":22,"losses":17,"wins":23},"claude-sonnet-5-5":{"draws":23,"losses":53,"wins":50},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":21},"deepseek/deepseek-v4-flash":{"draws":29,"losses":12,"wins":59},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":7,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"fireworks/ember-1":{"draws":35,"losses":47,"wins":54},"gemini-3.1-pro-preview":{"draws":31,"losses":29,"wins":66},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":34,"losses":26,"wins":30},"google/gemini-3.5-flash-lite":{"draws":27,"losses":18,"wins":55},"google/gemini-3.6-flash":{"draws":29,"losses":47,"wins":44},"google/gemini-3.8-flash":{"draws":13,"losses":22,"wins":21},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":26},"gpt-4.1":{"draws":8,"losses":6,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":19,"losses":7,"wins":10},"gpt-5.4":{"draws":21,"losses":16,"wins":15},"gpt-5.4-mini":{"draws":8,"losses":9,"wins":35},"gpt-5.4-nano":{"draws":14,"losses":17,"wins":35},"gpt-5.5":{"draws":25,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":29,"losses":9,"wins":26},"gpt-5.6-sol":{"draws":14,"losses":27,"wins":11},"gpt-5.6-terra":{"draws":23,"losses":23,"wins":44},"gpt-6-astra":{"draws":6,"losses":55,"wins":3},"gpt-6-luna":{"draws":35,"losses":39,"wins":64},"gpt-6-sol":{"draws":20,"losses":87,"wins":37},"gpt-6.1-sol":{"draws":17,"losses":89,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":20,"losses":3,"wins":27},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":37},"meituan/longcat-2.0":{"draws":32,"losses":10,"wins":47},"meta/muse-glimmer-30b":{"draws":18,"losses":9,"wins":33},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":19},"meta/muse-spark-1.3":{"draws":17,"losses":21,"wins":14},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":28},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":20,"losses":22,"wins":26},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":34},"o3":{"draws":6,"losses":18,"wins":60},"openai/gpt-oss-120b":{"draws":16,"losses":9,"wins":35},"poolside/laguna-s-2.1":{"draws":17,"losses":13,"wins":28},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":26},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":21,"wins":22},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":16,"losses":12,"wins":28},"qwen/qwen3.8-max":{"draws":28,"losses":23,"wins":29},"qwen/qwen3.8-max-0902":{"draws":36,"losses":50,"wins":52},"stealth/ox-alpha":{"draws":35,"losses":66,"wins":107},"stealth/space-bunny-alpha":{"draws":29,"losses":21,"wins":46},"stepfun/step-3.7-flash":{"draws":12,"losses":6,"wins":20},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":9,"losses":30,"wins":23},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":51},"thinkingmachines/inkling-small":{"draws":22,"losses":10,"wins":26},"x-ai/grok-4.5":{"draws":24,"losses":26,"wins":46},"x-ai/grok-4.6":{"draws":23,"losses":42,"wins":25},"x-ai/grok-4.7":{"draws":14,"losses":77,"wins":27},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":21},"xiaomi/mimo-v2.5":{"draws":43,"losses":9,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":4,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":34,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":37,"wins":36},"z-ai/glm-5.2":{"draws":35,"losses":26,"wins":59},"z-ai/glm-5.3":{"draws":23,"losses":33,"wins":10},"z-ai/glm-5.3-flash":{"draws":24,"losses":43,"wins":29},"z-ai/glm-5.3-flashx":{"draws":32,"losses":32,"wins":32}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":14,"wins":17},"claude-fable-5":{"draws":12,"losses":48,"wins":8},"claude-fable-5-1":{"draws":2,"losses":61,"wins":1},"claude-opus-4-5":{"draws":33,"losses":34,"wins":13},"claude-opus-4-8":{"draws":4,"losses":8,"wins":2},"claude-opus-5":{"draws":1,"losses":36,"wins":9},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":23,"losses":25,"wins":10},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":30,"losses":23,"wins":21},"deepseek/deepseek-v4-pro":{"draws":14,"losses":27,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":21,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":11,"wins":3},"fireworks/ember-1":{"draws":6,"losses":9,"wins":5},"gemini-3.1-pro-preview":{"draws":9,"losses":9,"wins":8},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":27,"losses":30,"wins":15},"google/gemini-3.5-flash-lite":{"draws":58,"losses":26,"wins":36},"google/gemini-3.6-flash":{"draws":34,"losses":39,"wins":25},"google/gemini-3.8-flash":{"draws":21,"losses":31,"wins":10},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":2,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":10,"wins":7},"gpt-5.4":{"draws":19,"losses":18,"wins":13},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":8},"gpt-5.5":{"draws":18,"losses":14,"wins":8},"gpt-5.6-luna":{"draws":31,"losses":20,"wins":21},"gpt-5.6-sol":{"draws":13,"losses":33,"wins":12},"gpt-5.6-terra":{"draws":24,"losses":24,"wins":14},"gpt-6-astra":{"draws":3,"losses":42,"wins":1},"gpt-6-luna":{"draws":7,"losses":13,"wins":10},"gpt-6-sol":{"draws":3,"losses":10,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":20,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":23,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":15},"meituan/longcat-2.0":{"draws":17,"losses":8,"wins":19},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":22},"meta/muse-spark-1.2":{"draws":16,"losses":12,"wins":12},"meta/muse-spark-1.3":{"draws":15,"losses":31,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":13},"mistralai/mistral-medium-3-5":{"draws":18,"losses":6,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":23,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":8},"o3":{"draws":14,"losses":28,"wins":28},"openai/gpt-oss-120b":{"draws":31,"losses":10,"wins":25},"poolside/laguna-s-2.1":{"draws":27,"losses":6,"wins":13},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":23,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":14},"qwen/qwen3.8-flash":{"draws":20,"losses":22,"wins":10},"qwen/qwen3.8-max":{"draws":28,"losses":24,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":10,"wins":3},"stealth/ox-alpha":{"draws":58,"losses":96,"wins":42},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":12},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":24,"losses":36,"wins":10},"thinkingmachines/inkling":{"draws":26,"losses":9,"wins":31},"thinkingmachines/inkling-small":{"draws":30,"losses":12,"wins":26},"x-ai/grok-4.5":{"draws":19,"losses":34,"wins":11},"x-ai/grok-4.6":{"draws":14,"losses":45,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":14,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":7,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":3},"z-ai/glm-5.2":{"draws":39,"losses":27,"wins":30},"z-ai/glm-5.3":{"draws":13,"losses":31,"wins":4},"z-ai/glm-5.3-flash":{"draws":25,"losses":36,"wins":9},"z-ai/glm-5.3-flashx":{"draws":4,"losses":12,"wins":0}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":50},"claude-fable-5":{"draws":2,"losses":20,"wins":18},"claude-fable-5-1":{"draws":10,"losses":76,"wins":22},"claude-opus-4-5":{"draws":10,"losses":11,"wins":89},"claude-opus-4-8":{"draws":5,"losses":13,"wins":30},"claude-opus-5":{"draws":11,"losses":45,"wins":34},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":16,"losses":8,"wins":60},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":18},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":80},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":10,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":8,"wins":34},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":14,"losses":7,"wins":75},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":106},"google/gemini-3.6-flash":{"draws":21,"losses":25,"wins":86},"google/gemini-3.8-flash":{"draws":14,"losses":34,"wins":42},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":17},"gpt-4.1":{"draws":2,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":13,"wins":27},"gpt-5.4":{"draws":16,"losses":32,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":40},"gpt-5.5":{"draws":4,"losses":19,"wins":23},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":55},"gpt-5.6-sol":{"draws":12,"losses":29,"wins":53},"gpt-5.6-terra":{"draws":19,"losses":11,"wins":50},"gpt-6-astra":{"draws":9,"losses":70,"wins":17},"gpt-6-luna":{"draws":9,"losses":9,"wins":28},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":38},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":29},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":46},"meta/muse-glimmer-30b":{"draws":13,"losses":2,"wins":47},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":47},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":45},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":56},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":28},"o3":{"draws":10,"losses":16,"wins":58},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":46},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":43},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":55},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":37},"qwen/qwen3.8-flash":{"draws":15,"losses":6,"wins":33},"qwen/qwen3.8-max":{"draws":13,"losses":17,"wins":48},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":37},"stealth/ox-alpha":{"draws":43,"losses":39,"wins":196},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":12,"losses":17,"wins":49},"thinkingmachines/inkling":{"draws":11,"losses":2,"wins":57},"thinkingmachines/inkling-small":{"draws":11,"losses":2,"wins":55},"x-ai/grok-4.5":{"draws":3,"losses":18,"wins":51},"x-ai/grok-4.6":{"draws":20,"losses":26,"wins":46},"x-ai/grok-4.7":{"draws":2,"losses":2,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":12},"z-ai/glm-5.2":{"draws":19,"losses":13,"wins":86},"z-ai/glm-5.3":{"draws":16,"losses":28,"wins":46},"z-ai/glm-5.3-flash":{"draws":17,"losses":16,"wins":53},"z-ai/glm-5.3-flashx":{"draws":11,"losses":8,"wins":29}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":68},"claude-fable-5":{"draws":3,"losses":7,"wins":92},"claude-fable-5-1":{"draws":4,"losses":20,"wins":64},"claude-opus-4-5":{"draws":1,"losses":2,"wins":89},"claude-opus-4-8":{"draws":0,"losses":0,"wins":26},"claude-opus-5":{"draws":4,"losses":11,"wins":51},"claude-opus-5-5":{"draws":5,"losses":10,"wins":9},"claude-sonnet-5":{"draws":0,"losses":1,"wins":83},"claude-sonnet-5-5":{"draws":1,"losses":7,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":95},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":62},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":31},"fireworks/ember-1":{"draws":0,"losses":1,"wins":43},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":28},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":20},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":75},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":99},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":107},"google/gemini-3.8-flash":{"draws":6,"losses":4,"wins":76},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":12},"gpt-4.1":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":36},"gpt-5.4":{"draws":0,"losses":3,"wins":71},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":18},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":26},"gpt-5.5":{"draws":0,"losses":2,"wins":36},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":59},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":83},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":86},"gpt-6-astra":{"draws":5,"losses":38,"wins":55},"gpt-6-luna":{"draws":0,"losses":1,"wins":33},"gpt-6-sol":{"draws":0,"losses":5,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":10,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":37},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":35},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":32},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":48},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":48},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":73},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":78},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"o3":{"draws":0,"losses":0,"wins":64},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":49},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":37},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":24},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":72},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":44},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":51},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":84},"qwen/qwen3.8-max-0902":{"draws":0,"losses":5,"wins":27},"stealth/ox-alpha":{"draws":18,"losses":7,"wins":271},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":30},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":18},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":18},"tencent/hy4-preview":{"draws":1,"losses":1,"wins":86},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":61},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":72},"x-ai/grok-4.6":{"draws":2,"losses":10,"wins":86},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":17},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":20},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":84},"z-ai/glm-5.3":{"draws":2,"losses":8,"wins":70},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":93},"z-ai/glm-5.3-flashx":{"draws":4,"losses":1,"wins":39}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":9,"wins":36},"claude-fable-5":{"draws":14,"losses":55,"wins":13},"claude-fable-5-1":{"draws":5,"losses":69,"wins":4},"claude-opus-4-5":{"draws":21,"losses":31,"wins":24},"claude-opus-4-8":{"draws":10,"losses":24,"wins":10},"claude-opus-5":{"draws":14,"losses":106,"wins":6},"claude-opus-5-5":{"draws":2,"losses":28,"wins":0},"claude-sonnet-5":{"draws":49,"losses":19,"wins":50},"claude-sonnet-5-5":{"draws":6,"losses":12,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":23,"losses":13,"wins":40},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":28,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":10,"wins":3},"fireworks/ember-1":{"draws":10,"losses":2,"wins":8},"gemini-3.1-pro-preview":{"draws":7,"losses":3,"wins":12},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":17,"losses":31,"wins":28},"google/gemini-3.5-flash-lite":{"draws":89,"losses":58,"wins":107},"google/gemini-3.6-flash":{"draws":62,"losses":102,"wins":66},"google/gemini-3.8-flash":{"draws":16,"losses":38,"wins":10},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":8},"gpt-4.1":{"draws":7,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":10,"wins":13},"gpt-5.4":{"draws":39,"losses":58,"wins":21},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":6,"wins":12},"gpt-5.5":{"draws":13,"losses":23,"wins":10},"gpt-5.6-luna":{"draws":42,"losses":27,"wins":49},"gpt-5.6-sol":{"draws":14,"losses":80,"wins":28},"gpt-5.6-terra":{"draws":22,"losses":16,"wins":30},"gpt-6-astra":{"draws":1,"losses":74,"wins":1},"gpt-6-luna":{"draws":6,"losses":9,"wins":11},"gpt-6-sol":{"draws":1,"losses":11,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":12,"losses":14,"wins":22},"meituan/longcat-2.0":{"draws":20,"losses":21,"wins":51},"meta/muse-glimmer-30b":{"draws":24,"losses":6,"wins":32},"meta/muse-spark-1.2":{"draws":22,"losses":40,"wins":22},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":9},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":39,"losses":51,"wins":36},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":4,"wins":19},"o3":{"draws":28,"losses":36,"wins":96},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":30},"poolside/laguna-s-2.1":{"draws":44,"losses":6,"wins":40},"qwen/qwen3.7-max":{"draws":8,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":28,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":10,"wins":14},"qwen/qwen3.8-flash":{"draws":16,"losses":20,"wins":16},"qwen/qwen3.8-max":{"draws":21,"losses":30,"wins":15},"qwen/qwen3.8-max-0902":{"draws":3,"losses":8,"wins":3},"stealth/ox-alpha":{"draws":65,"losses":93,"wins":72},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":12,"losses":2,"wins":32},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":22,"losses":33,"wins":21},"thinkingmachines/inkling":{"draws":34,"losses":7,"wins":53},"thinkingmachines/inkling-small":{"draws":32,"losses":14,"wins":32},"x-ai/grok-4.5":{"draws":43,"losses":60,"wins":29},"x-ai/grok-4.6":{"draws":19,"losses":42,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":6,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":12,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":8,"wins":1},"z-ai/glm-5.2":{"draws":32,"losses":23,"wins":51},"z-ai/glm-5.3":{"draws":15,"losses":52,"wins":9},"z-ai/glm-5.3-flash":{"draws":16,"losses":34,"wins":20},"z-ai/glm-5.3-flashx":{"draws":10,"losses":8,"wins":2}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":4,"wins":20},"claude-fable-5":{"draws":3,"losses":7,"wins":12},"claude-fable-5-1":{"draws":2,"losses":22,"wins":6},"claude-opus-4-5":{"draws":14,"losses":19,"wins":75},"claude-opus-4-8":{"draws":2,"losses":6,"wins":26},"claude-opus-5":{"draws":33,"losses":71,"wins":46},"claude-opus-5-5":{"draws":5,"losses":7,"wins":4},"claude-sonnet-5":{"draws":5,"losses":3,"wins":20},"claude-sonnet-5-5":{"draws":5,"losses":4,"wins":13},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":41},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":13},"fireworks/ember-1":{"draws":8,"losses":1,"wins":11},"gemini-3.1-pro-preview":{"draws":7,"losses":0,"wins":23},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":37},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":27},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":48},"google/gemini-3.6-flash":{"draws":8,"losses":30,"wins":36},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":18},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":13},"gpt-4.1":{"draws":0,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":12,"wins":45},"gpt-5.4":{"draws":2,"losses":9,"wins":13},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":8,"losses":3,"wins":43},"gpt-5.5":{"draws":13,"losses":27,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":21},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":15},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":26},"gpt-6-astra":{"draws":6,"losses":19,"wins":1},"gpt-6-luna":{"draws":5,"losses":3,"wins":18},"gpt-6-sol":{"draws":3,"losses":6,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":9,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":18},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":22},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":22},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":12},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":14},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":29},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2-pro":{"draws":1,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":50},"o3":{"draws":0,"losses":11,"wins":55},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":3,"losses":2,"wins":29},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":23},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":3,"wins":13},"qwen/qwen3.8-max":{"draws":0,"losses":11,"wins":15},"qwen/qwen3.8-max-0902":{"draws":8,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":19,"losses":11,"wins":38},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":22},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":26},"tencent/hy4-preview":{"draws":3,"losses":7,"wins":16},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":49},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":26},"x-ai/grok-4.5":{"draws":13,"losses":13,"wins":32},"x-ai/grok-4.6":{"draws":4,"losses":9,"wins":15},"x-ai/grok-4.7":{"draws":6,"losses":7,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":16},"xiaomi/mimo-v2.5":{"draws":16,"losses":1,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":14},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":64},"z-ai/glm-5.3":{"draws":5,"losses":9,"wins":12},"z-ai/glm-5.3-flash":{"draws":4,"losses":8,"wins":22},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":20}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":34},"claude-fable-5":{"draws":3,"losses":15,"wins":52},"claude-fable-5-1":{"draws":8,"losses":23,"wins":27},"claude-opus-4-5":{"draws":7,"losses":15,"wins":142},"claude-opus-4-8":{"draws":9,"losses":27,"wins":78},"claude-opus-5":{"draws":23,"losses":90,"wins":157},"claude-opus-5-5":{"draws":4,"losses":23,"wins":13},"claude-sonnet-5":{"draws":2,"losses":5,"wins":37},"claude-sonnet-5-5":{"draws":2,"losses":6,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":23},"deepseek/deepseek-v4-flash":{"draws":3,"losses":6,"wins":69},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":37},"fireworks/ember-1":{"draws":2,"losses":4,"wins":24},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":30},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":48},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":48},"google/gemini-3.5-flash-lite":{"draws":6,"losses":6,"wins":104},"google/gemini-3.6-flash":{"draws":11,"losses":16,"wins":97},"google/gemini-3.8-flash":{"draws":2,"losses":14,"wins":40},"google/gemma-4-31b-it":{"draws":0,"losses":8,"wins":20},"gpt-4.1":{"draws":1,"losses":1,"wins":30},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":7,"wins":71},"gpt-5.4":{"draws":0,"losses":2,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":41},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":59},"gpt-5.5":{"draws":5,"losses":16,"wins":71},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":38},"gpt-5.6-sol":{"draws":10,"losses":11,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":54},"gpt-6-astra":{"draws":10,"losses":27,"wins":19},"gpt-6-luna":{"draws":6,"losses":2,"wins":34},"gpt-6-sol":{"draws":3,"losses":14,"wins":19},"gpt-6.1-sol":{"draws":6,"losses":16,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":25},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":24},"meituan/longcat-2.0":{"draws":3,"losses":8,"wins":39},"meta/muse-glimmer-30b":{"draws":1,"losses":2,"wins":37},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":25},"meta/muse-spark-1.3":{"draws":8,"losses":10,"wins":36},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":41},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":29},"moonshotai/kimi-k3":{"draws":6,"losses":8,"wins":54},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":80},"o3":{"draws":0,"losses":6,"wins":88},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":56},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":3,"wins":29},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":24},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":36},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":43},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":28},"stealth/ox-alpha":{"draws":13,"losses":17,"wins":160},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":29},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":35},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":48},"tencent/hy4-preview":{"draws":3,"losses":3,"wins":52},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":92},"thinkingmachines/inkling-small":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.5":{"draws":7,"losses":22,"wins":83},"x-ai/grok-4.6":{"draws":4,"losses":8,"wins":52},"x-ai/grok-4.7":{"draws":3,"losses":9,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":25},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":15},"z-ai/glm-5.2":{"draws":9,"losses":10,"wins":83},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":39},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":56},"z-ai/glm-5.3-flashx":{"draws":0,"losses":1,"wins":35}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":18},"claude-fable-5":{"draws":2,"losses":2,"wins":28},"claude-fable-5-1":{"draws":2,"losses":6,"wins":12},"claude-opus-4-5":{"draws":0,"losses":0,"wins":38},"claude-opus-4-8":{"draws":2,"losses":0,"wins":26},"claude-opus-5":{"draws":2,"losses":4,"wins":24},"claude-opus-5-5":{"draws":3,"losses":7,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":16},"claude-sonnet-5-5":{"draws":4,"losses":5,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":28},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":37},"fireworks/ember-1":{"draws":0,"losses":0,"wins":34},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":45},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":21},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":37},"google/gemini-3.8-flash":{"draws":1,"losses":1,"wins":20},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":10},"gpt-5":{"draws":0,"losses":0,"wins":14},"gpt-5.4":{"draws":0,"losses":2,"wins":18},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":10},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":14},"gpt-5.5":{"draws":0,"losses":2,"wins":14},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":19},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":28},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":32},"gpt-6-astra":{"draws":3,"losses":10,"wins":13},"gpt-6-luna":{"draws":1,"losses":0,"wins":45},"gpt-6-sol":{"draws":2,"losses":1,"wins":45},"gpt-6.1-sol":{"draws":8,"losses":6,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":16},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":26},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":24},"meta/muse-spark-1.2":{"draws":1,"losses":2,"wins":17},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":12},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":18},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":22},"o3":{"draws":0,"losses":0,"wins":24},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":26},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":22},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":13},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":2,"wins":16},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":18},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":30},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":41},"stealth/ox-alpha":{"draws":1,"losses":0,"wins":63},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":0,"losses":0,"wins":24},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":21},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":18},"x-ai/grok-4.5":{"draws":2,"losses":1,"wins":33},"x-ai/grok-4.6":{"draws":1,"losses":1,"wins":28},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":24},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":45},"z-ai/glm-5.3":{"draws":0,"losses":1,"wins":21},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":27},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":43}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":4,"wins":28},"claude-fable-5":{"draws":10,"losses":37,"wins":17},"claude-fable-5-1":{"draws":1,"losses":68,"wins":3},"claude-opus-4-5":{"draws":36,"losses":35,"wins":41},"claude-opus-4-8":{"draws":5,"losses":9,"wins":12},"claude-opus-5":{"draws":5,"losses":40,"wins":11},"claude-opus-5-5":{"draws":2,"losses":19,"wins":1},"claude-sonnet-5":{"draws":20,"losses":11,"wins":47},"claude-sonnet-5-5":{"draws":5,"losses":16,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":20,"losses":9,"wins":39},"deepseek/deepseek-v4-pro":{"draws":14,"losses":15,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":21,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":7,"wins":6},"fireworks/ember-1":{"draws":9,"losses":7,"wins":14},"gemini-3.1-pro-preview":{"draws":6,"losses":4,"wins":14},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":26},"google/gemini-3.5-flash-lite":{"draws":34,"losses":28,"wins":112},"google/gemini-3.6-flash":{"draws":29,"losses":57,"wins":84},"google/gemini-3.8-flash":{"draws":15,"losses":27,"wins":24},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":13},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":7,"losses":3,"wins":14},"gpt-5.4":{"draws":27,"losses":45,"wins":32},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":18},"gpt-5.5":{"draws":6,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":27,"losses":29,"wins":38},"gpt-5.6-sol":{"draws":21,"losses":78,"wins":21},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":35},"gpt-6-astra":{"draws":1,"losses":61,"wins":10},"gpt-6-luna":{"draws":6,"losses":12,"wins":10},"gpt-6-sol":{"draws":5,"losses":18,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":23,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":26},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":43},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":23,"losses":12,"wins":45},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":25},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":9},"mistralai/mistral-medium-3-5":{"draws":6,"losses":7,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":31,"losses":36,"wins":31},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":13},"o3":{"draws":3,"losses":40,"wins":75},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":17,"losses":3,"wins":46},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":18,"wins":17},"qwen/qwen3.8-27b":{"draws":12,"losses":9,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":11,"losses":21,"wins":30},"qwen/qwen3.8-max-0902":{"draws":6,"losses":3,"wins":3},"stealth/ox-alpha":{"draws":54,"losses":75,"wins":74},"stealth/space-bunny-alpha":{"draws":4,"losses":3,"wins":13},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":19},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":23},"thinkingmachines/inkling":{"draws":20,"losses":10,"wins":42},"thinkingmachines/inkling-small":{"draws":19,"losses":10,"wins":39},"x-ai/grok-4.5":{"draws":34,"losses":37,"wins":19},"x-ai/grok-4.6":{"draws":18,"losses":29,"wins":27},"x-ai/grok-4.7":{"draws":4,"losses":13,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":14,"losses":7,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":21,"wins":42},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":11},"z-ai/glm-5.3-flash":{"draws":6,"losses":42,"wins":22},"z-ai/glm-5.3-flashx":{"draws":9,"losses":6,"wins":9}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":21},"claude-fable-5":{"draws":2,"losses":0,"wins":16},"claude-fable-5-1":{"draws":6,"losses":12,"wins":20},"claude-opus-4-5":{"draws":3,"losses":1,"wins":26},"claude-opus-4-8":{"draws":3,"losses":0,"wins":17},"claude-opus-5":{"draws":5,"losses":11,"wins":28},"claude-opus-5-5":{"draws":8,"losses":17,"wins":19},"claude-sonnet-5":{"draws":0,"losses":0,"wins":30},"claude-sonnet-5-5":{"draws":1,"losses":1,"wins":30},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":40},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":36},"fireworks/ember-1":{"draws":5,"losses":0,"wins":43},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":45},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":25},"google/gemini-3.6-flash":{"draws":6,"losses":3,"wins":45},"google/gemini-3.8-flash":{"draws":1,"losses":0,"wins":13},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":3,"losses":0,"wins":17},"gpt-5.4":{"draws":1,"losses":1,"wins":10},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":19},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":22},"gpt-5.5":{"draws":3,"losses":0,"wins":21},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":27},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":20},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":16},"gpt-6-astra":{"draws":6,"losses":11,"wins":17},"gpt-6-luna":{"draws":5,"losses":0,"wins":23},"gpt-6-sol":{"draws":4,"losses":6,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":14,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":15},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":29},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":20},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":14},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":25},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":20},"o3":{"draws":1,"losses":0,"wins":29},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":25},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":27},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":14},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":0,"wins":27},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":10},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":25},"qwen/qwen3.8-max-0902":{"draws":4,"losses":0,"wins":36},"stealth/ox-alpha":{"draws":1,"losses":1,"wins":80},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":8},"tencent/hy4-preview":{"draws":1,"losses":0,"wins":19},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":23},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":25},"x-ai/grok-4.5":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":28},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":44},"z-ai/glm-5.3":{"draws":4,"losses":2,"wins":18},"z-ai/glm-5.3-flash":{"draws":1,"losses":0,"wins":15},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":34}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":8,"wins":10},"claude-fable-5":{"draws":11,"losses":35,"wins":8},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-opus-4-5":{"draws":16,"losses":30,"wins":16},"claude-opus-4-8":{"draws":9,"losses":12,"wins":5},"claude-opus-5":{"draws":7,"losses":26,"wins":5},"claude-opus-5-5":{"draws":3,"losses":24,"wins":1},"claude-sonnet-5":{"draws":26,"losses":21,"wins":11},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":16,"losses":14,"wins":20},"deepseek/deepseek-v4-pro":{"draws":27,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":13,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":12,"wins":0},"fireworks/ember-1":{"draws":11,"losses":13,"wins":2},"gemini-3.1-pro-preview":{"draws":6,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":26,"losses":20,"wins":18},"google/gemini-3.5-flash-lite":{"draws":47,"losses":32,"wins":25},"google/gemini-3.6-flash":{"draws":29,"losses":35,"wins":16},"google/gemini-3.8-flash":{"draws":16,"losses":23,"wins":13},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":6},"gpt-4.1":{"draws":4,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":6,"wins":4},"gpt-5.4":{"draws":18,"losses":13,"wins":15},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":8,"wins":11},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":34,"losses":9,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":27,"losses":17,"wins":12},"gpt-6-astra":{"draws":2,"losses":38,"wins":2},"gpt-6-luna":{"draws":14,"losses":8,"wins":4},"gpt-6-sol":{"draws":5,"losses":19,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":16},"inclusionai/ling-3.0-flash":{"draws":9,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":16,"losses":3,"wins":15},"meta/muse-glimmer-30b":{"draws":35,"losses":5,"wins":8},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":8},"meta/muse-spark-1.3":{"draws":15,"losses":23,"wins":8},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":12,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":1},"o3":{"draws":14,"losses":21,"wins":17},"openai/gpt-oss-120b":{"draws":29,"losses":17,"wins":4},"poolside/laguna-s-2.1":{"draws":21,"losses":8,"wins":7},"qwen/qwen3.7-max":{"draws":11,"losses":2,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":19,"wins":15},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":12,"losses":16,"wins":6},"qwen/qwen3.8-max":{"draws":21,"losses":26,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":8,"wins":3},"stealth/ox-alpha":{"draws":64,"losses":71,"wins":41},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":12},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":6},"tencent/hy4-preview":{"draws":18,"losses":26,"wins":12},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":11},"thinkingmachines/inkling-small":{"draws":32,"losses":9,"wins":17},"x-ai/grok-4.5":{"draws":12,"losses":18,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":33,"wins":9},"x-ai/grok-4.7":{"draws":2,"losses":19,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":23,"losses":11,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":32,"losses":24,"wins":14},"z-ai/glm-5.3":{"draws":13,"losses":25,"wins":4},"z-ai/glm-5.3-flash":{"draws":21,"losses":27,"wins":12},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":4}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":29},"claude-fable-5":{"draws":18,"losses":37,"wins":17},"claude-fable-5-1":{"draws":4,"losses":63,"wins":1},"claude-opus-4-5":{"draws":22,"losses":16,"wins":30},"claude-opus-4-8":{"draws":5,"losses":10,"wins":15},"claude-opus-5":{"draws":5,"losses":37,"wins":6},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":22,"losses":26,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":30,"losses":15,"wins":33},"deepseek/deepseek-v4-pro":{"draws":16,"losses":8,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":26,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":3,"wins":3},"fireworks/ember-1":{"draws":4,"losses":6,"wins":2},"gemini-3.1-pro-preview":{"draws":8,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":23,"losses":22,"wins":33},"google/gemini-3.5-flash-lite":{"draws":41,"losses":24,"wins":43},"google/gemini-3.6-flash":{"draws":28,"losses":48,"wins":38},"google/gemini-3.8-flash":{"draws":27,"losses":36,"wins":13},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":5},"gpt-4.1":{"draws":5,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":14,"losses":5,"wins":13},"gpt-5.4":{"draws":31,"losses":24,"wins":15},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":17},"gpt-5.5":{"draws":10,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":23,"losses":9,"wins":26},"gpt-5.6-sol":{"draws":9,"losses":35,"wins":20},"gpt-5.6-terra":{"draws":29,"losses":24,"wins":17},"gpt-6-astra":{"draws":6,"losses":57,"wins":3},"gpt-6-luna":{"draws":9,"losses":11,"wins":8},"gpt-6-sol":{"draws":3,"losses":20,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":20,"losses":4,"wins":20},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":20},"meta/muse-glimmer-30b":{"draws":25,"losses":10,"wins":25},"meta/muse-spark-1.2":{"draws":8,"losses":20,"wins":14},"meta/muse-spark-1.3":{"draws":18,"losses":23,"wins":17},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":12,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":19,"wins":17},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":5},"o3":{"draws":19,"losses":19,"wins":42},"openai/gpt-oss-120b":{"draws":25,"losses":7,"wins":20},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":22,"wins":20},"qwen/qwen3.8-27b":{"draws":5,"losses":24,"wins":15},"qwen/qwen3.8-flash":{"draws":15,"losses":15,"wins":14},"qwen/qwen3.8-max":{"draws":21,"losses":25,"wins":16},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":69,"losses":90,"wins":55},"stealth/space-bunny-alpha":{"draws":4,"losses":4,"wins":8},"stepfun/step-3.7-flash":{"draws":11,"losses":3,"wins":14},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":8},"tencent/hy4-preview":{"draws":21,"losses":25,"wins":18},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":31},"thinkingmachines/inkling-small":{"draws":34,"losses":0,"wins":36},"x-ai/grok-4.5":{"draws":12,"losses":21,"wins":27},"x-ai/grok-4.6":{"draws":24,"losses":35,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":24,"losses":6,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":32,"losses":36,"wins":32},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":29,"losses":31,"wins":20},"z-ai/glm-5.3-flashx":{"draws":0,"losses":4,"wins":6}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":7,"wins":29},"claude-fable-5":{"draws":18,"losses":37,"wins":17},"claude-fable-5-1":{"draws":4,"losses":69,"wins":1},"claude-opus-4-5":{"draws":16,"losses":18,"wins":48},"claude-opus-4-8":{"draws":12,"losses":7,"wins":11},"claude-opus-5":{"draws":6,"losses":52,"wins":10},"claude-opus-5-5":{"draws":0,"losses":19,"wins":1},"claude-sonnet-5":{"draws":24,"losses":15,"wins":35},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":34,"losses":7,"wins":29},"deepseek/deepseek-v4-pro":{"draws":17,"losses":21,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":8,"wins":1},"fireworks/ember-1":{"draws":4,"losses":0,"wins":10},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":14},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":6},"google/gemini-3.5-flash":{"draws":28,"losses":22,"wins":32},"google/gemini-3.5-flash-lite":{"draws":44,"losses":11,"wins":61},"google/gemini-3.6-flash":{"draws":29,"losses":47,"wins":48},"google/gemini-3.8-flash":{"draws":15,"losses":29,"wins":32},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":13},"gpt-4.1":{"draws":7,"losses":1,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":12,"losses":8,"wins":22},"gpt-5.4":{"draws":20,"losses":18,"wins":24},"gpt-5.4-mini":{"draws":11,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":19},"gpt-5.5":{"draws":6,"losses":13,"wins":11},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":26},"gpt-5.6-sol":{"draws":10,"losses":41,"wins":23},"gpt-5.6-terra":{"draws":25,"losses":12,"wins":27},"gpt-6-astra":{"draws":8,"losses":56,"wins":0},"gpt-6-luna":{"draws":10,"losses":9,"wins":7},"gpt-6-sol":{"draws":5,"losses":13,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":20,"losses":3,"wins":31},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":31},"meta/muse-glimmer-30b":{"draws":20,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":22},"meta/muse-spark-1.3":{"draws":19,"losses":20,"wins":23},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":11},"mistralai/mistral-medium-3-5":{"draws":15,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":24,"losses":5,"wins":23},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":1,"wins":11},"o3":{"draws":14,"losses":6,"wins":44},"openai/gpt-oss-120b":{"draws":26,"losses":6,"wins":20},"poolside/laguna-s-2.1":{"draws":18,"losses":4,"wins":22},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":33},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":17},"qwen/qwen3.8-flash":{"draws":17,"losses":16,"wins":17},"qwen/qwen3.8-max":{"draws":22,"losses":16,"wins":30},"qwen/qwen3.8-max-0902":{"draws":10,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":56,"losses":66,"wins":102},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":1,"wins":13},"tencent/hy3-preview":{"draws":13,"losses":5,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":25,"wins":30},"thinkingmachines/inkling":{"draws":14,"losses":17,"wins":25},"thinkingmachines/inkling-small":{"draws":22,"losses":12,"wins":32},"x-ai/grok-4.5":{"draws":13,"losses":13,"wins":24},"x-ai/grok-4.6":{"draws":22,"losses":34,"wins":22},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":26,"losses":7,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":3},"z-ai/glm-5.2":{"draws":29,"losses":35,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":35,"wins":21},"z-ai/glm-5.3-flash":{"draws":17,"losses":42,"wins":21},"z-ai/glm-5.3-flashx":{"draws":6,"losses":7,"wins":3}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":13},"claude-fable-5":{"draws":4,"losses":11,"wins":13},"claude-fable-5-1":{"draws":3,"losses":24,"wins":1},"claude-opus-4-5":{"draws":10,"losses":2,"wins":32},"claude-opus-4-8":{"draws":4,"losses":3,"wins":9},"claude-opus-5":{"draws":7,"losses":28,"wins":7},"claude-opus-5-5":{"draws":4,"losses":39,"wins":7},"claude-sonnet-5":{"draws":8,"losses":4,"wins":16},"claude-sonnet-5-5":{"draws":6,"losses":17,"wins":13},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":31},"deepseek/deepseek-v4-pro":{"draws":5,"losses":2,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":17},"fireworks/ember-1":{"draws":12,"losses":9,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":9,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":11},"google/gemini-3.5-flash-lite":{"draws":6,"losses":4,"wins":26},"google/gemini-3.6-flash":{"draws":7,"losses":10,"wins":19},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":3,"losses":0,"wins":11},"gpt-5":{"draws":3,"losses":0,"wins":7},"gpt-5.4":{"draws":8,"losses":3,"wins":5},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":14},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":13},"gpt-5.5":{"draws":6,"losses":1,"wins":13},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":5},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":18},"gpt-6-astra":{"draws":2,"losses":16,"wins":2},"gpt-6-luna":{"draws":12,"losses":8,"wins":26},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":3,"losses":28,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":16},"meituan/longcat-2.0":{"draws":9,"losses":1,"wins":20},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":14},"meta/muse-spark-1.2":{"draws":4,"losses":1,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":3,"wins":15},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":8},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":15},"o3":{"draws":4,"losses":5,"wins":17},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":11},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":7,"wins":15},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.8-flash":{"draws":5,"losses":1,"wins":14},"qwen/qwen3.8-max":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":9,"wins":25},"stealth/ox-alpha":{"draws":11,"losses":14,"wins":33},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":22},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":3,"losses":7,"wins":10},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":20},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":18},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":17},"x-ai/grok-4.6":{"draws":6,"losses":10,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":21,"wins":16},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":24},"z-ai/glm-5.3":{"draws":8,"losses":9,"wins":3},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":16},"z-ai/glm-5.3-flashx":{"draws":13,"losses":12,"wins":23}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":18},"claude-fable-5":{"draws":3,"losses":11,"wins":10},"claude-fable-5-1":{"draws":1,"losses":33,"wins":2},"claude-opus-4-5":{"draws":6,"losses":4,"wins":20},"claude-opus-4-8":{"draws":4,"losses":5,"wins":7},"claude-opus-5":{"draws":6,"losses":24,"wins":6},"claude-opus-5-5":{"draws":3,"losses":29,"wins":6},"claude-sonnet-5":{"draws":9,"losses":6,"wins":19},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":32},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":9,"wins":26},"fireworks/ember-1":{"draws":8,"losses":5,"wins":19},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":29},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":12},"google/gemini-3.5-flash-lite":{"draws":7,"losses":10,"wins":17},"google/gemini-3.6-flash":{"draws":7,"losses":14,"wins":19},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":17},"gpt-5.4":{"draws":8,"losses":6,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":12},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":15},"gpt-5.5":{"draws":7,"losses":1,"wins":14},"gpt-5.6-luna":{"draws":5,"losses":7,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":7},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":9},"gpt-6-astra":{"draws":0,"losses":17,"wins":3},"gpt-6-luna":{"draws":6,"losses":1,"wins":15},"gpt-6-sol":{"draws":7,"losses":25,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":14},"meituan/longcat-2.0":{"draws":8,"losses":1,"wins":25},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":16},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":8},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":19},"o3":{"draws":2,"losses":6,"wins":14},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":20},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":11},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":12},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":4,"wins":7},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":6},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.8-max":{"draws":3,"losses":7,"wins":16},"qwen/qwen3.8-max-0902":{"draws":10,"losses":13,"wins":21},"stealth/ox-alpha":{"draws":12,"losses":25,"wins":43},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":8},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":19},"thinkingmachines/inkling-small":{"draws":6,"losses":1,"wins":21},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":1},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":12,"losses":8,"wins":24},"z-ai/glm-5.3":{"draws":6,"losses":12,"wins":8},"z-ai/glm-5.3-flash":{"draws":4,"losses":7,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":14,"wins":22}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":4,"wins":17},"claude-fable-5":{"draws":0,"losses":9,"wins":7},"claude-fable-5-1":{"draws":0,"losses":25,"wins":3},"claude-opus-4-5":{"draws":3,"losses":8,"wins":15},"claude-opus-4-8":{"draws":6,"losses":7,"wins":9},"claude-opus-5":{"draws":2,"losses":27,"wins":9},"claude-opus-5-5":{"draws":1,"losses":42,"wins":7},"claude-sonnet-5":{"draws":4,"losses":6,"wins":12},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":2,"losses":6,"wins":26},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":8,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":12,"wins":22},"fireworks/ember-1":{"draws":6,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":22},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":12},"google/gemini-3.5-flash-lite":{"draws":6,"losses":7,"wins":27},"google/gemini-3.6-flash":{"draws":4,"losses":15,"wins":31},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":9},"gpt-4.1":{"draws":2,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":9},"gpt-5.4":{"draws":3,"losses":8,"wins":19},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":13},"gpt-5.5":{"draws":4,"losses":6,"wins":12},"gpt-5.6-luna":{"draws":7,"losses":4,"wins":25},"gpt-5.6-sol":{"draws":1,"losses":8,"wins":7},"gpt-5.6-terra":{"draws":4,"losses":7,"wins":7},"gpt-6-astra":{"draws":2,"losses":29,"wins":1},"gpt-6-luna":{"draws":4,"losses":4,"wins":18},"gpt-6-sol":{"draws":6,"losses":21,"wins":17},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":16},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":22},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":10},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":12},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":12},"o3":{"draws":1,"losses":8,"wins":19},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":18},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":8},"qwen/qwen3.8-max":{"draws":4,"losses":8,"wins":16},"qwen/qwen3.8-max-0902":{"draws":7,"losses":12,"wins":21},"stealth/ox-alpha":{"draws":11,"losses":25,"wins":40},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":10},"tencent/hy4-preview":{"draws":2,"losses":11,"wins":13},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":20},"thinkingmachines/inkling-small":{"draws":1,"losses":4,"wins":19},"x-ai/grok-4.5":{"draws":4,"losses":9,"wins":7},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":21,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":5,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":8,"losses":6,"wins":28},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":15},"z-ai/glm-5.3-flash":{"draws":4,"losses":8,"wins":8},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":19}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":10,"wins":2},"claude-fable-5":{"draws":3,"losses":16,"wins":1},"claude-fable-5-1":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":17,"losses":48,"wins":5},"claude-opus-4-8":{"draws":11,"losses":39,"wins":2},"claude-opus-5":{"draws":7,"losses":47,"wins":2},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":10,"losses":10,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":18,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":21,"wins":14},"deepseek/deepseek-v4-pro":{"draws":5,"losses":9,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":10,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":4,"wins":0},"fireworks/ember-1":{"draws":6,"losses":12,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":9,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":3},"google/gemini-3.5-flash-lite":{"draws":21,"losses":19,"wins":10},"google/gemini-3.6-flash":{"draws":14,"losses":32,"wins":4},"google/gemini-3.8-flash":{"draws":4,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":14,"wins":5},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-5":{"draws":12,"losses":19,"wins":1},"gpt-5.4":{"draws":5,"losses":13,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":34,"wins":12},"gpt-5.5":{"draws":9,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":6},"gpt-5.6-sol":{"draws":1,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":9,"losses":13,"wins":4},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":5,"losses":12,"wins":1},"gpt-6-sol":{"draws":1,"losses":11,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":9},"meituan/longcat-2.0":{"draws":13,"losses":12,"wins":9},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":4},"meta/muse-spark-1.2":{"draws":6,"losses":10,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":7,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":9,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":14,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":9,"wins":4},"o3":{"draws":6,"losses":36,"wins":6},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":10,"losses":9,"wins":7},"qwen/qwen3.7-max":{"draws":3,"losses":12,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":8,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":11,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.8-max":{"draws":2,"losses":12,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":36,"wins":4},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":13,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":4,"losses":12,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling-small":{"draws":4,"losses":6,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":23,"wins":1},"x-ai/grok-4.6":{"draws":2,"losses":14,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":17,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":31,"losses":18,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":21,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":15,"losses":26,"wins":11},"z-ai/glm-5.3":{"draws":1,"losses":14,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":10,"wins":2}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":3,"wins":31},"claude-fable-5":{"draws":10,"losses":45,"wins":21},"claude-fable-5-1":{"draws":5,"losses":69,"wins":10},"claude-opus-4-5":{"draws":20,"losses":11,"wins":43},"claude-opus-4-8":{"draws":12,"losses":9,"wins":9},"claude-opus-5":{"draws":11,"losses":46,"wins":7},"claude-opus-5-5":{"draws":3,"losses":24,"wins":5},"claude-sonnet-5":{"draws":15,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":15,"losses":7,"wins":44},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":10,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":8,"wins":15},"fireworks/ember-1":{"draws":4,"losses":4,"wins":12},"gemini-3.1-pro-preview":{"draws":2,"losses":3,"wins":13},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":9,"losses":4,"wins":29},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":63},"google/gemini-3.6-flash":{"draws":23,"losses":22,"wins":57},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":34},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":7},"gpt-4.1":{"draws":5,"losses":1,"wins":10},"gpt-5":{"draws":11,"losses":3,"wins":14},"gpt-5.4":{"draws":9,"losses":21,"wins":26},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":20},"gpt-5.5":{"draws":13,"losses":5,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":10,"wins":31},"gpt-5.6-sol":{"draws":9,"losses":35,"wins":32},"gpt-5.6-terra":{"draws":26,"losses":16,"wins":30},"gpt-6-astra":{"draws":12,"losses":51,"wins":3},"gpt-6-luna":{"draws":9,"losses":6,"wins":17},"gpt-6-sol":{"draws":2,"losses":13,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":11,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":20},"meituan/longcat-2.0":{"draws":15,"losses":2,"wins":41},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":27},"meta/muse-spark-1.3":{"draws":8,"losses":30,"wins":26},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":20,"wins":28},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":16},"o3":{"draws":6,"losses":11,"wins":45},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":34},"poolside/laguna-s-2.1":{"draws":10,"losses":2,"wins":36},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":22,"wins":37},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":31},"qwen/qwen3.8-max":{"draws":22,"losses":10,"wins":30},"qwen/qwen3.8-max-0902":{"draws":3,"losses":7,"wins":8},"stealth/ox-alpha":{"draws":54,"losses":71,"wins":101},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":12},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":32,"wins":27},"thinkingmachines/inkling":{"draws":10,"losses":3,"wins":37},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":29},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":28},"x-ai/grok-4.6":{"draws":21,"losses":37,"wins":24},"x-ai/grok-4.7":{"draws":2,"losses":11,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":7,"wins":8},"z-ai/glm-5.2":{"draws":12,"losses":24,"wins":44},"z-ai/glm-5.3":{"draws":10,"losses":38,"wins":14},"z-ai/glm-5.3-flash":{"draws":11,"losses":31,"wins":40},"z-ai/glm-5.3-flashx":{"draws":8,"losses":9,"wins":13}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":33,"wins":32},"claude-fable-5":{"draws":17,"losses":59,"wins":14},"claude-fable-5-1":{"draws":9,"losses":75,"wins":0},"claude-opus-4-5":{"draws":57,"losses":82,"wins":65},"claude-opus-4-8":{"draws":7,"losses":41,"wins":10},"claude-opus-5":{"draws":14,"losses":96,"wins":8},"claude-opus-5-5":{"draws":2,"losses":26,"wins":0},"claude-sonnet-5":{"draws":50,"losses":81,"wins":53},"claude-sonnet-5-5":{"draws":7,"losses":19,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":36,"losses":37,"wins":37},"deepseek/deepseek-v4-pro":{"draws":22,"losses":49,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":49,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":15,"wins":11},"fireworks/ember-1":{"draws":16,"losses":9,"wins":5},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":13},"google/gemini-3.1-flash-lite":{"draws":14,"losses":9,"wins":15},"google/gemini-3.5-flash":{"draws":28,"losses":54,"wins":32},"google/gemini-3.5-flash-lite":{"draws":96,"losses":123,"wins":135},"google/gemini-3.6-flash":{"draws":82,"losses":176,"wins":80},"google/gemini-3.8-flash":{"draws":13,"losses":63,"wins":8},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":11},"gpt-4.1":{"draws":3,"losses":9,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":20,"losses":22,"wins":10},"gpt-5.4":{"draws":35,"losses":88,"wins":41},"gpt-5.4-mini":{"draws":9,"losses":17,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":24},"gpt-5.5":{"draws":17,"losses":27,"wins":6},"gpt-5.6-luna":{"draws":57,"losses":53,"wins":68},"gpt-5.6-sol":{"draws":27,"losses":131,"wins":12},"gpt-5.6-terra":{"draws":28,"losses":45,"wins":29},"gpt-6-astra":{"draws":8,"losses":70,"wins":2},"gpt-6-luna":{"draws":7,"losses":25,"wins":8},"gpt-6-sol":{"draws":1,"losses":26,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":33,"losses":13,"wins":44},"inclusionai/ling-3.0-flash":{"draws":24,"losses":21,"wins":35},"meituan/longcat-2.0":{"draws":26,"losses":49,"wins":74},"meta/muse-glimmer-30b":{"draws":30,"losses":26,"wins":40},"meta/muse-spark-1.2":{"draws":29,"losses":61,"wins":38},"meta/muse-spark-1.3":{"draws":16,"losses":48,"wins":18},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":11},"mistralai/mistral-medium-3-5":{"draws":23,"losses":14,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":50,"losses":89,"wins":51},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":21,"wins":18},"o3":{"draws":21,"losses":140,"wins":99},"openai/gpt-oss-120b":{"draws":32,"losses":24,"wins":42},"poolside/laguna-s-2.1":{"draws":64,"losses":44,"wins":48},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":49,"wins":30},"qwen/qwen3.8-27b":{"draws":7,"losses":33,"wins":16},"qwen/qwen3.8-flash":{"draws":27,"losses":32,"wins":13},"qwen/qwen3.8-max":{"draws":32,"losses":37,"wins":21},"qwen/qwen3.8-max-0902":{"draws":5,"losses":15,"wins":2},"stealth/ox-alpha":{"draws":65,"losses":171,"wins":84},"stealth/space-bunny-alpha":{"draws":10,"losses":13,"wins":5},"stepfun/step-3.7-flash":{"draws":13,"losses":28,"wins":23},"tencent/hy3-preview":{"draws":9,"losses":11,"wins":12},"tencent/hy4-preview":{"draws":26,"losses":49,"wins":29},"thinkingmachines/inkling":{"draws":57,"losses":45,"wins":80},"thinkingmachines/inkling-small":{"draws":36,"losses":43,"wins":32},"x-ai/grok-4.5":{"draws":43,"losses":84,"wins":43},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":17,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":51,"losses":60,"wins":69},"z-ai/glm-5.3":{"draws":21,"losses":58,"wins":7},"z-ai/glm-5.3-flash":{"draws":26,"losses":68,"wins":14},"z-ai/glm-5.3-flashx":{"draws":3,"losses":13,"wins":8}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":40},"claude-fable-5":{"draws":9,"losses":50,"wins":45},"claude-fable-5-1":{"draws":10,"losses":73,"wins":15},"claude-opus-4-5":{"draws":35,"losses":47,"wins":100},"claude-opus-4-8":{"draws":10,"losses":20,"wins":28},"claude-opus-5":{"draws":26,"losses":94,"wins":24},"claude-opus-5-5":{"draws":5,"losses":39,"wins":4},"claude-sonnet-5":{"draws":16,"losses":38,"wins":98},"claude-sonnet-5-5":{"draws":5,"losses":20,"wins":23},"cohere/north-mini-code":{"draws":10,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":68},"deepseek/deepseek-v4-pro":{"draws":22,"losses":22,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":18,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":9,"wins":18},"fireworks/ember-1":{"draws":5,"losses":8,"wins":27},"gemini-3.1-pro-preview":{"draws":3,"losses":10,"wins":31},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":26,"losses":34,"wins":50},"google/gemini-3.5-flash-lite":{"draws":78,"losses":36,"wins":210},"google/gemini-3.6-flash":{"draws":43,"losses":88,"wins":151},"google/gemini-3.8-flash":{"draws":15,"losses":36,"wins":53},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":10},"gpt-4.1":{"draws":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":21,"wins":31},"gpt-5.4":{"draws":25,"losses":70,"wins":63},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":19},"gpt-5.5":{"draws":12,"losses":24,"wins":22},"gpt-5.6-luna":{"draws":26,"losses":38,"wins":78},"gpt-5.6-sol":{"draws":16,"losses":71,"wins":79},"gpt-5.6-terra":{"draws":19,"losses":16,"wins":49},"gpt-6-astra":{"draws":6,"losses":63,"wins":13},"gpt-6-luna":{"draws":12,"losses":6,"wins":40},"gpt-6-sol":{"draws":5,"losses":24,"wins":13},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":15,"losses":6,"wins":23},"inclusionai/ling-3.0-flash":{"draws":28,"losses":5,"wins":31},"meituan/longcat-2.0":{"draws":27,"losses":15,"wins":90},"meta/muse-glimmer-30b":{"draws":22,"losses":3,"wins":47},"meta/muse-spark-1.2":{"draws":15,"losses":40,"wins":61},"meta/muse-spark-1.3":{"draws":3,"losses":33,"wins":40},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":31,"losses":32,"wins":117},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":39},"o3":{"draws":41,"losses":42,"wins":151},"openai/gpt-oss-120b":{"draws":18,"losses":4,"wins":40},"poolside/laguna-s-2.1":{"draws":35,"losses":4,"wins":67},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":29,"wins":51},"qwen/qwen3.8-27b":{"draws":20,"losses":9,"wins":27},"qwen/qwen3.8-flash":{"draws":27,"losses":12,"wins":35},"qwen/qwen3.8-max":{"draws":21,"losses":22,"wins":48},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":14},"stealth/ox-alpha":{"draws":48,"losses":82,"wins":144},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":30},"stepfun/step-3.7-flash":{"draws":13,"losses":1,"wins":51},"tencent/hy3-preview":{"draws":7,"losses":12,"wins":21},"tencent/hy4-preview":{"draws":20,"losses":24,"wins":56},"thinkingmachines/inkling":{"draws":38,"losses":23,"wins":89},"thinkingmachines/inkling-small":{"draws":20,"losses":8,"wins":46},"x-ai/grok-4.5":{"draws":19,"losses":52,"wins":95},"x-ai/grok-4.6":{"draws":17,"losses":36,"wins":49},"x-ai/grok-4.7":{"draws":0,"losses":22,"wins":16},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":16,"losses":4,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":25,"losses":20,"wins":83},"z-ai/glm-5.3":{"draws":9,"losses":51,"wins":26},"z-ai/glm-5.3-flash":{"draws":27,"losses":37,"wins":46},"z-ai/glm-5.3-flashx":{"draws":5,"losses":8,"wins":19}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":39},"claude-fable-5":{"draws":9,"losses":33,"wins":28},"claude-fable-5-1":{"draws":9,"losses":55,"wins":8},"claude-opus-4-5":{"draws":10,"losses":15,"wins":41},"claude-opus-4-8":{"draws":1,"losses":9,"wins":14},"claude-opus-5":{"draws":4,"losses":48,"wins":16},"claude-opus-5-5":{"draws":3,"losses":16,"wins":3},"claude-sonnet-5":{"draws":8,"losses":18,"wins":42},"claude-sonnet-5-5":{"draws":2,"losses":4,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":4,"wins":45},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":21,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":7},"fireworks/ember-1":{"draws":1,"losses":6,"wins":15},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":16},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":14,"losses":7,"wins":41},"google/gemini-3.5-flash-lite":{"draws":10,"losses":4,"wins":70},"google/gemini-3.6-flash":{"draws":10,"losses":29,"wins":59},"google/gemini-3.8-flash":{"draws":9,"losses":17,"wins":20},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":10},"gpt-4.1":{"draws":2,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":6,"wins":19},"gpt-5.4":{"draws":13,"losses":33,"wins":30},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":11},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":24},"gpt-5.5":{"draws":4,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":31},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":34},"gpt-5.6-terra":{"draws":16,"losses":18,"wins":24},"gpt-6-astra":{"draws":8,"losses":56,"wins":6},"gpt-6-luna":{"draws":9,"losses":5,"wins":14},"gpt-6-sol":{"draws":4,"losses":7,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":10,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":27},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":17},"meituan/longcat-2.0":{"draws":10,"losses":2,"wins":27},"meta/muse-glimmer-30b":{"draws":6,"losses":6,"wins":30},"meta/muse-spark-1.2":{"draws":3,"losses":13,"wins":32},"meta/muse-spark-1.3":{"draws":7,"losses":28,"wins":19},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":28},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":13},"o3":{"draws":5,"losses":10,"wins":43},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":34},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":30},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":23,"wins":38},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":24},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":24},"qwen/qwen3.8-max":{"draws":13,"losses":19,"wins":24},"qwen/qwen3.8-max-0902":{"draws":6,"losses":6,"wins":10},"stealth/ox-alpha":{"draws":34,"losses":57,"wins":118},"stealth/space-bunny-alpha":{"draws":5,"losses":3,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":18},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":4,"losses":20,"wins":22},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":28},"thinkingmachines/inkling-small":{"draws":16,"losses":10,"wins":32},"x-ai/grok-4.5":{"draws":7,"losses":24,"wins":23},"x-ai/grok-4.6":{"draws":9,"losses":26,"wins":35},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":15,"losses":20,"wins":57},"z-ai/glm-5.3":{"draws":11,"losses":43,"wins":20},"z-ai/glm-5.3-flash":{"draws":18,"losses":23,"wins":35},"z-ai/glm-5.3-flashx":{"draws":5,"losses":5,"wins":12}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":10},"claude-fable-5":{"draws":9,"losses":17,"wins":10},"claude-fable-5-1":{"draws":1,"losses":26,"wins":1},"claude-opus-4-5":{"draws":44,"losses":15,"wins":23},"claude-opus-4-8":{"draws":19,"losses":33,"wins":14},"claude-opus-5":{"draws":9,"losses":100,"wins":9},"claude-opus-5-5":{"draws":1,"losses":16,"wins":3},"claude-sonnet-5":{"draws":12,"losses":15,"wins":9},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":2},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":29,"losses":2,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":11,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":8,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":4,"wins":4},"fireworks/ember-1":{"draws":6,"losses":8,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":1},"google/gemini-3.1-flash-lite":{"draws":16,"losses":2,"wins":28},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":15},"google/gemini-3.5-flash-lite":{"draws":35,"losses":15,"wins":20},"google/gemini-3.6-flash":{"draws":27,"losses":36,"wins":23},"google/gemini-3.8-flash":{"draws":3,"losses":16,"wins":13},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":10,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":11,"losses":3,"wins":18},"gpt-5.4":{"draws":8,"losses":14,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":9},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":35},"gpt-5.5":{"draws":23,"losses":27,"wins":16},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":9},"gpt-6-astra":{"draws":1,"losses":28,"wins":1},"gpt-6-luna":{"draws":11,"losses":6,"wins":9},"gpt-6-sol":{"draws":0,"losses":10,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":9,"losses":4,"wins":11},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":19},"meituan/longcat-2.0":{"draws":14,"losses":15,"wins":13},"meta/muse-glimmer-30b":{"draws":12,"losses":2,"wins":16},"meta/muse-spark-1.2":{"draws":7,"losses":9,"wins":10},"meta/muse-spark-1.3":{"draws":12,"losses":12,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":3,"wins":22},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":10},"nex-agi/nex-n2-pro":{"draws":13,"losses":2,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":2,"wins":31},"o3":{"draws":13,"losses":22,"wins":35},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":18,"losses":20,"wins":8},"qwen/qwen3.7-max":{"draws":17,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":7,"wins":12},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":15},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":7,"wins":5},"qwen/qwen3.8-max-0902":{"draws":8,"losses":1,"wins":3},"stealth/ox-alpha":{"draws":30,"losses":51,"wins":29},"stealth/space-bunny-alpha":{"draws":6,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":14,"losses":0,"wins":22},"tencent/hy3-preview":{"draws":17,"losses":12,"wins":19},"tencent/hy4-preview":{"draws":10,"losses":7,"wins":7},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":4,"wins":20},"x-ai/grok-4.5":{"draws":10,"losses":25,"wins":15},"x-ai/grok-4.6":{"draws":11,"losses":19,"wins":8},"x-ai/grok-4.7":{"draws":1,"losses":11,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":49,"losses":13,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":38,"losses":27,"wins":29},"z-ai/glm-5.3":{"draws":1,"losses":17,"wins":4},"z-ai/glm-5.3-flash":{"draws":16,"losses":21,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":3,"wins":7}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":21},"claude-fable-5":{"draws":16,"losses":23,"wins":37},"claude-fable-5-1":{"draws":8,"losses":48,"wins":12},"claude-opus-4-5":{"draws":12,"losses":12,"wins":62},"claude-opus-4-8":{"draws":4,"losses":8,"wins":16},"claude-opus-5":{"draws":5,"losses":34,"wins":9},"claude-opus-5-5":{"draws":1,"losses":19,"wins":4},"claude-sonnet-5":{"draws":14,"losses":18,"wins":66},"claude-sonnet-5-5":{"draws":4,"losses":6,"wins":12},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":9,"losses":7,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":7,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":14},"fireworks/ember-1":{"draws":2,"losses":5,"wins":13},"gemini-3.1-pro-preview":{"draws":2,"losses":8,"wins":14},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":48},"google/gemini-3.5-flash-lite":{"draws":20,"losses":13,"wins":131},"google/gemini-3.6-flash":{"draws":27,"losses":28,"wins":103},"google/gemini-3.8-flash":{"draws":5,"losses":17,"wins":38},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":12},"gpt-4.1":{"draws":2,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":1,"wins":13},"gpt-5.4":{"draws":12,"losses":6,"wins":57},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":9},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":26},"gpt-5.5":{"draws":7,"losses":6,"wins":11},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":79},"gpt-5.6-sol":{"draws":23,"losses":38,"wins":55},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":52},"gpt-6-astra":{"draws":6,"losses":51,"wins":7},"gpt-6-luna":{"draws":6,"losses":4,"wins":14},"gpt-6-sol":{"draws":0,"losses":11,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":18,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":7,"losses":0,"wins":49},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":20,"wins":53},"meta/muse-spark-1.3":{"draws":4,"losses":13,"wins":31},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":15,"wins":65},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":6},"o3":{"draws":0,"losses":9,"wins":93},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":19},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":35},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":13,"wins":26},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-max":{"draws":8,"losses":17,"wins":27},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":12},"stealth/ox-alpha":{"draws":52,"losses":40,"wins":95},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":17},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":24},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":7},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":35},"thinkingmachines/inkling":{"draws":13,"losses":14,"wins":41},"thinkingmachines/inkling-small":{"draws":7,"losses":3,"wins":22},"x-ai/grok-4.5":{"draws":15,"losses":14,"wins":54},"x-ai/grok-4.6":{"draws":12,"losses":15,"wins":43},"x-ai/grok-4.7":{"draws":3,"losses":12,"wins":5},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":16,"losses":16,"wins":42},"z-ai/glm-5.3":{"draws":3,"losses":28,"wins":33},"z-ai/glm-5.3-flash":{"draws":11,"losses":13,"wins":32},"z-ai/glm-5.3-flashx":{"draws":1,"losses":0,"wins":13}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":2,"wins":23},"claude-fable-5":{"draws":4,"losses":12,"wins":12},"claude-fable-5-1":{"draws":0,"losses":24,"wins":6},"claude-opus-4-5":{"draws":18,"losses":7,"wins":55},"claude-opus-4-8":{"draws":7,"losses":10,"wins":39},"claude-opus-5":{"draws":6,"losses":67,"wins":65},"claude-opus-5-5":{"draws":2,"losses":16,"wins":4},"claude-sonnet-5":{"draws":5,"losses":2,"wins":19},"claude-sonnet-5-5":{"draws":5,"losses":9,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":13,"losses":0,"wins":27},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":6,"wins":6},"fireworks/ember-1":{"draws":8,"losses":4,"wins":8},"gemini-3.1-pro-preview":{"draws":5,"losses":4,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":3,"wins":17},"google/gemini-3.5-flash-lite":{"draws":14,"losses":6,"wins":32},"google/gemini-3.6-flash":{"draws":17,"losses":15,"wins":32},"google/gemini-3.8-flash":{"draws":5,"losses":3,"wins":20},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":6},"gpt-4.1":{"draws":1,"losses":1,"wins":8},"gpt-5":{"draws":11,"losses":5,"wins":44},"gpt-5.4":{"draws":10,"losses":8,"wins":12},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":17},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":40},"gpt-5.5":{"draws":20,"losses":5,"wins":19},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":4,"wins":17},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":14},"gpt-6-astra":{"draws":1,"losses":10,"wins":1},"gpt-6-luna":{"draws":14,"losses":3,"wins":17},"gpt-6-sol":{"draws":4,"losses":14,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":15,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":26},"meituan/longcat-2.0":{"draws":10,"losses":5,"wins":21},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":16},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":9},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":2,"wins":30},"o3":{"draws":4,"losses":4,"wins":48},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":16},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":26},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":23},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":9},"qwen/qwen3.8-flash":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.8-max":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.8-max-0902":{"draws":11,"losses":7,"wins":10},"stealth/ox-alpha":{"draws":9,"losses":12,"wins":33},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":22},"tencent/hy3-preview":{"draws":16,"losses":0,"wins":20},"tencent/hy4-preview":{"draws":7,"losses":7,"wins":14},"thinkingmachines/inkling":{"draws":8,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":18,"losses":15,"wins":31},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":12},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":17,"losses":2,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":19,"losses":6,"wins":47},"z-ai/glm-5.3":{"draws":3,"losses":13,"wins":6},"z-ai/glm-5.3-flash":{"draws":3,"losses":16,"wins":13},"z-ai/glm-5.3-flashx":{"draws":7,"losses":8,"wins":9}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":13,"wins":23},"claude-fable-5":{"draws":17,"losses":28,"wins":21},"claude-fable-5-1":{"draws":5,"losses":55,"wins":6},"claude-opus-4-5":{"draws":36,"losses":20,"wins":38},"claude-opus-4-8":{"draws":15,"losses":9,"wins":6},"claude-opus-5":{"draws":5,"losses":36,"wins":3},"claude-opus-5-5":{"draws":1,"losses":19,"wins":0},"claude-sonnet-5":{"draws":36,"losses":29,"wins":53},"claude-sonnet-5-5":{"draws":9,"losses":12,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":33,"losses":4,"wins":39},"deepseek/deepseek-v4-pro":{"draws":18,"losses":11,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":10,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":3,"wins":6},"fireworks/ember-1":{"draws":12,"losses":6,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":27,"losses":14,"wins":25},"google/gemini-3.5-flash-lite":{"draws":77,"losses":28,"wins":83},"google/gemini-3.6-flash":{"draws":49,"losses":55,"wins":66},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":27},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":7},"gpt-4.1":{"draws":4,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":8,"wins":14},"gpt-5.4":{"draws":46,"losses":47,"wins":26},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":16},"gpt-5.5":{"draws":9,"losses":13,"wins":10},"gpt-5.6-luna":{"draws":37,"losses":11,"wins":31},"gpt-5.6-sol":{"draws":19,"losses":48,"wins":31},"gpt-5.6-terra":{"draws":29,"losses":11,"wins":34},"gpt-6-astra":{"draws":10,"losses":50,"wins":0},"gpt-6-luna":{"draws":10,"losses":7,"wins":9},"gpt-6-sol":{"draws":4,"losses":13,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":16,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":27,"losses":2,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":19},"meituan/longcat-2.0":{"draws":20,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":31,"losses":3,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":27,"wins":27},"meta/muse-spark-1.3":{"draws":16,"losses":17,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":11},"mistralai/mistral-medium-3-5":{"draws":20,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":36,"losses":23,"wins":39},"nex-agi/nex-n2-pro":{"draws":8,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":1,"wins":13},"o3":{"draws":18,"losses":22,"wins":66},"openai/gpt-oss-120b":{"draws":26,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":32,"losses":8,"wins":26},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":5,"wins":27},"qwen/qwen3.8-27b":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":16,"wins":14},"qwen/qwen3.8-max":{"draws":21,"losses":21,"wins":17},"qwen/qwen3.8-max-0902":{"draws":12,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":51,"losses":64,"wins":66},"stealth/space-bunny-alpha":{"draws":12,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":10,"losses":5,"wins":13},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":6},"tencent/hy4-preview":{"draws":27,"losses":16,"wins":19},"thinkingmachines/inkling":{"draws":27,"losses":5,"wins":46},"thinkingmachines/inkling-small":{"draws":25,"losses":10,"wins":21},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":58},"x-ai/grok-4.6":{"draws":18,"losses":29,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":16,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":1,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":11,"wins":5},"z-ai/glm-5.2":{"draws":41,"losses":22,"wins":19},"z-ai/glm-5.3":{"draws":13,"losses":32,"wins":13},"z-ai/glm-5.3-flash":{"draws":18,"losses":25,"wins":25},"z-ai/glm-5.3-flashx":{"draws":11,"losses":3,"wins":6}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":32},"claude-fable-5":{"draws":5,"losses":24,"wins":45},"claude-fable-5-1":{"draws":9,"losses":45,"wins":24},"claude-opus-4-5":{"draws":4,"losses":24,"wins":88},"claude-opus-4-8":{"draws":7,"losses":4,"wins":21},"claude-opus-5":{"draws":8,"losses":38,"wins":18},"claude-opus-5-5":{"draws":4,"losses":14,"wins":8},"claude-sonnet-5":{"draws":0,"losses":8,"wins":116},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":19},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":49},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":23},"fireworks/ember-1":{"draws":3,"losses":4,"wins":15},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":21},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":12,"wins":58},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":171},"google/gemini-3.6-flash":{"draws":11,"losses":30,"wins":121},"google/gemini-3.8-flash":{"draws":6,"losses":11,"wins":45},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":13},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":0,"wins":20},"gpt-5.4":{"draws":8,"losses":28,"wins":72},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":24},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":24},"gpt-5.5":{"draws":3,"losses":6,"wins":9},"gpt-5.6-luna":{"draws":4,"losses":10,"wins":86},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":72},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":56},"gpt-6-astra":{"draws":9,"losses":59,"wins":12},"gpt-6-luna":{"draws":3,"losses":2,"wins":23},"gpt-6-sol":{"draws":2,"losses":10,"wins":16},"gpt-6.1-sol":{"draws":3,"losses":11,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":22},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":30},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":57},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":23},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":72},"meta/muse-spark-1.3":{"draws":7,"losses":9,"wins":40},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":78},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":19},"o3":{"draws":0,"losses":16,"wins":92},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":61},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":12},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":43},"qwen/qwen3.8-27b":{"draws":2,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":3,"losses":7,"wins":32},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":48},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":17},"stealth/ox-alpha":{"draws":20,"losses":25,"wins":168},"stealth/space-bunny-alpha":{"draws":2,"losses":0,"wins":14},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":19},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":15},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":36},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":59},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":51},"x-ai/grok-4.5":{"draws":8,"losses":7,"wins":69},"x-ai/grok-4.6":{"draws":11,"losses":21,"wins":48},"x-ai/grok-4.7":{"draws":4,"losses":12,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":1,"losses":1,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":8},"z-ai/glm-5.2":{"draws":5,"losses":2,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":22,"wins":42},"z-ai/glm-5.3-flash":{"draws":8,"losses":17,"wins":49},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":14}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":6,"wins":29},"claude-fable-5":{"draws":22,"losses":33,"wins":15},"claude-fable-5-1":{"draws":5,"losses":53,"wins":2},"claude-opus-4-5":{"draws":26,"losses":23,"wins":25},"claude-opus-4-8":{"draws":4,"losses":12,"wins":16},"claude-opus-5":{"draws":6,"losses":36,"wins":2},"claude-opus-5-5":{"draws":1,"losses":24,"wins":1},"claude-sonnet-5":{"draws":22,"losses":13,"wins":25},"claude-sonnet-5-5":{"draws":8,"losses":11,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":14},"deepseek/deepseek-v4-flash":{"draws":26,"losses":11,"wins":47},"deepseek/deepseek-v4-pro":{"draws":17,"losses":20,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":16,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":7},"fireworks/ember-1":{"draws":7,"losses":4,"wins":13},"gemini-3.1-pro-preview":{"draws":13,"losses":3,"wins":16},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":19},"google/gemini-3.5-flash":{"draws":18,"losses":14,"wins":38},"google/gemini-3.5-flash-lite":{"draws":31,"losses":17,"wins":58},"google/gemini-3.6-flash":{"draws":36,"losses":39,"wins":33},"google/gemini-3.8-flash":{"draws":18,"losses":24,"wins":20},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":6},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":3,"wins":17},"gpt-5.4":{"draws":19,"losses":28,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":12},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":10},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":16,"losses":18,"wins":28},"gpt-5.6-sol":{"draws":13,"losses":39,"wins":16},"gpt-5.6-terra":{"draws":9,"losses":15,"wins":12},"gpt-6-astra":{"draws":2,"losses":57,"wins":3},"gpt-6-luna":{"draws":3,"losses":11,"wins":14},"gpt-6-sol":{"draws":5,"losses":14,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":15,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":20,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":22},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":26},"meta/muse-glimmer-30b":{"draws":23,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":26,"wins":16},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":23,"losses":12,"wins":21},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":18},"o3":{"draws":5,"losses":20,"wins":35},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":30},"poolside/laguna-s-2.1":{"draws":15,"losses":4,"wins":27},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":28,"wins":12},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":19},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":22},"qwen/qwen3.8-max":{"draws":24,"losses":27,"wins":17},"qwen/qwen3.8-max-0902":{"draws":3,"losses":4,"wins":3},"stealth/ox-alpha":{"draws":48,"losses":71,"wins":73},"stealth/space-bunny-alpha":{"draws":4,"losses":3,"wins":15},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":6},"tencent/hy4-preview":{"draws":14,"losses":23,"wins":25},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":36},"thinkingmachines/inkling-small":{"draws":23,"losses":7,"wins":40},"x-ai/grok-4.5":{"draws":18,"losses":30,"wins":22},"x-ai/grok-4.6":{"draws":17,"losses":41,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":17,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":3,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":10,"wins":8},"z-ai/glm-5.2":{"draws":41,"losses":18,"wins":47},"z-ai/glm-5.3":{"draws":26,"losses":32,"wins":10},"z-ai/glm-5.3-flash":{"draws":15,"losses":28,"wins":25},"z-ai/glm-5.3-flashx":{"draws":4,"losses":12,"wins":6}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":4,"wins":34},"claude-fable-5":{"draws":3,"losses":13,"wins":62},"claude-fable-5-1":{"draws":5,"losses":21,"wins":60},"claude-opus-4-5":{"draws":2,"losses":5,"wins":77},"claude-opus-4-8":{"draws":1,"losses":1,"wins":22},"claude-opus-5":{"draws":4,"losses":2,"wins":42},"claude-opus-5-5":{"draws":4,"losses":7,"wins":17},"claude-sonnet-5":{"draws":0,"losses":4,"wins":70},"claude-sonnet-5-5":{"draws":2,"losses":5,"wins":25},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":57},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":25},"fireworks/ember-1":{"draws":0,"losses":1,"wins":25},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":27},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":60},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":85},"google/gemini-3.6-flash":{"draws":4,"losses":1,"wins":81},"google/gemini-3.8-flash":{"draws":5,"losses":3,"wins":56},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":12},"gpt-4.1":{"draws":0,"losses":0,"wins":12},"gpt-5":{"draws":0,"losses":1,"wins":23},"gpt-5.4":{"draws":2,"losses":7,"wins":57},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":16},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":26},"gpt-5.5":{"draws":0,"losses":0,"wins":22},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":43},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":65},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":67},"gpt-6-astra":{"draws":1,"losses":11,"wins":34},"gpt-6-luna":{"draws":2,"losses":0,"wins":24},"gpt-6-sol":{"draws":1,"losses":2,"wins":15},"gpt-6.1-sol":{"draws":3,"losses":4,"wins":25},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":26},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":40},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":28},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":57},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":13},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":60},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":24},"o3":{"draws":1,"losses":2,"wins":53},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":40},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":1,"wins":55},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":34},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":53},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":21},"stealth/ox-alpha":{"draws":8,"losses":4,"wins":182},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":0,"losses":5,"wins":51},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":40},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":42},"x-ai/grok-4.5":{"draws":1,"losses":0,"wins":55},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":82},"x-ai/grok-4.7":{"draws":3,"losses":3,"wins":14},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":0,"wins":13},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":71},"z-ai/glm-5.3":{"draws":4,"losses":0,"wins":64},"z-ai/glm-5.3-flash":{"draws":8,"losses":2,"wins":68},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":22}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":9,"losses":26,"wins":13},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":7,"losses":17,"wins":20},"claude-opus-5":{"draws":11,"losses":61,"wins":10},"claude-opus-5-5":{"draws":8,"losses":43,"wins":1},"claude-sonnet-5":{"draws":8,"losses":14,"wins":26},"cohere/north-mini-code":{"draws":1,"losses":7,"wins":14},"deepseek/deepseek-v4-flash":{"draws":10,"losses":13,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":19,"wins":21},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":29},"google/gemini-3.5-flash-lite":{"draws":12,"losses":19,"wins":53},"google/gemini-3.6-flash":{"draws":13,"losses":35,"wins":36},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":2,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":14,"wins":23},"gpt-5.4":{"draws":11,"losses":18,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":32},"gpt-5.5":{"draws":9,"losses":18,"wins":17},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":11,"losses":26,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":9,"losses":36,"wins":3},"gpt-6-luna":{"draws":4,"losses":9,"wins":17},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":2,"losses":6,"wins":24},"meituan/longcat-2.0":{"draws":5,"losses":8,"wins":38},"meta/muse-glimmer-30b":{"draws":4,"losses":8,"wins":30},"meta/muse-spark-1.2":{"draws":8,"losses":11,"wins":15},"meta/muse-spark-1.3":{"draws":4,"losses":18,"wins":22},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":9,"wins":31},"o3":{"draws":0,"losses":17,"wins":41},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":14,"wins":28},"qwen/qwen3.7-max":{"draws":2,"losses":8,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":1,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":14,"wins":20},"stealth/ox-alpha":{"draws":31,"losses":57,"wins":68},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":20},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":7,"losses":11,"wins":36},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":34},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":19},"x-ai/grok-4.6":{"draws":11,"losses":26,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":14,"losses":14,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":5},"z-ai/glm-5.2":{"draws":21,"losses":26,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":4,"wins":18},"claude-fable-5":{"draws":2,"losses":6,"wins":16},"claude-fable-5-1":{"draws":1,"losses":4,"wins":15},"claude-opus-4-5":{"draws":2,"losses":5,"wins":27},"claude-opus-4-8":{"draws":2,"losses":3,"wins":17},"claude-opus-5":{"draws":6,"losses":9,"wins":15},"claude-opus-5-5":{"draws":6,"losses":27,"wins":19},"claude-sonnet-5":{"draws":1,"losses":0,"wins":19},"claude-sonnet-5-5":{"draws":3,"losses":10,"wins":29},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":3,"wins":35},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":8,"wins":35},"fireworks/ember-1":{"draws":3,"losses":5,"wins":34},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":31},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":22},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":33},"google/gemini-3.6-flash":{"draws":4,"losses":6,"wins":24},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":16},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":10},"gpt-4.1":{"draws":2,"losses":2,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":10},"gpt-5.4":{"draws":1,"losses":0,"wins":17},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":14},"gpt-5.5":{"draws":2,"losses":1,"wins":13},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":19},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":17},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":27},"gpt-6-astra":{"draws":1,"losses":14,"wins":5},"gpt-6-luna":{"draws":4,"losses":5,"wins":37},"gpt-6-sol":{"draws":3,"losses":8,"wins":21},"gpt-6.1-sol":{"draws":4,"losses":23,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":1,"losses":2,"wins":17},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":25},"meta/muse-glimmer-30b":{"draws":0,"losses":4,"wins":12},"meta/muse-spark-1.2":{"draws":1,"losses":0,"wins":13},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":14},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":18},"o3":{"draws":0,"losses":2,"wins":22},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":20},"poolside/laguna-s-2.1":{"draws":1,"losses":4,"wins":15},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":4,"wins":17},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":12},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":15},"qwen/qwen3.8-max":{"draws":0,"losses":6,"wins":22},"qwen/qwen3.8-max-0902":{"draws":1,"losses":9,"wins":36},"stealth/ox-alpha":{"draws":9,"losses":7,"wins":48},"stealth/space-bunny-alpha":{"draws":0,"losses":4,"wins":28},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":16},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":2,"losses":4,"wins":12},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":22},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":19},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":24},"x-ai/grok-4.6":{"draws":1,"losses":3,"wins":30},"x-ai/grok-4.7":{"draws":5,"losses":15,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":4,"losses":7,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":22},"z-ai/glm-5.2":{"draws":3,"losses":0,"wins":33},"z-ai/glm-5.3":{"draws":6,"losses":3,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":23},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":36}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":26},"claude-fable-5":{"draws":1,"losses":2,"wins":21},"claude-fable-5-1":{"draws":4,"losses":6,"wins":18},"claude-opus-4-5":{"draws":0,"losses":0,"wins":42},"claude-opus-4-8":{"draws":1,"losses":1,"wins":18},"claude-opus-5":{"draws":5,"losses":7,"wins":30},"claude-opus-5-5":{"draws":3,"losses":17,"wins":20},"claude-sonnet-5":{"draws":0,"losses":0,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":7,"wins":39},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":38},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":30},"fireworks/ember-1":{"draws":0,"losses":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":46},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":20},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":27},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":30},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":34},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":13},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":18},"gpt-5.4":{"draws":2,"losses":3,"wins":21},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":21},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":15},"gpt-5.5":{"draws":1,"losses":2,"wins":15},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":24},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":21},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":12},"gpt-6-astra":{"draws":5,"losses":8,"wins":11},"gpt-6-luna":{"draws":0,"losses":0,"wins":28},"gpt-6-sol":{"draws":3,"losses":3,"wins":38},"gpt-6.1-sol":{"draws":2,"losses":7,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":22},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":16},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":34},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":26},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":24},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":19},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":14},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":1,"losses":0,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":22},"o3":{"draws":0,"losses":0,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":25},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":22},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":12},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":14},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":29},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":40},"stealth/ox-alpha":{"draws":2,"losses":2,"wins":64},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":12},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":17},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":27},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":24},"x-ai/grok-4.5":{"draws":0,"losses":0,"wins":20},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":20},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":46},"z-ai/glm-5.3":{"draws":0,"losses":2,"wins":20},"z-ai/glm-5.3-flash":{"draws":0,"losses":0,"wins":12},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":36}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":0},"claude-fable-5":{"draws":7,"losses":1,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":2,"wins":0},"claude-opus-4-8":{"draws":4,"losses":0,"wins":0},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-opus-5-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":9,"losses":1,"wins":0},"claude-sonnet-5-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":5,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":0},"fireworks/ember-1":{"draws":2,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":14,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":5,"wins":0},"google/gemini-3.8-flash":{"draws":1,"losses":5,"wins":0},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":9,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":0},"gpt-5.5":{"draws":1,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":0},"gpt-6-astra":{"draws":1,"losses":3,"wins":0},"gpt-6-luna":{"draws":1,"losses":0,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":3,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.8-27b":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":28,"losses":10,"wins":4},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":6,"losses":3,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":4,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":9,"wins":13},"claude-fable-5":{"draws":11,"losses":25,"wins":0},"claude-fable-5-1":{"draws":2,"losses":26,"wins":0},"claude-opus-4-5":{"draws":23,"losses":26,"wins":1},"claude-opus-4-8":{"draws":6,"losses":19,"wins":1},"claude-opus-5":{"draws":3,"losses":19,"wins":2},"claude-opus-5-5":{"draws":2,"losses":30,"wins":0},"claude-sonnet-5":{"draws":20,"losses":28,"wins":0},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":30,"losses":26,"wins":4},"deepseek/deepseek-v4-pro":{"draws":18,"losses":18,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":23,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":12,"wins":0},"fireworks/ember-1":{"draws":13,"losses":11,"wins":0},"gemini-3.1-pro-preview":{"draws":14,"losses":6,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":24,"losses":31,"wins":1},"google/gemini-3.5-flash-lite":{"draws":43,"losses":42,"wins":5},"google/gemini-3.6-flash":{"draws":37,"losses":40,"wins":5},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":1},"gpt-4.1":{"draws":3,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":6,"losses":6,"wins":0},"gpt-5.4":{"draws":23,"losses":13,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":6},"gpt-5.5":{"draws":10,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":26,"losses":12,"wins":8},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":0},"gpt-5.6-terra":{"draws":20,"losses":28,"wins":4},"gpt-6-astra":{"draws":5,"losses":29,"wins":0},"gpt-6-luna":{"draws":15,"losses":10,"wins":3},"gpt-6-sol":{"draws":3,"losses":15,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":20,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":13,"losses":9,"wins":8},"meituan/longcat-2.0":{"draws":21,"losses":21,"wins":8},"meta/muse-glimmer-30b":{"draws":26,"losses":17,"wins":7},"meta/muse-spark-1.2":{"draws":14,"losses":28,"wins":0},"meta/muse-spark-1.3":{"draws":11,"losses":16,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":16,"losses":12,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":19,"losses":18,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":6},"o3":{"draws":13,"losses":38,"wins":5},"openai/gpt-oss-120b":{"draws":26,"losses":11,"wins":13},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":2},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":14,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.8-flash":{"draws":16,"losses":17,"wins":3},"qwen/qwen3.8-max":{"draws":25,"losses":17,"wins":4},"qwen/qwen3.8-max-0902":{"draws":12,"losses":14,"wins":0},"stealth/ox-alpha":{"draws":37,"losses":60,"wins":11},"stealth/space-bunny-alpha":{"draws":12,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":0},"thinkingmachines/inkling-small":{"draws":26,"losses":20,"wins":8},"x-ai/grok-4.5":{"draws":18,"losses":18,"wins":0},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":17,"losses":14,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":7,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":0},"z-ai/glm-5.2":{"draws":32,"losses":39,"wins":7},"z-ai/glm-5.3":{"draws":18,"losses":17,"wins":1},"z-ai/glm-5.3-flash":{"draws":16,"losses":23,"wins":3},"z-ai/glm-5.3-flashx":{"draws":10,"losses":15,"wins":1}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":12,"wins":19},"claude-fable-5":{"draws":13,"losses":34,"wins":3},"claude-fable-5-1":{"draws":4,"losses":36,"wins":1},"claude-opus-4-5":{"draws":21,"losses":25,"wins":8},"claude-opus-4-8":{"draws":11,"losses":9,"wins":6},"claude-opus-5":{"draws":4,"losses":29,"wins":3},"claude-opus-5-5":{"draws":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":26,"losses":20,"wins":12},"claude-sonnet-5-5":{"draws":5,"losses":15,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":39,"losses":14,"wins":21},"deepseek/deepseek-v4-pro":{"draws":18,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":6,"wins":3},"fireworks/ember-1":{"draws":14,"losses":6,"wins":2},"gemini-3.1-pro-preview":{"draws":14,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":9},"google/gemini-3.5-flash":{"draws":18,"losses":20,"wins":16},"google/gemini-3.5-flash-lite":{"draws":42,"losses":31,"wins":27},"google/gemini-3.6-flash":{"draws":34,"losses":38,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":9,"losses":10,"wins":3},"gpt-5.4":{"draws":22,"losses":20,"wins":8},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":9,"losses":5,"wins":4},"gpt-5.5":{"draws":15,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":34,"losses":14,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":32,"losses":15,"wins":7},"gpt-6-astra":{"draws":4,"losses":40,"wins":0},"gpt-6-luna":{"draws":11,"losses":11,"wins":4},"gpt-6-sol":{"draws":1,"losses":19,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":28,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":26,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":20,"losses":9,"wins":17},"meta/muse-glimmer-30b":{"draws":13,"losses":2,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":18,"losses":10,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":24,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":22,"losses":15,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":4},"o3":{"draws":16,"losses":22,"wins":12},"openai/gpt-oss-120b":{"draws":30,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":13},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":14,"wins":14},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":7},"qwen/qwen3.8-flash":{"draws":15,"losses":11,"wins":14},"qwen/qwen3.8-max":{"draws":17,"losses":19,"wins":16},"qwen/qwen3.8-max-0902":{"draws":16,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":44,"losses":85,"wins":31},"stealth/space-bunny-alpha":{"draws":10,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":0},"tencent/hy4-preview":{"draws":17,"losses":25,"wins":8},"thinkingmachines/inkling":{"draws":26,"losses":9,"wins":21},"thinkingmachines/inkling-small":{"draws":29,"losses":4,"wins":21},"x-ai/grok-4.5":{"draws":21,"losses":19,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":18,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":3,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":0},"z-ai/glm-5.2":{"draws":37,"losses":26,"wins":15},"z-ai/glm-5.3":{"draws":12,"losses":22,"wins":6},"z-ai/glm-5.3-flash":{"draws":17,"losses":31,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":11,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":8},"claude-fable-5":{"draws":6,"losses":6,"wins":8},"claude-fable-5-1":{"draws":1,"losses":13,"wins":2},"claude-opus-4-5":{"draws":5,"losses":5,"wins":14},"claude-opus-4-8":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":10,"wins":2},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":2,"losses":15,"wins":13},"claude-sonnet-5-5":{"draws":2,"losses":0,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":14},"fireworks/ember-1":{"draws":2,"losses":1,"wins":1},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":12,"wins":8},"google/gemini-3.5-flash-lite":{"draws":4,"losses":13,"wins":25},"google/gemini-3.6-flash":{"draws":9,"losses":13,"wins":28},"google/gemini-3.8-flash":{"draws":1,"losses":10,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":2,"losses":2,"wins":10},"gpt-5.4":{"draws":1,"losses":20,"wins":9},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":5},"gpt-5.5":{"draws":5,"losses":1,"wins":6},"gpt-5.6-luna":{"draws":0,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":0,"losses":25,"wins":3},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":14},"gpt-6-astra":{"draws":4,"losses":16,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":1,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":4},"meta/muse-glimmer-30b":{"draws":0,"losses":3,"wins":11},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":9},"meta/muse-spark-1.3":{"draws":2,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":11},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":3,"losses":13,"wins":14},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":1,"losses":6,"wins":11},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":6},"qwen/qwen3.8-max":{"draws":2,"losses":4,"wins":6},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":36,"wins":24},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":18},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":11},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":23},"z-ai/glm-5.3":{"draws":5,"losses":6,"wins":9},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":10},"z-ai/glm-5.3-flashx":{"draws":0,"losses":1,"wins":1}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":25},"claude-fable-5":{"draws":8,"losses":23,"wins":25},"claude-fable-5-1":{"draws":4,"losses":53,"wins":3},"claude-opus-4-5":{"draws":11,"losses":6,"wins":45},"claude-opus-4-8":{"draws":7,"losses":6,"wins":11},"claude-opus-5":{"draws":8,"losses":35,"wins":11},"claude-opus-5-5":{"draws":0,"losses":13,"wins":1},"claude-sonnet-5":{"draws":11,"losses":4,"wins":19},"claude-sonnet-5-5":{"draws":5,"losses":14,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":34},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":1,"wins":3},"fireworks/ember-1":{"draws":5,"losses":1,"wins":6},"gemini-3.1-pro-preview":{"draws":7,"losses":4,"wins":15},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":35},"google/gemini-3.5-flash-lite":{"draws":7,"losses":7,"wins":42},"google/gemini-3.6-flash":{"draws":5,"losses":14,"wins":45},"google/gemini-3.8-flash":{"draws":4,"losses":16,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":7},"gpt-4.1":{"draws":0,"losses":1,"wins":5},"gpt-5":{"draws":5,"losses":3,"wins":16},"gpt-5.4":{"draws":9,"losses":8,"wins":25},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":11},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":22},"gpt-5.5":{"draws":5,"losses":11,"wins":6},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":28},"gpt-5.6-sol":{"draws":13,"losses":14,"wins":25},"gpt-5.6-terra":{"draws":12,"losses":4,"wins":36},"gpt-6-astra":{"draws":5,"losses":43,"wins":8},"gpt-6-luna":{"draws":5,"losses":3,"wins":12},"gpt-6-sol":{"draws":3,"losses":5,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":9,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":13},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":10},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":14},"meta/muse-spark-1.2":{"draws":8,"losses":4,"wins":22},"meta/muse-spark-1.3":{"draws":4,"losses":5,"wins":15},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":7,"wins":20},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":10},"o3":{"draws":0,"losses":3,"wins":45},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":12,"losses":0,"wins":22},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":14,"wins":27},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":4,"wins":19},"qwen/qwen3.8-max":{"draws":8,"losses":7,"wins":33},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":28,"losses":43,"wins":78},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":21,"wins":23},"thinkingmachines/inkling":{"draws":9,"losses":2,"wins":15},"thinkingmachines/inkling-small":{"draws":8,"losses":3,"wins":21},"x-ai/grok-4.5":{"draws":8,"losses":12,"wins":28},"x-ai/grok-4.6":{"draws":14,"losses":20,"wins":26},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":4},"z-ai/glm-5.2":{"draws":12,"losses":9,"wins":33},"z-ai/glm-5.3":{"draws":16,"losses":22,"wins":14},"z-ai/glm-5.3-flash":{"draws":12,"losses":16,"wins":24},"z-ai/glm-5.3-flashx":{"draws":6,"losses":1,"wins":3}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":12,"wins":13},"claude-fable-5":{"draws":23,"losses":23,"wins":6},"claude-fable-5-1":{"draws":3,"losses":32,"wins":1},"claude-opus-4-5":{"draws":17,"losses":39,"wins":10},"claude-opus-4-8":{"draws":8,"losses":14,"wins":2},"claude-opus-5":{"draws":8,"losses":29,"wins":3},"claude-opus-5-5":{"draws":2,"losses":28,"wins":0},"claude-sonnet-5":{"draws":30,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":8,"losses":10,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":24,"losses":23,"wins":17},"deepseek/deepseek-v4-pro":{"draws":12,"losses":25,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":23,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":8,"wins":5},"fireworks/ember-1":{"draws":13,"losses":7,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":9,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":7,"wins":10},"google/gemini-3.5-flash":{"draws":21,"losses":32,"wins":9},"google/gemini-3.5-flash-lite":{"draws":44,"losses":40,"wins":26},"google/gemini-3.6-flash":{"draws":29,"losses":40,"wins":13},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":3},"gpt-4.1":{"draws":5,"losses":3,"wins":2},"gpt-5":{"draws":6,"losses":6,"wins":6},"gpt-5.4":{"draws":22,"losses":18,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":2},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":9},"gpt-5.5":{"draws":15,"losses":8,"wins":1},"gpt-5.6-luna":{"draws":30,"losses":24,"wins":8},"gpt-5.6-sol":{"draws":12,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":23,"losses":30,"wins":9},"gpt-6-astra":{"draws":2,"losses":36,"wins":0},"gpt-6-luna":{"draws":12,"losses":11,"wins":1},"gpt-6-sol":{"draws":3,"losses":14,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":21,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":24,"losses":11,"wins":17},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":11},"meituan/longcat-2.0":{"draws":23,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":30,"losses":18,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":18,"wins":6},"meta/muse-spark-1.3":{"draws":15,"losses":27,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":9,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":4},"o3":{"draws":8,"losses":38,"wins":10},"openai/gpt-oss-120b":{"draws":29,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":16,"losses":18,"wins":12},"qwen/qwen3.7-max":{"draws":8,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":32,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":12,"losses":18,"wins":4},"qwen/qwen3.8-max":{"draws":20,"losses":27,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":14,"wins":1},"stealth/ox-alpha":{"draws":46,"losses":85,"wins":37},"stealth/space-bunny-alpha":{"draws":6,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":2},"tencent/hy4-preview":{"draws":23,"losses":26,"wins":5},"thinkingmachines/inkling":{"draws":20,"losses":18,"wins":12},"thinkingmachines/inkling-small":{"draws":27,"losses":25,"wins":8},"x-ai/grok-4.5":{"draws":17,"losses":29,"wins":8},"x-ai/grok-4.6":{"draws":22,"losses":28,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":5,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":3,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":37,"losses":33,"wins":18},"z-ai/glm-5.3":{"draws":16,"losses":22,"wins":6},"z-ai/glm-5.3-flash":{"draws":16,"losses":27,"wins":11},"z-ai/glm-5.3-flashx":{"draws":13,"losses":8,"wins":3}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":3,"wins":9},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":6,"losses":54,"wins":2},"claude-opus-4-5":{"draws":39,"losses":10,"wins":33},"claude-opus-4-8":{"draws":11,"losses":7,"wins":8},"claude-opus-5":{"draws":10,"losses":41,"wins":5},"claude-opus-5-5":{"draws":1,"losses":19,"wins":0},"claude-sonnet-5":{"draws":22,"losses":11,"wins":25},"claude-sonnet-5-5":{"draws":4,"losses":7,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":15,"losses":12,"wins":21},"deepseek/deepseek-v4-pro":{"draws":14,"losses":4,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":5,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":5,"wins":7},"fireworks/ember-1":{"draws":5,"losses":6,"wins":3},"gemini-3.1-pro-preview":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":10},"google/gemini-3.5-flash-lite":{"draws":40,"losses":20,"wins":62},"google/gemini-3.6-flash":{"draws":24,"losses":46,"wins":50},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":16},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":4,"wins":13},"gpt-5.4":{"draws":20,"losses":15,"wins":21},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":2},"gpt-5.4-nano":{"draws":9,"losses":0,"wins":5},"gpt-5.5":{"draws":8,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":23},"gpt-5.6-sol":{"draws":26,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":19,"losses":6,"wins":25},"gpt-6-astra":{"draws":8,"losses":33,"wins":1},"gpt-6-luna":{"draws":4,"losses":6,"wins":10},"gpt-6-sol":{"draws":4,"losses":10,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":6,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":24},"meituan/longcat-2.0":{"draws":17,"losses":3,"wins":26},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":20},"meta/muse-spark-1.3":{"draws":19,"losses":5,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":21,"losses":5,"wins":30},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":9},"o3":{"draws":1,"losses":22,"wins":41},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":19},"poolside/laguna-s-2.1":{"draws":24,"losses":8,"wins":20},"qwen/qwen3.7-max":{"draws":5,"losses":0,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":5,"wins":16},"qwen/qwen3.8-27b":{"draws":10,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":2,"wins":7},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":15},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":7},"stealth/ox-alpha":{"draws":44,"losses":57,"wins":49},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":6,"wins":24},"thinkingmachines/inkling":{"draws":26,"losses":6,"wins":26},"thinkingmachines/inkling-small":{"draws":15,"losses":1,"wins":20},"x-ai/grok-4.5":{"draws":32,"losses":31,"wins":21},"x-ai/grok-4.6":{"draws":21,"losses":15,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":9,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":21,"losses":5,"wins":20},"z-ai/glm-5.3":{"draws":15,"losses":16,"wins":5},"z-ai/glm-5.3-flash":{"draws":15,"losses":32,"wins":5},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":9}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":5,"wins":8},"claude-fable-5":{"draws":14,"losses":27,"wins":1},"claude-fable-5-1":{"draws":4,"losses":36,"wins":0},"claude-opus-4-5":{"draws":62,"losses":59,"wins":9},"claude-opus-4-8":{"draws":25,"losses":43,"wins":8},"claude-opus-5":{"draws":19,"losses":85,"wins":2},"claude-opus-5-5":{"draws":2,"losses":36,"wins":0},"claude-sonnet-5":{"draws":21,"losses":14,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":17,"wins":4},"cohere/north-mini-code":{"draws":15,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":53,"losses":13,"wins":18},"deepseek/deepseek-v4-pro":{"draws":17,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":14,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":11,"losses":21,"wins":0},"gemini-3.1-pro-preview":{"draws":15,"losses":4,"wins":5},"google/gemini-3.1-flash-lite":{"draws":31,"losses":11,"wins":25},"google/gemini-3.5-flash":{"draws":26,"losses":23,"wins":9},"google/gemini-3.5-flash-lite":{"draws":41,"losses":28,"wins":25},"google/gemini-3.6-flash":{"draws":37,"losses":32,"wins":5},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":3},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":6},"gpt-4.1":{"draws":14,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":36,"losses":23,"wins":5},"gpt-5.4":{"draws":9,"losses":12,"wins":1},"gpt-5.4-mini":{"draws":31,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":24,"losses":23,"wins":19},"gpt-5.5":{"draws":29,"losses":31,"wins":0},"gpt-5.6-luna":{"draws":19,"losses":6,"wins":3},"gpt-5.6-sol":{"draws":7,"losses":21,"wins":0},"gpt-5.6-terra":{"draws":22,"losses":18,"wins":4},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":11,"losses":21,"wins":8},"gpt-6-sol":{"draws":1,"losses":25,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":30,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":3,"wins":6},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":9},"meituan/longcat-2.0":{"draws":31,"losses":13,"wins":24},"meta/muse-glimmer-30b":{"draws":22,"losses":3,"wins":3},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":1},"meta/muse-spark-1.3":{"draws":13,"losses":24,"wins":3},"minimax/minimax-m3":{"draws":24,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":12,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":15,"wins":1},"nex-agi/nex-n2-pro":{"draws":24,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":18,"wins":6},"o3":{"draws":28,"losses":40,"wins":16},"openai/gpt-oss-120b":{"draws":23,"losses":4,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":34,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":26,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":10,"wins":1},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":2},"qwen/qwen3.8-flash":{"draws":13,"losses":12,"wins":3},"qwen/qwen3.8-max":{"draws":19,"losses":15,"wins":2},"qwen/qwen3.8-max-0902":{"draws":13,"losses":15,"wins":2},"stealth/ox-alpha":{"draws":44,"losses":56,"wins":4},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":23,"losses":10,"wins":11},"tencent/hy3-preview":{"draws":35,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":13,"losses":17,"wins":2},"thinkingmachines/inkling":{"draws":38,"losses":24,"wins":34},"thinkingmachines/inkling-small":{"draws":29,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":30,"wins":2},"x-ai/grok-4.6":{"draws":17,"losses":20,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":1},"x-ai/grok-build-0.1":{"draws":18,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":79,"losses":17,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":12,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":10,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":14,"wins":1},"z-ai/glm-5.2":{"draws":73,"losses":40,"wins":11},"z-ai/glm-5.3":{"draws":12,"losses":19,"wins":3},"z-ai/glm-5.3-flash":{"draws":21,"losses":15,"wins":6},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":2}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":47,"wins":81},"claude-fable-5":{"draws":9,"losses":121,"wins":30},"claude-fable-5-1":{"draws":0,"losses":140,"wins":8},"claude-opus-4-5":{"draws":39,"losses":200,"wins":97},"claude-opus-4-8":{"draws":3,"losses":68,"wins":23},"claude-opus-5":{"draws":5,"losses":163,"wins":8},"claude-opus-5-5":{"draws":2,"losses":56,"wins":0},"claude-sonnet-5":{"draws":17,"losses":117,"wins":138},"claude-sonnet-5-5":{"draws":0,"losses":42,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4-flash":{"draws":19,"losses":66,"wins":109},"deepseek/deepseek-v4-pro":{"draws":19,"losses":77,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":74,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":27,"wins":14},"fireworks/ember-1":{"draws":5,"losses":33,"wins":20},"gemini-3.1-pro-preview":{"draws":7,"losses":19,"wins":24},"google/gemini-3.1-flash-lite":{"draws":5,"losses":7,"wins":62},"google/gemini-3.5-flash":{"draws":20,"losses":100,"wins":44},"google/gemini-3.5-flash-lite":{"draws":76,"losses":175,"wins":363},"google/gemini-3.6-flash":{"draws":71,"losses":295,"wins":204},"google/gemini-3.8-flash":{"draws":19,"losses":91,"wins":44},"google/gemma-4-31b-it":{"draws":2,"losses":8,"wins":28},"gpt-4.1":{"draws":0,"losses":16,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":6},"gpt-5":{"draws":12,"losses":55,"wins":33},"gpt-5.4":{"draws":24,"losses":169,"wins":55},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":23},"gpt-5.4-nano":{"draws":7,"losses":40,"wins":51},"gpt-5.5":{"draws":12,"losses":56,"wins":22},"gpt-5.6-luna":{"draws":31,"losses":105,"wins":134},"gpt-5.6-sol":{"draws":12,"losses":201,"wins":51},"gpt-5.6-terra":{"draws":20,"losses":68,"wins":68},"gpt-6-astra":{"draws":4,"losses":120,"wins":2},"gpt-6-luna":{"draws":9,"losses":34,"wins":27},"gpt-6-sol":{"draws":2,"losses":46,"wins":4},"gpt-6.1-sol":{"draws":0,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":16},"inception/mercury-2.5-preview":{"draws":15,"losses":15,"wins":66},"inclusionai/ling-3.0-flash":{"draws":10,"losses":26,"wins":82},"meituan/longcat-2.0":{"draws":16,"losses":60,"wins":140},"meta/muse-glimmer-30b":{"draws":28,"losses":19,"wins":81},"meta/muse-spark-1.2":{"draws":17,"losses":62,"wins":99},"meta/muse-spark-1.3":{"draws":6,"losses":93,"wins":39},"minimax/minimax-m3":{"draws":5,"losses":13,"wins":34},"mistralai/mistral-medium-3-5":{"draws":12,"losses":10,"wins":60},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":29,"losses":115,"wins":140},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":23,"wins":69},"o3":{"draws":37,"losses":169,"wins":196},"openai/gpt-oss-120b":{"draws":19,"losses":26,"wins":91},"poolside/laguna-s-2.1":{"draws":38,"losses":56,"wins":82},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":23},"qwen/qwen3.7-plus":{"draws":4,"losses":13,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":87,"wins":56},"qwen/qwen3.8-27b":{"draws":19,"losses":51,"wins":34},"qwen/qwen3.8-flash":{"draws":23,"losses":42,"wins":51},"qwen/qwen3.8-max":{"draws":24,"losses":84,"wins":60},"qwen/qwen3.8-max-0902":{"draws":7,"losses":24,"wins":9},"stealth/ox-alpha":{"draws":46,"losses":190,"wins":192},"stealth/space-bunny-alpha":{"draws":2,"losses":23,"wins":17},"stepfun/step-3.7-flash":{"draws":23,"losses":39,"wins":104},"tencent/hy3-preview":{"draws":9,"losses":28,"wins":29},"tencent/hy4-preview":{"draws":23,"losses":84,"wins":59},"thinkingmachines/inkling":{"draws":32,"losses":51,"wins":172},"thinkingmachines/inkling-small":{"draws":35,"losses":42,"wins":84},"x-ai/grok-4.5":{"draws":11,"losses":167,"wins":88},"x-ai/grok-4.6":{"draws":27,"losses":99,"wins":44},"x-ai/grok-4.7":{"draws":2,"losses":42,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":17},"xiaomi/mimo-v2.5":{"draws":15,"losses":17,"wins":80},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":26,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":25,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":14},"z-ai/glm-5.2":{"draws":33,"losses":78,"wins":109},"z-ai/glm-5.3":{"draws":9,"losses":100,"wins":31},"z-ai/glm-5.3-flash":{"draws":20,"losses":76,"wins":78},"z-ai/glm-5.3-flashx":{"draws":1,"losses":36,"wins":11}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":18,"losses":25,"wins":9},"claude-fable-5-1":{"draws":3,"losses":47,"wins":0},"claude-opus-4-5":{"draws":10,"losses":22,"wins":16},"claude-opus-4-8":{"draws":2,"losses":5,"wins":3},"claude-opus-5":{"draws":5,"losses":39,"wins":0},"claude-opus-5-5":{"draws":2,"losses":40,"wins":0},"claude-sonnet-5":{"draws":22,"losses":29,"wins":7},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":23,"losses":13,"wins":18},"deepseek/deepseek-v4-pro":{"draws":27,"losses":14,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":18,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":15,"wins":7},"fireworks/ember-1":{"draws":8,"losses":14,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":19,"losses":22,"wins":15},"google/gemini-3.5-flash-lite":{"draws":38,"losses":25,"wins":27},"google/gemini-3.6-flash":{"draws":34,"losses":43,"wins":13},"google/gemini-3.8-flash":{"draws":10,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":9,"losses":7,"wins":4},"gpt-5.4":{"draws":23,"losses":10,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":8},"gpt-5.5":{"draws":7,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":23,"losses":6,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":31,"wins":9},"gpt-5.6-terra":{"draws":24,"losses":22,"wins":12},"gpt-6-astra":{"draws":4,"losses":22,"wins":0},"gpt-6-luna":{"draws":11,"losses":16,"wins":5},"gpt-6-sol":{"draws":2,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":24,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":18},"meituan/longcat-2.0":{"draws":17,"losses":19,"wins":18},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":18,"wins":7},"meta/muse-spark-1.3":{"draws":9,"losses":20,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":8},"mistralai/mistral-medium-3-5":{"draws":23,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":13},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":11},"o3":{"draws":17,"losses":29,"wins":12},"openai/gpt-oss-120b":{"draws":21,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":28,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":20,"wins":6},"qwen/qwen3.8-27b":{"draws":5,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":16},"qwen/qwen3.8-max":{"draws":15,"losses":29,"wins":4},"qwen/qwen3.8-max-0902":{"draws":10,"losses":16,"wins":4},"stealth/ox-alpha":{"draws":42,"losses":62,"wins":41},"stealth/space-bunny-alpha":{"draws":2,"losses":9,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":15,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":8},"thinkingmachines/inkling-small":{"draws":32,"losses":12,"wins":10},"x-ai/grok-4.5":{"draws":17,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":14},"x-ai/grok-4.7":{"draws":0,"losses":22,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":10,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":1},"z-ai/glm-5.2":{"draws":32,"losses":32,"wins":16},"z-ai/glm-5.3":{"draws":18,"losses":18,"wins":4},"z-ai/glm-5.3-flash":{"draws":21,"losses":27,"wins":4},"z-ai/glm-5.3-flashx":{"draws":3,"losses":23,"wins":2}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":2,"wins":29},"claude-fable-5":{"draws":17,"losses":22,"wins":31},"claude-fable-5-1":{"draws":9,"losses":61,"wins":8},"claude-opus-4-5":{"draws":18,"losses":9,"wins":41},"claude-opus-4-8":{"draws":4,"losses":3,"wins":13},"claude-opus-5":{"draws":13,"losses":36,"wins":11},"claude-opus-5-5":{"draws":3,"losses":14,"wins":5},"claude-sonnet-5":{"draws":20,"losses":6,"wins":24},"claude-sonnet-5-5":{"draws":6,"losses":7,"wins":13},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":40},"deepseek/deepseek-v4-pro":{"draws":13,"losses":5,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":9,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":3,"wins":19},"fireworks/ember-1":{"draws":5,"losses":6,"wins":13},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":13,"losses":14,"wins":41},"google/gemini-3.5-flash-lite":{"draws":22,"losses":6,"wins":60},"google/gemini-3.6-flash":{"draws":24,"losses":22,"wins":46},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":34},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":7,"wins":21},"gpt-5.4":{"draws":10,"losses":16,"wins":38},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":26},"gpt-5.5":{"draws":11,"losses":7,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":27},"gpt-5.6-sol":{"draws":12,"losses":27,"wins":33},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":29},"gpt-6-astra":{"draws":1,"losses":57,"wins":6},"gpt-6-luna":{"draws":5,"losses":4,"wins":19},"gpt-6-sol":{"draws":4,"losses":11,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":15,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":21},"meituan/longcat-2.0":{"draws":9,"losses":3,"wins":28},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":29},"meta/muse-spark-1.2":{"draws":17,"losses":4,"wins":23},"meta/muse-spark-1.3":{"draws":14,"losses":13,"wins":29},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":23,"losses":12,"wins":19},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":13},"o3":{"draws":1,"losses":16,"wins":45},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":28},"poolside/laguna-s-2.1":{"draws":13,"losses":0,"wins":23},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":7,"wins":24},"qwen/qwen3.8-27b":{"draws":10,"losses":4,"wins":18},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-max":{"draws":16,"losses":12,"wins":34},"qwen/qwen3.8-max-0902":{"draws":6,"losses":2,"wins":14},"stealth/ox-alpha":{"draws":48,"losses":49,"wins":89},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":20,"wins":23},"thinkingmachines/inkling":{"draws":15,"losses":3,"wins":20},"thinkingmachines/inkling-small":{"draws":16,"losses":4,"wins":24},"x-ai/grok-4.5":{"draws":13,"losses":14,"wins":29},"x-ai/grok-4.6":{"draws":19,"losses":20,"wins":35},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":6},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":15,"losses":2,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":3,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":8},"z-ai/glm-5.2":{"draws":29,"losses":15,"wins":40},"z-ai/glm-5.3":{"draws":18,"losses":26,"wins":20},"z-ai/glm-5.3-flash":{"draws":10,"losses":20,"wins":42},"z-ai/glm-5.3-flashx":{"draws":8,"losses":2,"wins":12}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":9,"wins":28},"claude-fable-5":{"draws":4,"losses":30,"wins":18},"claude-fable-5-1":{"draws":3,"losses":54,"wins":1},"claude-opus-4-5":{"draws":9,"losses":15,"wins":36},"claude-opus-4-8":{"draws":4,"losses":6,"wins":12},"claude-opus-5":{"draws":6,"losses":27,"wins":3},"claude-opus-5-5":{"draws":2,"losses":12,"wins":0},"claude-sonnet-5":{"draws":6,"losses":15,"wins":23},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":4,"losses":17,"wins":35},"deepseek/deepseek-v4-pro":{"draws":3,"losses":17,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":8,"wins":7},"fireworks/ember-1":{"draws":2,"losses":7,"wins":9},"gemini-3.1-pro-preview":{"draws":1,"losses":2,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":33},"google/gemini-3.5-flash-lite":{"draws":8,"losses":11,"wins":63},"google/gemini-3.6-flash":{"draws":13,"losses":30,"wins":43},"google/gemini-3.8-flash":{"draws":8,"losses":26,"wins":26},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":16},"gpt-4.1":{"draws":1,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":9,"wins":16},"gpt-5.4":{"draws":10,"losses":28,"wins":18},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":10},"gpt-5.4-nano":{"draws":4,"losses":11,"wins":17},"gpt-5.5":{"draws":3,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":7,"losses":12,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":29,"wins":21},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":24},"gpt-6-astra":{"draws":0,"losses":54,"wins":0},"gpt-6-luna":{"draws":5,"losses":6,"wins":11},"gpt-6-sol":{"draws":3,"losses":12,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":2,"losses":3,"wins":25},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":22},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":29},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":32},"meta/muse-spark-1.2":{"draws":4,"losses":10,"wins":28},"meta/muse-spark-1.3":{"draws":4,"losses":14,"wins":22},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":22,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":13},"o3":{"draws":5,"losses":18,"wins":45},"openai/gpt-oss-120b":{"draws":1,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":24},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":0,"losses":7,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":8},"stealth/ox-alpha":{"draws":29,"losses":52,"wins":73},"stealth/space-bunny-alpha":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":8,"wins":13},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":16},"tencent/hy4-preview":{"draws":7,"losses":17,"wins":22},"thinkingmachines/inkling":{"draws":1,"losses":5,"wins":30},"thinkingmachines/inkling-small":{"draws":5,"losses":2,"wins":47},"x-ai/grok-4.5":{"draws":0,"losses":33,"wins":19},"x-ai/grok-4.6":{"draws":9,"losses":23,"wins":24},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":14,"losses":20,"wins":42},"z-ai/glm-5.3":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":28},"z-ai/glm-5.3-flashx":{"draws":5,"losses":6,"wins":3}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":16,"wins":23},"claude-fable-5":{"draws":13,"losses":44,"wins":17},"claude-fable-5-1":{"draws":2,"losses":64,"wins":2},"claude-opus-4-5":{"draws":22,"losses":14,"wins":30},"claude-opus-4-8":{"draws":3,"losses":11,"wins":12},"claude-opus-5":{"draws":5,"losses":40,"wins":7},"claude-opus-5-5":{"draws":3,"losses":25,"wins":2},"claude-sonnet-5":{"draws":10,"losses":14,"wins":30},"claude-sonnet-5-5":{"draws":6,"losses":15,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":23,"losses":17,"wins":34},"deepseek/deepseek-v4-pro":{"draws":17,"losses":17,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":15,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":10,"wins":14},"fireworks/ember-1":{"draws":10,"losses":10,"wins":14},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":21,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":28,"losses":17,"wins":51},"google/gemini-3.6-flash":{"draws":20,"losses":39,"wins":43},"google/gemini-3.8-flash":{"draws":20,"losses":34,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":7},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":3,"wins":3},"gpt-5.4":{"draws":19,"losses":18,"wins":23},"gpt-5.4-mini":{"draws":14,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":12},"gpt-5.6-luna":{"draws":11,"losses":12,"wins":24},"gpt-5.6-sol":{"draws":15,"losses":41,"wins":12},"gpt-5.6-terra":{"draws":31,"losses":15,"wins":22},"gpt-6-astra":{"draws":7,"losses":53,"wins":0},"gpt-6-luna":{"draws":8,"losses":13,"wins":17},"gpt-6-sol":{"draws":4,"losses":17,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":25},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":15},"meituan/longcat-2.0":{"draws":10,"losses":2,"wins":30},"meta/muse-glimmer-30b":{"draws":17,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":13,"wins":14},"meta/muse-spark-1.3":{"draws":12,"losses":36,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":8},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":10,"losses":22,"wins":25},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":12},"o3":{"draws":13,"losses":26,"wins":34},"openai/gpt-oss-120b":{"draws":12,"losses":1,"wins":31},"poolside/laguna-s-2.1":{"draws":18,"losses":6,"wins":16},"qwen/qwen3.7-max":{"draws":11,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":28,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":17,"losses":8,"wins":19},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":23},"qwen/qwen3.8-max-0902":{"draws":7,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":55,"losses":87,"wins":72},"stealth/space-bunny-alpha":{"draws":5,"losses":6,"wins":17},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":20},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":22},"thinkingmachines/inkling":{"draws":20,"losses":4,"wins":22},"thinkingmachines/inkling-small":{"draws":37,"losses":16,"wins":41},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":27},"x-ai/grok-4.6":{"draws":23,"losses":31,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":11},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":5,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":6},"z-ai/glm-5.2":{"draws":30,"losses":23,"wins":27},"z-ai/glm-5.3":{"draws":13,"losses":43,"wins":14},"z-ai/glm-5.3-flash":{"draws":23,"losses":20,"wins":35},"z-ai/glm-5.3-flashx":{"draws":11,"losses":9,"wins":12}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":1,"wins":19},"claude-fable-5":{"draws":5,"losses":11,"wins":10},"claude-fable-5-1":{"draws":4,"losses":13,"wins":5},"claude-opus-4-5":{"draws":8,"losses":3,"wins":21},"claude-opus-4-8":{"draws":5,"losses":2,"wins":13},"claude-opus-5":{"draws":7,"losses":12,"wins":19},"claude-opus-5-5":{"draws":6,"losses":28,"wins":12},"claude-sonnet-5":{"draws":6,"losses":2,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":15,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":9,"losses":0,"wins":17},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":6,"wins":25},"fireworks/ember-1":{"draws":15,"losses":5,"wins":18},"gemini-3.1-pro-preview":{"draws":9,"losses":4,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":14},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":19},"google/gemini-3.6-flash":{"draws":8,"losses":6,"wins":14},"google/gemini-3.8-flash":{"draws":6,"losses":1,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":3,"losses":0,"wins":5},"gpt-5":{"draws":4,"losses":0,"wins":2},"gpt-5.4":{"draws":5,"losses":2,"wins":9},"gpt-5.4-mini":{"draws":1,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":18},"gpt-5.5":{"draws":10,"losses":0,"wins":14},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":1,"wins":13},"gpt-6-astra":{"draws":4,"losses":4,"wins":4},"gpt-6-luna":{"draws":14,"losses":4,"wins":24},"gpt-6-sol":{"draws":6,"losses":21,"wins":15},"gpt-6.1-sol":{"draws":7,"losses":18,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":20},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":12},"meta/muse-spark-1.2":{"draws":3,"losses":3,"wins":12},"meta/muse-spark-1.3":{"draws":6,"losses":1,"wins":9},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":7},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":2,"wins":14},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":13},"o3":{"draws":6,"losses":0,"wins":16},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":17},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":14},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":11},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":8},"qwen/qwen3.8-max":{"draws":6,"losses":1,"wins":15},"qwen/qwen3.8-max-0902":{"draws":7,"losses":3,"wins":18},"stealth/ox-alpha":{"draws":17,"losses":6,"wins":35},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":18},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy4-preview":{"draws":3,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":11},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":4,"wins":17},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":0,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":3,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":6,"wins":11},"z-ai/glm-5.2":{"draws":8,"losses":2,"wins":26},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":9},"z-ai/glm-5.3-flash":{"draws":8,"losses":5,"wins":11},"z-ai/glm-5.3-flashx":{"draws":12,"losses":5,"wins":25}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":22,"wins":99},"claude-fable-5":{"draws":30,"losses":131,"wins":67},"claude-fable-5-1":{"draws":31,"losses":195,"wins":28},"claude-opus-4-5":{"draws":33,"losses":43,"wins":147},"claude-opus-4-8":{"draws":15,"losses":24,"wins":51},"claude-opus-5":{"draws":26,"losses":125,"wins":30},"claude-opus-5-5":{"draws":7,"losses":57,"wins":8},"claude-sonnet-5":{"draws":20,"losses":39,"wins":132},"claude-sonnet-5-5":{"draws":3,"losses":34,"wins":33},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":34},"deepseek/deepseek-v4-flash":{"draws":13,"losses":18,"wins":154},"deepseek/deepseek-v4-pro":{"draws":24,"losses":36,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":46,"wins":96},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":36},"fireworks/ember-1":{"draws":17,"losses":19,"wins":46},"gemini-3.1-pro-preview":{"draws":9,"losses":21,"wins":54},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":41},"google/gemini-3.5-flash":{"draws":23,"losses":58,"wins":130},"google/gemini-3.5-flash-lite":{"draws":28,"losses":31,"wins":202},"google/gemini-3.6-flash":{"draws":35,"losses":98,"wins":162},"google/gemini-3.8-flash":{"draws":24,"losses":78,"wins":110},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":30},"gpt-4.1":{"draws":3,"losses":7,"wins":22},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":7,"losses":12,"wins":51},"gpt-5.4":{"draws":36,"losses":57,"wins":88},"gpt-5.4-mini":{"draws":8,"losses":7,"wins":45},"gpt-5.4-nano":{"draws":3,"losses":20,"wins":61},"gpt-5.5":{"draws":10,"losses":19,"wins":43},"gpt-5.6-luna":{"draws":25,"losses":25,"wins":91},"gpt-5.6-sol":{"draws":23,"losses":99,"wins":97},"gpt-5.6-terra":{"draws":32,"losses":54,"wins":108},"gpt-6-astra":{"draws":35,"losses":154,"wins":27},"gpt-6-luna":{"draws":16,"losses":15,"wins":61},"gpt-6-sol":{"draws":13,"losses":32,"wins":13},"gpt-6.1-sol":{"draws":8,"losses":43,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":12,"losses":11,"wins":64},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":58},"meituan/longcat-2.0":{"draws":17,"losses":22,"wins":90},"meta/muse-glimmer-30b":{"draws":11,"losses":3,"wins":98},"meta/muse-spark-1.2":{"draws":23,"losses":22,"wins":98},"meta/muse-spark-1.3":{"draws":21,"losses":63,"wins":101},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":32},"mistralai/mistral-medium-3-5":{"draws":12,"losses":9,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":11},"moonshotai/kimi-k3":{"draws":28,"losses":43,"wins":112},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":48},"o3":{"draws":5,"losses":48,"wins":129},"openai/gpt-oss-120b":{"draws":11,"losses":5,"wins":97},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":90},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":39},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":52,"wins":106},"qwen/qwen3.8-27b":{"draws":14,"losses":23,"wins":68},"qwen/qwen3.8-flash":{"draws":20,"losses":35,"wins":84},"qwen/qwen3.8-max":{"draws":28,"losses":49,"wins":115},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":31},"stealth/ox-alpha":{"draws":104,"losses":148,"wins":403},"stealth/space-bunny-alpha":{"draws":4,"losses":9,"wins":35},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":36},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":18},"tencent/hy4-preview":{"draws":29,"losses":66,"wins":102},"thinkingmachines/inkling":{"draws":18,"losses":18,"wins":117},"thinkingmachines/inkling-small":{"draws":21,"losses":4,"wins":125},"x-ai/grok-4.5":{"draws":14,"losses":73,"wins":79},"x-ai/grok-4.6":{"draws":41,"losses":94,"wins":103},"x-ai/grok-4.7":{"draws":10,"losses":35,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":34},"xiaomi/mimo-v2.5":{"draws":9,"losses":6,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":18},"z-ai/glm-5.2":{"draws":31,"losses":42,"wins":155},"z-ai/glm-5.3":{"draws":22,"losses":91,"wins":81},"z-ai/glm-5.3-flash":{"draws":31,"losses":71,"wins":121},"z-ai/glm-5.3-flashx":{"draws":14,"losses":20,"wins":34}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":8},"claude-fable-5":{"draws":7,"losses":13,"wins":0},"claude-fable-5-1":{"draws":1,"losses":23,"wins":0},"claude-opus-4-5":{"draws":5,"losses":10,"wins":3},"claude-opus-4-8":{"draws":8,"losses":7,"wins":5},"claude-opus-5":{"draws":7,"losses":20,"wins":3},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":5,"losses":8,"wins":9},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":15},"deepseek/deepseek-v4-pro":{"draws":6,"losses":0,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":6,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":12,"wins":6},"fireworks/ember-1":{"draws":8,"losses":16,"wins":12},"gemini-3.1-pro-preview":{"draws":7,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":7},"google/gemini-3.5-flash-lite":{"draws":8,"losses":7,"wins":13},"google/gemini-3.6-flash":{"draws":4,"losses":23,"wins":7},"google/gemini-3.8-flash":{"draws":6,"losses":9,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":9},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":4,"wins":1},"gpt-5.4":{"draws":5,"losses":11,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":11},"gpt-5.5":{"draws":2,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":16,"wins":0},"gpt-6-luna":{"draws":5,"losses":5,"wins":8},"gpt-6-sol":{"draws":1,"losses":23,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":10},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":10},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":8},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":5},"meta/muse-spark-1.3":{"draws":3,"losses":9,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":9,"wins":9},"o3":{"draws":3,"losses":10,"wins":13},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":9},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":6,"wins":2},"qwen/qwen3.8-max":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":5},"stealth/ox-alpha":{"draws":7,"losses":26,"wins":23},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":5,"losses":5,"wins":6},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":6},"thinkingmachines/inkling-small":{"draws":7,"losses":5,"wins":12},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-4.6":{"draws":2,"losses":7,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":12,"wins":6},"z-ai/glm-5.2":{"draws":17,"losses":11,"wins":10},"z-ai/glm-5.3":{"draws":4,"losses":10,"wins":4},"z-ai/glm-5.3-flash":{"draws":0,"losses":7,"wins":3},"z-ai/glm-5.3-flashx":{"draws":9,"losses":11,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":17,"wins":5},"claude-fable-5":{"draws":2,"losses":18,"wins":2},"claude-fable-5-1":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":5,"losses":40,"wins":11},"claude-opus-4-8":{"draws":2,"losses":22,"wins":6},"claude-opus-5":{"draws":0,"losses":38,"wins":0},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":5,"losses":17,"wins":8},"claude-sonnet-5-5":{"draws":0,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":10,"losses":20,"wins":20},"deepseek/deepseek-v4-pro":{"draws":6,"losses":17,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":6,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":0},"fireworks/ember-1":{"draws":0,"losses":3,"wins":1},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":7},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":9},"google/gemini-3.6-flash":{"draws":8,"losses":32,"wins":3},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":7},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":14,"losses":32,"wins":2},"gpt-5.4":{"draws":6,"losses":15,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":26,"wins":16},"gpt-5.5":{"draws":4,"losses":33,"wins":5},"gpt-5.6-luna":{"draws":3,"losses":11,"wins":10},"gpt-5.6-sol":{"draws":0,"losses":13,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":14,"wins":2},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":4,"losses":11,"wins":5},"gpt-6-sol":{"draws":0,"losses":13,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"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":6,"losses":7,"wins":11},"meituan/longcat-2.0":{"draws":16,"losses":13,"wins":7},"meta/muse-glimmer-30b":{"draws":6,"losses":8,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":13,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":22,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":11,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":18,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":14,"wins":18},"o3":{"draws":17,"losses":44,"wins":17},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":16,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":20,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":16,"wins":2},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":3,"losses":13,"wins":0},"qwen/qwen3.8-max-0902":{"draws":3,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":8,"losses":29,"wins":5},"stealth/space-bunny-alpha":{"draws":2,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":2,"losses":11,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":9,"wins":32},"thinkingmachines/inkling-small":{"draws":5,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":33,"wins":3},"x-ai/grok-4.6":{"draws":4,"losses":14,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":10,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":28,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":14,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":29,"wins":13},"z-ai/glm-5.3":{"draws":0,"losses":16,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":15,"wins":1},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":3}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":11},"claude-fable-5":{"draws":9,"losses":14,"wins":3},"claude-fable-5-1":{"draws":0,"losses":28,"wins":0},"claude-opus-4-5":{"draws":34,"losses":35,"wins":15},"claude-opus-4-8":{"draws":11,"losses":26,"wins":11},"claude-opus-5":{"draws":9,"losses":78,"wins":5},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":7,"losses":16,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":21,"losses":21,"wins":26},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":8,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":3},"fireworks/ember-1":{"draws":7,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":9},"google/gemini-3.1-flash-lite":{"draws":13,"losses":14,"wins":23},"google/gemini-3.5-flash":{"draws":12,"losses":12,"wins":10},"google/gemini-3.5-flash-lite":{"draws":15,"losses":14,"wins":17},"google/gemini-3.6-flash":{"draws":20,"losses":30,"wins":16},"google/gemini-3.8-flash":{"draws":9,"losses":16,"wins":3},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":17},"gpt-4.1":{"draws":16,"losses":12,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":26,"wins":24},"gpt-5.4":{"draws":6,"losses":15,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":13,"wins":20},"gpt-5.5":{"draws":27,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":9,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":18,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":9},"gpt-6-astra":{"draws":3,"losses":23,"wins":0},"gpt-6-luna":{"draws":8,"losses":8,"wins":8},"gpt-6-sol":{"draws":3,"losses":13,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":21,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":14},"meituan/longcat-2.0":{"draws":11,"losses":16,"wins":19},"meta/muse-glimmer-30b":{"draws":8,"losses":4,"wins":16},"meta/muse-spark-1.2":{"draws":4,"losses":11,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":15,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":6,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":2},"nex-agi/nex-n2-pro":{"draws":12,"losses":7,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":12,"wins":21},"o3":{"draws":13,"losses":26,"wins":29},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":16},"qwen/qwen3.7-max":{"draws":15,"losses":19,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":6,"losses":6,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.8-max-0902":{"draws":3,"losses":4,"wins":5},"stealth/ox-alpha":{"draws":30,"losses":32,"wins":12},"stealth/space-bunny-alpha":{"draws":3,"losses":9,"wins":6},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":16,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"losses":7,"wins":16},"x-ai/grok-4.5":{"draws":8,"losses":32,"wins":4},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":23,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":20,"losses":23,"wins":31},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":2},"z-ai/glm-5.3-flashx":{"draws":1,"losses":4,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":4,"wins":22},"claude-fable-5":{"draws":17,"losses":31,"wins":28},"claude-fable-5-1":{"draws":3,"losses":61,"wins":10},"claude-opus-4-5":{"draws":23,"losses":16,"wins":43},"claude-opus-4-8":{"draws":7,"losses":9,"wins":16},"claude-opus-5":{"draws":9,"losses":49,"wins":6},"claude-opus-5-5":{"draws":2,"losses":14,"wins":2},"claude-sonnet-5":{"draws":23,"losses":6,"wins":31},"claude-sonnet-5-5":{"draws":1,"losses":8,"wins":7},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":24,"losses":5,"wins":43},"deepseek/deepseek-v4-pro":{"draws":17,"losses":14,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":8,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":2,"wins":13},"fireworks/ember-1":{"draws":6,"losses":3,"wins":9},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":13},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":14,"losses":10,"wins":44},"google/gemini-3.5-flash-lite":{"draws":36,"losses":8,"wins":44},"google/gemini-3.6-flash":{"draws":30,"losses":32,"wins":52},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":31},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":1,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":12,"losses":1,"wins":9},"gpt-5.4":{"draws":14,"losses":23,"wins":19},"gpt-5.4-mini":{"draws":10,"losses":0,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":23},"gpt-5.5":{"draws":7,"losses":7,"wins":14},"gpt-5.6-luna":{"draws":23,"losses":7,"wins":32},"gpt-5.6-sol":{"draws":12,"losses":38,"wins":32},"gpt-5.6-terra":{"draws":26,"losses":8,"wins":32},"gpt-6-astra":{"draws":9,"losses":57,"wins":8},"gpt-6-luna":{"draws":4,"losses":7,"wins":11},"gpt-6-sol":{"draws":5,"losses":5,"wins":6},"gpt-6.1-sol":{"draws":1,"losses":7,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":10},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":16},"meta/muse-glimmer-30b":{"draws":21,"losses":0,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":12,"wins":25},"meta/muse-spark-1.3":{"draws":13,"losses":19,"wins":34},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":16,"wins":27},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":12},"o3":{"draws":17,"losses":17,"wins":32},"openai/gpt-oss-120b":{"draws":18,"losses":4,"wins":10},"poolside/laguna-s-2.1":{"draws":21,"losses":5,"wins":14},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":36},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":22},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":15},"qwen/qwen3.8-max":{"draws":21,"losses":18,"wins":29},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":9},"stealth/ox-alpha":{"draws":56,"losses":40,"wins":116},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":17},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":9,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":3,"wins":24},"thinkingmachines/inkling-small":{"draws":21,"losses":2,"wins":33},"x-ai/grok-4.5":{"draws":6,"losses":20,"wins":36},"x-ai/grok-4.6":{"draws":29,"losses":25,"wins":24},"x-ai/grok-4.7":{"draws":2,"losses":11,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":0,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":0,"wins":5},"z-ai/glm-5.2":{"draws":29,"losses":6,"wins":43},"z-ai/glm-5.3":{"draws":11,"losses":38,"wins":17},"z-ai/glm-5.3-flash":{"draws":24,"losses":32,"wins":20},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":9}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":32,"wins":18},"claude-fable-5":{"draws":17,"losses":49,"wins":0},"claude-fable-5-1":{"draws":4,"losses":48,"wins":0},"claude-opus-4-5":{"draws":43,"losses":79,"wins":20},"claude-opus-4-8":{"draws":11,"losses":27,"wins":4},"claude-opus-5":{"draws":7,"losses":64,"wins":3},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":34,"losses":69,"wins":15},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":4},"cohere/north-mini-code":{"draws":7,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":41,"losses":30,"wins":23},"deepseek/deepseek-v4-pro":{"draws":28,"losses":36,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":29,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":12,"wins":3},"fireworks/ember-1":{"draws":5,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":9,"losses":12,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":9,"wins":17},"google/gemini-3.5-flash":{"draws":26,"losses":39,"wins":19},"google/gemini-3.5-flash-lite":{"draws":102,"losses":115,"wins":95},"google/gemini-3.6-flash":{"draws":81,"losses":143,"wins":36},"google/gemini-3.8-flash":{"draws":23,"losses":28,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":6,"wins":4},"gpt-4.1":{"draws":4,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":11,"losses":16,"wins":15},"gpt-5.4":{"draws":22,"losses":54,"wins":20},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":12},"gpt-5.5":{"draws":11,"losses":27,"wins":4},"gpt-5.6-luna":{"draws":55,"losses":51,"wins":28},"gpt-5.6-sol":{"draws":25,"losses":81,"wins":10},"gpt-5.6-terra":{"draws":29,"losses":36,"wins":11},"gpt-6-astra":{"draws":3,"losses":46,"wins":1},"gpt-6-luna":{"draws":11,"losses":17,"wins":8},"gpt-6-sol":{"draws":2,"losses":23,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":26,"losses":14,"wins":14},"inclusionai/ling-3.0-flash":{"draws":34,"losses":14,"wins":14},"meituan/longcat-2.0":{"draws":29,"losses":33,"wins":56},"meta/muse-glimmer-30b":{"draws":30,"losses":24,"wins":20},"meta/muse-spark-1.2":{"draws":29,"losses":45,"wins":6},"meta/muse-spark-1.3":{"draws":21,"losses":33,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":6},"mistralai/mistral-medium-3-5":{"draws":17,"losses":10,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":58,"losses":62,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":19,"wins":7},"o3":{"draws":34,"losses":108,"wins":40},"openai/gpt-oss-120b":{"draws":22,"losses":16,"wins":24},"poolside/laguna-s-2.1":{"draws":42,"losses":41,"wins":25},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":31,"wins":6},"qwen/qwen3.8-27b":{"draws":12,"losses":27,"wins":5},"qwen/qwen3.8-flash":{"draws":19,"losses":24,"wins":9},"qwen/qwen3.8-max":{"draws":20,"losses":31,"wins":17},"qwen/qwen3.8-max-0902":{"draws":3,"losses":14,"wins":1},"stealth/ox-alpha":{"draws":66,"losses":125,"wins":31},"stealth/space-bunny-alpha":{"draws":13,"losses":5,"wins":8},"stepfun/step-3.7-flash":{"draws":17,"losses":19,"wins":20},"tencent/hy3-preview":{"draws":6,"losses":11,"wins":7},"tencent/hy4-preview":{"draws":29,"losses":38,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":32,"wins":15},"thinkingmachines/inkling-small":{"draws":32,"losses":17,"wins":33},"x-ai/grok-4.5":{"draws":37,"losses":66,"wins":15},"x-ai/grok-4.6":{"draws":26,"losses":35,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":11,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":16,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":11,"wins":0},"z-ai/glm-5.2":{"draws":33,"losses":41,"wins":22},"z-ai/glm-5.3":{"draws":17,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":22,"losses":42,"wins":12},"z-ai/glm-5.3-flashx":{"draws":5,"losses":16,"wins":1}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":26,"wins":17},"claude-fable-5":{"draws":12,"losses":42,"wins":4},"claude-fable-5-1":{"draws":3,"losses":63,"wins":0},"claude-opus-4-5":{"draws":35,"losses":31,"wins":22},"claude-opus-4-8":{"draws":13,"losses":16,"wins":3},"claude-opus-5":{"draws":4,"losses":48,"wins":2},"claude-opus-5-5":{"draws":2,"losses":22,"wins":0},"claude-sonnet-5":{"draws":18,"losses":36,"wins":16},"claude-sonnet-5-5":{"draws":1,"losses":18,"wins":3},"cohere/north-mini-code":{"draws":9,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":32,"wins":20},"deepseek/deepseek-v4-pro":{"draws":29,"losses":26,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":10,"wins":2},"fireworks/ember-1":{"draws":8,"losses":12,"wins":2},"gemini-3.1-pro-preview":{"draws":5,"losses":11,"wins":10},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":13},"google/gemini-3.5-flash":{"draws":17,"losses":35,"wins":12},"google/gemini-3.5-flash-lite":{"draws":40,"losses":32,"wins":55},"google/gemini-3.6-flash":{"draws":45,"losses":40,"wins":14},"google/gemini-3.8-flash":{"draws":18,"losses":37,"wins":5},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":6},"gpt-4.1":{"draws":5,"losses":2,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":12,"losses":15,"wins":3},"gpt-5.4":{"draws":20,"losses":35,"wins":8},"gpt-5.4-mini":{"draws":10,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":6,"wins":16},"gpt-5.5":{"draws":11,"losses":11,"wins":0},"gpt-5.6-luna":{"draws":29,"losses":15,"wins":24},"gpt-5.6-sol":{"draws":10,"losses":44,"wins":9},"gpt-5.6-terra":{"draws":22,"losses":34,"wins":16},"gpt-6-astra":{"draws":8,"losses":54,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":4},"gpt-6-sol":{"draws":4,"losses":18,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":24,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":29,"losses":9,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":17},"meituan/longcat-2.0":{"draws":24,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":34,"losses":16,"wins":16},"meta/muse-spark-1.2":{"draws":17,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":24,"losses":37,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":2,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":23,"losses":28,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":0,"wins":9},"o3":{"draws":24,"losses":34,"wins":22},"openai/gpt-oss-120b":{"draws":31,"losses":16,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":20,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":24,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":19,"losses":11,"wins":12},"qwen/qwen3.8-max":{"draws":38,"losses":28,"wins":35},"qwen/qwen3.8-max-0902":{"draws":12,"losses":10,"wins":4},"stealth/ox-alpha":{"draws":69,"losses":118,"wins":35},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":8},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":8},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":27,"losses":32,"wins":7},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":21},"thinkingmachines/inkling-small":{"draws":28,"losses":12,"wins":34},"x-ai/grok-4.5":{"draws":13,"losses":34,"wins":13},"x-ai/grok-4.6":{"draws":28,"losses":39,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":0},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":21,"losses":6,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":46,"losses":30,"wins":22},"z-ai/glm-5.3":{"draws":14,"losses":40,"wins":6},"z-ai/glm-5.3-flash":{"draws":32,"losses":36,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":6,"wins":6}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":2,"wins":43},"claude-fable-5":{"draws":6,"losses":29,"wins":35},"claude-fable-5-1":{"draws":3,"losses":63,"wins":6},"claude-opus-4-5":{"draws":39,"losses":27,"wins":68},"claude-opus-4-8":{"draws":9,"losses":18,"wins":11},"claude-opus-5":{"draws":13,"losses":59,"wins":18},"claude-opus-5-5":{"draws":3,"losses":18,"wins":3},"claude-sonnet-5":{"draws":22,"losses":27,"wins":67},"claude-sonnet-5-5":{"draws":7,"losses":14,"wins":13},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":10,"losses":14,"wins":40},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":15,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":10},"fireworks/ember-1":{"draws":6,"losses":7,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":7,"wins":18},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":22},"google/gemini-3.5-flash-lite":{"draws":36,"losses":56,"wins":126},"google/gemini-3.6-flash":{"draws":27,"losses":88,"wins":121},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":35},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":11},"gpt-4.1":{"draws":1,"losses":1,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":8,"wins":21},"gpt-5.4":{"draws":26,"losses":39,"wins":48},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":10},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":19},"gpt-5.5":{"draws":12,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":22,"losses":36,"wins":54},"gpt-5.6-sol":{"draws":14,"losses":47,"wins":45},"gpt-5.6-terra":{"draws":17,"losses":8,"wins":49},"gpt-6-astra":{"draws":1,"losses":55,"wins":8},"gpt-6-luna":{"draws":4,"losses":10,"wins":14},"gpt-6-sol":{"draws":5,"losses":12,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":28,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":42},"meituan/longcat-2.0":{"draws":28,"losses":8,"wins":58},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":30},"meta/muse-spark-1.2":{"draws":12,"losses":16,"wins":46},"meta/muse-spark-1.3":{"draws":6,"losses":16,"wins":28},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":14},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":35,"losses":33,"wins":72},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":25},"o3":{"draws":10,"losses":24,"wins":106},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":35},"poolside/laguna-s-2.1":{"draws":26,"losses":10,"wins":58},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":14},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":19,"wins":33},"qwen/qwen3.8-27b":{"draws":0,"losses":10,"wins":24},"qwen/qwen3.8-flash":{"draws":4,"losses":10,"wins":22},"qwen/qwen3.8-max":{"draws":11,"losses":19,"wins":34},"qwen/qwen3.8-max-0902":{"draws":5,"losses":5,"wins":8},"stealth/ox-alpha":{"draws":37,"losses":49,"wins":98},"stealth/space-bunny-alpha":{"draws":6,"losses":7,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":33},"tencent/hy3-preview":{"draws":5,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":9,"losses":22,"wins":33},"thinkingmachines/inkling":{"draws":30,"losses":14,"wins":56},"thinkingmachines/inkling-small":{"draws":5,"losses":10,"wins":37},"x-ai/grok-4.5":{"draws":25,"losses":11,"wins":32},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":38},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":4},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":6,"losses":4,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":20,"losses":14,"wins":44},"z-ai/glm-5.3":{"draws":14,"losses":33,"wins":17},"z-ai/glm-5.3-flash":{"draws":10,"losses":28,"wins":26},"z-ai/glm-5.3-flashx":{"draws":4,"losses":11,"wins":5}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":11,"wins":22},"claude-fable-5":{"draws":20,"losses":29,"wins":31},"claude-fable-5-1":{"draws":5,"losses":54,"wins":17},"claude-opus-4-5":{"draws":19,"losses":16,"wins":41},"claude-opus-4-8":{"draws":1,"losses":15,"wins":14},"claude-opus-5":{"draws":7,"losses":37,"wins":23},"claude-opus-5-5":{"draws":0,"losses":15,"wins":1},"claude-sonnet-5":{"draws":11,"losses":10,"wins":37},"claude-sonnet-5-5":{"draws":2,"losses":8,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":6,"wins":37},"deepseek/deepseek-v4-pro":{"draws":14,"losses":16,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":18,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":11},"fireworks/ember-1":{"draws":6,"losses":5,"wins":19},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":17},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":22,"losses":10,"wins":46},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":62},"google/gemini-3.6-flash":{"draws":26,"losses":36,"wins":38},"google/gemini-3.8-flash":{"draws":18,"losses":19,"wins":29},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":3,"losses":1,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":5,"wins":17},"gpt-5.4":{"draws":19,"losses":21,"wins":26},"gpt-5.4-mini":{"draws":10,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":18},"gpt-5.5":{"draws":10,"losses":2,"wins":14},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":33},"gpt-5.6-sol":{"draws":11,"losses":28,"wins":39},"gpt-5.6-terra":{"draws":13,"losses":5,"wins":56},"gpt-6-astra":{"draws":7,"losses":58,"wins":9},"gpt-6-luna":{"draws":6,"losses":4,"wins":12},"gpt-6-sol":{"draws":1,"losses":11,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":17,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":5,"wins":22},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":11,"losses":1,"wins":32},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":19},"meta/muse-spark-1.2":{"draws":6,"losses":17,"wins":25},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":28},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":12},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":14,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":2,"wins":9},"o3":{"draws":17,"losses":15,"wins":30},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":24},"poolside/laguna-s-2.1":{"draws":10,"losses":2,"wins":30},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":26,"wins":28},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":15},"qwen/qwen3.8-flash":{"draws":20,"losses":7,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":24,"wins":34},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":13},"stealth/ox-alpha":{"draws":66,"losses":62,"wins":102},"stealth/space-bunny-alpha":{"draws":5,"losses":3,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":27,"losses":13,"wins":26},"thinkingmachines/inkling":{"draws":14,"losses":9,"wins":15},"thinkingmachines/inkling-small":{"draws":24,"losses":8,"wins":30},"x-ai/grok-4.5":{"draws":16,"losses":22,"wins":26},"x-ai/grok-4.6":{"draws":20,"losses":7,"wins":19},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":21,"losses":16,"wins":55},"z-ai/glm-5.3":{"draws":13,"losses":29,"wins":26},"z-ai/glm-5.3-flash":{"draws":18,"losses":31,"wins":27},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":9}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":21},"claude-fable-5":{"draws":1,"losses":5,"wins":8},"claude-fable-5-1":{"draws":1,"losses":13,"wins":8},"claude-opus-4-5":{"draws":0,"losses":2,"wins":22},"claude-opus-4-8":{"draws":2,"losses":4,"wins":10},"claude-opus-5":{"draws":2,"losses":11,"wins":19},"claude-opus-5-5":{"draws":0,"losses":28,"wins":12},"claude-sonnet-5":{"draws":0,"losses":3,"wins":17},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":33},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":28},"fireworks/ember-1":{"draws":3,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":4,"wins":36},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":26},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":30},"google/gemini-3.6-flash":{"draws":0,"losses":10,"wins":28},"google/gemini-3.8-flash":{"draws":0,"losses":3,"wins":13},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":3,"wins":14},"gpt-5.4":{"draws":0,"losses":3,"wins":9},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":15},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":17},"gpt-5.5":{"draws":3,"losses":4,"wins":19},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":16},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":17},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":13},"gpt-6-astra":{"draws":1,"losses":10,"wins":3},"gpt-6-luna":{"draws":0,"losses":2,"wins":20},"gpt-6-sol":{"draws":1,"losses":12,"wins":27},"gpt-6.1-sol":{"draws":1,"losses":24,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":20},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":16},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":21},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":16},"meta/muse-spark-1.2":{"draws":0,"losses":1,"wins":15},"meta/muse-spark-1.3":{"draws":4,"losses":2,"wins":16},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":22},"o3":{"draws":1,"losses":0,"wins":27},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":18},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":21},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":13},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":20},"qwen/qwen3.8-max-0902":{"draws":3,"losses":7,"wins":28},"stealth/ox-alpha":{"draws":3,"losses":4,"wins":57},"stealth/space-bunny-alpha":{"draws":0,"losses":5,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":13},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":22},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":18},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":18},"x-ai/grok-4.5":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.6":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":7,"wins":17},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":44},"z-ai/glm-5.3":{"draws":6,"losses":3,"wins":17},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":8},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":30}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":4},"claude-fable-5":{"draws":8,"losses":20,"wins":0},"claude-fable-5-1":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":41,"losses":20,"wins":3},"claude-opus-4-8":{"draws":18,"losses":14,"wins":4},"claude-opus-5":{"draws":9,"losses":43,"wins":4},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":7,"losses":4,"wins":3},"claude-sonnet-5-5":{"draws":6,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":16,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":29,"losses":5,"wins":8},"deepseek/deepseek-v4-pro":{"draws":15,"losses":6,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":5,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":3,"wins":1},"fireworks/ember-1":{"draws":4,"losses":4,"wins":4},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":19,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":17,"losses":6,"wins":5},"google/gemini-3.5-flash-lite":{"draws":28,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":27,"losses":12,"wins":5},"google/gemini-3.8-flash":{"draws":5,"losses":13,"wins":0},"google/gemma-4-31b-it":{"draws":10,"losses":0,"wins":2},"gpt-4.1":{"draws":12,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":31,"losses":8,"wins":5},"gpt-5.4":{"draws":4,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":25,"losses":2,"wins":9},"gpt-5.4-nano":{"draws":20,"losses":17,"wins":9},"gpt-5.5":{"draws":10,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":8,"wins":0},"gpt-5.6-sol":{"draws":8,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":15,"losses":6,"wins":1},"gpt-6-astra":{"draws":1,"losses":13,"wins":0},"gpt-6-luna":{"draws":12,"losses":11,"wins":3},"gpt-6-sol":{"draws":3,"losses":9,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":14,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":22,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":3},"meta/muse-glimmer-30b":{"draws":14,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":14,"wins":0},"minimax/minimax-m3":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":2},"nex-agi/nex-n2-pro":{"draws":13,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":4,"wins":6},"o3":{"draws":13,"losses":11,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":20,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":17,"losses":7,"wins":0},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":5,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.8-flash":{"draws":13,"losses":3,"wins":0},"qwen/qwen3.8-max":{"draws":15,"losses":4,"wins":1},"qwen/qwen3.8-max-0902":{"draws":8,"losses":1,"wins":1},"stealth/ox-alpha":{"draws":30,"losses":24,"wins":6},"stealth/space-bunny-alpha":{"draws":10,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":14,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":12,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":14,"losses":9,"wins":1},"thinkingmachines/inkling":{"draws":26,"losses":3,"wins":7},"thinkingmachines/inkling-small":{"draws":15,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":11,"losses":14,"wins":3},"x-ai/grok-4.6":{"draws":9,"losses":11,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":20,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":34,"losses":25,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":8,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":41,"losses":16,"wins":11},"z-ai/glm-5.3":{"draws":2,"losses":12,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":13,"wins":1},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":16,"wins":17},"claude-fable-5":{"draws":13,"losses":37,"wins":12},"claude-fable-5-1":{"draws":5,"losses":55,"wins":2},"claude-opus-4-5":{"draws":18,"losses":36,"wins":24},"claude-opus-4-8":{"draws":11,"losses":14,"wins":9},"claude-opus-5":{"draws":11,"losses":33,"wins":4},"claude-opus-5-5":{"draws":1,"losses":28,"wins":1},"claude-sonnet-5":{"draws":17,"losses":32,"wins":31},"claude-sonnet-5-5":{"draws":3,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":22,"losses":17,"wins":31},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":24,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":5},"fireworks/ember-1":{"draws":9,"losses":12,"wins":7},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":18},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":15,"losses":31,"wins":16},"google/gemini-3.5-flash-lite":{"draws":38,"losses":25,"wins":43},"google/gemini-3.6-flash":{"draws":24,"losses":44,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":13},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":3},"gpt-4.1":{"draws":2,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":11,"wins":6},"gpt-5.4":{"draws":21,"losses":32,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":11,"wins":5},"gpt-5.5":{"draws":8,"losses":15,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":14,"wins":25},"gpt-5.6-sol":{"draws":6,"losses":43,"wins":7},"gpt-5.6-terra":{"draws":34,"losses":30,"wins":4},"gpt-6-astra":{"draws":5,"losses":48,"wins":1},"gpt-6-luna":{"draws":11,"losses":11,"wins":8},"gpt-6-sol":{"draws":2,"losses":13,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":28,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":2,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":13,"wins":17},"inclusionai/ling-3.0-flash":{"draws":6,"losses":6,"wins":12},"meituan/longcat-2.0":{"draws":13,"losses":17,"wins":17},"meta/muse-glimmer-30b":{"draws":25,"losses":9,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":18,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":11},"mistralai/mistral-medium-3-5":{"draws":13,"losses":9,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":20,"losses":22,"wins":6},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":6,"wins":11},"o3":{"draws":15,"losses":37,"wins":16},"openai/gpt-oss-120b":{"draws":21,"losses":8,"wins":29},"poolside/laguna-s-2.1":{"draws":20,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":17},"qwen/qwen3.8-27b":{"draws":13,"losses":15,"wins":10},"qwen/qwen3.8-flash":{"draws":13,"losses":17,"wins":10},"qwen/qwen3.8-max":{"draws":20,"losses":21,"wins":15},"qwen/qwen3.8-max-0902":{"draws":6,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":61,"losses":90,"wins":41},"stealth/space-bunny-alpha":{"draws":14,"losses":4,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":10},"tencent/hy3-preview":{"draws":6,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":11},"thinkingmachines/inkling":{"draws":19,"losses":19,"wins":18},"thinkingmachines/inkling-small":{"draws":25,"losses":13,"wins":30},"x-ai/grok-4.5":{"draws":14,"losses":27,"wins":15},"x-ai/grok-4.6":{"draws":21,"losses":30,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":10,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":15,"wins":0},"z-ai/glm-5.2":{"draws":30,"losses":17,"wins":31},"z-ai/glm-5.3":{"draws":19,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":21,"losses":33,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":11,"wins":4}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":36},"claude-fable-5":{"draws":9,"losses":8,"wins":49},"claude-fable-5-1":{"draws":5,"losses":39,"wins":14},"claude-opus-4-5":{"draws":9,"losses":1,"wins":58},"claude-opus-4-8":{"draws":7,"losses":2,"wins":17},"claude-opus-5":{"draws":8,"losses":15,"wins":25},"claude-opus-5-5":{"draws":3,"losses":18,"wins":9},"claude-sonnet-5":{"draws":5,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":5,"losses":5,"wins":14},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":44},"deepseek/deepseek-v4-pro":{"draws":3,"losses":0,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":0,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":19},"fireworks/ember-1":{"draws":3,"losses":4,"wins":25},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":27},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":52},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":65},"google/gemini-3.6-flash":{"draws":6,"losses":3,"wins":71},"google/gemini-3.8-flash":{"draws":4,"losses":5,"wins":47},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":1,"losses":0,"wins":9},"gpt-5":{"draws":2,"losses":0,"wins":14},"gpt-5.4":{"draws":5,"losses":7,"wins":40},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":20},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":28},"gpt-5.5":{"draws":2,"losses":2,"wins":18},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":43},"gpt-5.6-terra":{"draws":7,"losses":1,"wins":48},"gpt-6-astra":{"draws":8,"losses":46,"wins":10},"gpt-6-luna":{"draws":4,"losses":2,"wins":26},"gpt-6-sol":{"draws":7,"losses":4,"wins":15},"gpt-6.1-sol":{"draws":2,"losses":11,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":17},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":36},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":19},"meta/muse-spark-1.2":{"draws":4,"losses":0,"wins":32},"meta/muse-spark-1.3":{"draws":6,"losses":1,"wins":45},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":13},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":35},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":18},"o3":{"draws":0,"losses":0,"wins":54},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":20},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":9},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":6,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":26},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":41},"qwen/qwen3.8-max":{"draws":7,"losses":2,"wins":47},"qwen/qwen3.8-max-0902":{"draws":6,"losses":2,"wins":12},"stealth/ox-alpha":{"draws":22,"losses":16,"wins":134},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":21},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":13},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":5,"wins":51},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":31},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":27},"x-ai/grok-4.5":{"draws":10,"losses":5,"wins":39},"x-ai/grok-4.6":{"draws":9,"losses":6,"wins":57},"x-ai/grok-4.7":{"draws":7,"losses":3,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":10},"z-ai/glm-5.2":{"draws":10,"losses":1,"wins":59},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":29},"z-ai/glm-5.3-flash":{"draws":5,"losses":1,"wins":50},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":20}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":16,"wins":39},"claude-fable-5":{"draws":13,"losses":33,"wins":36},"claude-fable-5-1":{"draws":10,"losses":74,"wins":14},"claude-opus-4-5":{"draws":19,"losses":22,"wins":63},"claude-opus-4-8":{"draws":8,"losses":20,"wins":24},"claude-opus-5":{"draws":11,"losses":64,"wins":25},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":11,"losses":24,"wins":49},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":55},"deepseek/deepseek-v4-pro":{"draws":10,"losses":22,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":15,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":20,"losses":30,"wins":42},"google/gemini-3.5-flash-lite":{"draws":34,"losses":18,"wins":86},"google/gemini-3.6-flash":{"draws":24,"losses":41,"wins":71},"google/gemini-3.8-flash":{"draws":13,"losses":35,"wins":36},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":16},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":6,"wins":27},"gpt-5.4":{"draws":11,"losses":28,"wins":37},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":15,"wins":28},"gpt-5.5":{"draws":8,"losses":15,"wins":25},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":44},"gpt-5.6-sol":{"draws":12,"losses":42,"wins":36},"gpt-5.6-terra":{"draws":17,"losses":23,"wins":40},"gpt-6-astra":{"draws":7,"losses":75,"wins":2},"gpt-6-luna":{"draws":12,"losses":7,"wins":27},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":15,"losses":11,"wins":26},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":25},"meituan/longcat-2.0":{"draws":13,"losses":15,"wins":38},"meta/muse-glimmer-30b":{"draws":15,"losses":3,"wins":46},"meta/muse-spark-1.2":{"draws":6,"losses":23,"wins":35},"meta/muse-spark-1.3":{"draws":14,"losses":24,"wins":40},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":9,"losses":9,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":17,"losses":16,"wins":43},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":9,"wins":20},"o3":{"draws":13,"losses":44,"wins":37},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":41},"poolside/laguna-s-2.1":{"draws":19,"losses":5,"wins":40},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":27,"wins":45},"qwen/qwen3.8-27b":{"draws":9,"losses":17,"wins":22},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":25},"qwen/qwen3.8-max":{"draws":23,"losses":30,"wins":33},"qwen/qwen3.8-max-0902":{"draws":14,"losses":11,"wins":21},"stealth/ox-alpha":{"draws":55,"losses":86,"wins":137},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":18},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":17,"losses":17,"wins":46},"thinkingmachines/inkling":{"draws":15,"losses":11,"wins":44},"thinkingmachines/inkling-small":{"draws":22,"losses":13,"wins":45},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":34},"x-ai/grok-4.6":{"draws":13,"losses":37,"wins":36},"x-ai/grok-4.7":{"draws":1,"losses":4,"wins":9},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":16,"losses":16,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":31,"losses":32,"wins":69},"z-ai/glm-5.3":{"draws":16,"losses":44,"wins":22},"z-ai/glm-5.3-flash":{"draws":16,"losses":13,"wins":9},"z-ai/glm-5.3-flashx":{"draws":13,"losses":14,"wins":21}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":16},"claude-fable-5":{"draws":6,"losses":11,"wins":11},"claude-fable-5-1":{"draws":4,"losses":19,"wins":5},"claude-opus-4-5":{"draws":4,"losses":5,"wins":21},"claude-opus-4-8":{"draws":2,"losses":7,"wins":11},"claude-opus-5":{"draws":3,"losses":18,"wins":7},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":7,"losses":2,"wins":9},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":23},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":31},"fireworks/ember-1":{"draws":6,"losses":10,"wins":32},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":28},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":4,"wins":15},"google/gemini-3.5-flash-lite":{"draws":9,"losses":1,"wins":22},"google/gemini-3.6-flash":{"draws":9,"losses":8,"wins":21},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":10},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":7},"gpt-4.1":{"draws":2,"losses":3,"wins":5},"gpt-5":{"draws":7,"losses":0,"wins":3},"gpt-5.4":{"draws":4,"losses":4,"wins":10},"gpt-5.4-mini":{"draws":1,"losses":3,"wins":14},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":13},"gpt-5.5":{"draws":6,"losses":2,"wins":14},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":20},"gpt-6-astra":{"draws":2,"losses":18,"wins":2},"gpt-6-luna":{"draws":10,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":24,"wins":17},"gpt-6.1-sol":{"draws":10,"losses":32,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":10},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":2,"wins":20},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":12},"meta/muse-spark-1.2":{"draws":2,"losses":3,"wins":11},"meta/muse-spark-1.3":{"draws":4,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":13},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":11},"o3":{"draws":2,"losses":4,"wins":22},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":5,"wins":8},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":8},"qwen/qwen3.8-flash":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":14},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":25},"stealth/ox-alpha":{"draws":6,"losses":12,"wins":46},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":3,"losses":7,"wins":12},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":18},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":22},"x-ai/grok-4.6":{"draws":5,"losses":10,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":22,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":0,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":25},"z-ai/glm-5.3":{"draws":6,"losses":9,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":12,"wins":13},"z-ai/glm-5.3-flashx":{"draws":10,"losses":5,"wins":17}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":19},"claude-fable-5":{"draws":9,"losses":29,"wins":12},"claude-fable-5-1":{"draws":1,"losses":42,"wins":3},"claude-opus-4-5":{"draws":20,"losses":28,"wins":24},"claude-opus-4-8":{"draws":4,"losses":10,"wins":14},"claude-opus-5":{"draws":8,"losses":30,"wins":12},"claude-opus-5-5":{"draws":1,"losses":29,"wins":2},"claude-sonnet-5":{"draws":21,"losses":25,"wins":16},"claude-sonnet-5-5":{"draws":4,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":20,"losses":21,"wins":25},"deepseek/deepseek-v4-pro":{"draws":20,"losses":21,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":21,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":4,"losses":14,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":7},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":16},"google/gemini-3.5-flash-lite":{"draws":33,"losses":29,"wins":42},"google/gemini-3.6-flash":{"draws":25,"losses":41,"wins":28},"google/gemini-3.8-flash":{"draws":11,"losses":22,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":6,"losses":7,"wins":11},"gpt-5.4":{"draws":11,"losses":10,"wins":15},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":8,"losses":5,"wins":21},"gpt-5.5":{"draws":9,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":32},"gpt-5.6-sol":{"draws":8,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":20,"losses":23,"wins":13},"gpt-6-astra":{"draws":5,"losses":29,"wins":10},"gpt-6-luna":{"draws":6,"losses":10,"wins":16},"gpt-6-sol":{"draws":2,"losses":21,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":19,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":14,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":13},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":18},"meta/muse-glimmer-30b":{"draws":16,"losses":13,"wins":25},"meta/muse-spark-1.2":{"draws":8,"losses":10,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":11,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":12},"o3":{"draws":10,"losses":24,"wins":22},"openai/gpt-oss-120b":{"draws":12,"losses":14,"wins":16},"poolside/laguna-s-2.1":{"draws":15,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":4,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":16,"wins":18},"qwen/qwen3.8-max":{"draws":18,"losses":21,"wins":25},"qwen/qwen3.8-max-0902":{"draws":5,"losses":17,"wins":2},"stealth/ox-alpha":{"draws":41,"losses":76,"wins":45},"stealth/space-bunny-alpha":{"draws":3,"losses":4,"wins":9},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":9},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":28,"wins":12},"thinkingmachines/inkling":{"draws":11,"losses":12,"wins":31},"thinkingmachines/inkling-small":{"draws":21,"losses":13,"wins":32},"x-ai/grok-4.5":{"draws":12,"losses":25,"wins":7},"x-ai/grok-4.6":{"draws":22,"losses":21,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":13,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":5},"z-ai/glm-5.2":{"draws":22,"losses":29,"wins":31},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":13,"losses":27,"wins":16},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":4}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":24},"claude-fable-5":{"draws":11,"losses":11,"wins":20},"claude-fable-5-1":{"draws":0,"losses":67,"wins":13},"claude-opus-4-5":{"draws":20,"losses":5,"wins":45},"claude-opus-4-8":{"draws":6,"losses":2,"wins":8},"claude-opus-5":{"draws":6,"losses":54,"wins":20},"claude-opus-5-5":{"draws":2,"losses":25,"wins":3},"claude-sonnet-5":{"draws":11,"losses":12,"wins":37},"claude-sonnet-5-5":{"draws":7,"losses":8,"wins":15},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":3,"wins":45},"deepseek/deepseek-v4-pro":{"draws":15,"losses":18,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":11,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":5,"wins":13},"fireworks/ember-1":{"draws":5,"losses":4,"wins":23},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":19},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":9,"losses":19,"wins":42},"google/gemini-3.5-flash-lite":{"draws":17,"losses":16,"wins":47},"google/gemini-3.6-flash":{"draws":16,"losses":39,"wins":41},"google/gemini-3.8-flash":{"draws":6,"losses":17,"wins":39},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":7,"losses":8,"wins":19},"gpt-5.4":{"draws":15,"losses":16,"wins":33},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":15},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":15},"gpt-5.5":{"draws":4,"losses":5,"wins":15},"gpt-5.6-luna":{"draws":10,"losses":10,"wins":18},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":29},"gpt-5.6-terra":{"draws":22,"losses":9,"wins":41},"gpt-6-astra":{"draws":5,"losses":49,"wins":10},"gpt-6-luna":{"draws":6,"losses":5,"wins":23},"gpt-6-sol":{"draws":5,"losses":8,"wins":9},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":13},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":17},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":35},"meta/muse-glimmer-30b":{"draws":8,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":19},"meta/muse-spark-1.3":{"draws":15,"losses":16,"wins":31},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":12,"wins":42},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":0,"wins":21},"o3":{"draws":3,"losses":9,"wins":52},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":12,"wins":26},"qwen/qwen3.8-27b":{"draws":8,"losses":7,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":5,"wins":22},"qwen/qwen3.8-max":{"draws":6,"losses":21,"wins":33},"qwen/qwen3.8-max-0902":{"draws":5,"losses":8,"wins":15},"stealth/ox-alpha":{"draws":53,"losses":43,"wins":110},"stealth/space-bunny-alpha":{"draws":10,"losses":2,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":19},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":10,"wins":39},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":24},"thinkingmachines/inkling-small":{"draws":14,"losses":9,"wins":27},"x-ai/grok-4.5":{"draws":11,"losses":20,"wins":23},"x-ai/grok-4.6":{"draws":20,"losses":30,"wins":24},"x-ai/grok-4.7":{"draws":1,"losses":12,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.2":{"draws":17,"losses":12,"wins":43},"z-ai/glm-5.3":{"draws":11,"losses":36,"wins":19},"z-ai/glm-5.3-flash":{"draws":15,"losses":19,"wins":42},"z-ai/glm-5.3-flashx":{"draws":0,"losses":6,"wins":18}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":33},"claude-fable-5":{"draws":5,"losses":14,"wins":51},"claude-fable-5-1":{"draws":3,"losses":35,"wins":20},"claude-opus-4-5":{"draws":3,"losses":3,"wins":72},"claude-opus-4-8":{"draws":2,"losses":4,"wins":14},"claude-opus-5":{"draws":8,"losses":22,"wins":28},"claude-opus-5-5":{"draws":2,"losses":9,"wins":7},"claude-sonnet-5":{"draws":5,"losses":3,"wins":60},"claude-sonnet-5-5":{"draws":3,"losses":5,"wins":10},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":56},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":16},"fireworks/ember-1":{"draws":0,"losses":1,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":0,"wins":16},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":59},"google/gemini-3.5-flash-lite":{"draws":12,"losses":0,"wins":72},"google/gemini-3.6-flash":{"draws":4,"losses":15,"wins":75},"google/gemini-3.8-flash":{"draws":8,"losses":7,"wins":55},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":0,"wins":23},"gpt-5.4":{"draws":9,"losses":9,"wins":46},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":18},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":20},"gpt-5.5":{"draws":2,"losses":4,"wins":26},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":14,"wins":52},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":51},"gpt-6-astra":{"draws":6,"losses":52,"wins":12},"gpt-6-luna":{"draws":1,"losses":3,"wins":18},"gpt-6-sol":{"draws":0,"losses":10,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":12,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":24},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":30},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":28},"meta/muse-spark-1.3":{"draws":2,"losses":3,"wins":53},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":17},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":49},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":33},"o3":{"draws":0,"losses":5,"wins":49},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":33},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":38},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":7,"wins":53},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":28},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":42},"qwen/qwen3.8-max":{"draws":1,"losses":2,"wins":47},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":10},"stealth/ox-alpha":{"draws":14,"losses":18,"wins":176},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":16},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":2,"losses":7,"wins":47},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":28},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":51},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":47},"x-ai/grok-4.6":{"draws":4,"losses":14,"wins":56},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":14},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":8},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":64},"z-ai/glm-5.3":{"draws":7,"losses":12,"wins":43},"z-ai/glm-5.3-flash":{"draws":3,"losses":11,"wins":64},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":18}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":13,"wins":32},"claude-fable-5":{"draws":11,"losses":50,"wins":5},"claude-fable-5-1":{"draws":3,"losses":69,"wins":0},"claude-opus-4-5":{"draws":20,"losses":18,"wins":32},"claude-opus-4-8":{"draws":16,"losses":19,"wins":13},"claude-opus-5":{"draws":21,"losses":59,"wins":18},"claude-opus-5-5":{"draws":2,"losses":18,"wins":0},"claude-sonnet-5":{"draws":27,"losses":24,"wins":59},"claude-sonnet-5-5":{"draws":5,"losses":7,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":20},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":41},"deepseek/deepseek-v4-pro":{"draws":8,"losses":24,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":27,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":9,"wins":6},"fireworks/ember-1":{"draws":9,"losses":5,"wins":2},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":19,"losses":29,"wins":26},"google/gemini-3.5-flash-lite":{"draws":57,"losses":46,"wins":117},"google/gemini-3.6-flash":{"draws":45,"losses":96,"wins":73},"google/gemini-3.8-flash":{"draws":12,"losses":43,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":10,"wins":10},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":15,"wins":12},"gpt-5.4":{"draws":23,"losses":56,"wins":25},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":36},"gpt-5.5":{"draws":18,"losses":22,"wins":12},"gpt-5.6-luna":{"draws":30,"losses":31,"wins":41},"gpt-5.6-sol":{"draws":18,"losses":79,"wins":21},"gpt-5.6-terra":{"draws":18,"losses":11,"wins":29},"gpt-6-astra":{"draws":10,"losses":51,"wins":3},"gpt-6-luna":{"draws":12,"losses":6,"wins":12},"gpt-6-sol":{"draws":3,"losses":13,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":15,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":5,"wins":25},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":28},"meituan/longcat-2.0":{"draws":18,"losses":13,"wins":47},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":29},"meta/muse-spark-1.2":{"draws":21,"losses":32,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":32,"wins":15},"minimax/minimax-m3":{"draws":12,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":6,"wins":9},"moonshotai/kimi-k3":{"draws":44,"losses":37,"wins":33},"nex-agi/nex-n2-pro":{"draws":10,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":14},"o3":{"draws":15,"losses":49,"wins":106},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":24,"losses":6,"wins":48},"qwen/qwen3.7-max":{"draws":13,"losses":8,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":9,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":26,"wins":25},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":18},"qwen/qwen3.8-flash":{"draws":18,"losses":11,"wins":19},"qwen/qwen3.8-max":{"draws":13,"losses":32,"wins":16},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":3},"stealth/ox-alpha":{"draws":58,"losses":75,"wins":60},"stealth/space-bunny-alpha":{"draws":7,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":22},"tencent/hy3-preview":{"draws":13,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":30,"wins":18},"thinkingmachines/inkling":{"draws":22,"losses":19,"wins":55},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":41},"x-ai/grok-4.5":{"draws":42,"losses":48,"wins":42},"x-ai/grok-4.6":{"draws":16,"losses":38,"wins":16},"x-ai/grok-4.7":{"draws":1,"losses":14,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":16},"xiaomi/mimo-v2.5":{"draws":31,"losses":13,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":40},"z-ai/glm-5.3":{"draws":18,"losses":30,"wins":10},"z-ai/glm-5.3-flash":{"draws":17,"losses":38,"wins":21},"z-ai/glm-5.3-flashx":{"draws":0,"losses":4,"wins":4}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":6,"wins":5},"claude-fable-5":{"draws":12,"losses":20,"wins":8},"claude-fable-5-1":{"draws":0,"losses":25,"wins":1},"claude-opus-4-5":{"draws":33,"losses":30,"wins":35},"claude-opus-4-8":{"draws":10,"losses":28,"wins":12},"claude-opus-5":{"draws":14,"losses":83,"wins":3},"claude-opus-5-5":{"draws":3,"losses":35,"wins":2},"claude-sonnet-5":{"draws":11,"losses":13,"wins":6},"claude-sonnet-5-5":{"draws":3,"losses":13,"wins":4},"cohere/north-mini-code":{"draws":15,"losses":5,"wins":24},"deepseek/deepseek-v4-flash":{"draws":30,"losses":8,"wins":16},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":13,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":10,"wins":5},"fireworks/ember-1":{"draws":4,"losses":5,"wins":5},"gemini-3.1-pro-preview":{"draws":6,"losses":2,"wins":8},"google/gemini-3.1-flash-lite":{"draws":18,"losses":3,"wins":31},"google/gemini-3.5-flash":{"draws":14,"losses":11,"wins":17},"google/gemini-3.5-flash-lite":{"draws":28,"losses":9,"wins":37},"google/gemini-3.6-flash":{"draws":29,"losses":28,"wins":21},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":11},"google/gemma-4-31b-it":{"draws":13,"losses":0,"wins":21},"gpt-4.1":{"draws":16,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":24,"losses":14,"wins":20},"gpt-5.4":{"draws":4,"losses":11,"wins":9},"gpt-5.4-mini":{"draws":23,"losses":20,"wins":13},"gpt-5.4-nano":{"draws":23,"losses":19,"wins":34},"gpt-5.5":{"draws":25,"losses":15,"wins":14},"gpt-5.6-luna":{"draws":17,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":12,"losses":15,"wins":11},"gpt-5.6-terra":{"draws":18,"losses":11,"wins":13},"gpt-6-astra":{"draws":1,"losses":38,"wins":3},"gpt-6-luna":{"draws":9,"losses":14,"wins":7},"gpt-6-sol":{"draws":2,"losses":20,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":25,"losses":0,"wins":15},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":24},"meta/muse-glimmer-30b":{"draws":15,"losses":5,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":11,"wins":15},"meta/muse-spark-1.3":{"draws":16,"losses":14,"wins":12},"minimax/minimax-m3":{"draws":14,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":15,"wins":11},"nex-agi/nex-n2-pro":{"draws":24,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":9,"wins":16},"o3":{"draws":13,"losses":10,"wins":35},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":6},"poolside/laguna-s-2.1":{"draws":26,"losses":8,"wins":28},"qwen/qwen3.7-max":{"draws":28,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":11,"wins":9},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":11,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":12,"wins":3},"stealth/ox-alpha":{"draws":38,"losses":63,"wins":35},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":12},"tencent/hy3-preview":{"draws":15,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":7},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":20},"thinkingmachines/inkling-small":{"draws":17,"losses":3,"wins":14},"x-ai/grok-4.5":{"draws":18,"losses":19,"wins":17},"x-ai/grok-4.6":{"draws":15,"losses":20,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":21},"xiaomi/mimo-v2.5":{"draws":46,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":9,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":9,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":43,"losses":22,"wins":39},"z-ai/glm-5.3":{"draws":6,"losses":22,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":19,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":8}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":4,"wins":31},"claude-fable-5":{"draws":5,"losses":20,"wins":51},"claude-fable-5-1":{"draws":3,"losses":39,"wins":12},"claude-opus-4-5":{"draws":33,"losses":16,"wins":159},"claude-opus-4-8":{"draws":21,"losses":21,"wins":70},"claude-opus-5":{"draws":33,"losses":128,"wins":103},"claude-opus-5-5":{"draws":1,"losses":23,"wins":18},"claude-sonnet-5":{"draws":9,"losses":6,"wins":45},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":24},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-flash":{"draws":16,"losses":2,"wins":80},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":6,"wins":13},"fireworks/ember-1":{"draws":3,"losses":4,"wins":17},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":22},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":34},"google/gemini-3.5-flash":{"draws":14,"losses":5,"wins":67},"google/gemini-3.5-flash-lite":{"draws":26,"losses":9,"wins":97},"google/gemini-3.6-flash":{"draws":12,"losses":19,"wins":109},"google/gemini-3.8-flash":{"draws":9,"losses":9,"wins":56},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":28},"gpt-4.1":{"draws":4,"losses":4,"wins":34},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":6,"wins":86},"gpt-5.4":{"draws":2,"losses":8,"wins":30},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":58},"gpt-5.4-nano":{"draws":12,"losses":12,"wins":80},"gpt-5.5":{"draws":13,"losses":36,"wins":79},"gpt-5.6-luna":{"draws":3,"losses":7,"wins":36},"gpt-5.6-sol":{"draws":12,"losses":15,"wins":45},"gpt-5.6-terra":{"draws":11,"losses":5,"wins":48},"gpt-6-astra":{"draws":4,"losses":35,"wins":7},"gpt-6-luna":{"draws":5,"losses":4,"wins":35},"gpt-6-sol":{"draws":3,"losses":12,"wins":15},"gpt-6.1-sol":{"draws":3,"losses":18,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":36},"meituan/longcat-2.0":{"draws":8,"losses":12,"wins":90},"meta/muse-glimmer-30b":{"draws":2,"losses":5,"wins":31},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":37},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":54},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":41},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":36},"moonshotai/kimi-k3":{"draws":13,"losses":6,"wins":57},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":0,"wins":68},"o3":{"draws":4,"losses":5,"wins":81},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":54},"poolside/laguna-s-2.1":{"draws":8,"losses":6,"wins":96},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":56},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":16},"qwen/qwen3.8-flash":{"draws":8,"losses":3,"wins":37},"qwen/qwen3.8-max":{"draws":6,"losses":0,"wins":38},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":15},"stealth/ox-alpha":{"draws":25,"losses":16,"wins":142},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":1,"wins":37},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":43},"tencent/hy4-preview":{"draws":4,"losses":7,"wins":45},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":68},"thinkingmachines/inkling-small":{"draws":11,"losses":4,"wins":39},"x-ai/grok-4.5":{"draws":14,"losses":23,"wins":65},"x-ai/grok-4.6":{"draws":11,"losses":18,"wins":46},"x-ai/grok-4.7":{"draws":2,"losses":17,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":3,"wins":24},"xiaomi/mimo-v2.5":{"draws":30,"losses":10,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":0,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":3,"wins":11},"z-ai/glm-5.2":{"draws":26,"losses":11,"wins":135},"z-ai/glm-5.3":{"draws":10,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":8,"losses":23,"wins":57},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":20}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":22},"claude-fable-5":{"draws":2,"losses":2,"wins":30},"claude-fable-5-1":{"draws":3,"losses":9,"wins":18},"claude-opus-4-5":{"draws":1,"losses":0,"wins":45},"claude-opus-4-8":{"draws":1,"losses":1,"wins":30},"claude-opus-5":{"draws":3,"losses":12,"wins":29},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":1,"wins":27},"claude-sonnet-5-5":{"draws":3,"losses":6,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":46},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":51},"fireworks/ember-1":{"draws":0,"losses":0,"wins":38},"gemini-3.1-pro-preview":{"draws":1,"losses":2,"wins":43},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":20},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":33},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":41},"google/gemini-3.6-flash":{"draws":3,"losses":3,"wins":46},"google/gemini-3.8-flash":{"draws":2,"losses":1,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":16},"gpt-4.1":{"draws":0,"losses":0,"wins":14},"gpt-5":{"draws":0,"losses":0,"wins":20},"gpt-5.4":{"draws":0,"losses":1,"wins":23},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":20},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":20},"gpt-5.5":{"draws":2,"losses":0,"wins":22},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":29},"gpt-5.6-sol":{"draws":1,"losses":4,"wins":27},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":39},"gpt-6-astra":{"draws":5,"losses":12,"wins":11},"gpt-6-luna":{"draws":2,"losses":0,"wins":50},"gpt-6-sol":{"draws":3,"losses":12,"wins":39},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":24},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":22},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":36},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":30},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":28},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":20},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":14},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":1,"losses":0,"wins":25},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":22},"o3":{"draws":0,"losses":0,"wins":30},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":30},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":26},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":14},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":0,"wins":25},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":14},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":18},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":31},"qwen/qwen3.8-max-0902":{"draws":2,"losses":3,"wins":47},"stealth/ox-alpha":{"draws":6,"losses":4,"wins":70},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":30},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":24},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":28},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":26},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":27},"x-ai/grok-4.6":{"draws":2,"losses":1,"wins":43},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":35},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":30},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":52},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":31},"z-ai/glm-5.3-flash":{"draws":3,"losses":3,"wins":30},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":50}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":7,"wins":41},"claude-fable-5":{"draws":14,"losses":49,"wins":9},"claude-fable-5-1":{"draws":5,"losses":70,"wins":1},"claude-opus-4-5":{"draws":27,"losses":45,"wins":20},"claude-opus-4-8":{"draws":10,"losses":10,"wins":2},"claude-opus-5":{"draws":7,"losses":30,"wins":9},"claude-opus-5-5":{"draws":2,"losses":20,"wins":2},"claude-sonnet-5":{"draws":21,"losses":32,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":6},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":14,"wins":40},"deepseek/deepseek-v4-pro":{"draws":19,"losses":18,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":27,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":7},"fireworks/ember-1":{"draws":10,"losses":10,"wins":8},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":12},"google/gemini-3.1-flash-lite":{"draws":12,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":28,"losses":25,"wins":19},"google/gemini-3.5-flash-lite":{"draws":70,"losses":53,"wins":85},"google/gemini-3.6-flash":{"draws":56,"losses":77,"wins":39},"google/gemini-3.8-flash":{"draws":20,"losses":32,"wins":12},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":5},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":9,"losses":5,"wins":12},"gpt-5.4":{"draws":37,"losses":58,"wins":19},"gpt-5.4-mini":{"draws":10,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":11},"gpt-5.5":{"draws":12,"losses":15,"wins":3},"gpt-5.6-luna":{"draws":42,"losses":28,"wins":56},"gpt-5.6-sol":{"draws":17,"losses":95,"wins":15},"gpt-5.6-terra":{"draws":33,"losses":21,"wins":12},"gpt-6-astra":{"draws":5,"losses":62,"wins":3},"gpt-6-luna":{"draws":8,"losses":13,"wins":13},"gpt-6-sol":{"draws":0,"losses":20,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":32,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":24,"losses":7,"wins":21},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":28},"meituan/longcat-2.0":{"draws":26,"losses":8,"wins":30},"meta/muse-glimmer-30b":{"draws":26,"losses":8,"wins":28},"meta/muse-spark-1.2":{"draws":25,"losses":32,"wins":19},"meta/muse-spark-1.3":{"draws":19,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":24,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":39,"losses":47,"wins":18},"nex-agi/nex-n2-pro":{"draws":13,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":3,"wins":13},"o3":{"draws":20,"losses":53,"wins":45},"openai/gpt-oss-120b":{"draws":27,"losses":7,"wins":34},"poolside/laguna-s-2.1":{"draws":28,"losses":8,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":18,"wins":11},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":11},"qwen/qwen3.8-flash":{"draws":24,"losses":14,"wins":18},"qwen/qwen3.8-max":{"draws":25,"losses":30,"wins":16},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":5},"stealth/ox-alpha":{"draws":48,"losses":116,"wins":46},"stealth/space-bunny-alpha":{"draws":5,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":15,"losses":6,"wins":13},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":31,"losses":28,"wins":9},"thinkingmachines/inkling":{"draws":30,"losses":11,"wins":45},"thinkingmachines/inkling-small":{"draws":20,"losses":8,"wins":34},"x-ai/grok-4.5":{"draws":26,"losses":48,"wins":22},"x-ai/grok-4.6":{"draws":21,"losses":40,"wins":11},"x-ai/grok-4.7":{"draws":1,"losses":21,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":4},"z-ai/glm-5.2":{"draws":39,"losses":28,"wins":37},"z-ai/glm-5.3":{"draws":10,"losses":44,"wins":4},"z-ai/glm-5.3-flash":{"draws":21,"losses":39,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":12,"wins":5}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":8},"claude-fable-5":{"draws":9,"losses":8,"wins":1},"claude-fable-5-1":{"draws":2,"losses":21,"wins":1},"claude-opus-4-5":{"draws":12,"losses":10,"wins":22},"claude-opus-4-8":{"draws":3,"losses":10,"wins":9},"claude-opus-5":{"draws":6,"losses":34,"wins":6},"claude-opus-5-5":{"draws":1,"losses":42,"wins":3},"claude-sonnet-5":{"draws":5,"losses":7,"wins":10},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":9,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":17},"fireworks/ember-1":{"draws":13,"losses":20,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":21},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":12},"google/gemini-3.5-flash-lite":{"draws":12,"losses":10,"wins":28},"google/gemini-3.6-flash":{"draws":16,"losses":21,"wins":13},"google/gemini-3.8-flash":{"draws":3,"losses":8,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":8},"gpt-5.4":{"draws":10,"losses":6,"wins":4},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":2,"wins":15},"gpt-5.5":{"draws":7,"losses":8,"wins":9},"gpt-5.6-luna":{"draws":13,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":19,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":8},"gpt-6-astra":{"draws":1,"losses":26,"wins":1},"gpt-6-luna":{"draws":10,"losses":7,"wins":11},"gpt-6-sol":{"draws":2,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":18},"meta/muse-glimmer-30b":{"draws":5,"losses":5,"wins":6},"meta/muse-spark-1.2":{"draws":8,"losses":4,"wins":6},"meta/muse-spark-1.3":{"draws":5,"losses":8,"wins":11},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":9},"nex-agi/nex-n2-pro":{"draws":1,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":16},"o3":{"draws":0,"losses":3,"wins":15},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":10},"poolside/laguna-s-2.1":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":8},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":10,"wins":9},"qwen/qwen3.8-27b":{"draws":0,"losses":3,"wins":5},"qwen/qwen3.8-flash":{"draws":0,"losses":6,"wins":6},"qwen/qwen3.8-max":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-max-0902":{"draws":9,"losses":20,"wins":15},"stealth/ox-alpha":{"draws":17,"losses":29,"wins":26},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":8,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":14},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":18},"x-ai/grok-4.5":{"draws":3,"losses":9,"wins":8},"x-ai/grok-4.6":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":12,"wins":9},"z-ai/glm-5.2":{"draws":14,"losses":13,"wins":25},"z-ai/glm-5.3":{"draws":8,"losses":14,"wins":6},"z-ai/glm-5.3-flash":{"draws":2,"losses":6,"wins":6},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":12}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":7},"claude-fable-5":{"draws":0,"losses":22,"wins":2},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-opus-4-5":{"draws":11,"losses":33,"wins":10},"claude-opus-4-8":{"draws":11,"losses":26,"wins":5},"claude-opus-5":{"draws":4,"losses":33,"wins":1},"claude-opus-5-5":{"draws":2,"losses":22,"wins":0},"claude-sonnet-5":{"draws":2,"losses":9,"wins":5},"claude-sonnet-5-5":{"draws":2,"losses":8,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":23},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":8,"wins":3},"fireworks/ember-1":{"draws":3,"losses":11,"wins":4},"gemini-3.1-pro-preview":{"draws":7,"losses":8,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":20,"wins":17},"google/gemini-3.5-flash":{"draws":8,"losses":18,"wins":6},"google/gemini-3.5-flash-lite":{"draws":22,"losses":21,"wins":15},"google/gemini-3.6-flash":{"draws":22,"losses":34,"wins":6},"google/gemini-3.8-flash":{"draws":3,"losses":17,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":11},"gpt-4.1":{"draws":7,"losses":11,"wins":2},"gpt-5":{"draws":13,"losses":30,"wins":7},"gpt-5.4":{"draws":5,"losses":15,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":16,"wins":6},"gpt-5.4-nano":{"draws":17,"losses":31,"wins":12},"gpt-5.5":{"draws":15,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":14,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":19,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":18,"wins":6},"gpt-6-astra":{"draws":2,"losses":18,"wins":0},"gpt-6-luna":{"draws":9,"losses":11,"wins":2},"gpt-6-sol":{"draws":6,"losses":11,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":16,"losses":18,"wins":12},"meituan/longcat-2.0":{"draws":20,"losses":28,"wins":8},"meta/muse-glimmer-30b":{"draws":8,"losses":10,"wins":8},"meta/muse-spark-1.2":{"draws":0,"losses":14,"wins":4},"meta/muse-spark-1.3":{"draws":2,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":4,"losses":15,"wins":5},"nex-agi/nex-n2-pro":{"draws":16,"losses":14,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":14},"o3":{"draws":16,"losses":24,"wins":12},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":3},"poolside/laguna-s-2.1":{"draws":23,"losses":2,"wins":19},"qwen/qwen3.7-max":{"draws":12,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":17,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":22,"wins":0},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.8-max":{"draws":5,"losses":18,"wins":1},"qwen/qwen3.8-max-0902":{"draws":4,"losses":13,"wins":1},"stealth/ox-alpha":{"draws":19,"losses":47,"wins":8},"stealth/space-bunny-alpha":{"draws":3,"losses":8,"wins":5},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":13,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":11,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":21},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":29,"wins":4},"x-ai/grok-4.6":{"draws":7,"losses":19,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":10,"losses":14,"wins":6},"xiaomi/mimo-v2.5":{"draws":32,"losses":21,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":27,"wins":12},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":19,"wins":2},"z-ai/glm-5.3-flashx":{"draws":3,"losses":10,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":36,"wins":37},"claude-fable-5":{"draws":23,"losses":96,"wins":9},"claude-fable-5-1":{"draws":2,"losses":132,"wins":0},"claude-opus-4-5":{"draws":69,"losses":81,"wins":32},"claude-opus-4-8":{"draws":34,"losses":61,"wins":9},"claude-opus-5":{"draws":22,"losses":154,"wins":8},"claude-opus-5-5":{"draws":0,"losses":61,"wins":3},"claude-sonnet-5":{"draws":34,"losses":56,"wins":22},"claude-sonnet-5-5":{"draws":14,"losses":44,"wins":6},"cohere/north-mini-code":{"draws":28,"losses":25,"wins":25},"deepseek/deepseek-v4-flash":{"draws":51,"losses":47,"wins":48},"deepseek/deepseek-v4-pro":{"draws":37,"losses":49,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":47,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":43,"wins":6},"fireworks/ember-1":{"draws":24,"losses":41,"wins":11},"gemini-3.1-pro-preview":{"draws":20,"losses":27,"wins":17},"google/gemini-3.1-flash-lite":{"draws":25,"losses":38,"wins":65},"google/gemini-3.5-flash":{"draws":36,"losses":61,"wins":25},"google/gemini-3.5-flash-lite":{"draws":71,"losses":37,"wins":72},"google/gemini-3.6-flash":{"draws":66,"losses":109,"wins":41},"google/gemini-3.8-flash":{"draws":28,"losses":75,"wins":15},"google/gemma-4-31b-it":{"draws":13,"losses":24,"wins":33},"gpt-4.1":{"draws":28,"losses":20,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":56,"losses":42,"wins":14},"gpt-5.4":{"draws":31,"losses":59,"wins":6},"gpt-5.4-mini":{"draws":48,"losses":26,"wins":24},"gpt-5.4-nano":{"draws":41,"losses":38,"wins":43},"gpt-5.5":{"draws":52,"losses":49,"wins":11},"gpt-5.6-luna":{"draws":46,"losses":48,"wins":28},"gpt-5.6-sol":{"draws":15,"losses":77,"wins":8},"gpt-5.6-terra":{"draws":54,"losses":65,"wins":23},"gpt-6-astra":{"draws":2,"losses":96,"wins":2},"gpt-6-luna":{"draws":14,"losses":53,"wins":11},"gpt-6-sol":{"draws":3,"losses":58,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":55,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":35,"losses":10,"wins":29},"inclusionai/ling-3.0-flash":{"draws":47,"losses":28,"wins":35},"meituan/longcat-2.0":{"draws":41,"losses":36,"wins":33},"meta/muse-glimmer-30b":{"draws":49,"losses":16,"wins":45},"meta/muse-spark-1.2":{"draws":18,"losses":43,"wins":15},"meta/muse-spark-1.3":{"draws":27,"losses":59,"wins":12},"minimax/minimax-m3":{"draws":34,"losses":32,"wins":34},"mistralai/mistral-medium-3-5":{"draws":25,"losses":10,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":21,"wins":12},"moonshotai/kimi-k3":{"draws":34,"losses":65,"wins":19},"nex-agi/nex-n2-pro":{"draws":24,"losses":30,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":71,"losses":30,"wins":45},"o3":{"draws":20,"losses":87,"wins":53},"openai/gpt-oss-120b":{"draws":35,"losses":21,"wins":32},"poolside/laguna-s-2.1":{"draws":63,"losses":28,"wins":37},"qwen/qwen3.7-max":{"draws":36,"losses":27,"wins":19},"qwen/qwen3.7-plus":{"draws":28,"losses":32,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":58,"wins":18},"qwen/qwen3.8-27b":{"draws":14,"losses":32,"wins":24},"qwen/qwen3.8-flash":{"draws":32,"losses":24,"wins":24},"qwen/qwen3.8-max":{"draws":43,"losses":50,"wins":19},"qwen/qwen3.8-max-0902":{"draws":20,"losses":29,"wins":5},"stealth/ox-alpha":{"draws":108,"losses":174,"wins":55},"stealth/space-bunny-alpha":{"draws":15,"losses":24,"wins":7},"stepfun/step-3.7-flash":{"draws":30,"losses":38,"wins":28},"tencent/hy3-preview":{"draws":31,"losses":35,"wins":22},"tencent/hy4-preview":{"draws":40,"losses":56,"wins":16},"thinkingmachines/inkling":{"draws":42,"losses":66,"wins":52},"thinkingmachines/inkling-small":{"draws":58,"losses":19,"wins":53},"x-ai/grok-4.5":{"draws":27,"losses":88,"wins":23},"x-ai/grok-4.6":{"draws":42,"losses":81,"wins":9},"x-ai/grok-4.7":{"draws":2,"losses":50,"wins":0},"x-ai/grok-build-0.1":{"draws":25,"losses":14,"wins":25},"xiaomi/mimo-v2.5":{"draws":101,"losses":94,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":36,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":33,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.2":{"draws":79,"losses":99,"wins":42},"z-ai/glm-5.3":{"draws":23,"losses":59,"wins":4},"z-ai/glm-5.3-flash":{"draws":34,"losses":72,"wins":22},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":14,"wins":39},"claude-fable-5":{"draws":13,"losses":43,"wins":26},"claude-fable-5-1":{"draws":6,"losses":67,"wins":3},"claude-opus-4-5":{"draws":17,"losses":20,"wins":35},"claude-opus-4-8":{"draws":8,"losses":9,"wins":9},"claude-opus-5":{"draws":9,"losses":43,"wins":8},"claude-opus-5-5":{"draws":1,"losses":25,"wins":0},"claude-sonnet-5":{"draws":22,"losses":17,"wins":27},"claude-sonnet-5-5":{"draws":6,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":34},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":21,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":18,"wins":8},"fireworks/ember-1":{"draws":6,"losses":13,"wins":9},"gemini-3.1-pro-preview":{"draws":5,"losses":7,"wins":16},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":19,"losses":35,"wins":22},"google/gemini-3.5-flash-lite":{"draws":22,"losses":30,"wins":64},"google/gemini-3.6-flash":{"draws":22,"losses":33,"wins":47},"google/gemini-3.8-flash":{"draws":9,"losses":38,"wins":23},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":10},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":6,"losses":4,"wins":14},"gpt-5.4":{"draws":11,"losses":35,"wins":22},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":6},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":16},"gpt-5.5":{"draws":7,"losses":12,"wins":11},"gpt-5.6-luna":{"draws":24,"losses":16,"wins":22},"gpt-5.6-sol":{"draws":5,"losses":36,"wins":21},"gpt-5.6-terra":{"draws":16,"losses":19,"wins":41},"gpt-6-astra":{"draws":2,"losses":50,"wins":10},"gpt-6-luna":{"draws":9,"losses":14,"wins":13},"gpt-6-sol":{"draws":2,"losses":22,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":22,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":22,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":9,"losses":6,"wins":21},"meituan/longcat-2.0":{"draws":17,"losses":4,"wins":29},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":25},"meta/muse-spark-1.3":{"draws":4,"losses":33,"wins":23},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":14},"mistralai/mistral-medium-3-5":{"draws":9,"losses":5,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":15,"losses":34,"wins":15},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":13},"o3":{"draws":4,"losses":22,"wins":50},"openai/gpt-oss-120b":{"draws":19,"losses":10,"wins":29},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":33},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":27,"wins":16},"qwen/qwen3.8-27b":{"draws":3,"losses":13,"wins":18},"qwen/qwen3.8-flash":{"draws":11,"losses":16,"wins":19},"qwen/qwen3.8-max":{"draws":19,"losses":25,"wins":24},"qwen/qwen3.8-max-0902":{"draws":7,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":59,"losses":76,"wins":79},"stealth/space-bunny-alpha":{"draws":2,"losses":4,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":24},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":26,"wins":23},"thinkingmachines/inkling":{"draws":19,"losses":7,"wins":30},"thinkingmachines/inkling-small":{"draws":23,"losses":7,"wins":36},"x-ai/grok-4.5":{"draws":18,"losses":28,"wins":22},"x-ai/grok-4.6":{"draws":9,"losses":44,"wins":27},"x-ai/grok-4.7":{"draws":3,"losses":15,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":22,"losses":6,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":4},"z-ai/glm-5.2":{"draws":24,"losses":20,"wins":40},"z-ai/glm-5.3":{"draws":11,"losses":42,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":33,"wins":28},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":12}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":20,"wins":28},"claude-fable-5":{"draws":8,"losses":44,"wins":14},"claude-fable-5-1":{"draws":2,"losses":59,"wins":3},"claude-opus-4-5":{"draws":20,"losses":18,"wins":26},"claude-opus-4-8":{"draws":8,"losses":13,"wins":11},"claude-opus-5":{"draws":5,"losses":34,"wins":7},"claude-opus-5-5":{"draws":2,"losses":18,"wins":0},"claude-sonnet-5":{"draws":18,"losses":17,"wins":31},"claude-sonnet-5-5":{"draws":5,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":25,"losses":26,"wins":31},"deepseek/deepseek-v4-pro":{"draws":17,"losses":27,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":12,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":3,"wins":2},"fireworks/ember-1":{"draws":5,"losses":7,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":32,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":36,"losses":19,"wins":55},"google/gemini-3.6-flash":{"draws":31,"losses":57,"wins":26},"google/gemini-3.8-flash":{"draws":16,"losses":29,"wins":17},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":5},"gpt-4.1":{"draws":3,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":9,"wins":4},"gpt-5.4":{"draws":16,"losses":32,"wins":14},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":12},"gpt-5.5":{"draws":9,"losses":7,"wins":10},"gpt-5.6-luna":{"draws":17,"losses":24,"wins":17},"gpt-5.6-sol":{"draws":12,"losses":38,"wins":10},"gpt-5.6-terra":{"draws":19,"losses":29,"wins":22},"gpt-6-astra":{"draws":3,"losses":55,"wins":0},"gpt-6-luna":{"draws":4,"losses":9,"wins":11},"gpt-6-sol":{"draws":4,"losses":13,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":19,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":25},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":8},"meituan/longcat-2.0":{"draws":20,"losses":13,"wins":17},"meta/muse-glimmer-30b":{"draws":21,"losses":9,"wins":34},"meta/muse-spark-1.2":{"draws":21,"losses":14,"wins":19},"meta/muse-spark-1.3":{"draws":14,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":17},"mistralai/mistral-medium-3-5":{"draws":7,"losses":8,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":26,"wins":10},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":16},"o3":{"draws":14,"losses":25,"wins":35},"openai/gpt-oss-120b":{"draws":14,"losses":12,"wins":24},"poolside/laguna-s-2.1":{"draws":16,"losses":14,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":21,"wins":22},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":17},"qwen/qwen3.8-flash":{"draws":19,"losses":18,"wins":9},"qwen/qwen3.8-max":{"draws":32,"losses":23,"wins":11},"qwen/qwen3.8-max-0902":{"draws":5,"losses":4,"wins":3},"stealth/ox-alpha":{"draws":59,"losses":84,"wins":69},"stealth/space-bunny-alpha":{"draws":3,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":11},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":27,"wins":15},"thinkingmachines/inkling":{"draws":18,"losses":11,"wins":25},"thinkingmachines/inkling-small":{"draws":19,"losses":11,"wins":38},"x-ai/grok-4.5":{"draws":18,"losses":28,"wins":24},"x-ai/grok-4.6":{"draws":17,"losses":34,"wins":19},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":7,"losses":9,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":40,"losses":25,"wins":37},"z-ai/glm-5.3":{"draws":18,"losses":34,"wins":10},"z-ai/glm-5.3-flash":{"draws":14,"losses":33,"wins":19},"z-ai/glm-5.3-flashx":{"draws":2,"losses":11,"wins":3}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":3,"wins":10},"claude-fable-5":{"draws":7,"losses":17,"wins":6},"claude-fable-5-1":{"draws":6,"losses":19,"wins":3},"claude-opus-4-5":{"draws":11,"losses":7,"wins":14},"claude-opus-4-8":{"draws":4,"losses":4,"wins":12},"claude-opus-5":{"draws":9,"losses":24,"wins":5},"claude-opus-5-5":{"draws":4,"losses":39,"wins":7},"claude-sonnet-5":{"draws":3,"losses":7,"wins":6},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":14,"losses":1,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":1,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":12,"wins":13},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":10,"wins":14},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":9,"losses":5,"wins":10},"google/gemini-3.5-flash-lite":{"draws":13,"losses":5,"wins":20},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":8},"google/gemini-3.8-flash":{"draws":2,"losses":7,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":5,"losses":6,"wins":3},"gpt-5.4":{"draws":10,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":11},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":7},"gpt-5.5":{"draws":8,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":2,"wins":10},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":8},"gpt-6-astra":{"draws":1,"losses":16,"wins":1},"gpt-6-luna":{"draws":14,"losses":12,"wins":20},"gpt-6-sol":{"draws":9,"losses":27,"wins":12},"gpt-6.1-sol":{"draws":6,"losses":31,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":17},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":5,"wins":7},"meta/muse-spark-1.3":{"draws":7,"losses":2,"wins":5},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":9},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":14},"o3":{"draws":9,"losses":2,"wins":15},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":9,"wins":7},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.8-max":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-max-0902":{"draws":15,"losses":15,"wins":16},"stealth/ox-alpha":{"draws":15,"losses":25,"wins":28},"stealth/space-bunny-alpha":{"draws":11,"losses":5,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":4},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":8},"thinkingmachines/inkling":{"draws":8,"losses":7,"wins":7},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":10},"x-ai/grok-4.6":{"draws":10,"losses":14,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":23,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":1,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":11,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":12,"wins":5},"z-ai/glm-5.2":{"draws":13,"losses":8,"wins":13},"z-ai/glm-5.3":{"draws":6,"losses":8,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":13,"wins":16},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":16}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":13},"claude-fable-5":{"draws":7,"losses":12,"wins":1},"claude-fable-5-1":{"draws":1,"losses":35,"wins":2},"claude-opus-4-5":{"draws":19,"losses":11,"wins":4},"claude-opus-4-8":{"draws":9,"losses":7,"wins":4},"claude-opus-5":{"draws":6,"losses":24,"wins":8},"claude-opus-5-5":{"draws":3,"losses":33,"wins":4},"claude-sonnet-5":{"draws":6,"losses":7,"wins":5},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":15,"losses":5,"wins":24},"deepseek/deepseek-v4-pro":{"draws":6,"losses":5,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":17},"fireworks/ember-1":{"draws":11,"losses":7,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":10},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":14},"google/gemini-3.6-flash":{"draws":16,"losses":15,"wins":17},"google/gemini-3.8-flash":{"draws":7,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":6},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":3,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":10},"gpt-5.5":{"draws":13,"losses":9,"wins":6},"gpt-5.6-luna":{"draws":15,"losses":3,"wins":8},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":8},"gpt-6-astra":{"draws":1,"losses":20,"wins":1},"gpt-6-luna":{"draws":10,"losses":7,"wins":11},"gpt-6-sol":{"draws":5,"losses":29,"wins":8},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":14},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":23},"meta/muse-glimmer-30b":{"draws":12,"losses":2,"wins":10},"meta/muse-spark-1.2":{"draws":6,"losses":1,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":5,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":3,"wins":9},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":14},"o3":{"draws":2,"losses":7,"wins":21},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":13},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":14},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-flash":{"draws":3,"losses":1,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":6,"wins":10},"qwen/qwen3.8-max-0902":{"draws":18,"losses":13,"wins":9},"stealth/ox-alpha":{"draws":26,"losses":29,"wins":33},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":12,"wins":8},"thinkingmachines/inkling":{"draws":12,"losses":3,"wins":15},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":15},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":7},"x-ai/grok-4.6":{"draws":4,"losses":7,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":1,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":10,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":9,"wins":19},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":17}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":7},"claude-fable-5":{"draws":8,"losses":8,"wins":4},"claude-fable-5-1":{"draws":2,"losses":28,"wins":0},"claude-opus-4-5":{"draws":14,"losses":22,"wins":8},"claude-opus-4-8":{"draws":6,"losses":18,"wins":0},"claude-opus-5":{"draws":5,"losses":26,"wins":3},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":10,"losses":12,"wins":4},"claude-sonnet-5-5":{"draws":8,"losses":30,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":15},"deepseek/deepseek-v4-pro":{"draws":9,"losses":6,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":6,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":13,"wins":14},"fireworks/ember-1":{"draws":16,"losses":23,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":10,"losses":12,"wins":4},"google/gemini-3.5-flash-lite":{"draws":18,"losses":13,"wins":7},"google/gemini-3.6-flash":{"draws":12,"losses":15,"wins":11},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":4},"gpt-5.4":{"draws":8,"losses":9,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":8},"gpt-5.5":{"draws":11,"losses":6,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":11},"gpt-5.6-sol":{"draws":1,"losses":18,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":6},"gpt-6-astra":{"draws":4,"losses":16,"wins":0},"gpt-6-luna":{"draws":12,"losses":7,"wins":7},"gpt-6-sol":{"draws":5,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":9,"losses":4,"wins":16},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":5},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":8},"minimax/minimax-m3":{"draws":4,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":6},"o3":{"draws":10,"losses":8,"wins":8},"openai/gpt-oss-120b":{"draws":12,"losses":2,"wins":12},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":8},"stealth/ox-alpha":{"draws":17,"losses":48,"wins":19},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":8},"tencent/hy3-preview":{"draws":5,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":13,"losses":9,"wins":6},"thinkingmachines/inkling-small":{"draws":11,"losses":3,"wins":14},"x-ai/grok-4.5":{"draws":2,"losses":10,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":8,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":26,"losses":8,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":19,"wins":3},"z-ai/glm-5.2":{"draws":33,"losses":19,"wins":10},"z-ai/glm-5.3":{"draws":6,"losses":20,"wins":2},"z-ai/glm-5.3-flash":{"draws":3,"losses":4,"wins":3},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":7}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":11,"wins":4},"claude-fable-5":{"draws":2,"losses":15,"wins":1},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":17,"losses":43,"wins":2},"claude-opus-4-8":{"draws":16,"losses":37,"wins":5},"claude-opus-5":{"draws":7,"losses":33,"wins":4},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":10,"losses":15,"wins":1},"claude-sonnet-5-5":{"draws":3,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":21,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":32,"wins":14},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":10,"wins":1},"fireworks/ember-1":{"draws":6,"losses":14,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":13,"wins":17},"google/gemini-3.5-flash":{"draws":9,"losses":9,"wins":8},"google/gemini-3.5-flash-lite":{"draws":20,"losses":15,"wins":13},"google/gemini-3.6-flash":{"draws":7,"losses":28,"wins":5},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":0},"google/gemma-4-31b-it":{"draws":11,"losses":19,"wins":12},"gpt-4.1":{"draws":5,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":14,"losses":18,"wins":2},"gpt-5.4":{"draws":4,"losses":16,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":19,"wins":6},"gpt-5.4-nano":{"draws":12,"losses":46,"wins":16},"gpt-5.5":{"draws":13,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":9,"losses":21,"wins":4},"gpt-6-astra":{"draws":0,"losses":20,"wins":0},"gpt-6-luna":{"draws":7,"losses":23,"wins":2},"gpt-6-sol":{"draws":4,"losses":20,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":12,"losses":12,"wins":12},"meituan/longcat-2.0":{"draws":8,"losses":19,"wins":16},"meta/muse-glimmer-30b":{"draws":8,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":5,"losses":12,"wins":3},"meta/muse-spark-1.3":{"draws":1,"losses":15,"wins":0},"minimax/minimax-m3":{"draws":10,"losses":18,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":18,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":12,"wins":1},"nex-agi/nex-n2-pro":{"draws":10,"losses":9,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":12,"wins":23},"o3":{"draws":12,"losses":32,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":12,"wins":3},"poolside/laguna-s-2.1":{"draws":6,"losses":18,"wins":12},"qwen/qwen3.7-max":{"draws":14,"losses":19,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":22,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":10,"wins":0},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":36,"wins":6},"stealth/space-bunny-alpha":{"draws":3,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":6,"losses":19,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":1},"thinkingmachines/inkling":{"draws":11,"losses":24,"wins":15},"thinkingmachines/inkling-small":{"draws":7,"losses":9,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":34,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":17,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":19,"wins":3},"xiaomi/mimo-v2.5":{"draws":32,"losses":33,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":27,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":21,"losses":45,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.3-flashx":{"draws":4,"losses":18,"wins":0}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":7,"wins":25},"claude-fable-5":{"draws":16,"losses":41,"wins":13},"claude-fable-5-1":{"draws":8,"losses":66,"wins":2},"claude-opus-4-5":{"draws":15,"losses":17,"wins":34},"claude-opus-4-8":{"draws":4,"losses":12,"wins":16},"claude-opus-5":{"draws":7,"losses":47,"wins":6},"claude-opus-5-5":{"draws":2,"losses":16,"wins":2},"claude-sonnet-5":{"draws":17,"losses":12,"wins":37},"claude-sonnet-5-5":{"draws":6,"losses":17,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":20,"losses":7,"wins":31},"deepseek/deepseek-v4-pro":{"draws":17,"losses":12,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":8,"wins":5},"fireworks/ember-1":{"draws":5,"losses":6,"wins":13},"gemini-3.1-pro-preview":{"draws":7,"losses":5,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":17,"wins":19},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":56},"google/gemini-3.6-flash":{"draws":25,"losses":28,"wins":39},"google/gemini-3.8-flash":{"draws":20,"losses":24,"wins":24},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":10},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":4,"wins":10},"gpt-5.4":{"draws":14,"losses":28,"wins":20},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":3,"wins":17},"gpt-5.5":{"draws":8,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":22,"losses":7,"wins":23},"gpt-5.6-sol":{"draws":8,"losses":40,"wins":18},"gpt-5.6-terra":{"draws":17,"losses":23,"wins":26},"gpt-6-astra":{"draws":7,"losses":52,"wins":3},"gpt-6-luna":{"draws":5,"losses":9,"wins":16},"gpt-6-sol":{"draws":4,"losses":16,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":19,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":19},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":22},"meta/muse-glimmer-30b":{"draws":17,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":30},"meta/muse-spark-1.3":{"draws":12,"losses":24,"wins":18},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":23,"losses":12,"wins":27},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":16},"o3":{"draws":8,"losses":14,"wins":36},"openai/gpt-oss-120b":{"draws":22,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":18},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":26},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":11},"qwen/qwen3.8-flash":{"draws":16,"losses":11,"wins":19},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":5},"stealth/ox-alpha":{"draws":53,"losses":57,"wins":95},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":5,"losses":26,"wins":23},"thinkingmachines/inkling":{"draws":16,"losses":8,"wins":16},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"x-ai/grok-4.5":{"draws":11,"losses":18,"wins":27},"x-ai/grok-4.6":{"draws":18,"losses":39,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":7,"wins":7},"z-ai/glm-5.2":{"draws":26,"losses":26,"wins":40},"z-ai/glm-5.3":{"draws":14,"losses":36,"wins":20},"z-ai/glm-5.3-flash":{"draws":24,"losses":24,"wins":28},"z-ai/glm-5.3-flashx":{"draws":17,"losses":6,"wins":7}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":37,"wins":29},"claude-fable-5":{"draws":26,"losses":70,"wins":6},"claude-fable-5-1":{"draws":6,"losses":58,"wins":0},"claude-opus-4-5":{"draws":84,"losses":124,"wins":12},"claude-opus-4-8":{"draws":30,"losses":37,"wins":1},"claude-opus-5":{"draws":17,"losses":96,"wins":7},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":50,"losses":106,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":3},"cohere/north-mini-code":{"draws":23,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":52,"losses":51,"wins":23},"deepseek/deepseek-v4-pro":{"draws":32,"losses":41,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":39,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":18,"wins":3},"fireworks/ember-1":{"draws":14,"losses":17,"wins":3},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":7},"google/gemini-3.1-flash-lite":{"draws":25,"losses":12,"wins":21},"google/gemini-3.5-flash":{"draws":32,"losses":63,"wins":25},"google/gemini-3.5-flash-lite":{"draws":126,"losses":122,"wins":102},"google/gemini-3.6-flash":{"draws":142,"losses":181,"wins":46},"google/gemini-3.8-flash":{"draws":21,"losses":49,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":18,"wins":8},"gpt-4.1":{"draws":9,"losses":10,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":8},"gpt-5":{"draws":31,"losses":16,"wins":19},"gpt-5.4":{"draws":56,"losses":103,"wins":13},"gpt-5.4-mini":{"draws":27,"losses":23,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":19,"wins":32},"gpt-5.5":{"draws":39,"losses":25,"wins":4},"gpt-5.6-luna":{"draws":65,"losses":86,"wins":33},"gpt-5.6-sol":{"draws":29,"losses":131,"wins":6},"gpt-5.6-terra":{"draws":43,"losses":63,"wins":8},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"gpt-6-luna":{"draws":16,"losses":27,"wins":11},"gpt-6-sol":{"draws":8,"losses":31,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":33,"losses":25,"wins":26},"inclusionai/ling-3.0-flash":{"draws":34,"losses":28,"wins":32},"meituan/longcat-2.0":{"draws":44,"losses":85,"wins":40},"meta/muse-glimmer-30b":{"draws":51,"losses":24,"wins":31},"meta/muse-spark-1.2":{"draws":32,"losses":86,"wins":18},"meta/muse-spark-1.3":{"draws":23,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":13},"mistralai/mistral-medium-3-5":{"draws":30,"losses":22,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":7},"moonshotai/kimi-k3":{"draws":74,"losses":100,"wins":24},"nex-agi/nex-n2-pro":{"draws":18,"losses":11,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":16,"wins":16},"o3":{"draws":57,"losses":186,"wins":41},"openai/gpt-oss-120b":{"draws":42,"losses":38,"wins":20},"poolside/laguna-s-2.1":{"draws":72,"losses":68,"wins":30},"qwen/qwen3.7-max":{"draws":14,"losses":8,"wins":10},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":51,"wins":5},"qwen/qwen3.8-27b":{"draws":13,"losses":42,"wins":13},"qwen/qwen3.8-flash":{"draws":30,"losses":35,"wins":3},"qwen/qwen3.8-max":{"draws":38,"losses":36,"wins":17},"qwen/qwen3.8-max-0902":{"draws":19,"losses":19,"wins":4},"stealth/ox-alpha":{"draws":98,"losses":199,"wins":34},"stealth/space-bunny-alpha":{"draws":8,"losses":18,"wins":2},"stepfun/step-3.7-flash":{"draws":24,"losses":39,"wins":19},"tencent/hy3-preview":{"draws":16,"losses":7,"wins":1},"tencent/hy4-preview":{"draws":33,"losses":53,"wins":14},"thinkingmachines/inkling":{"draws":64,"losses":54,"wins":64},"thinkingmachines/inkling-small":{"draws":47,"losses":33,"wins":45},"x-ai/grok-4.5":{"draws":59,"losses":122,"wins":13},"x-ai/grok-4.6":{"draws":41,"losses":63,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":32,"wins":2},"x-ai/grok-build-0.1":{"draws":17,"losses":20,"wins":5},"xiaomi/mimo-v2.5":{"draws":49,"losses":47,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":25,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":0},"z-ai/glm-5.2":{"draws":69,"losses":65,"wins":32},"z-ai/glm-5.3":{"draws":26,"losses":57,"wins":3},"z-ai/glm-5.3-flash":{"draws":38,"losses":56,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":2}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":15,"wins":36},"claude-fable-5":{"draws":15,"losses":62,"wins":35},"claude-fable-5-1":{"draws":3,"losses":85,"wins":10},"claude-opus-4-5":{"draws":46,"losses":45,"wins":99},"claude-opus-4-8":{"draws":24,"losses":24,"wins":42},"claude-opus-5":{"draws":10,"losses":92,"wins":28},"claude-opus-5-5":{"draws":5,"losses":39,"wins":8},"claude-sonnet-5":{"draws":40,"losses":40,"wins":68},"claude-sonnet-5-5":{"draws":11,"losses":19,"wins":20},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":35},"deepseek/deepseek-v4-flash":{"draws":29,"losses":18,"wins":81},"deepseek/deepseek-v4-pro":{"draws":21,"losses":27,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":24,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":11},"fireworks/ember-1":{"draws":15,"losses":17,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":42},"google/gemini-3.5-flash":{"draws":24,"losses":39,"wins":45},"google/gemini-3.5-flash-lite":{"draws":81,"losses":48,"wins":186},"google/gemini-3.6-flash":{"draws":55,"losses":82,"wins":137},"google/gemini-3.8-flash":{"draws":13,"losses":40,"wins":37},"google/gemma-4-31b-it":{"draws":3,"losses":7,"wins":24},"gpt-4.1":{"draws":7,"losses":2,"wins":19},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":0},"gpt-5":{"draws":14,"losses":11,"wins":37},"gpt-5.4":{"draws":42,"losses":68,"wins":52},"gpt-5.4-mini":{"draws":17,"losses":13,"wins":27},"gpt-5.4-nano":{"draws":17,"losses":10,"wins":49},"gpt-5.5":{"draws":22,"losses":20,"wins":28},"gpt-5.6-luna":{"draws":27,"losses":20,"wins":93},"gpt-5.6-sol":{"draws":22,"losses":76,"wins":52},"gpt-5.6-terra":{"draws":29,"losses":23,"wins":48},"gpt-6-astra":{"draws":11,"losses":85,"wins":6},"gpt-6-luna":{"draws":13,"losses":16,"wins":27},"gpt-6-sol":{"draws":5,"losses":28,"wins":13},"gpt-6.1-sol":{"draws":3,"losses":36,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":20,"losses":6,"wins":36},"inclusionai/ling-3.0-flash":{"draws":33,"losses":4,"wins":41},"meituan/longcat-2.0":{"draws":47,"losses":17,"wins":80},"meta/muse-glimmer-30b":{"draws":23,"losses":11,"wins":42},"meta/muse-spark-1.2":{"draws":23,"losses":42,"wins":55},"meta/muse-spark-1.3":{"draws":16,"losses":34,"wins":30},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":21},"mistralai/mistral-medium-3-5":{"draws":11,"losses":8,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":3,"wins":15},"moonshotai/kimi-k3":{"draws":43,"losses":54,"wins":89},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":5,"wins":19},"o3":{"draws":29,"losses":42,"wins":147},"openai/gpt-oss-120b":{"draws":23,"losses":10,"wins":39},"poolside/laguna-s-2.1":{"draws":35,"losses":18,"wins":61},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":32},"qwen/qwen3.7-plus":{"draws":17,"losses":5,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":30,"wins":41},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":33},"qwen/qwen3.8-flash":{"draws":18,"losses":18,"wins":24},"qwen/qwen3.8-max":{"draws":24,"losses":32,"wins":40},"qwen/qwen3.8-max-0902":{"draws":12,"losses":14,"wins":12},"stealth/ox-alpha":{"draws":71,"losses":107,"wins":130},"stealth/space-bunny-alpha":{"draws":10,"losses":4,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":47},"tencent/hy3-preview":{"draws":13,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":17,"losses":39,"wins":48},"thinkingmachines/inkling":{"draws":37,"losses":26,"wins":81},"thinkingmachines/inkling-small":{"draws":24,"losses":7,"wins":52},"x-ai/grok-4.5":{"draws":43,"losses":63,"wins":88},"x-ai/grok-4.6":{"draws":26,"losses":39,"wins":35},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":13},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":23},"xiaomi/mimo-v2.5":{"draws":50,"losses":14,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":8,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":11,"wins":13},"z-ai/glm-5.2":{"draws":42,"losses":43,"wins":55},"z-ai/glm-5.3":{"draws":16,"losses":48,"wins":22},"z-ai/glm-5.3-flash":{"draws":11,"losses":47,"wins":40},"z-ai/glm-5.3-flashx":{"draws":11,"losses":16,"wins":19}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":10,"wins":24},"claude-fable-5":{"draws":13,"losses":24,"wins":37},"claude-fable-5-1":{"draws":4,"losses":64,"wins":10},"claude-opus-4-5":{"draws":27,"losses":13,"wins":40},"claude-opus-4-8":{"draws":10,"losses":7,"wins":15},"claude-opus-5":{"draws":8,"losses":48,"wins":12},"claude-opus-5-5":{"draws":4,"losses":13,"wins":3},"claude-sonnet-5":{"draws":23,"losses":19,"wins":30},"claude-sonnet-5-5":{"draws":3,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":40},"deepseek/deepseek-v4-pro":{"draws":25,"losses":17,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":12,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":6},"fireworks/ember-1":{"draws":8,"losses":6,"wins":8},"gemini-3.1-pro-preview":{"draws":9,"losses":0,"wins":7},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":23,"losses":22,"wins":31},"google/gemini-3.5-flash-lite":{"draws":37,"losses":4,"wins":59},"google/gemini-3.6-flash":{"draws":29,"losses":35,"wins":41},"google/gemini-3.8-flash":{"draws":13,"losses":18,"wins":17},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":11},"gpt-4.1":{"draws":5,"losses":1,"wins":8},"gpt-5":{"draws":8,"losses":14,"wins":6},"gpt-5.4":{"draws":21,"losses":23,"wins":24},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":8,"wins":18},"gpt-5.5":{"draws":10,"losses":11,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":37},"gpt-5.6-sol":{"draws":12,"losses":37,"wins":21},"gpt-5.6-terra":{"draws":25,"losses":13,"wins":28},"gpt-6-astra":{"draws":6,"losses":59,"wins":3},"gpt-6-luna":{"draws":4,"losses":8,"wins":12},"gpt-6-sol":{"draws":3,"losses":13,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":12,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":19,"losses":1,"wins":20},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":20},"meta/muse-glimmer-30b":{"draws":23,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":8,"losses":24,"wins":10},"meta/muse-spark-1.3":{"draws":16,"losses":25,"wins":19},"minimax/minimax-m3":{"draws":10,"losses":0,"wins":16},"mistralai/mistral-medium-3-5":{"draws":11,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":25,"losses":13,"wins":28},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":1,"wins":16},"o3":{"draws":14,"losses":21,"wins":41},"openai/gpt-oss-120b":{"draws":19,"losses":7,"wins":24},"poolside/laguna-s-2.1":{"draws":19,"losses":9,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":32},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":26},"qwen/qwen3.8-flash":{"draws":20,"losses":9,"wins":23},"qwen/qwen3.8-max":{"draws":20,"losses":20,"wins":22},"qwen/qwen3.8-max-0902":{"draws":3,"losses":5,"wins":4},"stealth/ox-alpha":{"draws":57,"losses":68,"wins":99},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":1,"wins":20},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":8},"tencent/hy4-preview":{"draws":22,"losses":20,"wins":24},"thinkingmachines/inkling":{"draws":20,"losses":2,"wins":30},"thinkingmachines/inkling-small":{"draws":24,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":18},"x-ai/grok-4.6":{"draws":27,"losses":29,"wins":22},"x-ai/grok-4.7":{"draws":1,"losses":13,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":17,"losses":4,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":30,"losses":15,"wins":45},"z-ai/glm-5.3":{"draws":11,"losses":35,"wins":20},"z-ai/glm-5.3-flash":{"draws":19,"losses":26,"wins":37},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":5}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":5},"claude-fable-5":{"draws":0,"losses":15,"wins":1},"claude-fable-5-1":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":10,"losses":27,"wins":25},"claude-opus-4-8":{"draws":12,"losses":17,"wins":9},"claude-opus-5":{"draws":8,"losses":34,"wins":4},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":3,"losses":10,"wins":5},"claude-sonnet-5-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":11},"deepseek/deepseek-v4-flash":{"draws":3,"losses":12,"wins":15},"deepseek/deepseek-v4-pro":{"draws":1,"losses":9,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":12,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":8,"wins":2},"fireworks/ember-1":{"draws":4,"losses":5,"wins":1},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":10,"wins":18},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":7},"google/gemini-3.5-flash-lite":{"draws":8,"losses":14,"wins":24},"google/gemini-3.6-flash":{"draws":2,"losses":20,"wins":10},"google/gemini-3.8-flash":{"draws":3,"losses":14,"wins":3},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":7},"gpt-4.1":{"draws":2,"losses":8,"wins":2},"gpt-5":{"draws":1,"losses":22,"wins":5},"gpt-5.4":{"draws":3,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":2,"losses":14,"wins":16},"gpt-5.4-nano":{"draws":2,"losses":22,"wins":16},"gpt-5.5":{"draws":12,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":7},"gpt-5.6-sol":{"draws":1,"losses":20,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":14,"wins":2},"gpt-6-astra":{"draws":0,"losses":14,"wins":0},"gpt-6-luna":{"draws":1,"losses":8,"wins":5},"gpt-6-sol":{"draws":1,"losses":10,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":9,"wins":9},"meituan/longcat-2.0":{"draws":1,"losses":26,"wins":17},"meta/muse-glimmer-30b":{"draws":3,"losses":6,"wins":9},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":7,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":13,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":10,"wins":12},"o3":{"draws":5,"losses":29,"wins":6},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":2,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":4,"losses":20,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":17,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":11,"wins":5},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":0,"losses":12,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":10,"wins":2},"stealth/ox-alpha":{"draws":8,"losses":34,"wins":14},"stealth/space-bunny-alpha":{"draws":3,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":3,"losses":19,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":15,"wins":3},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":23},"thinkingmachines/inkling-small":{"draws":0,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":19,"wins":6},"x-ai/grok-4.6":{"draws":1,"losses":14,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":15,"losses":7,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":18,"losses":23,"wins":11},"z-ai/glm-5.3":{"draws":2,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":0,"losses":16,"wins":4},"z-ai/glm-5.3-flashx":{"draws":0,"losses":7,"wins":3}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":11,"wins":12},"claude-fable-5":{"draws":5,"losses":19,"wins":8},"claude-fable-5-1":{"draws":1,"losses":27,"wins":0},"claude-opus-4-5":{"draws":19,"losses":39,"wins":28},"claude-opus-4-8":{"draws":12,"losses":27,"wins":19},"claude-opus-5":{"draws":11,"losses":57,"wins":8},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":7,"wins":7},"claude-sonnet-5-5":{"draws":7,"losses":13,"wins":4},"cohere/north-mini-code":{"draws":13,"losses":4,"wins":27},"deepseek/deepseek-v4-flash":{"draws":17,"losses":11,"wins":16},"deepseek/deepseek-v4-pro":{"draws":11,"losses":11,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":7,"wins":5},"fireworks/ember-1":{"draws":6,"losses":7,"wins":7},"gemini-3.1-pro-preview":{"draws":2,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":10},"google/gemini-3.5-flash-lite":{"draws":25,"losses":19,"wins":18},"google/gemini-3.6-flash":{"draws":9,"losses":29,"wins":22},"google/gemini-3.8-flash":{"draws":3,"losses":17,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":7,"wins":14},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":8,"losses":20,"wins":4},"gpt-5.4":{"draws":6,"losses":7,"wins":5},"gpt-5.4-mini":{"draws":20,"losses":12,"wins":12},"gpt-5.4-nano":{"draws":12,"losses":21,"wins":19},"gpt-5.5":{"draws":11,"losses":28,"wins":21},"gpt-5.6-luna":{"draws":4,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":3,"losses":15,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":6},"gpt-6-astra":{"draws":1,"losses":21,"wins":0},"gpt-6-luna":{"draws":5,"losses":8,"wins":5},"gpt-6-sol":{"draws":1,"losses":7,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":14,"wins":10},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":35},"meta/muse-glimmer-30b":{"draws":8,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":6,"losses":15,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":14,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":9,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":17,"wins":14},"o3":{"draws":12,"losses":15,"wins":25},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":16,"wins":12},"qwen/qwen3.7-max":{"draws":14,"losses":9,"wins":21},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":19,"wins":2},"qwen/qwen3.8-27b":{"draws":3,"losses":16,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":8,"wins":6},"qwen/qwen3.8-max":{"draws":8,"losses":12,"wins":2},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":22,"losses":32,"wins":24},"stealth/space-bunny-alpha":{"draws":2,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":2,"wins":13},"tencent/hy3-preview":{"draws":6,"losses":10,"wins":12},"tencent/hy4-preview":{"draws":9,"losses":11,"wins":6},"thinkingmachines/inkling":{"draws":17,"losses":9,"wins":22},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":16},"x-ai/grok-4.5":{"draws":7,"losses":27,"wins":14},"x-ai/grok-4.6":{"draws":6,"losses":21,"wins":5},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":9,"wins":20},"xiaomi/mimo-v2.5":{"draws":32,"losses":23,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":8,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":30,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":4,"losses":15,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":21,"wins":4},"z-ai/glm-5.3-flashx":{"draws":6,"losses":4,"wins":0}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":19},"claude-fable-5":{"draws":23,"losses":29,"wins":18},"claude-fable-5-1":{"draws":0,"losses":56,"wins":6},"claude-opus-4-5":{"draws":34,"losses":14,"wins":52},"claude-opus-4-8":{"draws":1,"losses":6,"wins":7},"claude-opus-5":{"draws":2,"losses":41,"wins":3},"claude-opus-5-5":{"draws":3,"losses":19,"wins":0},"claude-sonnet-5":{"draws":48,"losses":22,"wins":48},"claude-sonnet-5-5":{"draws":9,"losses":4,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":23,"losses":9,"wins":36},"deepseek/deepseek-v4-pro":{"draws":21,"losses":16,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":15,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":5,"wins":4},"fireworks/ember-1":{"draws":10,"losses":5,"wins":5},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":9},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":12},"google/gemini-3.5-flash":{"draws":15,"losses":23,"wins":30},"google/gemini-3.5-flash-lite":{"draws":62,"losses":25,"wins":93},"google/gemini-3.6-flash":{"draws":57,"losses":53,"wins":68},"google/gemini-3.8-flash":{"draws":25,"losses":23,"wins":24},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":5},"gpt-4.1":{"draws":4,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":7,"wins":12},"gpt-5.4":{"draws":27,"losses":23,"wins":39},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":18},"gpt-5.5":{"draws":10,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":44,"losses":18,"wins":54},"gpt-5.6-sol":{"draws":18,"losses":65,"wins":35},"gpt-5.6-terra":{"draws":31,"losses":11,"wins":28},"gpt-6-astra":{"draws":9,"losses":42,"wins":11},"gpt-6-luna":{"draws":12,"losses":8,"wins":16},"gpt-6-sol":{"draws":2,"losses":20,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":21,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":26,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":9,"losses":11,"wins":16},"meituan/longcat-2.0":{"draws":25,"losses":11,"wins":30},"meta/muse-glimmer-30b":{"draws":24,"losses":3,"wins":19},"meta/muse-spark-1.2":{"draws":26,"losses":12,"wins":38},"meta/muse-spark-1.3":{"draws":16,"losses":14,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":6,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":25,"losses":26,"wins":47},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":2,"wins":8},"o3":{"draws":15,"losses":23,"wins":76},"openai/gpt-oss-120b":{"draws":30,"losses":8,"wins":16},"poolside/laguna-s-2.1":{"draws":26,"losses":7,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":33,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":19},"qwen/qwen3.8-max":{"draws":28,"losses":25,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":6,"wins":9},"stealth/ox-alpha":{"draws":63,"losses":47,"wins":70},"stealth/space-bunny-alpha":{"draws":12,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":17},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":17,"losses":18,"wins":19},"thinkingmachines/inkling":{"draws":16,"losses":16,"wins":40},"thinkingmachines/inkling-small":{"draws":38,"losses":7,"wins":30},"x-ai/grok-4.5":{"draws":24,"losses":33,"wins":41},"x-ai/grok-4.6":{"draws":30,"losses":21,"wins":19},"x-ai/grok-4.7":{"draws":4,"losses":9,"wins":5},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":2,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":4},"z-ai/glm-5.2":{"draws":38,"losses":15,"wins":33},"z-ai/glm-5.3":{"draws":18,"losses":33,"wins":19},"z-ai/glm-5.3-flash":{"draws":17,"losses":33,"wins":22},"z-ai/glm-5.3-flashx":{"draws":11,"losses":5,"wins":2}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":6,"wins":9},"claude-fable-5":{"draws":8,"losses":18,"wins":6},"claude-fable-5-1":{"draws":3,"losses":23,"wins":0},"claude-opus-4-5":{"draws":33,"losses":38,"wins":39},"claude-opus-4-8":{"draws":17,"losses":26,"wins":31},"claude-opus-5":{"draws":15,"losses":78,"wins":11},"claude-opus-5-5":{"draws":2,"losses":28,"wins":2},"claude-sonnet-5":{"draws":8,"losses":7,"wins":7},"claude-sonnet-5-5":{"draws":5,"losses":14,"wins":11},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":21},"deepseek/deepseek-v4-flash":{"draws":25,"losses":9,"wins":26},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":9},"fireworks/ember-1":{"draws":8,"losses":11,"wins":9},"gemini-3.1-pro-preview":{"draws":4,"losses":6,"wins":14},"google/gemini-3.1-flash-lite":{"draws":12,"losses":6,"wins":18},"google/gemini-3.5-flash":{"draws":12,"losses":13,"wins":17},"google/gemini-3.5-flash-lite":{"draws":24,"losses":8,"wins":42},"google/gemini-3.6-flash":{"draws":15,"losses":31,"wins":19},"google/gemini-3.8-flash":{"draws":7,"losses":17,"wins":12},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":16},"gpt-4.1":{"draws":12,"losses":7,"wins":15},"gpt-5":{"draws":16,"losses":7,"wins":27},"gpt-5.4":{"draws":2,"losses":5,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":17,"losses":29,"wins":30},"gpt-5.5":{"draws":27,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":1,"wins":8},"gpt-5.6-sol":{"draws":5,"losses":28,"wins":5},"gpt-5.6-terra":{"draws":15,"losses":9,"wins":8},"gpt-6-astra":{"draws":2,"losses":22,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":8},"gpt-6-sol":{"draws":3,"losses":14,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":11},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":16},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":39},"meta/muse-glimmer-30b":{"draws":12,"losses":0,"wins":14},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":16,"wins":4},"minimax/minimax-m3":{"draws":23,"losses":6,"wins":29},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":5,"wins":20},"nex-agi/nex-n2-pro":{"draws":14,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":13,"wins":22},"o3":{"draws":7,"losses":16,"wins":23},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":25,"losses":10,"wins":31},"qwen/qwen3.7-max":{"draws":15,"losses":15,"wins":12},"qwen/qwen3.7-plus":{"draws":14,"losses":11,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":14,"wins":4},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.8-max-0902":{"draws":5,"losses":12,"wins":9},"stealth/ox-alpha":{"draws":28,"losses":49,"wins":31},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":13,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":19},"thinkingmachines/inkling-small":{"draws":15,"losses":6,"wins":9},"x-ai/grok-4.5":{"draws":12,"losses":26,"wins":8},"x-ai/grok-4.6":{"draws":9,"losses":22,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":21,"wins":4},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":18},"xiaomi/mimo-v2.5":{"draws":42,"losses":19,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":8,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":11,"wins":3},"z-ai/glm-5.2":{"draws":44,"losses":29,"wins":17},"z-ai/glm-5.3":{"draws":2,"losses":15,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":21,"wins":5},"z-ai/glm-5.3-flashx":{"draws":0,"losses":19,"wins":9}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":14,"wins":15},"claude-fable-5":{"draws":3,"losses":36,"wins":7},"claude-fable-5-1":{"draws":0,"losses":24,"wins":0},"claude-opus-4-5":{"draws":43,"losses":53,"wins":60},"claude-opus-4-8":{"draws":22,"losses":53,"wins":27},"claude-opus-5":{"draws":11,"losses":100,"wins":25},"claude-opus-5-5":{"draws":0,"losses":26,"wins":2},"claude-sonnet-5":{"draws":6,"losses":18,"wins":14},"claude-sonnet-5-5":{"draws":7,"losses":17,"wins":8},"cohere/north-mini-code":{"draws":19,"losses":22,"wins":27},"deepseek/deepseek-v4-flash":{"draws":22,"losses":21,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":24,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":26,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":10,"losses":7,"wins":13},"gemini-3.1-pro-preview":{"draws":10,"losses":12,"wins":16},"google/gemini-3.1-flash-lite":{"draws":12,"losses":13,"wins":61},"google/gemini-3.5-flash":{"draws":14,"losses":33,"wins":23},"google/gemini-3.5-flash-lite":{"draws":14,"losses":56,"wins":26},"google/gemini-3.6-flash":{"draws":19,"losses":47,"wins":30},"google/gemini-3.8-flash":{"draws":9,"losses":30,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":20,"wins":23},"gpt-4.1":{"draws":3,"losses":13,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":14,"losses":33,"wins":31},"gpt-5.4":{"draws":9,"losses":26,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":23,"wins":40},"gpt-5.4-nano":{"draws":15,"losses":41,"wins":42},"gpt-5.5":{"draws":22,"losses":42,"wins":30},"gpt-5.6-luna":{"draws":7,"losses":13,"wins":22},"gpt-5.6-sol":{"draws":5,"losses":27,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":23,"wins":22},"gpt-6-astra":{"draws":1,"losses":43,"wins":0},"gpt-6-luna":{"draws":13,"losses":18,"wins":17},"gpt-6-sol":{"draws":3,"losses":25,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":28,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":5},"inception/mercury-2.5-preview":{"draws":7,"losses":7,"wins":20},"inclusionai/ling-3.0-flash":{"draws":20,"losses":17,"wins":15},"meituan/longcat-2.0":{"draws":15,"losses":36,"wins":53},"meta/muse-glimmer-30b":{"draws":6,"losses":10,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":21,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":8},"minimax/minimax-m3":{"draws":15,"losses":16,"wins":29},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":16,"wins":15},"moonshotai/kimi-k3":{"draws":19,"losses":26,"wins":11},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":34,"wins":24},"o3":{"draws":6,"losses":54,"wins":46},"openai/gpt-oss-120b":{"draws":6,"losses":13,"wins":13},"poolside/laguna-s-2.1":{"draws":22,"losses":34,"wins":24},"qwen/qwen3.7-max":{"draws":15,"losses":25,"wins":24},"qwen/qwen3.7-plus":{"draws":18,"losses":33,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":28,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":23,"wins":9},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":6,"losses":24,"wins":6},"qwen/qwen3.8-max-0902":{"draws":6,"losses":18,"wins":8},"stealth/ox-alpha":{"draws":19,"losses":74,"wins":31},"stealth/space-bunny-alpha":{"draws":7,"losses":4,"wins":17},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":39},"tencent/hy3-preview":{"draws":6,"losses":11,"wins":13},"tencent/hy4-preview":{"draws":3,"losses":21,"wins":8},"thinkingmachines/inkling":{"draws":7,"losses":18,"wins":45},"thinkingmachines/inkling-small":{"draws":15,"losses":16,"wins":13},"x-ai/grok-4.5":{"draws":10,"losses":40,"wins":32},"x-ai/grok-4.6":{"draws":5,"losses":32,"wins":7},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":15,"wins":27},"xiaomi/mimo-v2.5":{"draws":46,"losses":56,"wins":78},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":32,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":16,"wins":2},"z-ai/glm-5.2":{"draws":34,"losses":57,"wins":55},"z-ai/glm-5.3":{"draws":3,"losses":41,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":6,"losses":22,"wins":10}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":6,"wins":8},"claude-fable-5":{"draws":2,"losses":21,"wins":11},"claude-fable-5-1":{"draws":3,"losses":25,"wins":2},"claude-opus-4-5":{"draws":40,"losses":29,"wins":33},"claude-opus-4-8":{"draws":26,"losses":19,"wins":27},"claude-opus-5":{"draws":17,"losses":81,"wins":20},"claude-opus-5-5":{"draws":1,"losses":9,"wins":4},"claude-sonnet-5":{"draws":12,"losses":5,"wins":11},"claude-sonnet-5-5":{"draws":4,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":13,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":24,"losses":10,"wins":24},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":11,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":4},"fireworks/ember-1":{"draws":10,"losses":10,"wins":6},"gemini-3.1-pro-preview":{"draws":7,"losses":6,"wins":11},"google/gemini-3.1-flash-lite":{"draws":16,"losses":6,"wins":18},"google/gemini-3.5-flash":{"draws":15,"losses":12,"wins":19},"google/gemini-3.5-flash-lite":{"draws":31,"losses":3,"wins":24},"google/gemini-3.6-flash":{"draws":23,"losses":24,"wins":25},"google/gemini-3.8-flash":{"draws":13,"losses":13,"wins":6},"google/gemma-4-31b-it":{"draws":9,"losses":1,"wins":20},"gpt-4.1":{"draws":8,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":16,"wins":27},"gpt-5.4":{"draws":9,"losses":7,"wins":12},"gpt-5.4-mini":{"draws":30,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":24,"losses":39,"wins":23},"gpt-5.5":{"draws":13,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":8,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":8,"losses":9,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":7,"wins":11},"gpt-6-astra":{"draws":1,"losses":22,"wins":3},"gpt-6-luna":{"draws":6,"losses":7,"wins":11},"gpt-6-sol":{"draws":2,"losses":8,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":7,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":16},"meituan/longcat-2.0":{"draws":17,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":12,"losses":2,"wins":12},"meta/muse-spark-1.2":{"draws":8,"losses":8,"wins":6},"meta/muse-spark-1.3":{"draws":8,"losses":12,"wins":10},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":26},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":3,"wins":33},"o3":{"draws":16,"losses":17,"wins":17},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":12},"poolside/laguna-s-2.1":{"draws":20,"losses":11,"wins":15},"qwen/qwen3.7-max":{"draws":17,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":20,"losses":6,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":18},"qwen/qwen3.8-flash":{"draws":11,"losses":5,"wins":10},"qwen/qwen3.8-max":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.8-max-0902":{"draws":9,"losses":5,"wins":4},"stealth/ox-alpha":{"draws":32,"losses":41,"wins":23},"stealth/space-bunny-alpha":{"draws":3,"losses":3,"wins":6},"stepfun/step-3.7-flash":{"draws":8,"losses":2,"wins":24},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":7,"losses":7,"wins":10},"thinkingmachines/inkling":{"draws":15,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":12,"losses":27,"wins":23},"x-ai/grok-4.6":{"draws":7,"losses":18,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":8},"x-ai/grok-build-0.1":{"draws":23,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":39,"losses":13,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":44,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":13,"losses":18,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":13,"wins":15},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":3}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":21,"wins":25},"claude-fable-5":{"draws":16,"losses":46,"wins":4},"claude-fable-5-1":{"draws":8,"losses":44,"wins":0},"claude-opus-4-5":{"draws":34,"losses":39,"wins":27},"claude-opus-4-8":{"draws":13,"losses":15,"wins":2},"claude-opus-5":{"draws":8,"losses":34,"wins":6},"claude-opus-5-5":{"draws":0,"losses":20,"wins":0},"claude-sonnet-5":{"draws":43,"losses":40,"wins":29},"claude-sonnet-5-5":{"draws":6,"losses":18,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":33,"losses":25,"wins":32},"deepseek/deepseek-v4-pro":{"draws":23,"losses":20,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":27,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":7,"wins":0},"fireworks/ember-1":{"draws":10,"losses":11,"wins":7},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":26,"losses":24,"wins":16},"google/gemini-3.5-flash-lite":{"draws":68,"losses":44,"wins":80},"google/gemini-3.6-flash":{"draws":50,"losses":88,"wins":42},"google/gemini-3.8-flash":{"draws":18,"losses":36,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":10},"gpt-4.1":{"draws":5,"losses":1,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":14,"wins":2},"gpt-5.4":{"draws":39,"losses":63,"wins":18},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":9,"wins":13},"gpt-5.5":{"draws":9,"losses":12,"wins":7},"gpt-5.6-luna":{"draws":38,"losses":20,"wins":29},"gpt-5.6-sol":{"draws":23,"losses":78,"wins":13},"gpt-5.6-terra":{"draws":24,"losses":22,"wins":28},"gpt-6-astra":{"draws":8,"losses":44,"wins":0},"gpt-6-luna":{"draws":8,"losses":16,"wins":2},"gpt-6-sol":{"draws":3,"losses":10,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":27,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":25,"losses":2,"wins":27},"inclusionai/ling-3.0-flash":{"draws":14,"losses":10,"wins":14},"meituan/longcat-2.0":{"draws":22,"losses":11,"wins":29},"meta/muse-glimmer-30b":{"draws":32,"losses":10,"wins":26},"meta/muse-spark-1.2":{"draws":20,"losses":39,"wins":21},"meta/muse-spark-1.3":{"draws":21,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":15,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":29,"losses":53,"wins":18},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":1},"o3":{"draws":22,"losses":44,"wins":50},"openai/gpt-oss-120b":{"draws":23,"losses":11,"wins":22},"poolside/laguna-s-2.1":{"draws":26,"losses":9,"wins":29},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":24,"wins":12},"qwen/qwen3.8-27b":{"draws":7,"losses":13,"wins":16},"qwen/qwen3.8-flash":{"draws":12,"losses":17,"wins":19},"qwen/qwen3.8-max":{"draws":22,"losses":24,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":7,"wins":0},"stealth/ox-alpha":{"draws":76,"losses":76,"wins":52},"stealth/space-bunny-alpha":{"draws":11,"losses":5,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":14},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":9},"tencent/hy4-preview":{"draws":19,"losses":38,"wins":7},"thinkingmachines/inkling":{"draws":35,"losses":16,"wins":39},"thinkingmachines/inkling-small":{"draws":27,"losses":15,"wins":30},"x-ai/grok-4.5":{"draws":27,"losses":36,"wins":25},"x-ai/grok-4.6":{"draws":23,"losses":36,"wins":9},"x-ai/grok-4.7":{"draws":3,"losses":13,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":19,"losses":5,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":3,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":11,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":15,"losses":34,"wins":7},"z-ai/glm-5.3-flash":{"draws":21,"losses":36,"wins":11},"z-ai/glm-5.3-flashx":{"draws":6,"losses":2,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":14,"wins":30},"claude-fable-5":{"draws":13,"losses":33,"wins":24},"claude-fable-5-1":{"draws":9,"losses":68,"wins":5},"claude-opus-4-5":{"draws":23,"losses":21,"wins":64},"claude-opus-4-8":{"draws":1,"losses":18,"wins":7},"claude-opus-5":{"draws":16,"losses":44,"wins":16},"claude-opus-5-5":{"draws":1,"losses":23,"wins":2},"claude-sonnet-5":{"draws":16,"losses":18,"wins":81},"claude-sonnet-5-5":{"draws":3,"losses":14,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":47},"deepseek/deepseek-v4-pro":{"draws":2,"losses":15,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":14,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":6},"fireworks/ember-1":{"draws":5,"losses":7,"wins":12},"gemini-3.1-pro-preview":{"draws":3,"losses":9,"wins":16},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":7,"losses":17,"wins":38},"google/gemini-3.5-flash-lite":{"draws":18,"losses":21,"wins":129},"google/gemini-3.6-flash":{"draws":22,"losses":51,"wins":85},"google/gemini-3.8-flash":{"draws":7,"losses":32,"wins":31},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":11},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":0,"wins":14},"gpt-5.4":{"draws":22,"losses":31,"wins":57},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":12},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":22},"gpt-5.5":{"draws":8,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":10,"losses":21,"wins":65},"gpt-5.6-sol":{"draws":18,"losses":51,"wins":15},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":33},"gpt-6-astra":{"draws":8,"losses":55,"wins":3},"gpt-6-luna":{"draws":7,"losses":3,"wins":12},"gpt-6-sol":{"draws":2,"losses":4,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":22,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.0-flash":{"draws":3,"losses":6,"wins":23},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":40},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":26},"meta/muse-spark-1.2":{"draws":7,"losses":16,"wins":57},"meta/muse-spark-1.3":{"draws":11,"losses":18,"wins":15},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":28,"losses":26,"wins":42},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":13},"o3":{"draws":13,"losses":15,"wins":86},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":14,"losses":1,"wins":51},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":14,"wins":40},"qwen/qwen3.8-27b":{"draws":6,"losses":10,"wins":20},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":28},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":28},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":8},"stealth/ox-alpha":{"draws":30,"losses":53,"wins":116},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":16},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":6,"losses":16,"wins":40},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":14,"wins":28},"x-ai/grok-4.5":{"draws":11,"losses":38,"wins":51},"x-ai/grok-4.6":{"draws":13,"losses":33,"wins":28},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":12,"wins":71},"z-ai/glm-5.3":{"draws":16,"losses":19,"wins":25},"z-ai/glm-5.3-flash":{"draws":15,"losses":30,"wins":33},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":6}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":11,"wins":22},"claude-fable-5":{"draws":15,"losses":47,"wins":14},"claude-fable-5-1":{"draws":7,"losses":67,"wins":4},"claude-opus-4-5":{"draws":21,"losses":25,"wins":20},"claude-opus-4-8":{"draws":14,"losses":15,"wins":7},"claude-opus-5":{"draws":4,"losses":52,"wins":2},"claude-opus-5-5":{"draws":1,"losses":27,"wins":0},"claude-sonnet-5":{"draws":16,"losses":19,"wins":27},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":34,"losses":13,"wins":23},"deepseek/deepseek-v4-pro":{"draws":25,"losses":20,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":18,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":9},"fireworks/ember-1":{"draws":6,"losses":13,"wins":9},"gemini-3.1-pro-preview":{"draws":6,"losses":10,"wins":12},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":16,"losses":21,"wins":31},"google/gemini-3.5-flash-lite":{"draws":34,"losses":20,"wins":58},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":32},"google/gemini-3.8-flash":{"draws":20,"losses":20,"wins":24},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":14},"gpt-4.1":{"draws":11,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":2,"wins":20},"gpt-5.4":{"draws":21,"losses":32,"wins":11},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":10,"wins":16},"gpt-5.5":{"draws":6,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":30,"losses":26,"wins":14},"gpt-5.6-sol":{"draws":18,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":10,"losses":14,"wins":12},"gpt-6-astra":{"draws":6,"losses":65,"wins":3},"gpt-6-luna":{"draws":8,"losses":12,"wins":14},"gpt-6-sol":{"draws":2,"losses":17,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":23,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":16},"meituan/longcat-2.0":{"draws":14,"losses":15,"wins":33},"meta/muse-glimmer-30b":{"draws":20,"losses":7,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":24},"meta/muse-spark-1.3":{"draws":17,"losses":31,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":7,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":36,"wins":18},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":13},"o3":{"draws":10,"losses":22,"wins":38},"openai/gpt-oss-120b":{"draws":16,"losses":9,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":22},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":25,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.8-flash":{"draws":15,"losses":15,"wins":10},"qwen/qwen3.8-max":{"draws":26,"losses":21,"wins":17},"qwen/qwen3.8-max-0902":{"draws":6,"losses":11,"wins":5},"stealth/ox-alpha":{"draws":64,"losses":80,"wins":62},"stealth/space-bunny-alpha":{"draws":6,"losses":7,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":14},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":16,"losses":33,"wins":11},"thinkingmachines/inkling":{"draws":16,"losses":7,"wins":21},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":32},"x-ai/grok-4.5":{"draws":12,"losses":30,"wins":18},"x-ai/grok-4.6":{"draws":22,"losses":39,"wins":19},"x-ai/grok-4.7":{"draws":6,"losses":17,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":14,"losses":3,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":5},"z-ai/glm-5.2":{"draws":34,"losses":24,"wins":30},"z-ai/glm-5.3":{"draws":13,"losses":37,"wins":12},"z-ai/glm-5.3-flash":{"draws":15,"losses":30,"wins":25},"z-ai/glm-5.3-flashx":{"draws":6,"losses":8,"wins":12}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":36},"claude-fable-5":{"draws":6,"losses":12,"wins":58},"claude-fable-5-1":{"draws":6,"losses":26,"wins":38},"claude-opus-4-5":{"draws":6,"losses":2,"wins":60},"claude-opus-4-8":{"draws":0,"losses":0,"wins":28},"claude-opus-5":{"draws":6,"losses":12,"wins":26},"claude-opus-5-5":{"draws":4,"losses":11,"wins":11},"claude-sonnet-5":{"draws":2,"losses":0,"wins":64},"claude-sonnet-5-5":{"draws":6,"losses":7,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":59},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":11},"fireworks/ember-1":{"draws":1,"losses":1,"wins":22},"gemini-3.1-pro-preview":{"draws":5,"losses":0,"wins":25},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":8,"losses":6,"wins":54},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":70},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":87},"google/gemini-3.8-flash":{"draws":8,"losses":3,"wins":65},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":10},"gpt-4.1":{"draws":0,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":20},"gpt-5.4":{"draws":5,"losses":8,"wins":57},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":34},"gpt-5.5":{"draws":1,"losses":2,"wins":21},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":49},"gpt-5.6-sol":{"draws":8,"losses":9,"wins":51},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":64},"gpt-6-astra":{"draws":4,"losses":28,"wins":10},"gpt-6-luna":{"draws":6,"losses":1,"wins":25},"gpt-6-sol":{"draws":4,"losses":0,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":8,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":24},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":19},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":33},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":31},"meta/muse-spark-1.2":{"draws":7,"losses":0,"wins":41},"meta/muse-spark-1.3":{"draws":6,"losses":3,"wins":45},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":4,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":13},"o3":{"draws":2,"losses":0,"wins":62},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":23},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":30},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":17},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":56},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":34},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":35},"qwen/qwen3.8-max":{"draws":8,"losses":0,"wins":50},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":12},"stealth/ox-alpha":{"draws":33,"losses":13,"wins":148},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":15},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":5,"losses":3,"wins":52},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":42},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":39},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":58},"x-ai/grok-4.6":{"draws":7,"losses":8,"wins":53},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":1,"wins":9},"z-ai/glm-5.2":{"draws":7,"losses":2,"wins":71},"z-ai/glm-5.3":{"draws":10,"losses":10,"wins":50},"z-ai/glm-5.3-flash":{"draws":9,"losses":3,"wins":54},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":16}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":9},"claude-fable-5":{"draws":4,"losses":15,"wins":5},"claude-fable-5-1":{"draws":1,"losses":17,"wins":0},"claude-opus-4-5":{"draws":18,"losses":12,"wins":4},"claude-opus-4-8":{"draws":7,"losses":9,"wins":6},"claude-opus-5":{"draws":9,"losses":22,"wins":1},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":4,"losses":6,"wins":6},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":12,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":15,"losses":18,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":16,"wins":14},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":14,"wins":8},"google/gemini-3.5-flash-lite":{"draws":14,"losses":11,"wins":15},"google/gemini-3.6-flash":{"draws":12,"losses":22,"wins":4},"google/gemini-3.8-flash":{"draws":7,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":5,"losses":1,"wins":0},"gpt-5.4":{"draws":10,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":6},"gpt-5.5":{"draws":12,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":12,"losses":2,"wins":6},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":11},"gpt-6-astra":{"draws":3,"losses":18,"wins":1},"gpt-6-luna":{"draws":8,"losses":11,"wins":11},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":10},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":3},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":5,"losses":10,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":10},"o3":{"draws":10,"losses":9,"wins":9},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":10},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":6,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":4,"losses":12,"wins":8},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":13},"stealth/ox-alpha":{"draws":13,"losses":28,"wins":19},"stealth/space-bunny-alpha":{"draws":15,"losses":8,"wins":13},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":3,"wins":9},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":11,"losses":9,"wins":8},"x-ai/grok-4.6":{"draws":10,"losses":19,"wins":1},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":18,"losses":15,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":13,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":5},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":20},"claude-fable-5":{"draws":3,"losses":12,"wins":15},"claude-fable-5-1":{"draws":0,"losses":15,"wins":7},"claude-opus-4-5":{"draws":8,"losses":3,"wins":19},"claude-opus-4-8":{"draws":5,"losses":4,"wins":13},"claude-opus-5":{"draws":5,"losses":12,"wins":15},"claude-opus-5-5":{"draws":5,"losses":35,"wins":12},"claude-sonnet-5":{"draws":3,"losses":2,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":16,"wins":25},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":33},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":7,"wins":29},"fireworks/ember-1":{"draws":7,"losses":6,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":35},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":21},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":28},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":30},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":8},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":1,"losses":2,"wins":11},"gpt-5":{"draws":1,"losses":0,"wins":13},"gpt-5.4":{"draws":4,"losses":2,"wins":14},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":11},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":12},"gpt-5.5":{"draws":5,"losses":3,"wins":16},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":0,"wins":19},"gpt-6-astra":{"draws":4,"losses":12,"wins":2},"gpt-6-luna":{"draws":8,"losses":7,"wins":31},"gpt-6-sol":{"draws":6,"losses":12,"wins":14},"gpt-6.1-sol":{"draws":6,"losses":26,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":23},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":28},"meta/muse-glimmer-30b":{"draws":0,"losses":1,"wins":17},"meta/muse-spark-1.2":{"draws":1,"losses":2,"wins":13},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":9},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":17},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":18},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":18},"o3":{"draws":2,"losses":0,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":21},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":17},"qwen/qwen3.7-max":{"draws":5,"losses":0,"wins":9},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":3,"wins":11},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":7},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":9},"qwen/qwen3.8-max":{"draws":3,"losses":4,"wins":17},"qwen/qwen3.8-max-0902":{"draws":6,"losses":8,"wins":32},"stealth/ox-alpha":{"draws":7,"losses":6,"wins":35},"stealth/space-bunny-alpha":{"draws":6,"losses":3,"wins":25},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":13},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":9},"tencent/hy4-preview":{"draws":3,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":18},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":22},"x-ai/grok-4.6":{"draws":7,"losses":6,"wins":21},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":15},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":9,"wins":16},"z-ai/glm-5.2":{"draws":7,"losses":1,"wins":40},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":7,"wins":22},"z-ai/glm-5.3-flashx":{"draws":7,"losses":10,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":19},"claude-fable-5":{"draws":1,"losses":1,"wins":12},"claude-fable-5-1":{"draws":3,"losses":9,"wins":18},"claude-opus-4-5":{"draws":1,"losses":3,"wins":36},"claude-opus-4-8":{"draws":1,"losses":2,"wins":19},"claude-opus-5":{"draws":5,"losses":8,"wins":13},"claude-opus-5-5":{"draws":3,"losses":23,"wins":20},"claude-sonnet-5":{"draws":0,"losses":0,"wins":28},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":34},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":32},"fireworks/ember-1":{"draws":0,"losses":8,"wins":40},"gemini-3.1-pro-preview":{"draws":4,"losses":3,"wins":41},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":14},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":42},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":37},"google/gemini-3.8-flash":{"draws":2,"losses":4,"wins":12},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":10},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":12},"gpt-5.4":{"draws":0,"losses":2,"wins":20},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":13},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":22},"gpt-5.5":{"draws":1,"losses":2,"wins":15},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":21},"gpt-5.6-sol":{"draws":2,"losses":1,"wins":17},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":17},"gpt-6-astra":{"draws":2,"losses":14,"wins":6},"gpt-6-luna":{"draws":1,"losses":0,"wins":21},"gpt-6-sol":{"draws":5,"losses":7,"wins":32},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":23},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":28},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":17},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":16},"meta/muse-spark-1.3":{"draws":2,"losses":2,"wins":22},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":15},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":30},"o3":{"draws":0,"losses":0,"wins":30},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":24},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":21},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":21},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":3,"wins":21},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":19},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.8-max-0902":{"draws":4,"losses":5,"wins":29},"stealth/ox-alpha":{"draws":10,"losses":3,"wins":71},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":11},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":19},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":24},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":30},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":17},"x-ai/grok-4.6":{"draws":1,"losses":1,"wins":14},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":23},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":42},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":16},"z-ai/glm-5.3-flash":{"draws":3,"losses":0,"wins":15},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":30}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":12,"wins":0},"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":4,"losses":16,"wins":0},"claude-opus-4-8":{"draws":2,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5-5":{"draws":2,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":9,"losses":11,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":2,"losses":6,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":14,"wins":0},"google/gemini-3.5-flash-lite":{"draws":16,"losses":14,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":25,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":10,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":0},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":0,"losses":8,"wins":0},"gpt-5.4":{"draws":4,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":2},"gpt-5.5":{"draws":1,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":11,"wins":0},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":3,"losses":5,"wins":0},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":6,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":8,"wins":3},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":14,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":13,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":0},"o3":{"draws":6,"losses":20,"wins":0},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":0},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":9,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":13,"losses":27,"wins":0},"stealth/space-bunny-alpha":{"draws":4,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":0},"thinkingmachines/inkling-small":{"draws":8,"losses":10,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":10,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":14,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":4,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":6,"wins":2},"z-ai/glm-5.3":{"draws":4,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":4,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":17,"wins":8},"claude-fable-5":{"draws":13,"losses":25,"wins":0},"claude-fable-5-1":{"draws":4,"losses":26,"wins":0},"claude-opus-4-5":{"draws":18,"losses":37,"wins":1},"claude-opus-4-8":{"draws":4,"losses":17,"wins":1},"claude-opus-5":{"draws":4,"losses":34,"wins":2},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":26,"losses":27,"wins":3},"claude-sonnet-5-5":{"draws":6,"losses":18,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":27,"losses":22,"wins":3},"deepseek/deepseek-v4-pro":{"draws":20,"losses":26,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":4,"wins":2},"fireworks/ember-1":{"draws":6,"losses":10,"wins":0},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":6},"google/gemini-3.5-flash-lite":{"draws":43,"losses":44,"wins":13},"google/gemini-3.6-flash":{"draws":25,"losses":35,"wins":4},"google/gemini-3.8-flash":{"draws":18,"losses":19,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":5},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":6,"losses":11,"wins":1},"gpt-5.4":{"draws":16,"losses":20,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":20,"wins":3},"gpt-5.5":{"draws":7,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":30,"losses":18,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":24,"wins":0},"gpt-5.6-terra":{"draws":24,"losses":24,"wins":0},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":6,"losses":9,"wins":1},"gpt-6-sol":{"draws":0,"losses":8,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":2,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":11,"wins":3},"meituan/longcat-2.0":{"draws":13,"losses":18,"wins":10},"meta/muse-glimmer-30b":{"draws":28,"losses":12,"wins":4},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":4},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":21,"losses":11,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":30,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":5},"o3":{"draws":11,"losses":33,"wins":8},"openai/gpt-oss-120b":{"draws":22,"losses":21,"wins":5},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":19,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":15,"wins":2},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":17,"losses":18,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":33,"losses":78,"wins":9},"stealth/space-bunny-alpha":{"draws":5,"losses":11,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":15,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":4},"tencent/hy4-preview":{"draws":17,"losses":20,"wins":3},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":8},"thinkingmachines/inkling-small":{"draws":22,"losses":20,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":26,"wins":0},"x-ai/grok-4.6":{"draws":12,"losses":35,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":19,"losses":16,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":31,"losses":36,"wins":5},"z-ai/glm-5.3":{"draws":17,"losses":24,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":29,"wins":5},"z-ai/glm-5.3-flashx":{"draws":8,"losses":6,"wins":2}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":22,"wins":11},"claude-fable-5":{"draws":8,"losses":26,"wins":2},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-opus-4-5":{"draws":27,"losses":45,"wins":22},"claude-opus-4-8":{"draws":14,"losses":16,"wins":0},"claude-opus-5":{"draws":10,"losses":30,"wins":2},"claude-opus-5-5":{"draws":3,"losses":25,"wins":0},"claude-sonnet-5":{"draws":28,"losses":59,"wins":11},"claude-sonnet-5-5":{"draws":4,"losses":7,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":16},"deepseek/deepseek-v4-flash":{"draws":20,"losses":26,"wins":24},"deepseek/deepseek-v4-pro":{"draws":9,"losses":24,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":17,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":2},"fireworks/ember-1":{"draws":7,"losses":11,"wins":2},"gemini-3.1-pro-preview":{"draws":2,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":14,"losses":33,"wins":9},"google/gemini-3.5-flash-lite":{"draws":54,"losses":101,"wins":45},"google/gemini-3.6-flash":{"draws":65,"losses":84,"wins":33},"google/gemini-3.8-flash":{"draws":5,"losses":30,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":10},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":8,"losses":18,"wins":2},"gpt-5.4":{"draws":15,"losses":40,"wins":17},"gpt-5.4-mini":{"draws":6,"losses":10,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":11},"gpt-5.5":{"draws":8,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":29,"losses":25,"wins":30},"gpt-5.6-sol":{"draws":11,"losses":50,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":36,"wins":8},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":7,"losses":16,"wins":3},"gpt-6-sol":{"draws":2,"losses":23,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":20,"losses":7,"wins":19},"inclusionai/ling-3.0-flash":{"draws":4,"losses":14,"wins":16},"meituan/longcat-2.0":{"draws":25,"losses":42,"wins":33},"meta/muse-glimmer-30b":{"draws":20,"losses":17,"wins":11},"meta/muse-spark-1.2":{"draws":21,"losses":21,"wins":12},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":14,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":10,"wins":4},"moonshotai/kimi-k3":{"draws":20,"losses":60,"wins":22},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":15},"o3":{"draws":7,"losses":87,"wins":38},"openai/gpt-oss-120b":{"draws":12,"losses":29,"wins":9},"poolside/laguna-s-2.1":{"draws":24,"losses":27,"wins":9},"qwen/qwen3.7-max":{"draws":11,"losses":22,"wins":1},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":21,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":19,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":22,"wins":11},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":6},"stealth/ox-alpha":{"draws":22,"losses":75,"wins":27},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":17,"wins":13},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":2},"tencent/hy4-preview":{"draws":7,"losses":30,"wins":5},"thinkingmachines/inkling":{"draws":32,"losses":27,"wins":31},"thinkingmachines/inkling-small":{"draws":17,"losses":28,"wins":14},"x-ai/grok-4.5":{"draws":33,"losses":63,"wins":10},"x-ai/grok-4.6":{"draws":12,"losses":29,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":16,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":13,"wins":4},"xiaomi/mimo-v2.5":{"draws":9,"losses":15,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":14,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":16,"losses":30,"wins":20},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":32,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":17,"wins":1}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":34,"wins":18},"claude-fable-5":{"draws":17,"losses":54,"wins":17},"claude-fable-5-1":{"draws":2,"losses":56,"wins":2},"claude-opus-4-5":{"draws":47,"losses":110,"wins":35},"claude-opus-4-8":{"draws":17,"losses":25,"wins":9},"claude-opus-5":{"draws":15,"losses":82,"wins":14},"claude-opus-5-5":{"draws":4,"losses":51,"wins":3},"claude-sonnet-5":{"draws":47,"losses":85,"wins":16},"claude-sonnet-5-5":{"draws":8,"losses":30,"wins":10},"cohere/north-mini-code":{"draws":9,"losses":9,"wins":22},"deepseek/deepseek-v4-flash":{"draws":33,"losses":35,"wins":20},"deepseek/deepseek-v4-pro":{"draws":30,"losses":45,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":43,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":31,"wins":12},"fireworks/ember-1":{"draws":13,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":9,"losses":25,"wins":12},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":19},"google/gemini-3.5-flash":{"draws":27,"losses":71,"wins":16},"google/gemini-3.5-flash-lite":{"draws":84,"losses":148,"wins":159},"google/gemini-3.6-flash":{"draws":88,"losses":190,"wins":46},"google/gemini-3.8-flash":{"draws":23,"losses":31,"wins":13},"google/gemma-4-31b-it":{"draws":3,"losses":11,"wins":18},"gpt-4.1":{"draws":7,"losses":9,"wins":4},"gpt-5":{"draws":13,"losses":21,"wins":4},"gpt-5.4":{"draws":42,"losses":76,"wins":20},"gpt-5.4-mini":{"draws":14,"losses":24,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":24,"wins":21},"gpt-5.5":{"draws":17,"losses":31,"wins":9},"gpt-5.6-luna":{"draws":52,"losses":64,"wins":46},"gpt-5.6-sol":{"draws":28,"losses":111,"wins":21},"gpt-5.6-terra":{"draws":33,"losses":50,"wins":27},"gpt-6-astra":{"draws":4,"losses":60,"wins":2},"gpt-6-luna":{"draws":13,"losses":32,"wins":7},"gpt-6-sol":{"draws":4,"losses":38,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":40,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":2,"wins":5},"inception/mercury-2.5-preview":{"draws":26,"losses":15,"wins":34},"inclusionai/ling-3.0-flash":{"draws":30,"losses":24,"wins":42},"meituan/longcat-2.0":{"draws":33,"losses":30,"wins":34},"meta/muse-glimmer-30b":{"draws":29,"losses":32,"wins":25},"meta/muse-spark-1.2":{"draws":32,"losses":48,"wins":40},"meta/muse-spark-1.3":{"draws":21,"losses":39,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":13,"wins":15},"mistralai/mistral-medium-3-5":{"draws":22,"losses":11,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":49,"losses":106,"wins":17},"nex-agi/nex-n2-pro":{"draws":7,"losses":9,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":15,"wins":17},"o3":{"draws":23,"losses":160,"wins":61},"openai/gpt-oss-120b":{"draws":31,"losses":18,"wins":33},"poolside/laguna-s-2.1":{"draws":50,"losses":30,"wins":58},"qwen/qwen3.7-max":{"draws":7,"losses":18,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":51,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":32,"wins":14},"qwen/qwen3.8-flash":{"draws":20,"losses":29,"wins":13},"qwen/qwen3.8-max":{"draws":34,"losses":49,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":33,"wins":8},"stealth/ox-alpha":{"draws":72,"losses":152,"wins":42},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":8},"stepfun/step-3.7-flash":{"draws":15,"losses":32,"wins":29},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":30,"losses":52,"wins":10},"thinkingmachines/inkling":{"draws":41,"losses":66,"wins":51},"thinkingmachines/inkling-small":{"draws":26,"losses":35,"wins":36},"x-ai/grok-4.5":{"draws":43,"losses":105,"wins":32},"x-ai/grok-4.6":{"draws":25,"losses":53,"wins":15},"x-ai/grok-4.7":{"draws":2,"losses":38,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":20,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":8,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":11,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":29,"losses":55,"wins":45},"z-ai/glm-5.3":{"draws":22,"losses":50,"wins":8},"z-ai/glm-5.3-flash":{"draws":22,"losses":54,"wins":20},"z-ai/glm-5.3-flashx":{"draws":18,"losses":25,"wins":6}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":19},"claude-fable-5":{"draws":14,"losses":26,"wins":2},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-opus-4-5":{"draws":31,"losses":32,"wins":9},"claude-opus-4-8":{"draws":11,"losses":17,"wins":2},"claude-opus-5":{"draws":3,"losses":28,"wins":3},"claude-opus-5-5":{"draws":2,"losses":24,"wins":0},"claude-sonnet-5":{"draws":20,"losses":28,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":47,"losses":32,"wins":7},"deepseek/deepseek-v4-pro":{"draws":22,"losses":25,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":28,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":20,"wins":2},"fireworks/ember-1":{"draws":10,"losses":16,"wins":2},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":25,"losses":31,"wins":8},"google/gemini-3.5-flash-lite":{"draws":56,"losses":46,"wins":18},"google/gemini-3.6-flash":{"draws":41,"losses":51,"wins":8},"google/gemini-3.8-flash":{"draws":20,"losses":27,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":7,"wins":2},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":9,"losses":12,"wins":7},"gpt-5.4":{"draws":12,"losses":12,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":7},"gpt-5.5":{"draws":8,"losses":16,"wins":0},"gpt-5.6-luna":{"draws":30,"losses":22,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":18,"wins":2},"gpt-5.6-terra":{"draws":27,"losses":35,"wins":10},"gpt-6-astra":{"draws":3,"losses":27,"wins":0},"gpt-6-luna":{"draws":7,"losses":15,"wins":4},"gpt-6-sol":{"draws":3,"losses":17,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":28,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":28,"losses":13,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":10},"meituan/longcat-2.0":{"draws":20,"losses":15,"wins":11},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":8},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":11},"meta/muse-spark-1.3":{"draws":18,"losses":20,"wins":2},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":18,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":28,"wins":7},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":6},"o3":{"draws":17,"losses":40,"wins":7},"openai/gpt-oss-120b":{"draws":28,"losses":18,"wins":12},"poolside/laguna-s-2.1":{"draws":35,"losses":16,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":3},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":32,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":24,"wins":2},"qwen/qwen3.8-flash":{"draws":20,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":23,"losses":25,"wins":12},"qwen/qwen3.8-max-0902":{"draws":5,"losses":22,"wins":1},"stealth/ox-alpha":{"draws":66,"losses":92,"wins":18},"stealth/space-bunny-alpha":{"draws":4,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":10,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":20,"losses":32,"wins":4},"thinkingmachines/inkling":{"draws":27,"losses":17,"wins":16},"thinkingmachines/inkling-small":{"draws":39,"losses":24,"wins":25},"x-ai/grok-4.5":{"draws":12,"losses":33,"wins":5},"x-ai/grok-4.6":{"draws":18,"losses":27,"wins":7},"x-ai/grok-4.7":{"draws":0,"losses":21,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":17,"losses":12,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":12,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":12,"wins":2},"z-ai/glm-5.2":{"draws":42,"losses":30,"wins":12},"z-ai/glm-5.3":{"draws":9,"losses":15,"wins":4},"z-ai/glm-5.3-flash":{"draws":23,"losses":35,"wins":8},"z-ai/glm-5.3-flashx":{"draws":3,"losses":20,"wins":3}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":14},"claude-fable-5":{"draws":8,"losses":37,"wins":17},"claude-fable-5-1":{"draws":3,"losses":50,"wins":7},"claude-opus-4-5":{"draws":25,"losses":13,"wins":48},"claude-opus-4-8":{"draws":7,"losses":8,"wins":11},"claude-opus-5":{"draws":6,"losses":35,"wins":9},"claude-opus-5-5":{"draws":5,"losses":28,"wins":5},"claude-sonnet-5":{"draws":36,"losses":28,"wins":36},"claude-sonnet-5-5":{"draws":10,"losses":8,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":21,"losses":4,"wins":33},"deepseek/deepseek-v4-pro":{"draws":7,"losses":19,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":10,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":9,"wins":8},"fireworks/ember-1":{"draws":8,"losses":7,"wins":5},"gemini-3.1-pro-preview":{"draws":10,"losses":7,"wins":11},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":9},"google/gemini-3.5-flash":{"draws":18,"losses":23,"wins":33},"google/gemini-3.5-flash-lite":{"draws":47,"losses":22,"wins":99},"google/gemini-3.6-flash":{"draws":26,"losses":37,"wins":95},"google/gemini-3.8-flash":{"draws":8,"losses":16,"wins":34},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":13},"gpt-4.1":{"draws":4,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":3,"wins":13},"gpt-5.4":{"draws":22,"losses":38,"wins":34},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":17},"gpt-5.5":{"draws":5,"losses":6,"wins":7},"gpt-5.6-luna":{"draws":30,"losses":12,"wins":52},"gpt-5.6-sol":{"draws":11,"losses":64,"wins":33},"gpt-5.6-terra":{"draws":27,"losses":13,"wins":26},"gpt-6-astra":{"draws":7,"losses":42,"wins":1},"gpt-6-luna":{"draws":12,"losses":7,"wins":15},"gpt-6-sol":{"draws":3,"losses":21,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":20,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":16},"meituan/longcat-2.0":{"draws":22,"losses":12,"wins":36},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":26},"meta/muse-spark-1.2":{"draws":11,"losses":7,"wins":28},"meta/muse-spark-1.3":{"draws":15,"losses":15,"wins":22},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":30,"wins":35},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":12},"o3":{"draws":8,"losses":28,"wins":54},"openai/gpt-oss-120b":{"draws":18,"losses":2,"wins":24},"poolside/laguna-s-2.1":{"draws":21,"losses":7,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":23,"wins":15},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":16},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":8},"stealth/ox-alpha":{"draws":49,"losses":75,"wins":55},"stealth/space-bunny-alpha":{"draws":8,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":22},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":10,"losses":18,"wins":14},"thinkingmachines/inkling":{"draws":21,"losses":5,"wins":34},"thinkingmachines/inkling-small":{"draws":20,"losses":3,"wins":25},"x-ai/grok-4.5":{"draws":16,"losses":32,"wins":28},"x-ai/grok-4.6":{"draws":16,"losses":33,"wins":19},"x-ai/grok-4.7":{"draws":1,"losses":18,"wins":5},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":12,"losses":1,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":11,"wins":4},"z-ai/glm-5.2":{"draws":15,"losses":24,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":30,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":24},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":8}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":8,"wins":24},"claude-fable-5":{"draws":15,"losses":37,"wins":24},"claude-fable-5-1":{"draws":4,"losses":69,"wins":7},"claude-opus-4-5":{"draws":12,"losses":13,"wins":43},"claude-opus-4-8":{"draws":6,"losses":7,"wins":17},"claude-opus-5":{"draws":12,"losses":37,"wins":19},"claude-opus-5-5":{"draws":2,"losses":20,"wins":4},"claude-sonnet-5":{"draws":17,"losses":14,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":8,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":13,"losses":7,"wins":52},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":13,"wins":10},"fireworks/ember-1":{"draws":2,"losses":9,"wins":9},"gemini-3.1-pro-preview":{"draws":2,"losses":3,"wins":11},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":55},"google/gemini-3.5-flash-lite":{"draws":15,"losses":15,"wins":60},"google/gemini-3.6-flash":{"draws":17,"losses":31,"wins":48},"google/gemini-3.8-flash":{"draws":11,"losses":22,"wins":41},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":10},"gpt-4.1":{"draws":5,"losses":0,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":5,"wins":23},"gpt-5.4":{"draws":5,"losses":22,"wins":27},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":21},"gpt-5.5":{"draws":2,"losses":7,"wins":11},"gpt-5.6-luna":{"draws":8,"losses":7,"wins":19},"gpt-5.6-sol":{"draws":15,"losses":27,"wins":24},"gpt-5.6-terra":{"draws":22,"losses":17,"wins":39},"gpt-6-astra":{"draws":8,"losses":56,"wins":6},"gpt-6-luna":{"draws":4,"losses":8,"wins":20},"gpt-6-sol":{"draws":1,"losses":12,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":14,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":7,"losses":5,"wins":18},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":18},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":34},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":24},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":27},"meta/muse-spark-1.3":{"draws":7,"losses":10,"wins":15},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":38},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":20},"o3":{"draws":1,"losses":11,"wins":58},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":28},"poolside/laguna-s-2.1":{"draws":9,"losses":6,"wins":29},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":26,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":25},"qwen/qwen3.8-flash":{"draws":13,"losses":8,"wins":27},"qwen/qwen3.8-max":{"draws":8,"losses":16,"wins":34},"qwen/qwen3.8-max-0902":{"draws":4,"losses":5,"wins":15},"stealth/ox-alpha":{"draws":43,"losses":65,"wins":104},"stealth/space-bunny-alpha":{"draws":4,"losses":3,"wins":13},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":31},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":30},"thinkingmachines/inkling":{"draws":9,"losses":4,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":2,"wins":42},"x-ai/grok-4.5":{"draws":4,"losses":20,"wins":32},"x-ai/grok-4.6":{"draws":13,"losses":35,"wins":32},"x-ai/grok-4.7":{"draws":2,"losses":17,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":17,"losses":18,"wins":43},"z-ai/glm-5.3":{"draws":5,"losses":39,"wins":22},"z-ai/glm-5.3-flash":{"draws":14,"losses":32,"wins":34},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":16}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":5},"claude-fable-5":{"draws":6,"losses":17,"wins":1},"claude-fable-5-1":{"draws":1,"losses":37,"wins":0},"claude-opus-4-5":{"draws":27,"losses":38,"wins":3},"claude-opus-4-8":{"draws":16,"losses":24,"wins":4},"claude-opus-5":{"draws":6,"losses":40,"wins":4},"claude-opus-5-5":{"draws":0,"losses":26,"wins":0},"claude-sonnet-5":{"draws":7,"losses":11,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":16},"deepseek/deepseek-v4-flash":{"draws":30,"losses":27,"wins":19},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":20,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":14,"wins":4},"fireworks/ember-1":{"draws":8,"losses":21,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":11,"wins":7},"google/gemini-3.1-flash-lite":{"draws":14,"losses":30,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":13,"wins":3},"google/gemini-3.5-flash-lite":{"draws":21,"losses":22,"wins":11},"google/gemini-3.6-flash":{"draws":17,"losses":29,"wins":2},"google/gemini-3.8-flash":{"draws":14,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":10},"gpt-4.1":{"draws":10,"losses":10,"wins":2},"gpt-5":{"draws":24,"losses":22,"wins":6},"gpt-5.4":{"draws":7,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":18,"losses":28,"wins":10},"gpt-5.4-nano":{"draws":21,"losses":35,"wins":10},"gpt-5.5":{"draws":15,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":9,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":13,"wins":3},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":7,"losses":16,"wins":7},"gpt-6-sol":{"draws":0,"losses":24,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":27,"losses":14,"wins":15},"meituan/longcat-2.0":{"draws":15,"losses":26,"wins":11},"meta/muse-glimmer-30b":{"draws":8,"losses":9,"wins":5},"meta/muse-spark-1.2":{"draws":7,"losses":15,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":11,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":15,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":4},"nex-agi/nex-n2-pro":{"draws":13,"losses":11,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":19,"wins":13},"o3":{"draws":12,"losses":26,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":3},"poolside/laguna-s-2.1":{"draws":32,"losses":17,"wins":7},"qwen/qwen3.7-max":{"draws":16,"losses":19,"wins":9},"qwen/qwen3.7-plus":{"draws":11,"losses":19,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":0},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":12,"wins":4},"stealth/ox-alpha":{"draws":20,"losses":36,"wins":4},"stealth/space-bunny-alpha":{"draws":8,"losses":14,"wins":4},"stepfun/step-3.7-flash":{"draws":17,"losses":9,"wins":6},"tencent/hy3-preview":{"draws":26,"losses":17,"wins":1},"tencent/hy4-preview":{"draws":7,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":10,"losses":26,"wins":12},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":37,"wins":2},"x-ai/grok-4.6":{"draws":11,"losses":18,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":15,"wins":3},"x-ai/grok-build-0.1":{"draws":14,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":55,"losses":46,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":16,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":10,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":16,"wins":2},"z-ai/glm-5.2":{"draws":38,"losses":34,"wins":6},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":3},"z-ai/glm-5.3-flashx":{"draws":3,"losses":20,"wins":1}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":8,"wins":12},"claude-fable-5":{"draws":7,"losses":12,"wins":5},"claude-fable-5-1":{"draws":3,"losses":25,"wins":0},"claude-opus-4-5":{"draws":19,"losses":39,"wins":28},"claude-opus-4-8":{"draws":14,"losses":22,"wins":10},"claude-opus-5":{"draws":11,"losses":87,"wins":4},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":6,"losses":8,"wins":14},"claude-sonnet-5-5":{"draws":4,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":9,"wins":17},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":27},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":10,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":8},"fireworks/ember-1":{"draws":4,"losses":9,"wins":5},"gemini-3.1-pro-preview":{"draws":2,"losses":8,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":31},"google/gemini-3.5-flash":{"draws":10,"losses":6,"wins":12},"google/gemini-3.5-flash-lite":{"draws":15,"losses":15,"wins":18},"google/gemini-3.6-flash":{"draws":13,"losses":26,"wins":13},"google/gemini-3.8-flash":{"draws":6,"losses":9,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":26},"gpt-4.1":{"draws":11,"losses":6,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":10,"losses":16,"wins":18},"gpt-5.4":{"draws":3,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":19},"gpt-5.4-nano":{"draws":12,"losses":25,"wins":19},"gpt-5.5":{"draws":25,"losses":12,"wins":17},"gpt-5.6-luna":{"draws":8,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":16,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":9},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":3,"losses":8,"wins":7},"gpt-6-sol":{"draws":4,"losses":13,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":20,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":14},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":17},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":20},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":5,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":14,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":10},"nex-agi/nex-n2-pro":{"draws":12,"losses":0,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":30},"o3":{"draws":2,"losses":17,"wins":27},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":22,"wins":12},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.7-plus":{"draws":20,"losses":2,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":4},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":6},"stealth/ox-alpha":{"draws":16,"losses":22,"wins":18},"stealth/space-bunny-alpha":{"draws":1,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":5,"wins":14},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":12},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":26,"wins":4},"x-ai/grok-4.6":{"draws":6,"losses":13,"wins":5},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":21},"xiaomi/mimo-v2.5":{"draws":44,"losses":16,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":28,"wins":37},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":10},"z-ai/glm-5.3-flashx":{"draws":9,"losses":4,"wins":9}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":18,"wins":25},"claude-fable-5":{"draws":21,"losses":51,"wins":2},"claude-fable-5-1":{"draws":9,"losses":42,"wins":1},"claude-opus-4-5":{"draws":45,"losses":48,"wins":31},"claude-opus-4-8":{"draws":9,"losses":11,"wins":10},"claude-opus-5":{"draws":10,"losses":58,"wins":6},"claude-opus-5-5":{"draws":0,"losses":13,"wins":5},"claude-sonnet-5":{"draws":43,"losses":32,"wins":41},"claude-sonnet-5-5":{"draws":4,"losses":15,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":27},"deepseek/deepseek-v4-pro":{"draws":22,"losses":20,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":18,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":8,"wins":5},"fireworks/ember-1":{"draws":7,"losses":9,"wins":4},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":28,"losses":27,"wins":19},"google/gemini-3.5-flash-lite":{"draws":86,"losses":54,"wins":114},"google/gemini-3.6-flash":{"draws":82,"losses":94,"wins":64},"google/gemini-3.8-flash":{"draws":30,"losses":37,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":14},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":14,"wins":5},"gpt-5.4":{"draws":37,"losses":69,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":9},"gpt-5.4-nano":{"draws":16,"losses":13,"wins":23},"gpt-5.5":{"draws":19,"losses":10,"wins":11},"gpt-5.6-luna":{"draws":44,"losses":29,"wins":39},"gpt-5.6-sol":{"draws":21,"losses":70,"wins":23},"gpt-5.6-terra":{"draws":27,"losses":15,"wins":26},"gpt-6-astra":{"draws":3,"losses":53,"wins":4},"gpt-6-luna":{"draws":11,"losses":11,"wins":8},"gpt-6-sol":{"draws":5,"losses":21,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":24,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":24,"losses":2,"wins":26},"inclusionai/ling-3.0-flash":{"draws":17,"losses":11,"wins":28},"meituan/longcat-2.0":{"draws":32,"losses":8,"wins":52},"meta/muse-glimmer-30b":{"draws":29,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":19,"losses":30,"wins":33},"meta/muse-spark-1.3":{"draws":13,"losses":32,"wins":15},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":9},"mistralai/mistral-medium-3-5":{"draws":18,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":31,"losses":32,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":7},"o3":{"draws":23,"losses":68,"wins":57},"openai/gpt-oss-120b":{"draws":20,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":38,"losses":4,"wins":46},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":27,"wins":18},"qwen/qwen3.8-27b":{"draws":16,"losses":10,"wins":14},"qwen/qwen3.8-flash":{"draws":21,"losses":5,"wins":22},"qwen/qwen3.8-max":{"draws":23,"losses":17,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":67,"losses":98,"wins":60},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":11},"stepfun/step-3.7-flash":{"draws":20,"losses":3,"wins":29},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":22,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":43,"losses":6,"wins":51},"thinkingmachines/inkling-small":{"draws":31,"losses":7,"wins":27},"x-ai/grok-4.5":{"draws":34,"losses":52,"wins":28},"x-ai/grok-4.6":{"draws":39,"losses":26,"wins":15},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":12},"xiaomi/mimo-v2.5":{"draws":22,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":1},"z-ai/glm-5.2":{"draws":33,"losses":23,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":41,"wins":14},"z-ai/glm-5.3-flash":{"draws":25,"losses":19,"wins":28},"z-ai/glm-5.3-flashx":{"draws":12,"losses":7,"wins":5}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":17,"wins":4},"claude-fable-5":{"draws":1,"losses":19,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":6,"losses":37,"wins":1},"claude-opus-4-8":{"draws":7,"losses":23,"wins":0},"claude-opus-5":{"draws":0,"losses":36,"wins":0},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":8,"losses":17,"wins":1},"claude-sonnet-5-5":{"draws":1,"losses":9,"wins":2},"cohere/north-mini-code":{"draws":13,"losses":13,"wins":8},"deepseek/deepseek-v4-flash":{"draws":1,"losses":26,"wins":23},"deepseek/deepseek-v4-pro":{"draws":0,"losses":14,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":19,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":11,"wins":1},"fireworks/ember-1":{"draws":0,"losses":13,"wins":1},"gemini-3.1-pro-preview":{"draws":3,"losses":9,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":21,"wins":25},"google/gemini-3.5-flash":{"draws":3,"losses":15,"wins":6},"google/gemini-3.5-flash-lite":{"draws":6,"losses":18,"wins":6},"google/gemini-3.6-flash":{"draws":1,"losses":38,"wins":3},"google/gemini-3.8-flash":{"draws":1,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":13,"wins":11},"gpt-4.1":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":2,"losses":30,"wins":6},"gpt-5.4":{"draws":4,"losses":14,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":4,"losses":32,"wins":16},"gpt-5.5":{"draws":2,"losses":43,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":15,"wins":3},"gpt-5.6-sol":{"draws":1,"losses":16,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":12,"wins":1},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":14,"wins":2},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":16,"wins":12},"meituan/longcat-2.0":{"draws":3,"losses":33,"wins":14},"meta/muse-glimmer-30b":{"draws":4,"losses":14,"wins":2},"meta/muse-spark-1.2":{"draws":1,"losses":9,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":16,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":21,"wins":10},"mistralai/mistral-medium-3-5":{"draws":1,"losses":5,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":14,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":20,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":28,"wins":12},"o3":{"draws":3,"losses":40,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":14,"losses":20,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":24,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":18,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":4,"losses":16,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":18,"wins":0},"qwen/qwen3.8-max-0902":{"draws":0,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":6,"losses":37,"wins":9},"stealth/space-bunny-alpha":{"draws":1,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":12,"wins":12},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":0,"losses":16,"wins":2},"thinkingmachines/inkling":{"draws":1,"losses":17,"wins":14},"thinkingmachines/inkling-small":{"draws":5,"losses":10,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":30,"wins":2},"x-ai/grok-4.6":{"draws":4,"losses":20,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":11,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":43,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":23,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":19,"losses":24,"wins":3},"z-ai/glm-5.3":{"draws":0,"losses":17,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":20,"wins":3},"z-ai/glm-5.3-flashx":{"draws":0,"losses":8,"wins":0}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":5},"claude-fable-5":{"draws":5,"losses":19,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":24,"losses":16,"wins":16},"claude-opus-4-8":{"draws":8,"losses":25,"wins":1},"claude-opus-5":{"draws":2,"losses":51,"wins":1},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":6,"losses":7,"wins":5},"claude-sonnet-5-5":{"draws":0,"losses":8,"wins":2},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":20,"losses":7,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":8,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":13,"wins":2},"fireworks/ember-1":{"draws":7,"losses":4,"wins":5},"gemini-3.1-pro-preview":{"draws":6,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":3},"google/gemini-3.5-flash-lite":{"draws":20,"losses":14,"wins":8},"google/gemini-3.6-flash":{"draws":15,"losses":17,"wins":4},"google/gemini-3.8-flash":{"draws":7,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":11,"wins":2},"gpt-4.1":{"draws":4,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":15,"losses":17,"wins":12},"gpt-5.4":{"draws":4,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":22,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":22,"losses":15,"wins":21},"gpt-5.5":{"draws":16,"losses":24,"wins":6},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":8},"gpt-6-astra":{"draws":1,"losses":9,"wins":0},"gpt-6-luna":{"draws":7,"losses":7,"wins":8},"gpt-6-sol":{"draws":2,"losses":12,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":15,"losses":12,"wins":7},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":15},"meta/muse-glimmer-30b":{"draws":8,"losses":4,"wins":2},"meta/muse-spark-1.2":{"draws":4,"losses":8,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":10,"wins":5},"minimax/minimax-m3":{"draws":14,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":6,"wins":8},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":6,"wins":12},"o3":{"draws":12,"losses":22,"wins":4},"openai/gpt-oss-120b":{"draws":7,"losses":9,"wins":2},"poolside/laguna-s-2.1":{"draws":23,"losses":9,"wins":4},"qwen/qwen3.7-max":{"draws":14,"losses":13,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":8,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":8,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":5,"wins":2},"qwen/qwen3.8-flash":{"draws":8,"losses":5,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-max-0902":{"draws":4,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":17,"losses":19,"wins":10},"stealth/space-bunny-alpha":{"draws":6,"losses":4,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":8},"tencent/hy3-preview":{"draws":16,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":8,"wins":6},"thinkingmachines/inkling-small":{"draws":9,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":11,"losses":21,"wins":6},"x-ai/grok-4.6":{"draws":6,"losses":12,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":18,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":32,"losses":25,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":14,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":32,"losses":12,"wins":12},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":7,"wins":7},"z-ai/glm-5.3-flashx":{"draws":5,"losses":6,"wins":3}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":8},"claude-fable-5":{"draws":6,"losses":21,"wins":3},"claude-fable-5-1":{"draws":0,"losses":7,"wins":1},"claude-opus-4-5":{"draws":24,"losses":38,"wins":22},"claude-opus-4-8":{"draws":11,"losses":24,"wins":15},"claude-opus-5":{"draws":5,"losses":55,"wins":8},"claude-opus-5-5":{"draws":1,"losses":23,"wins":2},"claude-sonnet-5":{"draws":7,"losses":9,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":9,"wins":5},"cohere/north-mini-code":{"draws":14,"losses":4,"wins":20},"deepseek/deepseek-v4-flash":{"draws":14,"losses":12,"wins":22},"deepseek/deepseek-v4-pro":{"draws":12,"losses":13,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":5,"wins":4},"fireworks/ember-1":{"draws":5,"losses":6,"wins":5},"gemini-3.1-pro-preview":{"draws":3,"losses":6,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":9,"losses":16,"wins":15},"google/gemini-3.5-flash-lite":{"draws":14,"losses":4,"wins":40},"google/gemini-3.6-flash":{"draws":19,"losses":23,"wins":22},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":6},"google/gemma-4-31b-it":{"draws":8,"losses":0,"wins":24},"gpt-4.1":{"draws":8,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":15,"wins":12},"gpt-5.4":{"draws":5,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":9,"losses":16,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":24,"wins":34},"gpt-5.5":{"draws":18,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":2},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":5},"gpt-6-astra":{"draws":0,"losses":22,"wins":0},"gpt-6-luna":{"draws":4,"losses":11,"wins":9},"gpt-6-sol":{"draws":2,"losses":12,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"meituan/longcat-2.0":{"draws":18,"losses":15,"wins":31},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":1,"losses":19,"wins":8},"meta/muse-spark-1.3":{"draws":4,"losses":17,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":1,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":12,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":6,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":7,"wins":9},"o3":{"draws":6,"losses":8,"wins":16},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":7,"losses":4,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":6},"qwen/qwen3.8-max":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-max-0902":{"draws":4,"losses":13,"wins":7},"stealth/ox-alpha":{"draws":14,"losses":41,"wins":17},"stealth/space-bunny-alpha":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":13,"losses":5,"wins":12},"tencent/hy3-preview":{"draws":14,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":5,"losses":10,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":11,"wins":13},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":13},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":15},"x-ai/grok-4.6":{"draws":8,"losses":18,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":19},"xiaomi/mimo-v2.5":{"draws":30,"losses":5,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":6,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":12,"losses":36,"wins":30},"z-ai/glm-5.3":{"draws":2,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":9,"wins":13},"z-ai/glm-5.3-flashx":{"draws":1,"losses":15,"wins":4}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":18,"wins":18},"claude-fable-5":{"draws":16,"losses":38,"wins":2},"claude-fable-5-1":{"draws":5,"losses":38,"wins":1},"claude-opus-4-5":{"draws":20,"losses":43,"wins":5},"claude-opus-4-8":{"draws":10,"losses":13,"wins":1},"claude-opus-5":{"draws":9,"losses":47,"wins":0},"claude-opus-5-5":{"draws":3,"losses":21,"wins":0},"claude-sonnet-5":{"draws":27,"losses":29,"wins":8},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":34,"losses":20,"wins":16},"deepseek/deepseek-v4-pro":{"draws":19,"losses":32,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":6},"fireworks/ember-1":{"draws":9,"losses":15,"wins":2},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":22,"losses":33,"wins":9},"google/gemini-3.5-flash-lite":{"draws":43,"losses":48,"wins":35},"google/gemini-3.6-flash":{"draws":34,"losses":41,"wins":15},"google/gemini-3.8-flash":{"draws":10,"losses":31,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":6},"gpt-4.1":{"draws":4,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":7,"losses":12,"wins":1},"gpt-5.4":{"draws":27,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":11,"wins":10},"gpt-5.5":{"draws":9,"losses":13,"wins":2},"gpt-5.6-luna":{"draws":29,"losses":28,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":35,"wins":2},"gpt-5.6-terra":{"draws":30,"losses":35,"wins":3},"gpt-6-astra":{"draws":1,"losses":39,"wins":0},"gpt-6-luna":{"draws":11,"losses":16,"wins":7},"gpt-6-sol":{"draws":3,"losses":20,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":24,"losses":11,"wins":17},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":21,"wins":11},"meta/muse-glimmer-30b":{"draws":29,"losses":15,"wins":14},"meta/muse-spark-1.2":{"draws":14,"losses":21,"wins":5},"meta/muse-spark-1.3":{"draws":17,"losses":26,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":20,"losses":10,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":34,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":5},"o3":{"draws":10,"losses":43,"wins":13},"openai/gpt-oss-120b":{"draws":20,"losses":13,"wins":5},"poolside/laguna-s-2.1":{"draws":16,"losses":17,"wins":7},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":32,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":17,"wins":10},"qwen/qwen3.8-flash":{"draws":17,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":31,"losses":30,"wins":3},"qwen/qwen3.8-max-0902":{"draws":10,"losses":13,"wins":1},"stealth/ox-alpha":{"draws":58,"losses":112,"wins":18},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":6,"losses":12,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":3},"tencent/hy4-preview":{"draws":25,"losses":25,"wins":10},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":17},"thinkingmachines/inkling-small":{"draws":27,"losses":19,"wins":18},"x-ai/grok-4.5":{"draws":22,"losses":33,"wins":3},"x-ai/grok-4.6":{"draws":22,"losses":33,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":23,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":16,"losses":16,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":31,"losses":33,"wins":16},"z-ai/glm-5.3":{"draws":12,"losses":32,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":43,"wins":8},"z-ai/glm-5.3-flashx":{"draws":7,"losses":9,"wins":6}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":28,"wins":20},"claude-fable-5":{"draws":22,"losses":47,"wins":7},"claude-fable-5-1":{"draws":6,"losses":60,"wins":0},"claude-opus-4-5":{"draws":73,"losses":87,"wins":8},"claude-opus-4-8":{"draws":23,"losses":24,"wins":3},"claude-opus-5":{"draws":12,"losses":88,"wins":8},"claude-opus-5-5":{"draws":0,"losses":36,"wins":0},"claude-sonnet-5":{"draws":56,"losses":81,"wins":11},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":6},"cohere/north-mini-code":{"draws":16,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":59,"losses":30,"wins":19},"deepseek/deepseek-v4-pro":{"draws":40,"losses":29,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":47,"losses":26,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":8,"wins":3},"fireworks/ember-1":{"draws":9,"losses":7,"wins":4},"gemini-3.1-pro-preview":{"draws":19,"losses":12,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":43,"losses":42,"wins":15},"google/gemini-3.5-flash-lite":{"draws":185,"losses":97,"wins":102},"google/gemini-3.6-flash":{"draws":150,"losses":136,"wins":30},"google/gemini-3.8-flash":{"draws":25,"losses":50,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":14,"wins":4},"gpt-4.1":{"draws":11,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":4},"gpt-5":{"draws":25,"losses":12,"wins":9},"gpt-5.4":{"draws":58,"losses":61,"wins":9},"gpt-5.4-mini":{"draws":25,"losses":20,"wins":7},"gpt-5.4-nano":{"draws":24,"losses":15,"wins":19},"gpt-5.5":{"draws":17,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":62,"losses":50,"wins":36},"gpt-5.6-sol":{"draws":30,"losses":119,"wins":1},"gpt-5.6-terra":{"draws":39,"losses":36,"wins":5},"gpt-6-astra":{"draws":12,"losses":56,"wins":0},"gpt-6-luna":{"draws":20,"losses":21,"wins":11},"gpt-6-sol":{"draws":8,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":35,"losses":13,"wins":18},"inclusionai/ling-3.0-flash":{"draws":51,"losses":9,"wins":22},"meituan/longcat-2.0":{"draws":62,"losses":55,"wins":43},"meta/muse-glimmer-30b":{"draws":52,"losses":16,"wins":24},"meta/muse-spark-1.2":{"draws":32,"losses":61,"wins":11},"meta/muse-spark-1.3":{"draws":31,"losses":37,"wins":6},"minimax/minimax-m3":{"draws":22,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":30,"losses":11,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":75,"losses":95,"wins":2},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":5},"o3":{"draws":53,"losses":73,"wins":52},"openai/gpt-oss-120b":{"draws":47,"losses":18,"wins":15},"poolside/laguna-s-2.1":{"draws":55,"losses":31,"wins":24},"qwen/qwen3.7-max":{"draws":17,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":19,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":36,"wins":7},"qwen/qwen3.8-27b":{"draws":12,"losses":26,"wins":10},"qwen/qwen3.8-flash":{"draws":33,"losses":24,"wins":9},"qwen/qwen3.8-max":{"draws":36,"losses":26,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":96,"losses":130,"wins":32},"stealth/space-bunny-alpha":{"draws":12,"losses":9,"wins":5},"stepfun/step-3.7-flash":{"draws":26,"losses":21,"wins":9},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":7},"tencent/hy4-preview":{"draws":34,"losses":30,"wins":12},"thinkingmachines/inkling":{"draws":68,"losses":42,"wins":54},"thinkingmachines/inkling-small":{"draws":57,"losses":17,"wins":39},"x-ai/grok-4.5":{"draws":60,"losses":81,"wins":19},"x-ai/grok-4.6":{"draws":28,"losses":54,"wins":6},"x-ai/grok-4.7":{"draws":6,"losses":24,"wins":4},"x-ai/grok-build-0.1":{"draws":18,"losses":11,"wins":5},"xiaomi/mimo-v2.5":{"draws":36,"losses":19,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":11,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":9,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":1},"z-ai/glm-5.2":{"draws":83,"losses":39,"wins":22},"z-ai/glm-5.3":{"draws":24,"losses":42,"wins":4},"z-ai/glm-5.3-flash":{"draws":44,"losses":44,"wins":12},"z-ai/glm-5.3-flashx":{"draws":14,"losses":14,"wins":4}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":6,"wins":17},"claude-fable-5":{"draws":5,"losses":15,"wins":4},"claude-fable-5-1":{"draws":1,"losses":23,"wins":0},"claude-opus-4-5":{"draws":42,"losses":42,"wins":26},"claude-opus-4-8":{"draws":24,"losses":26,"wins":16},"claude-opus-5":{"draws":6,"losses":64,"wins":18},"claude-opus-5-5":{"draws":1,"losses":15,"wins":0},"claude-sonnet-5":{"draws":9,"losses":16,"wins":9},"claude-sonnet-5-5":{"draws":0,"losses":12,"wins":4},"cohere/north-mini-code":{"draws":14,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":26,"losses":10,"wins":10},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":10,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":0,"wins":5},"fireworks/ember-1":{"draws":5,"losses":9,"wins":8},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":6},"google/gemini-3.1-flash-lite":{"draws":23,"losses":5,"wins":14},"google/gemini-3.5-flash":{"draws":17,"losses":14,"wins":11},"google/gemini-3.5-flash-lite":{"draws":21,"losses":20,"wins":17},"google/gemini-3.6-flash":{"draws":11,"losses":30,"wins":13},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":18},"gpt-4.1":{"draws":14,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":24,"losses":22,"wins":14},"gpt-5.4":{"draws":2,"losses":17,"wins":7},"gpt-5.4-mini":{"draws":15,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":19,"losses":22,"wins":31},"gpt-5.5":{"draws":25,"losses":28,"wins":13},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":19,"wins":7},"gpt-6-astra":{"draws":3,"losses":30,"wins":1},"gpt-6-luna":{"draws":9,"losses":11,"wins":6},"gpt-6-sol":{"draws":6,"losses":9,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":21,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":10},"inclusionai/ling-3.0-flash":{"draws":22,"losses":3,"wins":17},"meituan/longcat-2.0":{"draws":24,"losses":7,"wins":28},"meta/muse-glimmer-30b":{"draws":8,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":2,"losses":16,"wins":2},"meta/muse-spark-1.3":{"draws":10,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":14,"losses":10,"wins":18},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":8},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":10,"wins":14},"o3":{"draws":16,"losses":13,"wins":17},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":8},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":18},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":9,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":8,"wins":8},"qwen/qwen3.8-27b":{"draws":1,"losses":17,"wins":6},"qwen/qwen3.8-flash":{"draws":13,"losses":8,"wins":7},"qwen/qwen3.8-max":{"draws":12,"losses":9,"wins":11},"qwen/qwen3.8-max-0902":{"draws":5,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":20,"losses":33,"wins":19},"stealth/space-bunny-alpha":{"draws":5,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":17},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":14},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":8},"thinkingmachines/inkling":{"draws":24,"losses":8,"wins":28},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":12},"x-ai/grok-4.5":{"draws":19,"losses":25,"wins":12},"x-ai/grok-4.6":{"draws":4,"losses":16,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":16,"losses":8,"wins":10},"xiaomi/mimo-v2.5":{"draws":40,"losses":15,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":12,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":27,"losses":34,"wins":27},"z-ai/glm-5.3":{"draws":10,"losses":11,"wins":9},"z-ai/glm-5.3-flash":{"draws":13,"losses":8,"wins":9},"z-ai/glm-5.3-flashx":{"draws":8,"losses":6,"wins":2}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":8},"claude-fable-5":{"draws":7,"losses":20,"wins":1},"claude-fable-5-1":{"draws":0,"losses":22,"wins":0},"claude-opus-4-5":{"draws":20,"losses":28,"wins":26},"claude-opus-4-8":{"draws":10,"losses":30,"wins":12},"claude-opus-5":{"draws":14,"losses":51,"wins":1},"claude-opus-5-5":{"draws":1,"losses":17,"wins":0},"claude-sonnet-5":{"draws":8,"losses":10,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":14,"losses":9,"wins":21},"deepseek/deepseek-v4-flash":{"draws":16,"losses":20,"wins":20},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":7,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":8,"wins":2},"fireworks/ember-1":{"draws":7,"losses":5,"wins":0},"gemini-3.1-pro-preview":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":6,"wins":26},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":9},"google/gemini-3.5-flash-lite":{"draws":24,"losses":11,"wins":25},"google/gemini-3.6-flash":{"draws":18,"losses":34,"wins":16},"google/gemini-3.8-flash":{"draws":10,"losses":19,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":6,"wins":16},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":18,"losses":15,"wins":13},"gpt-5.4":{"draws":6,"losses":19,"wins":5},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":20},"gpt-5.4-nano":{"draws":14,"losses":21,"wins":39},"gpt-5.5":{"draws":27,"losses":15,"wins":8},"gpt-5.6-luna":{"draws":2,"losses":8,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":7,"wins":7},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":3,"losses":12,"wins":5},"gpt-6-sol":{"draws":0,"losses":10,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":15},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":17},"meituan/longcat-2.0":{"draws":14,"losses":14,"wins":22},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":8},"meta/muse-spark-1.2":{"draws":4,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":8},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":19},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":10},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":14,"wins":16},"o3":{"draws":8,"losses":26,"wins":26},"openai/gpt-oss-120b":{"draws":10,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":30,"losses":14,"wins":8},"qwen/qwen3.7-max":{"draws":16,"losses":14,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":14,"wins":8},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":8},"qwen/qwen3.8-flash":{"draws":8,"losses":5,"wins":9},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":4},"stealth/ox-alpha":{"draws":17,"losses":44,"wins":13},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":12,"losses":6,"wins":18},"tencent/hy3-preview":{"draws":16,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":9,"losses":12,"wins":3},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":26},"thinkingmachines/inkling-small":{"draws":11,"losses":2,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":33,"wins":11},"x-ai/grok-4.6":{"draws":8,"losses":14,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":10,"losses":1,"wins":17},"xiaomi/mimo-v2.5":{"draws":34,"losses":7,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":12,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":34,"losses":34,"wins":20},"z-ai/glm-5.3":{"draws":4,"losses":17,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":12,"wins":3},"z-ai/glm-5.3-flashx":{"draws":2,"losses":5,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":19,"wins":19},"claude-fable-5":{"draws":23,"losses":47,"wins":8},"claude-fable-5-1":{"draws":11,"losses":52,"wins":1},"claude-opus-4-5":{"draws":41,"losses":25,"wins":8},"claude-opus-4-8":{"draws":14,"losses":12,"wins":6},"claude-opus-5":{"draws":10,"losses":49,"wins":7},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":30,"losses":24,"wins":12},"claude-sonnet-5-5":{"draws":7,"losses":17,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":35,"losses":21,"wins":18},"deepseek/deepseek-v4-pro":{"draws":21,"losses":25,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":29,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":9,"wins":4},"fireworks/ember-1":{"draws":11,"losses":9,"wins":2},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":8},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":19,"losses":36,"wins":21},"google/gemini-3.5-flash-lite":{"draws":44,"losses":26,"wins":44},"google/gemini-3.6-flash":{"draws":33,"losses":45,"wins":26},"google/gemini-3.8-flash":{"draws":17,"losses":32,"wins":11},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":13},"gpt-4.1":{"draws":5,"losses":2,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":9,"losses":10,"wins":5},"gpt-5.4":{"draws":24,"losses":29,"wins":13},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":16,"losses":11,"wins":13},"gpt-5.5":{"draws":12,"losses":13,"wins":7},"gpt-5.6-luna":{"draws":33,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":14,"losses":45,"wins":7},"gpt-5.6-terra":{"draws":38,"losses":14,"wins":20},"gpt-6-astra":{"draws":4,"losses":45,"wins":1},"gpt-6-luna":{"draws":10,"losses":14,"wins":6},"gpt-6-sol":{"draws":0,"losses":12,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":15,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":6},"inception/mercury-2.5-preview":{"draws":15,"losses":5,"wins":24},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":15,"losses":11,"wins":26},"meta/muse-glimmer-30b":{"draws":37,"losses":2,"wins":17},"meta/muse-spark-1.2":{"draws":16,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":19,"losses":37,"wins":8},"minimax/minimax-m3":{"draws":9,"losses":1,"wins":8},"mistralai/mistral-medium-3-5":{"draws":21,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":34,"wins":10},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":4},"o3":{"draws":15,"losses":31,"wins":30},"openai/gpt-oss-120b":{"draws":32,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":20,"losses":3,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":8},"qwen/qwen3.8-27b":{"draws":14,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":20,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":30,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":7,"losses":12,"wins":1},"stealth/ox-alpha":{"draws":69,"losses":98,"wins":44},"stealth/space-bunny-alpha":{"draws":11,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":9},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":23,"losses":27,"wins":20},"thinkingmachines/inkling":{"draws":30,"losses":8,"wins":22},"thinkingmachines/inkling-small":{"draws":26,"losses":8,"wins":30},"x-ai/grok-4.5":{"draws":22,"losses":32,"wins":12},"x-ai/grok-4.6":{"draws":21,"losses":34,"wins":15},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":24,"losses":13,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":44,"losses":26,"wins":18},"z-ai/glm-5.3":{"draws":14,"losses":43,"wins":7},"z-ai/glm-5.3-flash":{"draws":17,"losses":37,"wins":10},"z-ai/glm-5.3-flashx":{"draws":3,"losses":10,"wins":3}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":21,"wins":19},"claude-fable-5":{"draws":2,"losses":26,"wins":6},"claude-fable-5-1":{"draws":0,"losses":28,"wins":0},"claude-opus-4-5":{"draws":11,"losses":23,"wins":12},"claude-opus-4-8":{"draws":5,"losses":12,"wins":5},"claude-opus-5":{"draws":1,"losses":17,"wins":4},"claude-opus-5-5":{"draws":2,"losses":10,"wins":0},"claude-sonnet-5":{"draws":12,"losses":15,"wins":15},"claude-sonnet-5-5":{"draws":0,"losses":2,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":11,"losses":23,"wins":28},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":5},"fireworks/ember-1":{"draws":0,"losses":4,"wins":2},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":21,"wins":17},"google/gemini-3.5-flash-lite":{"draws":8,"losses":35,"wins":39},"google/gemini-3.6-flash":{"draws":14,"losses":55,"wins":13},"google/gemini-3.8-flash":{"draws":4,"losses":38,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":8,"wins":7},"gpt-5.4":{"draws":2,"losses":29,"wins":9},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":12},"gpt-5.5":{"draws":2,"losses":11,"wins":9},"gpt-5.6-luna":{"draws":6,"losses":15,"wins":23},"gpt-5.6-sol":{"draws":2,"losses":27,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":18,"wins":11},"gpt-6-astra":{"draws":0,"losses":32,"wins":2},"gpt-6-luna":{"draws":0,"losses":12,"wins":4},"gpt-6-sol":{"draws":0,"losses":7,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":13},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":26},"meta/muse-spark-1.2":{"draws":7,"losses":19,"wins":10},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":8},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"mistralai/mistral-medium-3-5":{"draws":1,"losses":6,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":12,"wins":14},"nex-agi/nex-n2-pro":{"draws":1,"losses":7,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":0},"o3":{"draws":12,"losses":22,"wins":28},"openai/gpt-oss-120b":{"draws":3,"losses":17,"wins":20},"poolside/laguna-s-2.1":{"draws":2,"losses":17,"wins":15},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":14},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":17,"wins":17},"qwen/qwen3.8-27b":{"draws":0,"losses":5,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":6,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":3,"losses":6,"wins":1},"stealth/ox-alpha":{"draws":28,"losses":88,"wins":39},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":13},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":30,"wins":2},"thinkingmachines/inkling":{"draws":11,"losses":7,"wins":24},"thinkingmachines/inkling-small":{"draws":10,"losses":12,"wins":28},"x-ai/grok-4.5":{"draws":6,"losses":15,"wins":21},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":7},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":0,"losses":8,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":27,"wins":28},"z-ai/glm-5.3":{"draws":3,"losses":23,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":8},"z-ai/glm-5.3-flashx":{"draws":0,"losses":9,"wins":2}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":5,"wins":31},"claude-fable-5":{"draws":22,"losses":26,"wins":20},"claude-fable-5-1":{"draws":3,"losses":73,"wins":4},"claude-opus-4-5":{"draws":28,"losses":13,"wins":39},"claude-opus-4-8":{"draws":12,"losses":4,"wins":10},"claude-opus-5":{"draws":11,"losses":47,"wins":8},"claude-opus-5-5":{"draws":4,"losses":21,"wins":1},"claude-sonnet-5":{"draws":20,"losses":12,"wins":26},"claude-sonnet-5-5":{"draws":3,"losses":4,"wins":13},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":31,"losses":7,"wins":36},"deepseek/deepseek-v4-pro":{"draws":17,"losses":10,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":6,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":6,"wins":8},"fireworks/ember-1":{"draws":5,"losses":3,"wins":8},"gemini-3.1-pro-preview":{"draws":2,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":28,"losses":21,"wins":33},"google/gemini-3.5-flash-lite":{"draws":37,"losses":8,"wins":51},"google/gemini-3.6-flash":{"draws":40,"losses":31,"wins":43},"google/gemini-3.8-flash":{"draws":20,"losses":18,"wins":28},"google/gemma-4-31b-it":{"draws":10,"losses":0,"wins":6},"gpt-4.1":{"draws":4,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":13,"losses":7,"wins":16},"gpt-5.4":{"draws":14,"losses":24,"wins":20},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":4,"wins":14},"gpt-5.5":{"draws":9,"losses":16,"wins":9},"gpt-5.6-luna":{"draws":22,"losses":10,"wins":34},"gpt-5.6-sol":{"draws":21,"losses":36,"wins":21},"gpt-5.6-terra":{"draws":29,"losses":9,"wins":26},"gpt-6-astra":{"draws":11,"losses":52,"wins":3},"gpt-6-luna":{"draws":7,"losses":8,"wins":15},"gpt-6-sol":{"draws":7,"losses":9,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":0,"wins":18},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":18},"meituan/longcat-2.0":{"draws":15,"losses":5,"wins":20},"meta/muse-glimmer-30b":{"draws":21,"losses":14,"wins":17},"meta/muse-spark-1.2":{"draws":16,"losses":11,"wins":25},"meta/muse-spark-1.3":{"draws":27,"losses":19,"wins":24},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":23,"losses":9,"wins":22},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":2,"wins":12},"o3":{"draws":17,"losses":19,"wins":40},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":15},"poolside/laguna-s-2.1":{"draws":27,"losses":0,"wins":19},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":21,"wins":36},"qwen/qwen3.8-27b":{"draws":12,"losses":7,"wins":19},"qwen/qwen3.8-flash":{"draws":11,"losses":0,"wins":5},"qwen/qwen3.8-max":{"draws":22,"losses":11,"wins":27},"qwen/qwen3.8-max-0902":{"draws":8,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":63,"losses":54,"wins":98},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":1,"wins":12},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":11},"tencent/hy4-preview":{"draws":21,"losses":13,"wins":34},"thinkingmachines/inkling":{"draws":15,"losses":5,"wins":30},"thinkingmachines/inkling-small":{"draws":30,"losses":4,"wins":22},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":18},"x-ai/grok-4.6":{"draws":30,"losses":27,"wins":19},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":20,"losses":1,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":31,"losses":8,"wins":49},"z-ai/glm-5.3":{"draws":15,"losses":40,"wins":13},"z-ai/glm-5.3-flash":{"draws":16,"losses":22,"wins":40},"z-ai/glm-5.3-flashx":{"draws":8,"losses":8,"wins":10}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":14,"wins":29},"claude-fable-5":{"draws":6,"losses":44,"wins":16},"claude-fable-5-1":{"draws":4,"losses":58,"wins":0},"claude-opus-4-5":{"draws":24,"losses":16,"wins":43},"claude-opus-4-8":{"draws":11,"losses":12,"wins":11},"claude-opus-5":{"draws":10,"losses":39,"wins":5},"claude-opus-5-5":{"draws":4,"losses":24,"wins":0},"claude-sonnet-5":{"draws":18,"losses":15,"wins":27},"claude-sonnet-5-5":{"draws":3,"losses":16,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":10,"wins":43},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":7,"wins":6},"fireworks/ember-1":{"draws":8,"losses":10,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":10,"wins":12},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":18,"losses":32,"wins":14},"google/gemini-3.5-flash-lite":{"draws":34,"losses":26,"wins":42},"google/gemini-3.6-flash":{"draws":35,"losses":45,"wins":39},"google/gemini-3.8-flash":{"draws":18,"losses":22,"wins":20},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":7},"gpt-4.1":{"draws":7,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":10,"losses":3,"wins":7},"gpt-5.4":{"draws":16,"losses":23,"wins":15},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":18},"gpt-5.5":{"draws":7,"losses":10,"wins":7},"gpt-5.6-luna":{"draws":24,"losses":14,"wins":24},"gpt-5.6-sol":{"draws":12,"losses":38,"wins":18},"gpt-5.6-terra":{"draws":28,"losses":20,"wins":20},"gpt-6-astra":{"draws":12,"losses":52,"wins":2},"gpt-6-luna":{"draws":8,"losses":10,"wins":10},"gpt-6-sol":{"draws":4,"losses":10,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":17,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":19,"losses":6,"wins":15},"inclusionai/ling-3.0-flash":{"draws":16,"losses":6,"wins":12},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":20},"meta/muse-glimmer-30b":{"draws":17,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":12,"losses":11,"wins":17},"meta/muse-spark-1.3":{"draws":19,"losses":35,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":12},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":20,"losses":21,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":13},"o3":{"draws":10,"losses":22,"wins":45},"openai/gpt-oss-120b":{"draws":18,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":14},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":20,"wins":28},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":19,"wins":8},"qwen/qwen3.8-max":{"draws":22,"losses":15,"wins":28},"qwen/qwen3.8-max-0902":{"draws":5,"losses":5,"wins":4},"stealth/ox-alpha":{"draws":54,"losses":71,"wins":67},"stealth/space-bunny-alpha":{"draws":2,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":9},"tencent/hy4-preview":{"draws":18,"losses":33,"wins":21},"thinkingmachines/inkling":{"draws":11,"losses":15,"wins":28},"thinkingmachines/inkling-small":{"draws":37,"losses":33,"wins":45},"x-ai/grok-4.5":{"draws":14,"losses":33,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":37,"wins":17},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":7,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":6,"wins":3},"z-ai/glm-5.2":{"draws":23,"losses":21,"wins":32},"z-ai/glm-5.3":{"draws":18,"losses":25,"wins":11},"z-ai/glm-5.3-flash":{"draws":21,"losses":28,"wins":19},"z-ai/glm-5.3-flashx":{"draws":8,"losses":8,"wins":4}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":15},"claude-fable-5":{"draws":5,"losses":24,"wins":3},"claude-fable-5-1":{"draws":0,"losses":27,"wins":1},"claude-opus-4-5":{"draws":10,"losses":7,"wins":5},"claude-opus-4-8":{"draws":9,"losses":8,"wins":7},"claude-opus-5":{"draws":9,"losses":27,"wins":4},"claude-opus-5-5":{"draws":6,"losses":45,"wins":1},"claude-sonnet-5":{"draws":5,"losses":3,"wins":6},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":10,"wins":15},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":1,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":10},"fireworks/ember-1":{"draws":13,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":17},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":4},"google/gemini-3.5-flash-lite":{"draws":21,"losses":5,"wins":16},"google/gemini-3.6-flash":{"draws":9,"losses":13,"wins":6},"google/gemini-3.8-flash":{"draws":5,"losses":12,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":3},"gpt-4.1":{"draws":2,"losses":4,"wins":4},"gpt-5":{"draws":5,"losses":5,"wins":6},"gpt-5.4":{"draws":7,"losses":10,"wins":5},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":5,"wins":5},"gpt-5.5":{"draws":11,"losses":13,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":2,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":9},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":12,"losses":22,"wins":12},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":34,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":10},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":18},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":6},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":12},"o3":{"draws":4,"losses":9,"wins":11},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":5,"losses":8,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.8-max-0902":{"draws":6,"losses":17,"wins":7},"stealth/ox-alpha":{"draws":18,"losses":30,"wins":22},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":12},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":3,"wins":11},"thinkingmachines/inkling-small":{"draws":10,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":10,"wins":8},"x-ai/grok-4.6":{"draws":7,"losses":18,"wins":3},"x-ai/grok-4.7":{"draws":8,"losses":24,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":14,"losses":7,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":8,"losses":10,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":10,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":16,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":49,"wins":89},"claude-fable-5":{"draws":58,"losses":127,"wins":43},"claude-fable-5-1":{"draws":19,"losses":207,"wins":6},"claude-opus-4-5":{"draws":80,"losses":72,"wins":84},"claude-opus-4-8":{"draws":27,"losses":31,"wins":38},"claude-opus-5":{"draws":25,"losses":132,"wins":31},"claude-opus-5-5":{"draws":8,"losses":52,"wins":4},"claude-sonnet-5":{"draws":57,"losses":63,"wins":102},"claude-sonnet-5-5":{"draws":14,"losses":37,"wins":21},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":26},"deepseek/deepseek-v4-flash":{"draws":68,"losses":56,"wins":108},"deepseek/deepseek-v4-pro":{"draws":48,"losses":65,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":50,"losses":71,"wins":71},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":21,"wins":17},"fireworks/ember-1":{"draws":25,"losses":30,"wins":31},"gemini-3.1-pro-preview":{"draws":17,"losses":21,"wins":34},"google/gemini-3.1-flash-lite":{"draws":8,"losses":8,"wins":32},"google/gemini-3.5-flash":{"draws":61,"losses":68,"wins":93},"google/gemini-3.5-flash-lite":{"draws":88,"losses":74,"wins":194},"google/gemini-3.6-flash":{"draws":86,"losses":132,"wins":104},"google/gemini-3.8-flash":{"draws":46,"losses":107,"wins":59},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":25},"gpt-4.1":{"draws":12,"losses":3,"wins":17},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":22,"losses":29,"wins":47},"gpt-5.4":{"draws":55,"losses":73,"wins":60},"gpt-5.4-mini":{"draws":24,"losses":9,"wins":31},"gpt-5.4-nano":{"draws":17,"losses":22,"wins":47},"gpt-5.5":{"draws":20,"losses":31,"wins":31},"gpt-5.6-luna":{"draws":57,"losses":43,"wins":78},"gpt-5.6-sol":{"draws":35,"losses":147,"wins":40},"gpt-5.6-terra":{"draws":73,"losses":57,"wins":94},"gpt-6-astra":{"draws":25,"losses":173,"wins":10},"gpt-6-luna":{"draws":21,"losses":33,"wins":28},"gpt-6-sol":{"draws":7,"losses":43,"wins":2},"gpt-6.1-sol":{"draws":11,"losses":65,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":15,"losses":2,"wins":15},"inception/mercury-2.5-preview":{"draws":44,"losses":21,"wins":67},"inclusionai/ling-3.0-flash":{"draws":13,"losses":11,"wins":44},"meituan/longcat-2.0":{"draws":27,"losses":21,"wins":88},"meta/muse-glimmer-30b":{"draws":40,"losses":29,"wins":93},"meta/muse-spark-1.2":{"draws":32,"losses":59,"wins":73},"meta/muse-spark-1.3":{"draws":46,"losses":80,"wins":68},"minimax/minimax-m3":{"draws":16,"losses":8,"wins":28},"mistralai/mistral-medium-3-5":{"draws":23,"losses":25,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":6,"wins":9},"moonshotai/kimi-k3":{"draws":54,"losses":87,"wins":71},"nex-agi/nex-n2-pro":{"draws":16,"losses":8,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":7,"wins":45},"o3":{"draws":16,"losses":83,"wins":93},"openai/gpt-oss-120b":{"draws":41,"losses":29,"wins":88},"poolside/laguna-s-2.1":{"draws":42,"losses":26,"wins":78},"qwen/qwen3.7-max":{"draws":14,"losses":11,"wins":27},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":62,"losses":74,"wins":68},"qwen/qwen3.8-27b":{"draws":23,"losses":53,"wins":44},"qwen/qwen3.8-flash":{"draws":33,"losses":51,"wins":54},"qwen/qwen3.8-max":{"draws":66,"losses":56,"wins":62},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":12},"stealth/ox-alpha":{"draws":159,"losses":355,"wins":264},"stealth/space-bunny-alpha":{"draws":16,"losses":12,"wins":32},"stepfun/step-3.7-flash":{"draws":9,"losses":21,"wins":34},"tencent/hy3-preview":{"draws":23,"losses":6,"wins":23},"tencent/hy4-preview":{"draws":45,"losses":96,"wins":57},"thinkingmachines/inkling":{"draws":31,"losses":36,"wins":101},"thinkingmachines/inkling-small":{"draws":67,"losses":49,"wins":94},"x-ai/grok-4.5":{"draws":38,"losses":81,"wins":59},"x-ai/grok-4.6":{"draws":56,"losses":105,"wins":73},"x-ai/grok-4.7":{"draws":6,"losses":58,"wins":8},"x-ai/grok-build-0.1":{"draws":12,"losses":3,"wins":27},"xiaomi/mimo-v2.5":{"draws":41,"losses":22,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":21,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":13,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":78,"losses":69,"wins":127},"z-ai/glm-5.3":{"draws":45,"losses":113,"wins":42},"z-ai/glm-5.3-flash":{"draws":53,"losses":110,"wins":77},"z-ai/glm-5.3-flashx":{"draws":6,"losses":31,"wins":17}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":5,"wins":8},"claude-fable-5":{"draws":7,"losses":12,"wins":3},"claude-fable-5-1":{"draws":2,"losses":22,"wins":0},"claude-opus-4-5":{"draws":12,"losses":5,"wins":9},"claude-opus-4-8":{"draws":5,"losses":15,"wins":0},"claude-opus-5":{"draws":3,"losses":37,"wins":4},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":2,"losses":12,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":8},"deepseek/deepseek-v4-pro":{"draws":2,"losses":12,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":6,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":19,"wins":10},"fireworks/ember-1":{"draws":14,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":7},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.6-flash":{"draws":11,"losses":20,"wins":11},"google/gemini-3.8-flash":{"draws":4,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":7,"wins":5},"gpt-5.4":{"draws":8,"losses":7,"wins":5},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":3},"gpt-5.5":{"draws":6,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":2},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":10,"losses":9,"wins":5},"gpt-6-sol":{"draws":6,"losses":29,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":14},"meta/muse-glimmer-30b":{"draws":3,"losses":6,"wins":5},"meta/muse-spark-1.2":{"draws":8,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":12,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":6},"o3":{"draws":2,"losses":5,"wins":15},"openai/gpt-oss-120b":{"draws":5,"losses":9,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":9},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":11,"wins":4},"qwen/qwen3.8-27b":{"draws":1,"losses":5,"wins":0},"qwen/qwen3.8-flash":{"draws":5,"losses":5,"wins":2},"qwen/qwen3.8-max":{"draws":5,"losses":10,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":18,"losses":38,"wins":14},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":2},"tencent/hy4-preview":{"draws":0,"losses":16,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":6,"wins":11},"thinkingmachines/inkling-small":{"draws":3,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.6":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":11,"wins":8},"z-ai/glm-5.2":{"draws":21,"losses":13,"wins":12},"z-ai/glm-5.3":{"draws":6,"losses":16,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":8,"wins":2},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":4},"claude-fable-5":{"draws":6,"losses":15,"wins":1},"claude-fable-5-1":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":35,"losses":20,"wins":3},"claude-opus-4-8":{"draws":19,"losses":11,"wins":10},"claude-opus-5":{"draws":14,"losses":44,"wins":2},"claude-opus-5-5":{"draws":2,"losses":14,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":2,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":20,"losses":6,"wins":6},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":4},"fireworks/ember-1":{"draws":0,"losses":4,"wins":0},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":5,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":3},"google/gemini-3.5-flash-lite":{"draws":17,"losses":4,"wins":21},"google/gemini-3.6-flash":{"draws":15,"losses":19,"wins":2},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":17},"gpt-4.1":{"draws":8,"losses":4,"wins":2},"gpt-5":{"draws":16,"losses":7,"wins":3},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":5},"gpt-5.4-nano":{"draws":20,"losses":20,"wins":2},"gpt-5.5":{"draws":10,"losses":12,"wins":6},"gpt-5.6-luna":{"draws":10,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":10,"wins":3},"gpt-6-astra":{"draws":2,"losses":14,"wins":0},"gpt-6-luna":{"draws":7,"losses":11,"wins":0},"gpt-6-sol":{"draws":4,"losses":12,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":16},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":2},"meta/muse-spark-1.3":{"draws":8,"losses":11,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":7},"o3":{"draws":7,"losses":15,"wins":8},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":12,"losses":5,"wins":7},"qwen/qwen3.7-plus":{"draws":14,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.8-max":{"draws":10,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":19,"losses":32,"wins":5},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":10,"wins":1},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":7},"thinkingmachines/inkling-small":{"draws":11,"losses":1,"wins":2},"x-ai/grok-4.5":{"draws":16,"losses":13,"wins":3},"x-ai/grok-4.6":{"draws":8,"losses":11,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":2},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":0},"xiaomi/mimo-v2.5":{"draws":48,"losses":13,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":3,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":19,"wins":5},"z-ai/glm-5.3":{"draws":9,"losses":12,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":7,"wins":1}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":36},"claude-fable-5":{"draws":4,"losses":40,"wins":22},"claude-fable-5-1":{"draws":0,"losses":64,"wins":6},"claude-opus-4-5":{"draws":15,"losses":11,"wins":46},"claude-opus-4-8":{"draws":5,"losses":10,"wins":9},"claude-opus-5":{"draws":0,"losses":34,"wins":6},"claude-opus-5-5":{"draws":3,"losses":28,"wins":7},"claude-sonnet-5":{"draws":13,"losses":16,"wins":35},"claude-sonnet-5-5":{"draws":3,"losses":11,"wins":8},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":47},"deepseek/deepseek-v4-pro":{"draws":14,"losses":18,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":30,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":10,"wins":14},"fireworks/ember-1":{"draws":5,"losses":5,"wins":12},"gemini-3.1-pro-preview":{"draws":2,"losses":3,"wins":15},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":20},"google/gemini-3.5-flash":{"draws":4,"losses":20,"wins":32},"google/gemini-3.5-flash-lite":{"draws":16,"losses":28,"wins":62},"google/gemini-3.6-flash":{"draws":15,"losses":55,"wins":52},"google/gemini-3.8-flash":{"draws":8,"losses":17,"wins":21},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":3,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":9,"wins":10},"gpt-5.4":{"draws":8,"losses":23,"wins":27},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":11},"gpt-5.5":{"draws":6,"losses":8,"wins":12},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":34},"gpt-5.6-sol":{"draws":9,"losses":22,"wins":27},"gpt-5.6-terra":{"draws":17,"losses":16,"wins":33},"gpt-6-astra":{"draws":5,"losses":51,"wins":4},"gpt-6-luna":{"draws":5,"losses":7,"wins":20},"gpt-6-sol":{"draws":1,"losses":20,"wins":9},"gpt-6.1-sol":{"draws":1,"losses":15,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":26},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":14},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":32},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":38},"meta/muse-spark-1.2":{"draws":8,"losses":5,"wins":23},"meta/muse-spark-1.3":{"draws":8,"losses":19,"wins":27},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":26,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":20},"o3":{"draws":6,"losses":11,"wins":59},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":27},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":20},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":14},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":16,"wins":22},"qwen/qwen3.8-27b":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":26,"wins":28},"qwen/qwen3.8-max-0902":{"draws":0,"losses":17,"wins":13},"stealth/ox-alpha":{"draws":50,"losses":67,"wins":82},"stealth/space-bunny-alpha":{"draws":2,"losses":4,"wins":8},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":12},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":4,"losses":10,"wins":14},"thinkingmachines/inkling":{"draws":19,"losses":4,"wins":37},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":36},"x-ai/grok-4.5":{"draws":12,"losses":17,"wins":27},"x-ai/grok-4.6":{"draws":14,"losses":31,"wins":19},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":7,"losses":4,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":8},"z-ai/glm-5.2":{"draws":19,"losses":22,"wins":41},"z-ai/glm-5.3":{"draws":6,"losses":36,"wins":10},"z-ai/glm-5.3-flash":{"draws":2,"losses":28,"wins":26},"z-ai/glm-5.3-flashx":{"draws":2,"losses":12,"wins":18}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":23,"wins":9},"claude-fable-5":{"draws":5,"losses":28,"wins":3},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-opus-4-5":{"draws":26,"losses":43,"wins":11},"claude-opus-4-8":{"draws":7,"losses":14,"wins":3},"claude-opus-5":{"draws":5,"losses":38,"wins":5},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":28,"losses":38,"wins":8},"claude-sonnet-5-5":{"draws":5,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":21,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":18,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":4,"wins":2},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":13,"losses":22,"wins":9},"google/gemini-3.5-flash-lite":{"draws":69,"losses":63,"wins":32},"google/gemini-3.6-flash":{"draws":73,"losses":67,"wins":24},"google/gemini-3.8-flash":{"draws":12,"losses":23,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":0},"gpt-5":{"draws":7,"losses":12,"wins":3},"gpt-5.4":{"draws":15,"losses":41,"wins":14},"gpt-5.4-mini":{"draws":4,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":16,"wins":11},"gpt-5.5":{"draws":11,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":22,"losses":35,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":53,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":7},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":9,"losses":10,"wins":5},"gpt-6-sol":{"draws":1,"losses":13,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":22,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":14,"wins":12},"meituan/longcat-2.0":{"draws":16,"losses":29,"wins":21},"meta/muse-glimmer-30b":{"draws":22,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":13,"losses":30,"wins":9},"meta/muse-spark-1.3":{"draws":11,"losses":15,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":39,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":11,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":7},"o3":{"draws":28,"losses":45,"wins":16},"openai/gpt-oss-120b":{"draws":18,"losses":14,"wins":4},"poolside/laguna-s-2.1":{"draws":24,"losses":19,"wins":13},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":12,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":12,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":23,"wins":5},"qwen/qwen3.8-max-0902":{"draws":10,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":24,"losses":86,"wins":25},"stealth/space-bunny-alpha":{"draws":6,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":6,"losses":13,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":18,"losses":17,"wins":3},"thinkingmachines/inkling":{"draws":15,"losses":18,"wins":17},"thinkingmachines/inkling-small":{"draws":19,"losses":11,"wins":12},"x-ai/grok-4.5":{"draws":20,"losses":34,"wins":10},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":16,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":8,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":22,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":25,"losses":15,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":22,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":2}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":15},"claude-fable-5":{"draws":19,"losses":32,"wins":7},"claude-fable-5-1":{"draws":3,"losses":47,"wins":0},"claude-opus-4-5":{"draws":19,"losses":52,"wins":8},"claude-opus-4-8":{"draws":5,"losses":21,"wins":2},"claude-opus-5":{"draws":6,"losses":38,"wins":4},"claude-opus-5-5":{"draws":2,"losses":18,"wins":0},"claude-sonnet-5":{"draws":17,"losses":34,"wins":9},"claude-sonnet-5-5":{"draws":8,"losses":15,"wins":1},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":41,"losses":32,"wins":15},"deepseek/deepseek-v4-pro":{"draws":20,"losses":38,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":33,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":7,"wins":0},"fireworks/ember-1":{"draws":14,"losses":13,"wins":1},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":22,"losses":32,"wins":18},"google/gemini-3.5-flash-lite":{"draws":53,"losses":56,"wins":22},"google/gemini-3.6-flash":{"draws":37,"losses":50,"wins":21},"google/gemini-3.8-flash":{"draws":21,"losses":27,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":5},"gpt-4.1":{"draws":3,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":13,"losses":14,"wins":7},"gpt-5.4":{"draws":28,"losses":23,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":3},"gpt-5.4-nano":{"draws":11,"losses":12,"wins":7},"gpt-5.5":{"draws":7,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":21,"losses":21,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":12},"gpt-5.6-terra":{"draws":22,"losses":30,"wins":16},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":6,"losses":13,"wins":5},"gpt-6-sol":{"draws":6,"losses":8,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":15,"wins":15},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":9},"meituan/longcat-2.0":{"draws":11,"losses":21,"wins":16},"meta/muse-glimmer-30b":{"draws":30,"losses":28,"wins":14},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":2},"mistralai/mistral-medium-3-5":{"draws":19,"losses":13,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":31,"wins":9},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":1},"o3":{"draws":21,"losses":38,"wins":21},"openai/gpt-oss-120b":{"draws":23,"losses":19,"wins":8},"poolside/laguna-s-2.1":{"draws":23,"losses":23,"wins":7},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":47,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":36,"wins":6},"qwen/qwen3.8-flash":{"draws":20,"losses":16,"wins":6},"qwen/qwen3.8-max":{"draws":39,"losses":55,"wins":19},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":69,"losses":103,"wins":34},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":7},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":1},"tencent/hy4-preview":{"draws":22,"losses":36,"wins":8},"thinkingmachines/inkling":{"draws":13,"losses":32,"wins":9},"thinkingmachines/inkling-small":{"draws":32,"losses":29,"wins":19},"x-ai/grok-4.5":{"draws":12,"losses":40,"wins":10},"x-ai/grok-4.6":{"draws":20,"losses":35,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":36,"losses":42,"wins":24},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":7},"z-ai/glm-5.3-flash":{"draws":18,"losses":39,"wins":13},"z-ai/glm-5.3-flashx":{"draws":6,"losses":5,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":16},"claude-fable-5":{"draws":4,"losses":17,"wins":13},"claude-fable-5-1":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":29,"losses":20,"wins":39},"claude-opus-4-8":{"draws":13,"losses":23,"wins":30},"claude-opus-5":{"draws":16,"losses":86,"wins":30},"claude-opus-5-5":{"draws":4,"losses":23,"wins":1},"claude-sonnet-5":{"draws":9,"losses":4,"wins":17},"claude-sonnet-5-5":{"draws":1,"losses":13,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":32},"deepseek/deepseek-v4-flash":{"draws":11,"losses":9,"wins":42},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":13,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":7},"fireworks/ember-1":{"draws":6,"losses":4,"wins":8},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":13},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":4,"losses":12,"wins":26},"google/gemini-3.5-flash-lite":{"draws":11,"losses":15,"wins":62},"google/gemini-3.6-flash":{"draws":23,"losses":37,"wins":42},"google/gemini-3.8-flash":{"draws":5,"losses":9,"wins":22},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":11},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":8,"wins":30},"gpt-5.4":{"draws":12,"losses":16,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":6,"losses":21,"wins":35},"gpt-5.5":{"draws":23,"losses":19,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":7,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":22,"wins":13},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":22},"gpt-6-astra":{"draws":3,"losses":25,"wins":2},"gpt-6-luna":{"draws":10,"losses":6,"wins":12},"gpt-6-sol":{"draws":6,"losses":13,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":41},"meituan/longcat-2.0":{"draws":7,"losses":14,"wins":51},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":12},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":15},"meta/muse-spark-1.3":{"draws":5,"losses":14,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":30},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":1,"wins":14},"moonshotai/kimi-k3":{"draws":17,"losses":17,"wins":16},"nex-agi/nex-n2-pro":{"draws":11,"losses":0,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":3,"wins":31},"o3":{"draws":5,"losses":15,"wins":32},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":10},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":44},"qwen/qwen3.7-max":{"draws":16,"losses":7,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":13,"wins":15},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":4,"wins":12},"qwen/qwen3.8-max":{"draws":5,"losses":10,"wins":11},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":6},"stealth/ox-alpha":{"draws":12,"losses":31,"wins":47},"stealth/space-bunny-alpha":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":10,"losses":5,"wins":23},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":6,"losses":6,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":6,"losses":6,"wins":16},"x-ai/grok-4.5":{"draws":11,"losses":11,"wins":12},"x-ai/grok-4.6":{"draws":12,"losses":12,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":12,"losses":0,"wins":22},"xiaomi/mimo-v2.5":{"draws":34,"losses":11,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":3},"z-ai/glm-5.2":{"draws":22,"losses":27,"wins":47},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":14,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":11,"wins":9}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":52},"claude-fable-5":{"draws":15,"losses":33,"wins":42},"claude-fable-5-1":{"draws":8,"losses":85,"wins":15},"claude-opus-4-5":{"draws":25,"losses":13,"wins":72},"claude-opus-4-8":{"draws":11,"losses":9,"wins":26},"claude-opus-5":{"draws":12,"losses":57,"wins":25},"claude-opus-5-5":{"draws":8,"losses":37,"wins":7},"claude-sonnet-5":{"draws":17,"losses":14,"wins":53},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":21},"deepseek/deepseek-v4-flash":{"draws":16,"losses":5,"wins":75},"deepseek/deepseek-v4-pro":{"draws":13,"losses":10,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":7,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":11,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":16,"losses":12,"wins":70},"google/gemini-3.5-flash-lite":{"draws":15,"losses":9,"wins":94},"google/gemini-3.6-flash":{"draws":23,"losses":29,"wins":80},"google/gemini-3.8-flash":{"draws":21,"losses":24,"wins":45},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":18},"gpt-4.1":{"draws":6,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":3,"wins":29},"gpt-5.4":{"draws":22,"losses":22,"wins":40},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":23},"gpt-5.4-nano":{"draws":5,"losses":0,"wins":43},"gpt-5.5":{"draws":8,"losses":13,"wins":23},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":46},"gpt-5.6-sol":{"draws":19,"losses":35,"wins":40},"gpt-5.6-terra":{"draws":21,"losses":15,"wins":48},"gpt-6-astra":{"draws":4,"losses":80,"wins":12},"gpt-6-luna":{"draws":9,"losses":1,"wins":36},"gpt-6-sol":{"draws":9,"losses":26,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":7},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":33},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":27},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":44},"meta/muse-glimmer-30b":{"draws":9,"losses":0,"wins":43},"meta/muse-spark-1.2":{"draws":11,"losses":5,"wins":42},"meta/muse-spark-1.3":{"draws":15,"losses":21,"wins":42},"minimax/minimax-m3":{"draws":9,"losses":0,"wins":19},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":29,"losses":11,"wins":38},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":33},"o3":{"draws":8,"losses":3,"wins":69},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":39},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":47},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":17,"wins":45},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":29},"qwen/qwen3.8-flash":{"draws":17,"losses":8,"wins":31},"qwen/qwen3.8-max":{"draws":18,"losses":11,"wins":51},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":27},"stealth/ox-alpha":{"draws":54,"losses":55,"wins":175},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":25},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":20},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":48},"thinkingmachines/inkling":{"draws":19,"losses":3,"wins":42},"thinkingmachines/inkling-small":{"draws":12,"losses":2,"wins":54},"x-ai/grok-4.5":{"draws":18,"losses":14,"wins":36},"x-ai/grok-4.6":{"draws":11,"losses":12,"wins":15},"x-ai/grok-4.7":{"draws":4,"losses":4,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":21,"losses":2,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":1,"wins":12},"z-ai/glm-5.2":{"draws":30,"losses":12,"wins":82},"z-ai/glm-5.3":{"draws":19,"losses":38,"wins":33},"z-ai/glm-5.3-flash":{"draws":20,"losses":22,"wins":42},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":16},"claude-fable-5":{"draws":0,"losses":0,"wins":12},"claude-fable-5-1":{"draws":2,"losses":14,"wins":4},"claude-opus-4-5":{"draws":1,"losses":2,"wins":43},"claude-opus-4-8":{"draws":2,"losses":2,"wins":12},"claude-opus-5":{"draws":4,"losses":9,"wins":25},"claude-opus-5-5":{"draws":5,"losses":26,"wins":11},"claude-sonnet-5":{"draws":3,"losses":2,"wins":19},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":29},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":26},"fireworks/ember-1":{"draws":2,"losses":4,"wins":36},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":32},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":17},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":29},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":31},"google/gemini-3.8-flash":{"draws":0,"losses":0,"wins":24},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":10},"gpt-5.4":{"draws":1,"losses":3,"wins":14},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":15},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":15},"gpt-5.5":{"draws":0,"losses":4,"wins":22},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":20},"gpt-5.6-sol":{"draws":3,"losses":1,"wins":20},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":16},"gpt-6-astra":{"draws":2,"losses":10,"wins":4},"gpt-6-luna":{"draws":1,"losses":1,"wins":18},"gpt-6-sol":{"draws":3,"losses":13,"wins":24},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":21},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":22},"meta/muse-spark-1.2":{"draws":0,"losses":1,"wins":17},"meta/muse-spark-1.3":{"draws":0,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":11},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":22},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":24},"o3":{"draws":0,"losses":1,"wins":17},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":22},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":17},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":2,"wins":25},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":24},"stealth/ox-alpha":{"draws":5,"losses":3,"wins":68},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":30},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":1,"losses":5,"wins":20},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":18},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":17},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":12},"x-ai/grok-4.6":{"draws":2,"losses":1,"wins":15},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":19},"z-ai/glm-5.2":{"draws":3,"losses":3,"wins":36},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":19},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":10},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":30}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":16,"wins":4},"claude-fable-5":{"draws":8,"losses":29,"wins":7},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-opus-4-5":{"draws":38,"losses":55,"wins":13},"claude-opus-4-8":{"draws":22,"losses":47,"wins":13},"claude-opus-5":{"draws":16,"losses":69,"wins":7},"claude-opus-5-5":{"draws":0,"losses":20,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":16,"losses":7,"wins":23},"deepseek/deepseek-v4-flash":{"draws":34,"losses":29,"wins":19},"deepseek/deepseek-v4-pro":{"draws":12,"losses":15,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":22,"wins":2},"fireworks/ember-1":{"draws":6,"losses":7,"wins":3},"gemini-3.1-pro-preview":{"draws":11,"losses":1,"wins":8},"google/gemini-3.1-flash-lite":{"draws":19,"losses":9,"wins":32},"google/gemini-3.5-flash":{"draws":15,"losses":31,"wins":6},"google/gemini-3.5-flash-lite":{"draws":30,"losses":23,"wins":29},"google/gemini-3.6-flash":{"draws":23,"losses":41,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":23,"wins":1},"google/gemma-4-31b-it":{"draws":15,"losses":9,"wins":22},"gpt-4.1":{"draws":11,"losses":11,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":21,"losses":30,"wins":13},"gpt-5.4":{"draws":4,"losses":20,"wins":2},"gpt-5.4-mini":{"draws":26,"losses":20,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":49,"wins":25},"gpt-5.5":{"draws":43,"losses":19,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":2},"gpt-5.6-sol":{"draws":7,"losses":20,"wins":3},"gpt-5.6-terra":{"draws":14,"losses":22,"wins":6},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":12,"losses":13,"wins":3},"gpt-6-sol":{"draws":5,"losses":15,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":32},"meituan/longcat-2.0":{"draws":21,"losses":25,"wins":26},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":24,"wins":6},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":21},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":21,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":14,"wins":16},"o3":{"draws":11,"losses":38,"wins":9},"openai/gpt-oss-120b":{"draws":10,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":27,"losses":15,"wins":24},"qwen/qwen3.7-max":{"draws":22,"losses":14,"wins":18},"qwen/qwen3.7-plus":{"draws":14,"losses":20,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":2},"qwen/qwen3.8-flash":{"draws":15,"losses":6,"wins":3},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":7},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":6},"stealth/ox-alpha":{"draws":35,"losses":84,"wins":13},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":21},"tencent/hy3-preview":{"draws":7,"losses":15,"wins":6},"tencent/hy4-preview":{"draws":17,"losses":23,"wins":2},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":23},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":9},"x-ai/grok-4.5":{"draws":19,"losses":38,"wins":5},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":1},"xiaomi/mimo-v2.5":{"draws":53,"losses":31,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":20,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":33,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":22,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":4},"z-ai/glm-5.3-flashx":{"draws":2,"losses":21,"wins":3}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":15,"wins":5},"claude-fable-5":{"draws":16,"losses":51,"wins":3},"claude-fable-5-1":{"draws":1,"losses":55,"wins":0},"claude-opus-4-5":{"draws":89,"losses":92,"wins":25},"claude-opus-4-8":{"draws":34,"losses":54,"wins":12},"claude-opus-5":{"draws":28,"losses":126,"wins":14},"claude-opus-5-5":{"draws":3,"losses":54,"wins":3},"claude-sonnet-5":{"draws":32,"losses":23,"wins":5},"claude-sonnet-5-5":{"draws":13,"losses":37,"wins":6},"cohere/north-mini-code":{"draws":17,"losses":19,"wins":24},"deepseek/deepseek-v4-flash":{"draws":53,"losses":30,"wins":45},"deepseek/deepseek-v4-pro":{"draws":24,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":17,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":29,"wins":2},"fireworks/ember-1":{"draws":22,"losses":30,"wins":2},"gemini-3.1-pro-preview":{"draws":25,"losses":24,"wins":11},"google/gemini-3.1-flash-lite":{"draws":34,"losses":23,"wins":45},"google/gemini-3.5-flash":{"draws":23,"losses":33,"wins":12},"google/gemini-3.5-flash-lite":{"draws":51,"losses":31,"wins":44},"google/gemini-3.6-flash":{"draws":49,"losses":51,"wins":8},"google/gemini-3.8-flash":{"draws":24,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":17,"losses":25,"wins":20},"gpt-4.1":{"draws":14,"losses":12,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":38,"losses":38,"wins":24},"gpt-5.4":{"draws":22,"losses":23,"wins":3},"gpt-5.4-mini":{"draws":39,"losses":36,"wins":15},"gpt-5.4-nano":{"draws":39,"losses":57,"wins":50},"gpt-5.5":{"draws":64,"losses":42,"wins":6},"gpt-5.6-luna":{"draws":23,"losses":15,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":25,"losses":40,"wins":5},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":25,"losses":28,"wins":13},"gpt-6-sol":{"draws":7,"losses":46,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":14},"inclusionai/ling-3.0-flash":{"draws":23,"losses":19,"wins":26},"meituan/longcat-2.0":{"draws":49,"losses":41,"wins":42},"meta/muse-glimmer-30b":{"draws":16,"losses":17,"wins":9},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":3},"meta/muse-spark-1.3":{"draws":17,"losses":24,"wins":3},"minimax/minimax-m3":{"draws":41,"losses":24,"wins":25},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":25,"losses":26,"wins":7},"moonshotai/kimi-k3":{"draws":23,"losses":29,"wins":6},"nex-agi/nex-n2-pro":{"draws":13,"losses":20,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":44,"wins":24},"o3":{"draws":24,"losses":69,"wins":7},"openai/gpt-oss-120b":{"draws":28,"losses":15,"wins":15},"poolside/laguna-s-2.1":{"draws":34,"losses":23,"wins":33},"qwen/qwen3.7-max":{"draws":36,"losses":31,"wins":17},"qwen/qwen3.7-plus":{"draws":49,"losses":29,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":21,"wins":5},"qwen/qwen3.8-27b":{"draws":9,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":10},"qwen/qwen3.8-max":{"draws":21,"losses":24,"wins":5},"qwen/qwen3.8-max-0902":{"draws":17,"losses":31,"wins":6},"stealth/ox-alpha":{"draws":44,"losses":72,"wins":22},"stealth/space-bunny-alpha":{"draws":23,"losses":18,"wins":7},"stepfun/step-3.7-flash":{"draws":34,"losses":18,"wins":12},"tencent/hy3-preview":{"draws":35,"losses":18,"wins":15},"tencent/hy4-preview":{"draws":14,"losses":24,"wins":2},"thinkingmachines/inkling":{"draws":38,"losses":20,"wins":46},"thinkingmachines/inkling-small":{"draws":24,"losses":13,"wins":9},"x-ai/grok-4.5":{"draws":42,"losses":50,"wins":6},"x-ai/grok-4.6":{"draws":27,"losses":39,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":42,"wins":2},"x-ai/grok-build-0.1":{"draws":22,"losses":21,"wins":11},"xiaomi/mimo-v2.5":{"draws":114,"losses":48,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":29,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":23,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":70,"losses":67,"wins":29},"z-ai/glm-5.3":{"draws":20,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":17,"losses":40,"wins":11},"z-ai/glm-5.3-flashx":{"draws":19,"losses":34,"wins":1}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":13},"claude-fable-5":{"draws":1,"losses":25,"wins":2},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-opus-4-5":{"draws":19,"losses":32,"wins":35},"claude-opus-4-8":{"draws":12,"losses":35,"wins":17},"claude-opus-5":{"draws":15,"losses":42,"wins":3},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":3,"losses":13,"wins":18},"claude-sonnet-5-5":{"draws":2,"losses":8,"wins":4},"cohere/north-mini-code":{"draws":7,"losses":10,"wins":19},"deepseek/deepseek-v4-flash":{"draws":13,"losses":10,"wins":25},"deepseek/deepseek-v4-pro":{"draws":2,"losses":9,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":18,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":4,"wins":7},"fireworks/ember-1":{"draws":0,"losses":6,"wins":2},"gemini-3.1-pro-preview":{"draws":7,"losses":5,"wins":6},"google/gemini-3.1-flash-lite":{"draws":13,"losses":6,"wins":39},"google/gemini-3.5-flash":{"draws":5,"losses":8,"wins":19},"google/gemini-3.5-flash-lite":{"draws":16,"losses":11,"wins":35},"google/gemini-3.6-flash":{"draws":14,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":5,"losses":16,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":6,"wins":12},"gpt-4.1":{"draws":3,"losses":9,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":17,"wins":13},"gpt-5.4":{"draws":3,"losses":30,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":23,"wins":32},"gpt-5.5":{"draws":10,"losses":25,"wins":13},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":9},"gpt-5.6-terra":{"draws":6,"losses":17,"wins":7},"gpt-6-astra":{"draws":2,"losses":26,"wins":2},"gpt-6-luna":{"draws":6,"losses":8,"wins":10},"gpt-6-sol":{"draws":3,"losses":13,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":4,"wins":11},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":18},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":24},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":8},"meta/muse-spark-1.2":{"draws":2,"losses":13,"wins":19},"meta/muse-spark-1.3":{"draws":1,"losses":14,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":14,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":9,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":20},"o3":{"draws":7,"losses":20,"wins":37},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":11,"losses":19,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":13,"wins":11},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":5,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":1,"losses":11,"wins":6},"qwen/qwen3.8-max-0902":{"draws":4,"losses":10,"wins":8},"stealth/ox-alpha":{"draws":4,"losses":33,"wins":31},"stealth/space-bunny-alpha":{"draws":6,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":14},"tencent/hy3-preview":{"draws":10,"losses":11,"wins":11},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":5},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":22},"thinkingmachines/inkling-small":{"draws":4,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":7,"losses":22,"wins":29},"x-ai/grok-4.6":{"draws":8,"losses":18,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":24,"losses":8,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":24,"losses":24,"wins":24},"z-ai/glm-5.3":{"draws":7,"losses":18,"wins":5},"z-ai/glm-5.3-flash":{"draws":2,"losses":14,"wins":10},"z-ai/glm-5.3-flashx":{"draws":11,"losses":1,"wins":2}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":15},"claude-fable-5":{"draws":5,"losses":15,"wins":8},"claude-fable-5-1":{"draws":2,"losses":16,"wins":6},"claude-opus-4-5":{"draws":7,"losses":8,"wins":15},"claude-opus-4-8":{"draws":3,"losses":7,"wins":12},"claude-opus-5":{"draws":3,"losses":25,"wins":6},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":4,"losses":3,"wins":11},"claude-sonnet-5-5":{"draws":2,"losses":21,"wins":23},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":5,"wins":24},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":5,"losses":18,"wins":23},"gemini-3.1-pro-preview":{"draws":8,"losses":11,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":13},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":25},"google/gemini-3.6-flash":{"draws":5,"losses":20,"wins":17},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":9},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":6,"losses":7,"wins":7},"gpt-5.4":{"draws":3,"losses":6,"wins":9},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":13},"gpt-5.5":{"draws":4,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":9},"gpt-5.6-sol":{"draws":1,"losses":11,"wins":6},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":12},"gpt-6-astra":{"draws":1,"losses":15,"wins":2},"gpt-6-luna":{"draws":9,"losses":10,"wins":27},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":10},"meta/muse-glimmer-30b":{"draws":5,"losses":3,"wins":14},"meta/muse-spark-1.2":{"draws":4,"losses":9,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":9,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":9},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":14},"o3":{"draws":4,"losses":2,"wins":16},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":15},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":18},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":7},"qwen/qwen3.8-27b":{"draws":1,"losses":4,"wins":5},"qwen/qwen3.8-flash":{"draws":5,"losses":5,"wins":10},"qwen/qwen3.8-max":{"draws":5,"losses":7,"wins":22},"qwen/qwen3.8-max-0902":{"draws":7,"losses":15,"wins":24},"stealth/ox-alpha":{"draws":5,"losses":30,"wins":37},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":3,"losses":4,"wins":9},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":17},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":13},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":18},"x-ai/grok-4.6":{"draws":7,"losses":10,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":13},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":7,"losses":4,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":5,"losses":8,"wins":25},"z-ai/glm-5.3":{"draws":6,"losses":9,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":12,"wins":15},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":16},"claude-fable-5":{"draws":2,"losses":5,"wins":13},"claude-fable-5-1":{"draws":2,"losses":18,"wins":6},"claude-opus-4-5":{"draws":3,"losses":4,"wins":25},"claude-opus-4-8":{"draws":0,"losses":9,"wins":17},"claude-opus-5":{"draws":7,"losses":17,"wins":16},"claude-opus-5-5":{"draws":4,"losses":27,"wins":7},"claude-sonnet-5":{"draws":2,"losses":2,"wins":20},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":34},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":28},"fireworks/ember-1":{"draws":5,"losses":7,"wins":30},"gemini-3.1-pro-preview":{"draws":3,"losses":5,"wins":34},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":1,"losses":9,"wins":14},"google/gemini-3.5-flash-lite":{"draws":1,"losses":3,"wins":24},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":23},"google/gemini-3.8-flash":{"draws":4,"losses":5,"wins":11},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":4,"wins":16},"gpt-5.4":{"draws":3,"losses":4,"wins":11},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":14},"gpt-5.5":{"draws":6,"losses":5,"wins":11},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":25},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":16},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":15},"gpt-6-astra":{"draws":3,"losses":13,"wins":2},"gpt-6-luna":{"draws":1,"losses":2,"wins":19},"gpt-6-sol":{"draws":4,"losses":20,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":21,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":13},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":23},"meta/muse-glimmer-30b":{"draws":2,"losses":2,"wins":16},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":11},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":14},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":1,"losses":0,"wins":13},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":21},"o3":{"draws":1,"losses":5,"wins":20},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":17},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":17},"qwen/qwen3.8-27b":{"draws":0,"losses":3,"wins":7},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":5},"qwen/qwen3.8-max":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":28},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":53},"stealth/space-bunny-alpha":{"draws":2,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":1,"losses":5,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":22},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":15},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":17,"wins":14},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":1,"losses":1,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":10},"z-ai/glm-5.2":{"draws":4,"losses":1,"wins":37},"z-ai/glm-5.3":{"draws":2,"losses":5,"wins":11},"z-ai/glm-5.3-flash":{"draws":1,"losses":7,"wins":12},"z-ai/glm-5.3-flashx":{"draws":2,"losses":13,"wins":23}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":18,"wins":32},"claude-fable-5":{"draws":25,"losses":56,"wins":21},"claude-fable-5-1":{"draws":10,"losses":62,"wins":2},"claude-opus-4-5":{"draws":55,"losses":52,"wins":57},"claude-opus-4-8":{"draws":38,"losses":43,"wins":29},"claude-opus-5":{"draws":23,"losses":118,"wins":5},"claude-opus-5-5":{"draws":1,"losses":30,"wins":3},"claude-sonnet-5":{"draws":27,"losses":29,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":19,"losses":13,"wins":26},"deepseek/deepseek-v4-flash":{"draws":57,"losses":25,"wins":58},"deepseek/deepseek-v4-pro":{"draws":42,"losses":27,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":35,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":3,"wins":5},"fireworks/ember-1":{"draws":19,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":19,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":17,"losses":6,"wins":29},"google/gemini-3.5-flash":{"draws":46,"losses":32,"wins":50},"google/gemini-3.5-flash-lite":{"draws":78,"losses":30,"wins":60},"google/gemini-3.6-flash":{"draws":41,"losses":56,"wins":51},"google/gemini-3.8-flash":{"draws":23,"losses":48,"wins":31},"google/gemma-4-31b-it":{"draws":14,"losses":5,"wins":19},"gpt-4.1":{"draws":14,"losses":4,"wins":20},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":38,"losses":26,"wins":22},"gpt-5.4":{"draws":27,"losses":25,"wins":24},"gpt-5.4-mini":{"draws":49,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":34,"losses":26,"wins":32},"gpt-5.5":{"draws":34,"losses":25,"wins":15},"gpt-5.6-luna":{"draws":42,"losses":14,"wins":26},"gpt-5.6-sol":{"draws":12,"losses":53,"wins":25},"gpt-5.6-terra":{"draws":53,"losses":26,"wins":29},"gpt-6-astra":{"draws":10,"losses":74,"wins":4},"gpt-6-luna":{"draws":16,"losses":20,"wins":24},"gpt-6-sol":{"draws":6,"losses":29,"wins":3},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":3,"wins":33},"inclusionai/ling-3.0-flash":{"draws":31,"losses":4,"wins":19},"meituan/longcat-2.0":{"draws":25,"losses":24,"wins":35},"meta/muse-glimmer-30b":{"draws":32,"losses":12,"wins":24},"meta/muse-spark-1.2":{"draws":9,"losses":39,"wins":22},"meta/muse-spark-1.3":{"draws":24,"losses":28,"wins":22},"minimax/minimax-m3":{"draws":23,"losses":10,"wins":15},"mistralai/mistral-medium-3-5":{"draws":21,"losses":7,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":9,"wins":10},"moonshotai/kimi-k3":{"draws":33,"losses":26,"wins":23},"nex-agi/nex-n2-pro":{"draws":28,"losses":3,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":11,"wins":27},"o3":{"draws":22,"losses":35,"wins":63},"openai/gpt-oss-120b":{"draws":30,"losses":9,"wins":23},"poolside/laguna-s-2.1":{"draws":61,"losses":11,"wins":26},"qwen/qwen3.7-max":{"draws":20,"losses":8,"wins":20},"qwen/qwen3.7-plus":{"draws":20,"losses":8,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":38,"wins":25},"qwen/qwen3.8-27b":{"draws":15,"losses":25,"wins":24},"qwen/qwen3.8-flash":{"draws":27,"losses":22,"wins":13},"qwen/qwen3.8-max":{"draws":25,"losses":30,"wins":21},"qwen/qwen3.8-max-0902":{"draws":10,"losses":13,"wins":7},"stealth/ox-alpha":{"draws":90,"losses":128,"wins":82},"stealth/space-bunny-alpha":{"draws":17,"losses":8,"wins":9},"stepfun/step-3.7-flash":{"draws":16,"losses":12,"wins":28},"tencent/hy3-preview":{"draws":28,"losses":12,"wins":10},"tencent/hy4-preview":{"draws":29,"losses":39,"wins":20},"thinkingmachines/inkling":{"draws":36,"losses":15,"wins":37},"thinkingmachines/inkling-small":{"draws":41,"losses":14,"wins":35},"x-ai/grok-4.5":{"draws":28,"losses":32,"wins":34},"x-ai/grok-4.6":{"draws":30,"losses":56,"wins":22},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":3},"x-ai/grok-build-0.1":{"draws":14,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":60,"losses":19,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":12,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":61,"losses":44,"wins":37},"z-ai/glm-5.3":{"draws":18,"losses":51,"wins":19},"z-ai/glm-5.3-flash":{"draws":44,"losses":41,"wins":25},"z-ai/glm-5.3-flashx":{"draws":4,"losses":16,"wins":10}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":30},"claude-fable-5":{"draws":13,"losses":27,"wins":42},"claude-fable-5-1":{"draws":4,"losses":49,"wins":17},"claude-opus-4-5":{"draws":14,"losses":10,"wins":46},"claude-opus-4-8":{"draws":5,"losses":9,"wins":20},"claude-opus-5":{"draws":11,"losses":39,"wins":10},"claude-opus-5-5":{"draws":0,"losses":21,"wins":7},"claude-sonnet-5":{"draws":6,"losses":6,"wins":44},"claude-sonnet-5-5":{"draws":6,"losses":8,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":1,"wins":45},"deepseek/deepseek-v4-pro":{"draws":7,"losses":12,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":11,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":10},"fireworks/ember-1":{"draws":4,"losses":3,"wins":23},"gemini-3.1-pro-preview":{"draws":2,"losses":6,"wins":16},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":12,"losses":15,"wins":51},"google/gemini-3.5-flash-lite":{"draws":14,"losses":3,"wins":69},"google/gemini-3.6-flash":{"draws":16,"losses":16,"wins":66},"google/gemini-3.8-flash":{"draws":13,"losses":14,"wins":41},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":14},"gpt-4.1":{"draws":4,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":19},"gpt-5.4":{"draws":6,"losses":20,"wins":42},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":26},"gpt-5.5":{"draws":9,"losses":7,"wins":16},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":37},"gpt-5.6-sol":{"draws":15,"losses":30,"wins":27},"gpt-5.6-terra":{"draws":25,"losses":6,"wins":39},"gpt-6-astra":{"draws":11,"losses":57,"wins":4},"gpt-6-luna":{"draws":3,"losses":4,"wins":21},"gpt-6-sol":{"draws":3,"losses":10,"wins":11},"gpt-6.1-sol":{"draws":6,"losses":16,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":22},"meituan/longcat-2.0":{"draws":9,"losses":3,"wins":30},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":10,"wins":32},"meta/muse-spark-1.3":{"draws":13,"losses":16,"wins":39},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":11},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":21,"wins":35},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":18},"o3":{"draws":6,"losses":9,"wins":51},"openai/gpt-oss-120b":{"draws":12,"losses":2,"wins":20},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":26},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":36},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":20},"qwen/qwen3.8-flash":{"draws":12,"losses":5,"wins":33},"qwen/qwen3.8-max":{"draws":16,"losses":9,"wins":33},"qwen/qwen3.8-max-0902":{"draws":6,"losses":3,"wins":9},"stealth/ox-alpha":{"draws":32,"losses":49,"wins":124},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":22},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":39},"thinkingmachines/inkling":{"draws":12,"losses":2,"wins":28},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":32},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":38},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":16,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":0,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":6},"z-ai/glm-5.2":{"draws":20,"losses":17,"wins":47},"z-ai/glm-5.3":{"draws":9,"losses":15,"wins":16},"z-ai/glm-5.3-flash":{"draws":16,"losses":12,"wins":40},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":10}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":8,"wins":20},"claude-fable-5":{"draws":10,"losses":39,"wins":25},"claude-fable-5-1":{"draws":9,"losses":69,"wins":8},"claude-opus-4-5":{"draws":22,"losses":16,"wins":42},"claude-opus-4-8":{"draws":2,"losses":10,"wins":10},"claude-opus-5":{"draws":7,"losses":49,"wins":18},"claude-opus-5-5":{"draws":3,"losses":18,"wins":3},"claude-sonnet-5":{"draws":12,"losses":7,"wins":39},"claude-sonnet-5-5":{"draws":4,"losses":14,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":39},"deepseek/deepseek-v4-pro":{"draws":19,"losses":20,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":12,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":12},"fireworks/ember-1":{"draws":8,"losses":9,"wins":15},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":11},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":17,"losses":18,"wins":35},"google/gemini-3.5-flash-lite":{"draws":30,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":27,"losses":25,"wins":50},"google/gemini-3.8-flash":{"draws":18,"losses":31,"wins":23},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":14},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":6,"wins":14},"gpt-5.4":{"draws":22,"losses":21,"wins":23},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":7,"losses":2,"wins":19},"gpt-5.5":{"draws":2,"losses":8,"wins":12},"gpt-5.6-luna":{"draws":13,"losses":14,"wins":27},"gpt-5.6-sol":{"draws":9,"losses":35,"wins":28},"gpt-5.6-terra":{"draws":17,"losses":19,"wins":28},"gpt-6-astra":{"draws":14,"losses":54,"wins":8},"gpt-6-luna":{"draws":9,"losses":7,"wins":14},"gpt-6-sol":{"draws":4,"losses":13,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":0,"wins":19},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":15},"meituan/longcat-2.0":{"draws":12,"losses":2,"wins":24},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":28},"meta/muse-spark-1.2":{"draws":9,"losses":17,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":28},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":20,"wins":27},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":0,"wins":11},"o3":{"draws":13,"losses":22,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":0,"wins":28},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":9,"losses":0,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":24},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":19},"qwen/qwen3.8-flash":{"draws":15,"losses":16,"wins":19},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":24},"qwen/qwen3.8-max-0902":{"draws":9,"losses":2,"wins":9},"stealth/ox-alpha":{"draws":46,"losses":69,"wins":98},"stealth/space-bunny-alpha":{"draws":6,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":2,"wins":13},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":13},"tencent/hy4-preview":{"draws":10,"losses":21,"wins":29},"thinkingmachines/inkling":{"draws":13,"losses":2,"wins":35},"thinkingmachines/inkling-small":{"draws":23,"losses":3,"wins":32},"x-ai/grok-4.5":{"draws":7,"losses":23,"wins":30},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":34},"x-ai/grok-4.7":{"draws":5,"losses":10,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":34,"losses":13,"wins":45},"z-ai/glm-5.3":{"draws":15,"losses":35,"wins":16},"z-ai/glm-5.3-flash":{"draws":14,"losses":7,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":6,"wins":18}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":5,"wins":13},"claude-fable-5":{"draws":8,"losses":16,"wins":6},"claude-fable-5-1":{"draws":4,"losses":27,"wins":3},"claude-opus-4-5":{"draws":10,"losses":7,"wins":13},"claude-opus-4-8":{"draws":4,"losses":10,"wins":10},"claude-opus-5":{"draws":5,"losses":28,"wins":3},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":5,"losses":10,"wins":5},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":18},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":0,"wins":17},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":5,"losses":12,"wins":25},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":10,"losses":13,"wins":7},"google/gemini-3.5-flash-lite":{"draws":6,"losses":11,"wins":17},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":14},"google/gemini-3.8-flash":{"draws":5,"losses":11,"wins":6},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":8},"gpt-4.1":{"draws":2,"losses":3,"wins":5},"gpt-5":{"draws":4,"losses":3,"wins":5},"gpt-5.4":{"draws":7,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":10},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":7},"gpt-5.5":{"draws":10,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":0,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":11},"gpt-6-astra":{"draws":2,"losses":15,"wins":1},"gpt-6-luna":{"draws":12,"losses":17,"wins":17},"gpt-6-sol":{"draws":4,"losses":34,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":14},"meituan/longcat-2.0":{"draws":9,"losses":3,"wins":12},"meta/muse-glimmer-30b":{"draws":4,"losses":6,"wins":14},"meta/muse-spark-1.2":{"draws":3,"losses":9,"wins":2},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":10},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":12,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":13},"o3":{"draws":0,"losses":12,"wins":12},"openai/gpt-oss-120b":{"draws":5,"losses":6,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":2,"wins":7},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":10,"wins":7},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":14},"stealth/ox-alpha":{"draws":14,"losses":26,"wins":34},"stealth/space-bunny-alpha":{"draws":12,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":9,"losses":1,"wins":14},"thinkingmachines/inkling-small":{"draws":5,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":8,"losses":10,"wins":12},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":13,"losses":12,"wins":13},"z-ai/glm-5.3":{"draws":9,"losses":10,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":12,"wins":9},"z-ai/glm-5.3-flashx":{"draws":12,"losses":15,"wins":5}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":19,"wins":6},"claude-fable-5":{"draws":8,"losses":27,"wins":3},"claude-fable-5-1":{"draws":1,"losses":35,"wins":0},"claude-opus-4-5":{"draws":17,"losses":37,"wins":6},"claude-opus-4-8":{"draws":5,"losses":17,"wins":0},"claude-opus-5":{"draws":2,"losses":26,"wins":0},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":17,"losses":41,"wins":6},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":3},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":2},"deepseek/deepseek-v4-flash":{"draws":21,"losses":28,"wins":13},"deepseek/deepseek-v4-pro":{"draws":16,"losses":34,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":25,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":8,"wins":3},"fireworks/ember-1":{"draws":12,"losses":12,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":15,"losses":35,"wins":6},"google/gemini-3.5-flash-lite":{"draws":30,"losses":46,"wins":24},"google/gemini-3.6-flash":{"draws":20,"losses":44,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":35,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":2,"losses":10,"wins":6},"gpt-5.4":{"draws":13,"losses":27,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":18,"wins":7},"gpt-5.5":{"draws":11,"losses":15,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":31,"wins":18},"gpt-5.6-sol":{"draws":3,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":13,"losses":38,"wins":5},"gpt-6-astra":{"draws":0,"losses":29,"wins":1},"gpt-6-luna":{"draws":8,"losses":17,"wins":5},"gpt-6-sol":{"draws":0,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":24,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":11,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":11},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":11},"meta/muse-glimmer-30b":{"draws":25,"losses":19,"wins":12},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":5},"meta/muse-spark-1.3":{"draws":6,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":22,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":14,"losses":47,"wins":11},"openai/gpt-oss-120b":{"draws":20,"losses":21,"wins":15},"poolside/laguna-s-2.1":{"draws":13,"losses":15,"wins":12},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":10,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":17,"losses":16,"wins":3},"qwen/qwen3.8-max":{"draws":21,"losses":26,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":13,"wins":2},"stealth/ox-alpha":{"draws":30,"losses":99,"wins":25},"stealth/space-bunny-alpha":{"draws":4,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":21,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":21,"wins":15},"thinkingmachines/inkling-small":{"draws":21,"losses":18,"wins":23},"x-ai/grok-4.5":{"draws":9,"losses":35,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":29,"wins":7},"x-ai/grok-4.7":{"draws":0,"losses":20,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":1},"z-ai/glm-5.2":{"draws":38,"losses":19,"wins":13},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":17,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":6}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":7,"wins":30},"claude-fable-5":{"draws":9,"losses":20,"wins":13},"claude-fable-5-1":{"draws":1,"losses":47,"wins":4},"claude-opus-4-5":{"draws":15,"losses":16,"wins":47},"claude-opus-4-8":{"draws":4,"losses":9,"wins":13},"claude-opus-5":{"draws":11,"losses":48,"wins":9},"claude-opus-5-5":{"draws":1,"losses":15,"wins":0},"claude-sonnet-5":{"draws":20,"losses":10,"wins":32},"claude-sonnet-5-5":{"draws":6,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":20,"losses":10,"wins":44},"deepseek/deepseek-v4-pro":{"draws":21,"losses":14,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":14,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":6,"wins":5},"fireworks/ember-1":{"draws":8,"losses":7,"wins":15},"gemini-3.1-pro-preview":{"draws":5,"losses":7,"wins":12},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":19,"losses":14,"wins":31},"google/gemini-3.5-flash-lite":{"draws":31,"losses":15,"wins":52},"google/gemini-3.6-flash":{"draws":22,"losses":32,"wins":48},"google/gemini-3.8-flash":{"draws":10,"losses":26,"wins":20},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":10},"gpt-4.1":{"draws":2,"losses":2,"wins":8},"gpt-5":{"draws":7,"losses":0,"wins":13},"gpt-5.4":{"draws":24,"losses":21,"wins":29},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":12},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":22},"gpt-5.5":{"draws":9,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":25,"losses":10,"wins":27},"gpt-5.6-sol":{"draws":14,"losses":30,"wins":26},"gpt-5.6-terra":{"draws":19,"losses":11,"wins":40},"gpt-6-astra":{"draws":3,"losses":51,"wins":14},"gpt-6-luna":{"draws":5,"losses":6,"wins":13},"gpt-6-sol":{"draws":2,"losses":9,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":22,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":22,"losses":0,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":13},"meituan/longcat-2.0":{"draws":9,"losses":11,"wins":20},"meta/muse-glimmer-30b":{"draws":18,"losses":2,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":22},"meta/muse-spark-1.3":{"draws":10,"losses":19,"wins":23},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":7},"mistralai/mistral-medium-3-5":{"draws":18,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":19,"losses":8,"wins":35},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":16},"o3":{"draws":4,"losses":9,"wins":51},"openai/gpt-oss-120b":{"draws":20,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":11,"losses":7,"wins":20},"qwen/qwen3.7-max":{"draws":5,"losses":2,"wins":7},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":21,"wins":25},"qwen/qwen3.8-27b":{"draws":1,"losses":14,"wins":15},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":18},"qwen/qwen3.8-max":{"draws":14,"losses":18,"wins":28},"qwen/qwen3.8-max-0902":{"draws":9,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":48,"losses":60,"wins":98},"stealth/space-bunny-alpha":{"draws":11,"losses":2,"wins":11},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":17},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":3},"tencent/hy4-preview":{"draws":11,"losses":24,"wins":33},"thinkingmachines/inkling":{"draws":12,"losses":2,"wins":32},"thinkingmachines/inkling-small":{"draws":19,"losses":6,"wins":23},"x-ai/grok-4.5":{"draws":13,"losses":25,"wins":26},"x-ai/grok-4.6":{"draws":17,"losses":25,"wins":34},"x-ai/grok-4.7":{"draws":0,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":10,"wins":8},"z-ai/glm-5.2":{"draws":28,"losses":23,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":44,"wins":14},"z-ai/glm-5.3-flash":{"draws":7,"losses":35,"wins":18},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":3}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":37},"claude-fable-5":{"draws":3,"losses":18,"wins":47},"claude-fable-5-1":{"draws":3,"losses":42,"wins":13},"claude-opus-4-5":{"draws":5,"losses":0,"wins":55},"claude-opus-4-8":{"draws":2,"losses":3,"wins":21},"claude-opus-5":{"draws":7,"losses":19,"wins":20},"claude-opus-5-5":{"draws":2,"losses":19,"wins":15},"claude-sonnet-5":{"draws":7,"losses":3,"wins":54},"claude-sonnet-5-5":{"draws":4,"losses":9,"wins":27},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":58},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":24},"fireworks/ember-1":{"draws":3,"losses":2,"wins":29},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":35},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":19},"google/gemini-3.5-flash":{"draws":9,"losses":6,"wins":49},"google/gemini-3.5-flash-lite":{"draws":12,"losses":0,"wins":58},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":75},"google/gemini-3.8-flash":{"draws":6,"losses":9,"wins":53},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":12},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":1,"losses":1,"wins":18},"gpt-5.4":{"draws":5,"losses":9,"wins":44},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":11},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":21},"gpt-5.5":{"draws":2,"losses":2,"wins":14},"gpt-5.6-luna":{"draws":7,"losses":4,"wins":37},"gpt-5.6-sol":{"draws":12,"losses":12,"wins":46},"gpt-5.6-terra":{"draws":12,"losses":0,"wins":56},"gpt-6-astra":{"draws":10,"losses":45,"wins":15},"gpt-6-luna":{"draws":4,"losses":1,"wins":29},"gpt-6-sol":{"draws":2,"losses":8,"wins":20},"gpt-6.1-sol":{"draws":3,"losses":23,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":25},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":24},"meta/muse-spark-1.2":{"draws":4,"losses":0,"wins":40},"meta/muse-spark-1.3":{"draws":5,"losses":7,"wins":40},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":17},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":0,"wins":47},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":19},"o3":{"draws":0,"losses":4,"wins":44},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":27},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":17},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":2,"wins":51},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":26},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":34},"qwen/qwen3.8-max":{"draws":5,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":29},"stealth/ox-alpha":{"draws":30,"losses":11,"wins":155},"stealth/space-bunny-alpha":{"draws":3,"losses":1,"wins":22},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":13},"tencent/hy4-preview":{"draws":3,"losses":8,"wins":47},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":34},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":36},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":43},"x-ai/grok-4.6":{"draws":9,"losses":10,"wins":51},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":9,"losses":3,"wins":50},"z-ai/glm-5.3":{"draws":4,"losses":15,"wins":35},"z-ai/glm-5.3-flash":{"draws":15,"losses":4,"wins":51},"z-ai/glm-5.3-flashx":{"draws":4,"losses":4,"wins":28}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":9,"wins":12},"claude-fable-5":{"draws":11,"losses":21,"wins":8},"claude-fable-5-1":{"draws":0,"losses":28,"wins":0},"claude-opus-4-5":{"draws":32,"losses":16,"wins":28},"claude-opus-4-8":{"draws":19,"losses":39,"wins":22},"claude-opus-5":{"draws":17,"losses":93,"wins":14},"claude-opus-5-5":{"draws":1,"losses":15,"wins":2},"claude-sonnet-5":{"draws":10,"losses":8,"wins":8},"claude-sonnet-5-5":{"draws":1,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":24},"deepseek/deepseek-v4-flash":{"draws":20,"losses":16,"wins":22},"deepseek/deepseek-v4-pro":{"draws":13,"losses":8,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"fireworks/ember-1":{"draws":4,"losses":7,"wins":1},"gemini-3.1-pro-preview":{"draws":0,"losses":5,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":15,"wins":8},"google/gemini-3.5-flash-lite":{"draws":35,"losses":22,"wins":21},"google/gemini-3.6-flash":{"draws":27,"losses":26,"wins":27},"google/gemini-3.8-flash":{"draws":14,"losses":12,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":7,"wins":23},"gpt-4.1":{"draws":14,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":21,"losses":7,"wins":12},"gpt-5.4":{"draws":8,"losses":7,"wins":5},"gpt-5.4-mini":{"draws":25,"losses":16,"wins":15},"gpt-5.4-nano":{"draws":20,"losses":16,"wins":38},"gpt-5.5":{"draws":29,"losses":22,"wins":9},"gpt-5.6-luna":{"draws":9,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":7},"gpt-5.6-terra":{"draws":24,"losses":10,"wins":6},"gpt-6-astra":{"draws":3,"losses":29,"wins":6},"gpt-6-luna":{"draws":12,"losses":13,"wins":9},"gpt-6-sol":{"draws":2,"losses":11,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":19,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":19,"losses":2,"wins":13},"meituan/longcat-2.0":{"draws":28,"losses":9,"wins":29},"meta/muse-glimmer-30b":{"draws":12,"losses":4,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":13,"losses":14,"wins":3},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":17},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":10},"moonshotai/kimi-k3":{"draws":26,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":31},"o3":{"draws":13,"losses":15,"wins":18},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":6},"poolside/laguna-s-2.1":{"draws":28,"losses":8,"wins":20},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":22},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":11,"wins":7},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":8},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":12,"wins":9},"qwen/qwen3.8-max-0902":{"draws":6,"losses":7,"wins":1},"stealth/ox-alpha":{"draws":43,"losses":48,"wins":19},"stealth/space-bunny-alpha":{"draws":3,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":12},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":18},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":28},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":19},"x-ai/grok-4.5":{"draws":19,"losses":23,"wins":18},"x-ai/grok-4.6":{"draws":13,"losses":18,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":11,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":33,"losses":15,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":17,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":5,"wins":2},"z-ai/glm-5.2":{"draws":24,"losses":33,"wins":53},"z-ai/glm-5.3":{"draws":9,"losses":11,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":22,"wins":10},"z-ai/glm-5.3-flashx":{"draws":5,"losses":9,"wins":0}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":10},"claude-fable-5":{"draws":0,"losses":24,"wins":4},"claude-fable-5-1":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":24,"losses":19,"wins":37},"claude-opus-4-8":{"draws":12,"losses":16,"wins":12},"claude-opus-5":{"draws":18,"losses":61,"wins":19},"claude-opus-5-5":{"draws":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":6,"losses":2,"wins":8},"claude-sonnet-5-5":{"draws":5,"losses":11,"wins":10},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":34},"deepseek/deepseek-v4-flash":{"draws":15,"losses":4,"wins":33},"deepseek/deepseek-v4-pro":{"draws":3,"losses":14,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":11,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":2},"fireworks/ember-1":{"draws":9,"losses":7,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":11},"google/gemini-3.1-flash-lite":{"draws":11,"losses":5,"wins":28},"google/gemini-3.5-flash":{"draws":18,"losses":17,"wins":19},"google/gemini-3.5-flash-lite":{"draws":20,"losses":11,"wins":27},"google/gemini-3.6-flash":{"draws":20,"losses":27,"wins":15},"google/gemini-3.8-flash":{"draws":7,"losses":15,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":16},"gpt-4.1":{"draws":8,"losses":3,"wins":15},"gpt-5":{"draws":10,"losses":10,"wins":6},"gpt-5.4":{"draws":3,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":11,"losses":12,"wins":25},"gpt-5.4-nano":{"draws":15,"losses":23,"wins":32},"gpt-5.5":{"draws":16,"losses":30,"wins":12},"gpt-5.6-luna":{"draws":11,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":14,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":7},"gpt-6-astra":{"draws":2,"losses":14,"wins":2},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":3,"losses":17,"wins":6},"gpt-6.1-sol":{"draws":1,"losses":21,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":21,"losses":0,"wins":17},"meituan/longcat-2.0":{"draws":5,"losses":8,"wins":25},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":10},"meta/muse-spark-1.2":{"draws":10,"losses":8,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":14,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":28},"o3":{"draws":3,"losses":18,"wins":17},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":6,"losses":16,"wins":14},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":10,"wins":10},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-max":{"draws":5,"losses":8,"wins":9},"qwen/qwen3.8-max-0902":{"draws":4,"losses":12,"wins":4},"stealth/ox-alpha":{"draws":15,"losses":45,"wins":26},"stealth/space-bunny-alpha":{"draws":6,"losses":4,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":21},"thinkingmachines/inkling-small":{"draws":4,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":17,"losses":27,"wins":10},"x-ai/grok-4.6":{"draws":6,"losses":14,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":12,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":18,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":17,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":2},"z-ai/glm-5.2":{"draws":36,"losses":31,"wins":29},"z-ai/glm-5.3":{"draws":10,"losses":18,"wins":6},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":1,"losses":18,"wins":5}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":12,"wins":27},"claude-fable-5":{"draws":20,"losses":28,"wins":44},"claude-fable-5-1":{"draws":8,"losses":37,"wins":13},"claude-opus-4-5":{"draws":47,"losses":38,"wins":117},"claude-opus-4-8":{"draws":35,"losses":20,"wins":67},"claude-opus-5":{"draws":34,"losses":125,"wins":83},"claude-opus-5-5":{"draws":6,"losses":24,"wins":8},"claude-sonnet-5":{"draws":9,"losses":17,"wins":24},"claude-sonnet-5-5":{"draws":11,"losses":20,"wins":29},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":32},"deepseek/deepseek-v4-flash":{"draws":14,"losses":7,"wins":59},"deepseek/deepseek-v4-pro":{"draws":7,"losses":9,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":10,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":6,"wins":27},"fireworks/ember-1":{"draws":11,"losses":8,"wins":33},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":26},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":19},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":54},"google/gemini-3.5-flash-lite":{"draws":19,"losses":11,"wins":106},"google/gemini-3.6-flash":{"draws":29,"losses":33,"wins":88},"google/gemini-3.8-flash":{"draws":13,"losses":17,"wins":32},"google/gemma-4-31b-it":{"draws":12,"losses":0,"wins":36},"gpt-4.1":{"draws":11,"losses":3,"wins":33},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":7,"wins":54},"gpt-5.4":{"draws":10,"losses":6,"wins":50},"gpt-5.4-mini":{"draws":21,"losses":6,"wins":39},"gpt-5.4-nano":{"draws":20,"losses":6,"wins":92},"gpt-5.5":{"draws":28,"losses":33,"wins":83},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":28},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":40},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":36},"gpt-6-astra":{"draws":6,"losses":33,"wins":7},"gpt-6-luna":{"draws":13,"losses":7,"wins":40},"gpt-6-sol":{"draws":10,"losses":8,"wins":18},"gpt-6.1-sol":{"draws":9,"losses":20,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":5,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":22,"losses":1,"wins":41},"meituan/longcat-2.0":{"draws":17,"losses":7,"wins":85},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":21},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":30},"meta/muse-spark-1.3":{"draws":12,"losses":14,"wins":22},"minimax/minimax-m3":{"draws":14,"losses":0,"wins":38},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":22},"moonshotai/kimi-k3":{"draws":16,"losses":22,"wins":46},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":1,"wins":46},"o3":{"draws":6,"losses":6,"wins":72},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":26},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":90},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":47},"qwen/qwen3.7-plus":{"draws":16,"losses":8,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":47},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":25},"qwen/qwen3.8-max":{"draws":15,"losses":12,"wins":31},"qwen/qwen3.8-max-0902":{"draws":12,"losses":10,"wins":24},"stealth/ox-alpha":{"draws":32,"losses":40,"wins":102},"stealth/space-bunny-alpha":{"draws":4,"losses":5,"wins":31},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":40},"tencent/hy3-preview":{"draws":20,"losses":2,"wins":36},"tencent/hy4-preview":{"draws":11,"losses":7,"wins":34},"thinkingmachines/inkling":{"draws":14,"losses":15,"wins":53},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":35},"x-ai/grok-4.5":{"draws":28,"losses":24,"wins":78},"x-ai/grok-4.6":{"draws":11,"losses":25,"wins":44},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":20},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":97},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":2,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":3,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":15},"z-ai/glm-5.2":{"draws":47,"losses":16,"wins":103},"z-ai/glm-5.3":{"draws":8,"losses":23,"wins":23},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":47},"z-ai/glm-5.3-flashx":{"draws":15,"losses":10,"wins":21}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":13},"claude-fable-5":{"draws":6,"losses":6,"wins":20},"claude-fable-5-1":{"draws":4,"losses":16,"wins":8},"claude-opus-4-5":{"draws":11,"losses":5,"wins":24},"claude-opus-4-8":{"draws":5,"losses":5,"wins":16},"claude-opus-5":{"draws":6,"losses":23,"wins":17},"claude-opus-5-5":{"draws":1,"losses":33,"wins":10},"claude-sonnet-5":{"draws":4,"losses":5,"wins":9},"claude-sonnet-5-5":{"draws":7,"losses":11,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":30},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":36},"fireworks/ember-1":{"draws":8,"losses":10,"wins":30},"gemini-3.1-pro-preview":{"draws":6,"losses":4,"wins":36},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":18},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":34},"google/gemini-3.6-flash":{"draws":8,"losses":6,"wins":38},"google/gemini-3.8-flash":{"draws":7,"losses":4,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":14},"gpt-4.1":{"draws":4,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":3,"wins":10},"gpt-5.4":{"draws":7,"losses":1,"wins":16},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":18},"gpt-5.5":{"draws":3,"losses":6,"wins":15},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":18},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":10},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":22},"gpt-6-astra":{"draws":3,"losses":12,"wins":3},"gpt-6-luna":{"draws":13,"losses":1,"wins":38},"gpt-6-sol":{"draws":8,"losses":26,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":32,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":15},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":28},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":20},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":13},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":13},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":0,"losses":7,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":26},"o3":{"draws":3,"losses":2,"wins":35},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":24},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":21},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":11},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":3,"wins":12},"qwen/qwen3.8-27b":{"draws":4,"losses":0,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":10},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":17},"qwen/qwen3.8-max-0902":{"draws":11,"losses":9,"wins":30},"stealth/ox-alpha":{"draws":15,"losses":8,"wins":51},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":11},"tencent/hy4-preview":{"draws":5,"losses":5,"wins":10},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":26},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":17},"x-ai/grok-4.5":{"draws":9,"losses":5,"wins":24},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":18},"x-ai/grok-4.7":{"draws":8,"losses":20,"wins":18},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":5,"losses":3,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":2,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":27},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":14},"z-ai/glm-5.3-flash":{"draws":5,"losses":5,"wins":26},"z-ai/glm-5.3-flashx":{"draws":10,"losses":6,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":21,"wins":22},"claude-fable-5":{"draws":23,"losses":43,"wins":4},"claude-fable-5-1":{"draws":6,"losses":59,"wins":3},"claude-opus-4-5":{"draws":38,"losses":55,"wins":17},"claude-opus-4-8":{"draws":7,"losses":15,"wins":4},"claude-opus-5":{"draws":8,"losses":36,"wins":8},"claude-opus-5-5":{"draws":0,"losses":13,"wins":3},"claude-sonnet-5":{"draws":23,"losses":37,"wins":16},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":29,"losses":21,"wins":32},"deepseek/deepseek-v4-pro":{"draws":23,"losses":23,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":26,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":5,"wins":7},"fireworks/ember-1":{"draws":11,"losses":10,"wins":5},"gemini-3.1-pro-preview":{"draws":10,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":26,"losses":33,"wins":19},"google/gemini-3.5-flash-lite":{"draws":65,"losses":56,"wins":89},"google/gemini-3.6-flash":{"draws":46,"losses":87,"wins":49},"google/gemini-3.8-flash":{"draws":17,"losses":42,"wins":11},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":10},"gpt-4.1":{"draws":1,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":8,"losses":10,"wins":6},"gpt-5.4":{"draws":38,"losses":61,"wins":15},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":8},"gpt-5.5":{"draws":12,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":44,"losses":34,"wins":44},"gpt-5.6-sol":{"draws":18,"losses":95,"wins":9},"gpt-5.6-terra":{"draws":30,"losses":27,"wins":11},"gpt-6-astra":{"draws":3,"losses":59,"wins":2},"gpt-6-luna":{"draws":6,"losses":10,"wins":4},"gpt-6-sol":{"draws":0,"losses":15,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":25,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":26,"losses":3,"wins":27},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":26},"meituan/longcat-2.0":{"draws":24,"losses":13,"wins":31},"meta/muse-glimmer-30b":{"draws":23,"losses":14,"wins":23},"meta/muse-spark-1.2":{"draws":29,"losses":37,"wins":20},"meta/muse-spark-1.3":{"draws":22,"losses":24,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":19,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":36,"losses":45,"wins":17},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":5},"o3":{"draws":10,"losses":58,"wins":56},"openai/gpt-oss-120b":{"draws":29,"losses":10,"wins":29},"poolside/laguna-s-2.1":{"draws":22,"losses":10,"wins":36},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":26,"wins":15},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":10},"qwen/qwen3.8-flash":{"draws":13,"losses":12,"wins":15},"qwen/qwen3.8-max":{"draws":21,"losses":25,"wins":8},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":50,"losses":102,"wins":46},"stealth/space-bunny-alpha":{"draws":6,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":16,"wins":19},"tencent/hy3-preview":{"draws":7,"losses":10,"wins":11},"tencent/hy4-preview":{"draws":20,"losses":28,"wins":12},"thinkingmachines/inkling":{"draws":26,"losses":13,"wins":41},"thinkingmachines/inkling-small":{"draws":18,"losses":19,"wins":35},"x-ai/grok-4.5":{"draws":35,"losses":50,"wins":13},"x-ai/grok-4.6":{"draws":19,"losses":36,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":17,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":14,"wins":2},"z-ai/glm-5.2":{"draws":38,"losses":34,"wins":36},"z-ai/glm-5.3":{"draws":19,"losses":43,"wins":4},"z-ai/glm-5.3-flash":{"draws":17,"losses":30,"wins":21},"z-ai/glm-5.3-flashx":{"draws":6,"losses":5,"wins":3}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":10,"wins":12},"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-fable-5-1":{"draws":0,"losses":26,"wins":0},"claude-opus-4-5":{"draws":6,"losses":14,"wins":12},"claude-opus-4-8":{"draws":7,"losses":17,"wins":2},"claude-opus-5":{"draws":4,"losses":36,"wins":4},"claude-opus-5-5":{"draws":5,"losses":37,"wins":0},"claude-sonnet-5":{"draws":7,"losses":13,"wins":10},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":21},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":10},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":15,"wins":8},"google/gemini-3.5-flash-lite":{"draws":11,"losses":11,"wins":16},"google/gemini-3.6-flash":{"draws":5,"losses":26,"wins":9},"google/gemini-3.8-flash":{"draws":5,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":2,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":10,"wins":9},"gpt-5.4":{"draws":9,"losses":12,"wins":7},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":11,"wins":5},"gpt-5.5":{"draws":7,"losses":5,"wins":8},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":15},"gpt-5.6-sol":{"draws":2,"losses":24,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":10,"wins":9},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":5,"losses":13,"wins":10},"gpt-6-sol":{"draws":3,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":10},"meta/muse-glimmer-30b":{"draws":5,"losses":8,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":6,"wins":1},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":3},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":6},"o3":{"draws":0,"losses":14,"wins":16},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":14},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":20,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":2},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":6},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":10},"stealth/ox-alpha":{"draws":13,"losses":45,"wins":14},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":3,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":8},"thinkingmachines/inkling-small":{"draws":8,"losses":5,"wins":9},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":3},"x-ai/grok-4.6":{"draws":4,"losses":10,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":3,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":19,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":15,"losses":24,"wins":19},"z-ai/glm-5.3":{"draws":7,"losses":16,"wins":1},"z-ai/glm-5.3-flash":{"draws":4,"losses":7,"wins":3},"z-ai/glm-5.3-flashx":{"draws":11,"losses":24,"wins":7}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":0},"claude-fable-5":{"draws":2,"losses":18,"wins":2},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":13,"losses":37,"wins":4},"claude-opus-4-8":{"draws":4,"losses":44,"wins":0},"claude-opus-5":{"draws":4,"losses":56,"wins":6},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":13,"wins":5},"deepseek/deepseek-v4-flash":{"draws":16,"losses":23,"wins":7},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":19,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":11,"wins":0},"fireworks/ember-1":{"draws":3,"losses":9,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":19,"wins":21},"google/gemini-3.5-flash":{"draws":10,"losses":23,"wins":5},"google/gemini-3.5-flash-lite":{"draws":23,"losses":25,"wins":4},"google/gemini-3.6-flash":{"draws":20,"losses":32,"wins":10},"google/gemini-3.8-flash":{"draws":3,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":14,"wins":2},"gpt-4.1":{"draws":4,"losses":10,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":14,"losses":12,"wins":6},"gpt-5.4":{"draws":3,"losses":13,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":16,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":28,"wins":17},"gpt-5.5":{"draws":15,"losses":14,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":10,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":22,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":25,"wins":0},"gpt-6-astra":{"draws":0,"losses":20,"wins":0},"gpt-6-luna":{"draws":2,"losses":11,"wins":5},"gpt-6-sol":{"draws":1,"losses":15,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":24,"losses":13,"wins":3},"meituan/longcat-2.0":{"draws":29,"losses":21,"wins":4},"meta/muse-glimmer-30b":{"draws":6,"losses":14,"wins":6},"meta/muse-spark-1.2":{"draws":1,"losses":24,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":28,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":11,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":22,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":14,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":7},"o3":{"draws":21,"losses":19,"wins":10},"openai/gpt-oss-120b":{"draws":4,"losses":9,"wins":1},"poolside/laguna-s-2.1":{"draws":29,"losses":9,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":24,"wins":3},"qwen/qwen3.7-plus":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":19,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":1},"qwen/qwen3.8-max":{"draws":3,"losses":10,"wins":3},"qwen/qwen3.8-max-0902":{"draws":1,"losses":9,"wins":0},"stealth/ox-alpha":{"draws":8,"losses":46,"wins":10},"stealth/space-bunny-alpha":{"draws":1,"losses":6,"wins":1},"stepfun/step-3.7-flash":{"draws":8,"losses":13,"wins":5},"tencent/hy3-preview":{"draws":5,"losses":15,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":26,"wins":8},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":30,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":18,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":9,"wins":1},"xiaomi/mimo-v2.5":{"draws":28,"losses":37,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":22,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":25,"losses":40,"wins":9},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":15,"wins":1},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":15,"wins":25},"claude-fable-5":{"draws":10,"losses":38,"wins":0},"claude-fable-5-1":{"draws":2,"losses":28,"wins":0},"claude-opus-4-5":{"draws":24,"losses":37,"wins":15},"claude-opus-4-8":{"draws":8,"losses":17,"wins":1},"claude-opus-5":{"draws":4,"losses":28,"wins":2},"claude-opus-5-5":{"draws":1,"losses":19,"wins":0},"claude-sonnet-5":{"draws":19,"losses":34,"wins":11},"claude-sonnet-5-5":{"draws":2,"losses":18,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":11,"losses":22,"wins":15},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":22,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":3},"fireworks/ember-1":{"draws":3,"losses":13,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":10,"wins":6},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":16,"losses":31,"wins":13},"google/gemini-3.5-flash-lite":{"draws":33,"losses":42,"wins":33},"google/gemini-3.6-flash":{"draws":19,"losses":65,"wins":12},"google/gemini-3.8-flash":{"draws":9,"losses":31,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-4.1":{"draws":2,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":4,"losses":17,"wins":3},"gpt-5.4":{"draws":13,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":4},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":9},"gpt-5.5":{"draws":6,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":17,"losses":23,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":20,"losses":31,"wins":9},"gpt-6-astra":{"draws":4,"losses":34,"wins":0},"gpt-6-luna":{"draws":8,"losses":11,"wins":7},"gpt-6-sol":{"draws":3,"losses":19,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":26,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":16,"losses":5,"wins":23},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":18,"wins":18},"meta/muse-glimmer-30b":{"draws":30,"losses":16,"wins":14},"meta/muse-spark-1.2":{"draws":9,"losses":23,"wins":8},"meta/muse-spark-1.3":{"draws":10,"losses":28,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":4},"mistralai/mistral-medium-3-5":{"draws":12,"losses":8,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":11},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":9},"o3":{"draws":9,"losses":34,"wins":29},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":14},"poolside/laguna-s-2.1":{"draws":16,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":22,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":21,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":24,"wins":6},"qwen/qwen3.8-max":{"draws":17,"losses":27,"wins":10},"qwen/qwen3.8-max-0902":{"draws":4,"losses":13,"wins":3},"stealth/ox-alpha":{"draws":43,"losses":88,"wins":37},"stealth/space-bunny-alpha":{"draws":5,"losses":4,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":28,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":15,"wins":22},"thinkingmachines/inkling-small":{"draws":27,"losses":14,"wins":27},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":31,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":19,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":6,"losses":8,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":3,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":10,"wins":2},"z-ai/glm-5.2":{"draws":28,"losses":43,"wins":23},"z-ai/glm-5.3":{"draws":13,"losses":31,"wins":2},"z-ai/glm-5.3-flash":{"draws":22,"losses":21,"wins":9},"z-ai/glm-5.3-flashx":{"draws":7,"losses":14,"wins":1}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":18,"wins":14},"claude-fable-5":{"draws":10,"losses":23,"wins":5},"claude-fable-5-1":{"draws":0,"losses":26,"wins":0},"claude-opus-4-5":{"draws":13,"losses":30,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":1,"losses":35,"wins":6},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":15},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":7},"cohere/north-mini-code":{"draws":8,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":24,"losses":7,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":18,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":3},"fireworks/ember-1":{"draws":6,"losses":4,"wins":4},"gemini-3.1-pro-preview":{"draws":9,"losses":6,"wins":7},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":17},"google/gemini-3.5-flash-lite":{"draws":38,"losses":21,"wins":37},"google/gemini-3.6-flash":{"draws":37,"losses":23,"wins":14},"google/gemini-3.8-flash":{"draws":18,"losses":20,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":6},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":12,"losses":6,"wins":8},"gpt-5.4":{"draws":11,"losses":11,"wins":12},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":10},"gpt-5.5":{"draws":6,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":25,"losses":13,"wins":10},"gpt-6-astra":{"draws":1,"losses":27,"wins":0},"gpt-6-luna":{"draws":7,"losses":11,"wins":6},"gpt-6-sol":{"draws":0,"losses":5,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":23,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":21},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":12},"meta/muse-spark-1.2":{"draws":0,"losses":23,"wins":17},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":10,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":5},"o3":{"draws":16,"losses":16,"wins":18},"openai/gpt-oss-120b":{"draws":16,"losses":13,"wins":17},"poolside/laguna-s-2.1":{"draws":21,"losses":10,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":9},"qwen/qwen3.8-27b":{"draws":15,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":15,"losses":8,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":6},"qwen/qwen3.8-max-0902":{"draws":1,"losses":7,"wins":0},"stealth/ox-alpha":{"draws":47,"losses":54,"wins":37},"stealth/space-bunny-alpha":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":19,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":17},"thinkingmachines/inkling-small":{"draws":27,"losses":16,"wins":15},"x-ai/grok-4.5":{"draws":13,"losses":15,"wins":10},"x-ai/grok-4.6":{"draws":18,"losses":25,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":31,"losses":23,"wins":22},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":17,"losses":26,"wins":7},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":2}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":16,"wins":10},"claude-fable-5":{"draws":12,"losses":24,"wins":4},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-opus-4-5":{"draws":18,"losses":31,"wins":7},"claude-opus-4-8":{"draws":2,"losses":20,"wins":2},"claude-opus-5":{"draws":2,"losses":26,"wins":4},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":14,"losses":16,"wins":8},"claude-sonnet-5-5":{"draws":0,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":14,"wins":22},"deepseek/deepseek-v4-pro":{"draws":30,"losses":9,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":13,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":5,"wins":2},"fireworks/ember-1":{"draws":0,"losses":2,"wins":4},"gemini-3.1-pro-preview":{"draws":2,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":16,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":35,"losses":39,"wins":16},"google/gemini-3.6-flash":{"draws":32,"losses":37,"wins":15},"google/gemini-3.8-flash":{"draws":17,"losses":27,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":10,"losses":10,"wins":4},"gpt-5.4":{"draws":19,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":8},"gpt-5.5":{"draws":6,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":23,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":25,"wins":10},"gpt-6-astra":{"draws":1,"losses":30,"wins":1},"gpt-6-luna":{"draws":8,"losses":11,"wins":3},"gpt-6-sol":{"draws":2,"losses":8,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":13,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":7,"wins":12},"meta/muse-glimmer-30b":{"draws":25,"losses":11,"wins":14},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":28,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":0,"wins":10},"o3":{"draws":18,"losses":15,"wins":21},"openai/gpt-oss-120b":{"draws":14,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":26,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":25,"wins":8},"qwen/qwen3.8-27b":{"draws":18,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":5,"wins":7},"qwen/qwen3.8-max":{"draws":12,"losses":18,"wins":8},"qwen/qwen3.8-max-0902":{"draws":4,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":58,"losses":62,"wins":28},"stealth/space-bunny-alpha":{"draws":2,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":8,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":8},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":9},"thinkingmachines/inkling-small":{"draws":28,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":10},"x-ai/grok-4.6":{"draws":27,"losses":16,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":4,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":31,"losses":22,"wins":25},"z-ai/glm-5.3":{"draws":2,"losses":25,"wins":3},"z-ai/glm-5.3-flash":{"draws":21,"losses":17,"wins":12},"z-ai/glm-5.3-flashx":{"draws":3,"losses":8,"wins":1}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":6},"claude-fable-5":{"draws":8,"losses":24,"wins":0},"claude-fable-5-1":{"draws":1,"losses":28,"wins":1},"claude-opus-4-5":{"draws":16,"losses":11,"wins":5},"claude-opus-4-8":{"draws":7,"losses":13,"wins":4},"claude-opus-5":{"draws":6,"losses":25,"wins":1},"claude-opus-5-5":{"draws":1,"losses":46,"wins":1},"claude-sonnet-5":{"draws":6,"losses":9,"wins":1},"claude-sonnet-5-5":{"draws":12,"losses":28,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":12},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":4,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":6},"fireworks/ember-1":{"draws":18,"losses":25,"wins":3},"gemini-3.1-pro-preview":{"draws":16,"losses":23,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":8,"losses":17,"wins":5},"google/gemini-3.5-flash-lite":{"draws":18,"losses":17,"wins":7},"google/gemini-3.6-flash":{"draws":12,"losses":15,"wins":7},"google/gemini-3.8-flash":{"draws":5,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":5},"gpt-4.1":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":6,"losses":8,"wins":2},"gpt-5.4":{"draws":6,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":10,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":5},"gpt-5.5":{"draws":11,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":12,"losses":5,"wins":5},"gpt-5.6-sol":{"draws":1,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":14,"wins":2},"gpt-6-astra":{"draws":3,"losses":21,"wins":0},"gpt-6-luna":{"draws":16,"losses":18,"wins":12},"gpt-6-sol":{"draws":9,"losses":32,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":11},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":4},"meta/muse-spark-1.2":{"draws":4,"losses":8,"wins":2},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":7},"o3":{"draws":9,"losses":11,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":3},"poolside/laguna-s-2.1":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":5},"qwen/qwen3.8-max-0902":{"draws":19,"losses":20,"wins":7},"stealth/ox-alpha":{"draws":17,"losses":34,"wins":17},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":1},"tencent/hy4-preview":{"draws":5,"losses":17,"wins":4},"thinkingmachines/inkling":{"draws":12,"losses":6,"wins":8},"thinkingmachines/inkling-small":{"draws":10,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":18,"wins":3},"x-ai/grok-4.6":{"draws":9,"losses":18,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":23,"wins":2},"z-ai/glm-5.2":{"draws":18,"losses":14,"wins":4},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":3},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":4},"z-ai/glm-5.3-flashx":{"draws":14,"losses":30,"wins":4}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":9,"wins":4},"claude-fable-5":{"draws":3,"losses":15,"wins":0},"claude-fable-5-1":{"draws":1,"losses":35,"wins":0},"claude-opus-4-5":{"draws":17,"losses":13,"wins":10},"claude-opus-4-8":{"draws":8,"losses":10,"wins":2},"claude-opus-5":{"draws":4,"losses":26,"wins":2},"claude-opus-5-5":{"draws":2,"losses":40,"wins":0},"claude-sonnet-5":{"draws":15,"losses":14,"wins":3},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":11},"deepseek/deepseek-v4-pro":{"draws":8,"losses":7,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":8,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":16,"wins":7},"fireworks/ember-1":{"draws":11,"losses":21,"wins":0},"gemini-3.1-pro-preview":{"draws":20,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":5},"google/gemini-3.5-flash-lite":{"draws":27,"losses":13,"wins":8},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":6},"google/gemini-3.8-flash":{"draws":4,"losses":13,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":6,"wins":2},"gpt-5.4":{"draws":8,"losses":11,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":10,"losses":8,"wins":4},"gpt-5.5":{"draws":13,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":17,"losses":6,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":11,"wins":0},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":11,"losses":10,"wins":7},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":5},"meituan/longcat-2.0":{"draws":16,"losses":5,"wins":9},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":4},"meta/muse-spark-1.2":{"draws":5,"losses":8,"wins":3},"meta/muse-spark-1.3":{"draws":5,"losses":8,"wins":7},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":6},"o3":{"draws":9,"losses":13,"wins":10},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":12,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":7,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-max":{"draws":12,"losses":15,"wins":7},"qwen/qwen3.8-max-0902":{"draws":18,"losses":18,"wins":6},"stealth/ox-alpha":{"draws":29,"losses":39,"wins":8},"stealth/space-bunny-alpha":{"draws":16,"losses":10,"wins":12},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":11,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":15,"losses":5,"wins":4},"thinkingmachines/inkling-small":{"draws":13,"losses":2,"wins":13},"x-ai/grok-4.5":{"draws":3,"losses":14,"wins":3},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":0},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":25,"losses":8,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":24,"losses":14,"wins":20},"z-ai/glm-5.3":{"draws":7,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":15,"wins":1},"z-ai/glm-5.3-flashx":{"draws":15,"losses":23,"wins":8}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":6,"wins":4},"claude-fable-5":{"draws":3,"losses":14,"wins":1},"claude-fable-5-1":{"draws":0,"losses":26,"wins":0},"claude-opus-4-5":{"draws":13,"losses":23,"wins":4},"claude-opus-4-8":{"draws":7,"losses":17,"wins":0},"claude-opus-5":{"draws":5,"losses":25,"wins":2},"claude-opus-5-5":{"draws":3,"losses":39,"wins":0},"claude-sonnet-5":{"draws":11,"losses":13,"wins":4},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":18,"losses":14,"wins":6},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":6},"fireworks/ember-1":{"draws":19,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":8,"losses":16,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":18,"wins":12},"google/gemini-3.6-flash":{"draws":11,"losses":32,"wins":3},"google/gemini-3.8-flash":{"draws":4,"losses":15,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":10,"wins":1},"gpt-5.4":{"draws":3,"losses":10,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":7,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":4},"gpt-5.5":{"draws":11,"losses":14,"wins":1},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":19,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":0},"gpt-6-astra":{"draws":1,"losses":22,"wins":1},"gpt-6-luna":{"draws":6,"losses":13,"wins":5},"gpt-6-sol":{"draws":8,"losses":32,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":5,"wins":3},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":9,"losses":13,"wins":5},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":1},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":1},"meta/muse-spark-1.3":{"draws":7,"losses":13,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":7},"o3":{"draws":7,"losses":17,"wins":2},"openai/gpt-oss-120b":{"draws":14,"losses":10,"wins":2},"poolside/laguna-s-2.1":{"draws":15,"losses":12,"wins":5},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-max-0902":{"draws":13,"losses":29,"wins":2},"stealth/ox-alpha":{"draws":23,"losses":50,"wins":7},"stealth/space-bunny-alpha":{"draws":15,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":1},"thinkingmachines/inkling":{"draws":9,"losses":6,"wins":7},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":12,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":9,"wins":1},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":18,"losses":14,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":20,"wins":9},"z-ai/glm-5.3":{"draws":4,"losses":21,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":8,"wins":0},"z-ai/glm-5.3-flashx":{"draws":10,"losses":33,"wins":3}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":4},"claude-fable-5":{"draws":4,"losses":14,"wins":0},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-opus-4-5":{"draws":15,"losses":30,"wins":3},"claude-opus-4-8":{"draws":5,"losses":20,"wins":1},"claude-opus-5":{"draws":6,"losses":21,"wins":1},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":4,"losses":16,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":15,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":15,"wins":7},"deepseek/deepseek-v4-flash":{"draws":17,"losses":28,"wins":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":3},"fireworks/ember-1":{"draws":6,"losses":16,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":12,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":14,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":21,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":23,"wins":1},"google/gemini-3.6-flash":{"draws":6,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":3,"losses":9,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":10,"wins":12},"gpt-4.1":{"draws":7,"losses":11,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":10,"losses":18,"wins":0},"gpt-5.4":{"draws":2,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":10},"gpt-5.5":{"draws":10,"losses":15,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":15,"wins":0},"gpt-6-astra":{"draws":2,"losses":14,"wins":0},"gpt-6-luna":{"draws":1,"losses":12,"wins":5},"gpt-6-sol":{"draws":1,"losses":15,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":3,"losses":11,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":26,"wins":7},"meta/muse-glimmer-30b":{"draws":8,"losses":10,"wins":2},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":9,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":16,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":34,"wins":6},"o3":{"draws":0,"losses":26,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":11,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":19,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":11,"wins":0},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-max":{"draws":6,"losses":12,"wins":0},"qwen/qwen3.8-max-0902":{"draws":1,"losses":13,"wins":0},"stealth/ox-alpha":{"draws":8,"losses":36,"wins":4},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":21,"wins":3},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":1},"tencent/hy4-preview":{"draws":2,"losses":16,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":17,"wins":9},"thinkingmachines/inkling-small":{"draws":7,"losses":12,"wins":1},"x-ai/grok-4.5":{"draws":4,"losses":20,"wins":2},"x-ai/grok-4.6":{"draws":1,"losses":15,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":16,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":10,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":43,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":21,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":14,"losses":35,"wins":5},"z-ai/glm-5.3":{"draws":2,"losses":12,"wins":0},"z-ai/glm-5.3-flash":{"draws":3,"losses":17,"wins":2},"z-ai/glm-5.3-flashx":{"draws":3,"losses":11,"wins":0}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":31},"claude-fable-5":{"draws":16,"losses":62,"wins":6},"claude-fable-5-1":{"draws":4,"losses":48,"wins":0},"claude-opus-4-5":{"draws":37,"losses":54,"wins":33},"claude-opus-4-8":{"draws":23,"losses":42,"wins":5},"claude-opus-5":{"draws":11,"losses":76,"wins":9},"claude-opus-5-5":{"draws":0,"losses":32,"wins":0},"claude-sonnet-5":{"draws":36,"losses":41,"wins":23},"claude-sonnet-5-5":{"draws":8,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":15},"deepseek/deepseek-v4-flash":{"draws":43,"losses":42,"wins":37},"deepseek/deepseek-v4-pro":{"draws":26,"losses":38,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":39,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":10,"wins":6},"fireworks/ember-1":{"draws":13,"losses":17,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":9},"google/gemini-3.1-flash-lite":{"draws":16,"losses":11,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":7},"google/gemini-3.5-flash-lite":{"draws":62,"losses":65,"wins":49},"google/gemini-3.6-flash":{"draws":49,"losses":73,"wins":32},"google/gemini-3.8-flash":{"draws":23,"losses":58,"wins":3},"google/gemma-4-31b-it":{"draws":15,"losses":9,"wins":10},"gpt-4.1":{"draws":9,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":21,"losses":26,"wins":17},"gpt-5.4":{"draws":14,"losses":52,"wins":16},"gpt-5.4-mini":{"draws":21,"losses":12,"wins":13},"gpt-5.4-nano":{"draws":18,"losses":31,"wins":41},"gpt-5.5":{"draws":21,"losses":30,"wins":11},"gpt-5.6-luna":{"draws":32,"losses":30,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":57,"wins":9},"gpt-5.6-terra":{"draws":32,"losses":37,"wins":13},"gpt-6-astra":{"draws":4,"losses":65,"wins":1},"gpt-6-luna":{"draws":13,"losses":30,"wins":17},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":29,"losses":15,"wins":32},"inclusionai/ling-3.0-flash":{"draws":21,"losses":7,"wins":24},"meituan/longcat-2.0":{"draws":16,"losses":16,"wins":48},"meta/muse-glimmer-30b":{"draws":36,"losses":22,"wins":26},"meta/muse-spark-1.2":{"draws":19,"losses":34,"wins":19},"meta/muse-spark-1.3":{"draws":20,"losses":51,"wins":9},"minimax/minimax-m3":{"draws":11,"losses":16,"wins":11},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":27,"losses":21,"wins":16},"nex-agi/nex-n2-pro":{"draws":15,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":11,"wins":18},"o3":{"draws":24,"losses":41,"wins":55},"openai/gpt-oss-120b":{"draws":25,"losses":24,"wins":25},"poolside/laguna-s-2.1":{"draws":39,"losses":17,"wins":24},"qwen/qwen3.7-max":{"draws":14,"losses":14,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":10,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":45,"wins":12},"qwen/qwen3.8-27b":{"draws":10,"losses":31,"wins":11},"qwen/qwen3.8-flash":{"draws":25,"losses":25,"wins":14},"qwen/qwen3.8-max":{"draws":24,"losses":22,"wins":20},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":3},"stealth/ox-alpha":{"draws":56,"losses":149,"wins":39},"stealth/space-bunny-alpha":{"draws":11,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":21},"tencent/hy3-preview":{"draws":10,"losses":11,"wins":9},"tencent/hy4-preview":{"draws":25,"losses":39,"wins":12},"thinkingmachines/inkling":{"draws":24,"losses":30,"wins":32},"thinkingmachines/inkling-small":{"draws":36,"losses":18,"wins":42},"x-ai/grok-4.5":{"draws":20,"losses":48,"wins":14},"x-ai/grok-4.6":{"draws":25,"losses":56,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":33,"losses":29,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":23,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":62,"losses":62,"wins":40},"z-ai/glm-5.3":{"draws":14,"losses":51,"wins":7},"z-ai/glm-5.3-flash":{"draws":23,"losses":45,"wins":14},"z-ai/glm-5.3-flashx":{"draws":9,"losses":15,"wins":6}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":42,"losses":32,"wins":40},"claude-fable-5":{"draws":24,"losses":76,"wins":18},"claude-fable-5-1":{"draws":9,"losses":96,"wins":1},"claude-opus-4-5":{"draws":81,"losses":81,"wins":80},"claude-opus-4-8":{"draws":13,"losses":34,"wins":13},"claude-opus-5":{"draws":20,"losses":115,"wins":11},"claude-opus-5-5":{"draws":2,"losses":38,"wins":2},"claude-sonnet-5":{"draws":69,"losses":99,"wins":54},"claude-sonnet-5-5":{"draws":12,"losses":28,"wins":12},"cohere/north-mini-code":{"draws":18,"losses":4,"wins":16},"deepseek/deepseek-v4-flash":{"draws":63,"losses":42,"wins":51},"deepseek/deepseek-v4-pro":{"draws":47,"losses":54,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":45,"losses":44,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":12},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":18},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":46,"losses":51,"wins":37},"google/gemini-3.5-flash-lite":{"draws":142,"losses":119,"wins":127},"google/gemini-3.6-flash":{"draws":156,"losses":186,"wins":100},"google/gemini-3.8-flash":{"draws":33,"losses":81,"wins":6},"google/gemma-4-31b-it":{"draws":9,"losses":11,"wins":14},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":0,"losses":7,"wins":7},"gpt-5":{"draws":28,"losses":18,"wins":12},"gpt-5.4":{"draws":58,"losses":111,"wins":23},"gpt-5.4-mini":{"draws":17,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":30,"losses":27,"wins":31},"gpt-5.5":{"draws":26,"losses":25,"wins":5},"gpt-5.6-luna":{"draws":72,"losses":69,"wins":83},"gpt-5.6-sol":{"draws":21,"losses":155,"wins":26},"gpt-5.6-terra":{"draws":49,"losses":42,"wins":43},"gpt-6-astra":{"draws":3,"losses":97,"wins":0},"gpt-6-luna":{"draws":17,"losses":24,"wins":17},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":5,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":10,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":51,"losses":8,"wins":37},"inclusionai/ling-3.0-flash":{"draws":61,"losses":7,"wins":74},"meituan/longcat-2.0":{"draws":57,"losses":50,"wins":100},"meta/muse-glimmer-30b":{"draws":56,"losses":19,"wins":37},"meta/muse-spark-1.2":{"draws":44,"losses":64,"wins":34},"meta/muse-spark-1.3":{"draws":28,"losses":52,"wins":26},"minimax/minimax-m3":{"draws":12,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":31,"losses":12,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":8},"moonshotai/kimi-k3":{"draws":81,"losses":109,"wins":46},"nex-agi/nex-n2-pro":{"draws":19,"losses":10,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":6,"wins":18},"o3":{"draws":51,"losses":101,"wins":116},"openai/gpt-oss-120b":{"draws":42,"losses":27,"wins":39},"poolside/laguna-s-2.1":{"draws":88,"losses":53,"wins":61},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":16},"qwen/qwen3.7-plus":{"draws":14,"losses":15,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":48,"wins":26},"qwen/qwen3.8-27b":{"draws":17,"losses":35,"wins":18},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":25},"qwen/qwen3.8-max":{"draws":35,"losses":45,"wins":38},"qwen/qwen3.8-max-0902":{"draws":19,"losses":17,"wins":4},"stealth/ox-alpha":{"draws":100,"losses":169,"wins":89},"stealth/space-bunny-alpha":{"draws":15,"losses":2,"wins":17},"stepfun/step-3.7-flash":{"draws":20,"losses":18,"wins":26},"tencent/hy3-preview":{"draws":21,"losses":15,"wins":6},"tencent/hy4-preview":{"draws":42,"losses":52,"wins":24},"thinkingmachines/inkling":{"draws":88,"losses":63,"wins":79},"thinkingmachines/inkling-small":{"draws":57,"losses":31,"wins":54},"x-ai/grok-4.5":{"draws":55,"losses":115,"wins":60},"x-ai/grok-4.6":{"draws":32,"losses":73,"wins":23},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":41,"losses":18,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":17,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":73,"losses":54,"wins":49},"z-ai/glm-5.3":{"draws":15,"losses":76,"wins":11},"z-ai/glm-5.3-flash":{"draws":37,"losses":82,"wins":27},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":8}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":45,"losses":41,"wins":48},"claude-fable-5":{"draws":35,"losses":63,"wins":16},"claude-fable-5-1":{"draws":9,"losses":99,"wins":0},"claude-opus-4-5":{"draws":93,"losses":104,"wins":53},"claude-opus-4-8":{"draws":23,"losses":28,"wins":15},"claude-opus-5":{"draws":16,"losses":108,"wins":16},"claude-opus-5-5":{"draws":1,"losses":43,"wins":0},"claude-sonnet-5":{"draws":75,"losses":94,"wins":55},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":7},"cohere/north-mini-code":{"draws":20,"losses":6,"wins":20},"deepseek/deepseek-v4-flash":{"draws":71,"losses":47,"wins":60},"deepseek/deepseek-v4-pro":{"draws":44,"losses":50,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":47,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":11,"wins":6},"fireworks/ember-1":{"draws":17,"losses":17,"wins":4},"gemini-3.1-pro-preview":{"draws":13,"losses":21,"wins":10},"google/gemini-3.1-flash-lite":{"draws":17,"losses":8,"wins":17},"google/gemini-3.5-flash":{"draws":47,"losses":55,"wins":28},"google/gemini-3.5-flash-lite":{"draws":221,"losses":142,"wins":147},"google/gemini-3.6-flash":{"draws":102,"losses":180,"wins":62},"google/gemini-3.8-flash":{"draws":34,"losses":67,"wins":16},"google/gemma-4-31b-it":{"draws":16,"losses":13,"wins":5},"gpt-4.1":{"draws":14,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":10,"wins":0},"gpt-5":{"draws":23,"losses":25,"wins":12},"gpt-5.4":{"draws":63,"losses":94,"wins":37},"gpt-5.4-mini":{"draws":29,"losses":11,"wins":14},"gpt-5.4-nano":{"draws":30,"losses":34,"wins":20},"gpt-5.5":{"draws":32,"losses":30,"wins":16},"gpt-5.6-luna":{"draws":99,"losses":64,"wins":79},"gpt-5.6-sol":{"draws":34,"losses":145,"wins":19},"gpt-5.6-terra":{"draws":57,"losses":49,"wins":30},"gpt-6-astra":{"draws":7,"losses":89,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":15},"gpt-6-sol":{"draws":3,"losses":28,"wins":1},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":51,"losses":9,"wins":42},"inclusionai/ling-3.0-flash":{"draws":81,"losses":37,"wins":58},"meituan/longcat-2.0":{"draws":67,"losses":47,"wins":80},"meta/muse-glimmer-30b":{"draws":67,"losses":23,"wins":46},"meta/muse-spark-1.2":{"draws":38,"losses":93,"wins":29},"meta/muse-spark-1.3":{"draws":33,"losses":57,"wins":18},"minimax/minimax-m3":{"draws":14,"losses":8,"wins":28},"mistralai/mistral-medium-3-5":{"draws":45,"losses":8,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":9,"wins":5},"moonshotai/kimi-k3":{"draws":101,"losses":121,"wins":30},"nex-agi/nex-n2-pro":{"draws":22,"losses":7,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":5,"wins":16},"o3":{"draws":64,"losses":165,"wins":77},"openai/gpt-oss-120b":{"draws":59,"losses":22,"wins":39},"poolside/laguna-s-2.1":{"draws":125,"losses":44,"wins":57},"qwen/qwen3.7-max":{"draws":18,"losses":10,"wins":20},"qwen/qwen3.7-plus":{"draws":21,"losses":14,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":47,"wins":25},"qwen/qwen3.8-27b":{"draws":19,"losses":30,"wins":35},"qwen/qwen3.8-flash":{"draws":50,"losses":22,"wins":26},"qwen/qwen3.8-max":{"draws":49,"losses":68,"wins":29},"qwen/qwen3.8-max-0902":{"draws":11,"losses":12,"wins":5},"stealth/ox-alpha":{"draws":118,"losses":179,"wins":100},"stealth/space-bunny-alpha":{"draws":14,"losses":16,"wins":14},"stepfun/step-3.7-flash":{"draws":21,"losses":17,"wins":32},"tencent/hy3-preview":{"draws":22,"losses":8,"wins":14},"tencent/hy4-preview":{"draws":47,"losses":69,"wins":26},"thinkingmachines/inkling":{"draws":118,"losses":34,"wins":114},"thinkingmachines/inkling-small":{"draws":70,"losses":39,"wins":42},"x-ai/grok-4.5":{"draws":60,"losses":123,"wins":69},"x-ai/grok-4.6":{"draws":45,"losses":66,"wins":15},"x-ai/grok-4.7":{"draws":0,"losses":28,"wins":2},"x-ai/grok-build-0.1":{"draws":11,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":47,"losses":20,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":17,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":20,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":4},"z-ai/glm-5.2":{"draws":71,"losses":59,"wins":48},"z-ai/glm-5.3":{"draws":23,"losses":75,"wins":8},"z-ai/glm-5.3-flash":{"draws":46,"losses":73,"wins":25},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":9}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":13,"wins":25},"claude-fable-5":{"draws":8,"losses":44,"wins":12},"claude-fable-5-1":{"draws":7,"losses":65,"wins":2},"claude-opus-4-5":{"draws":25,"losses":16,"wins":35},"claude-opus-4-8":{"draws":8,"losses":19,"wins":7},"claude-opus-5":{"draws":12,"losses":32,"wins":12},"claude-opus-5-5":{"draws":3,"losses":15,"wins":0},"claude-sonnet-5":{"draws":21,"losses":10,"wins":29},"claude-sonnet-5-5":{"draws":4,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":7,"wins":15},"deepseek/deepseek-v4-flash":{"draws":18,"losses":16,"wins":44},"deepseek/deepseek-v4-pro":{"draws":14,"losses":13,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":3},"fireworks/ember-1":{"draws":9,"losses":2,"wins":3},"gemini-3.1-pro-preview":{"draws":9,"losses":5,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":32,"wins":29},"google/gemini-3.5-flash-lite":{"draws":20,"losses":8,"wins":64},"google/gemini-3.6-flash":{"draws":23,"losses":42,"wins":43},"google/gemini-3.8-flash":{"draws":16,"losses":16,"wins":14},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":5,"wins":16},"gpt-5.4":{"draws":17,"losses":22,"wins":21},"gpt-5.4-mini":{"draws":5,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":23},"gpt-5.5":{"draws":7,"losses":6,"wins":7},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":22},"gpt-5.6-sol":{"draws":9,"losses":36,"wins":21},"gpt-5.6-terra":{"draws":29,"losses":17,"wins":28},"gpt-6-astra":{"draws":8,"losses":53,"wins":5},"gpt-6-luna":{"draws":10,"losses":11,"wins":7},"gpt-6-sol":{"draws":3,"losses":13,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":16,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":22,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":19},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":24},"meta/muse-glimmer-30b":{"draws":20,"losses":7,"wins":31},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":17},"meta/muse-spark-1.3":{"draws":7,"losses":23,"wins":26},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":11},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":19,"losses":16,"wins":27},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":14},"o3":{"draws":10,"losses":19,"wins":39},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":14},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":21,"wins":22},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":22},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":18},"qwen/qwen3.8-max":{"draws":15,"losses":18,"wins":25},"qwen/qwen3.8-max-0902":{"draws":7,"losses":1,"wins":4},"stealth/ox-alpha":{"draws":56,"losses":79,"wins":72},"stealth/space-bunny-alpha":{"draws":6,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":13},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":26,"wins":16},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":21},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":33},"x-ai/grok-4.5":{"draws":12,"losses":29,"wins":19},"x-ai/grok-4.6":{"draws":22,"losses":26,"wins":16},"x-ai/grok-4.7":{"draws":2,"losses":15,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":14,"losses":1,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":1,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":25,"losses":31,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":26,"wins":26},"z-ai/glm-5.3-flashx":{"draws":4,"losses":11,"wins":5}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":5,"wins":3},"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-fable-5-1":{"draws":2,"losses":20,"wins":0},"claude-opus-4-5":{"draws":22,"losses":38,"wins":4},"claude-opus-4-8":{"draws":18,"losses":33,"wins":1},"claude-opus-5":{"draws":10,"losses":50,"wins":10},"claude-opus-5-5":{"draws":0,"losses":26,"wins":0},"claude-sonnet-5":{"draws":6,"losses":18,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":18,"wins":2},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":18,"losses":29,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":12,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":13,"wins":3},"fireworks/ember-1":{"draws":5,"losses":13,"wins":0},"gemini-3.1-pro-preview":{"draws":8,"losses":15,"wins":5},"google/gemini-3.1-flash-lite":{"draws":12,"losses":19,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":5},"google/gemini-3.5-flash-lite":{"draws":22,"losses":19,"wins":13},"google/gemini-3.6-flash":{"draws":22,"losses":19,"wins":11},"google/gemini-3.8-flash":{"draws":5,"losses":15,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":7,"wins":5},"gpt-4.1":{"draws":8,"losses":11,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":19,"wins":5},"gpt-5.4":{"draws":4,"losses":14,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":8},"gpt-5.4-nano":{"draws":7,"losses":25,"wins":20},"gpt-5.5":{"draws":14,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":19,"wins":2},"gpt-6-astra":{"draws":0,"losses":22,"wins":0},"gpt-6-luna":{"draws":6,"losses":16,"wins":2},"gpt-6-sol":{"draws":0,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":10},"inclusionai/ling-3.0-flash":{"draws":16,"losses":8,"wins":20},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":15},"meta/muse-glimmer-30b":{"draws":6,"losses":4,"wins":4},"meta/muse-spark-1.2":{"draws":9,"losses":19,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":16,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":22,"wins":4},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":24,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":14,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":16},"o3":{"draws":12,"losses":25,"wins":9},"openai/gpt-oss-120b":{"draws":6,"losses":10,"wins":0},"poolside/laguna-s-2.1":{"draws":6,"losses":22,"wins":12},"qwen/qwen3.7-max":{"draws":4,"losses":19,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":14,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":9,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":0},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":13,"wins":3},"stealth/ox-alpha":{"draws":12,"losses":49,"wins":3},"stealth/space-bunny-alpha":{"draws":6,"losses":12,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":20,"wins":6},"tencent/hy3-preview":{"draws":16,"losses":16,"wins":6},"tencent/hy4-preview":{"draws":4,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":12,"losses":27,"wins":5},"thinkingmachines/inkling-small":{"draws":8,"losses":7,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":24,"wins":0},"x-ai/grok-4.6":{"draws":7,"losses":18,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":11,"losses":14,"wins":1},"xiaomi/mimo-v2.5":{"draws":33,"losses":51,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":18,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":0},"z-ai/glm-5.2":{"draws":20,"losses":25,"wins":9},"z-ai/glm-5.3":{"draws":1,"losses":18,"wins":1},"z-ai/glm-5.3-flash":{"draws":4,"losses":19,"wins":1},"z-ai/glm-5.3-flashx":{"draws":4,"losses":19,"wins":3}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":10},"claude-fable-5":{"draws":5,"losses":24,"wins":9},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-opus-4-5":{"draws":46,"losses":22,"wins":22},"claude-opus-4-8":{"draws":24,"losses":33,"wins":7},"claude-opus-5":{"draws":16,"losses":97,"wins":8},"claude-opus-5-5":{"draws":4,"losses":33,"wins":1},"claude-sonnet-5":{"draws":9,"losses":11,"wins":8},"claude-sonnet-5-5":{"draws":2,"losses":19,"wins":1},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":34,"losses":12,"wins":28},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":7},"fireworks/ember-1":{"draws":4,"losses":6,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":6},"google/gemini-3.1-flash-lite":{"draws":18,"losses":7,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":10},"google/gemini-3.5-flash-lite":{"draws":27,"losses":34,"wins":27},"google/gemini-3.6-flash":{"draws":24,"losses":38,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":17,"wins":4},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":21,"losses":13,"wins":18},"gpt-5.4":{"draws":6,"losses":15,"wins":3},"gpt-5.4-mini":{"draws":23,"losses":26,"wins":11},"gpt-5.4-nano":{"draws":14,"losses":29,"wins":25},"gpt-5.5":{"draws":21,"losses":21,"wins":14},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":7},"gpt-5.6-sol":{"draws":10,"losses":21,"wins":5},"gpt-5.6-terra":{"draws":17,"losses":6,"wins":11},"gpt-6-astra":{"draws":4,"losses":30,"wins":0},"gpt-6-luna":{"draws":11,"losses":12,"wins":15},"gpt-6-sol":{"draws":6,"losses":26,"wins":6},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":9,"losses":9,"wins":12},"inclusionai/ling-3.0-flash":{"draws":20,"losses":1,"wins":25},"meituan/longcat-2.0":{"draws":22,"losses":13,"wins":35},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":9},"meta/muse-spark-1.2":{"draws":6,"losses":11,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":1},"minimax/minimax-m3":{"draws":14,"losses":14,"wins":24},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":9,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":5},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":11,"wins":25},"o3":{"draws":12,"losses":20,"wins":26},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":18,"losses":16,"wins":20},"qwen/qwen3.7-max":{"draws":19,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":12,"wins":6},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":6,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":5},"stealth/ox-alpha":{"draws":30,"losses":50,"wins":20},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":12,"losses":8,"wins":16},"tencent/hy3-preview":{"draws":27,"losses":6,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":14,"losses":29,"wins":17},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":8},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":11},"x-ai/grok-4.6":{"draws":17,"losses":22,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":0},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":11},"xiaomi/mimo-v2.5":{"draws":48,"losses":26,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":12,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":29,"losses":44,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":21,"wins":9},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":6}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":8},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":8,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":5,"wins":1},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":8,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":6},"fireworks/ember-1":{"draws":2,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":15,"wins":18},"google/gemini-3.6-flash":{"draws":18,"losses":4,"wins":10},"google/gemini-3.8-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":4},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":6,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":8,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":0,"losses":1,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":6},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":4},"meta/muse-spark-1.2":{"draws":3,"losses":10,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":8,"wins":16},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":8,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":4},"stealth/ox-alpha":{"draws":2,"losses":23,"wins":1},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":14},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":4,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":5,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":5},"claude-fable-5":{"draws":6,"losses":23,"wins":3},"claude-fable-5-1":{"draws":0,"losses":24,"wins":0},"claude-opus-4-5":{"draws":14,"losses":11,"wins":15},"claude-opus-4-8":{"draws":6,"losses":11,"wins":3},"claude-opus-5":{"draws":11,"losses":54,"wins":3},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":8,"losses":10,"wins":2},"claude-sonnet-5-5":{"draws":2,"losses":4,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":20,"losses":8,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":13,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":4,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":1,"wins":5},"fireworks/ember-1":{"draws":0,"losses":9,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":13,"losses":15,"wins":8},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":18},"google/gemini-3.6-flash":{"draws":9,"losses":15,"wins":12},"google/gemini-3.8-flash":{"draws":12,"losses":8,"wins":8},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":6,"losses":2,"wins":4},"gpt-5":{"draws":7,"losses":6,"wins":7},"gpt-5.4":{"draws":9,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":13},"gpt-5.5":{"draws":18,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":18,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":17,"wins":5},"gpt-6-astra":{"draws":2,"losses":20,"wins":0},"gpt-6-luna":{"draws":6,"losses":9,"wins":3},"gpt-6-sol":{"draws":2,"losses":10,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":4},"inclusionai/ling-3.0-flash":{"draws":7,"losses":7,"wins":4},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":14},"meta/muse-glimmer-30b":{"draws":8,"losses":6,"wins":6},"meta/muse-spark-1.2":{"draws":6,"losses":10,"wins":2},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":12,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":5,"wins":9},"o3":{"draws":8,"losses":8,"wins":14},"openai/gpt-oss-120b":{"draws":11,"losses":4,"wins":9},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":9},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-flash":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":6,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":2},"stealth/ox-alpha":{"draws":23,"losses":41,"wins":10},"stealth/space-bunny-alpha":{"draws":1,"losses":4,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":9,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":7,"wins":12},"thinkingmachines/inkling-small":{"draws":11,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":15,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":16,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":23,"losses":8,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":19,"wins":20},"z-ai/glm-5.3":{"draws":6,"losses":15,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":17,"wins":10},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":0}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":16,"wins":15},"claude-fable-5":{"draws":16,"losses":42,"wins":14},"claude-fable-5-1":{"draws":6,"losses":57,"wins":3},"claude-opus-4-5":{"draws":32,"losses":34,"wins":32},"claude-opus-4-8":{"draws":4,"losses":10,"wins":8},"claude-opus-5":{"draws":5,"losses":37,"wins":4},"claude-opus-5-5":{"draws":3,"losses":19,"wins":0},"claude-sonnet-5":{"draws":40,"losses":26,"wins":50},"claude-sonnet-5-5":{"draws":7,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":30,"losses":11,"wins":29},"deepseek/deepseek-v4-pro":{"draws":20,"losses":25,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":22,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":5,"wins":4},"fireworks/ember-1":{"draws":12,"losses":3,"wins":5},"gemini-3.1-pro-preview":{"draws":5,"losses":9,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":14},"google/gemini-3.5-flash":{"draws":16,"losses":29,"wins":23},"google/gemini-3.5-flash-lite":{"draws":67,"losses":39,"wins":78},"google/gemini-3.6-flash":{"draws":46,"losses":71,"wins":61},"google/gemini-3.8-flash":{"draws":21,"losses":35,"wins":16},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":9},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":12,"losses":11,"wins":7},"gpt-5.4":{"draws":23,"losses":70,"wins":3},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":9},"gpt-5.5":{"draws":13,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":61,"losses":30,"wins":39},"gpt-5.6-sol":{"draws":25,"losses":59,"wins":24},"gpt-5.6-terra":{"draws":29,"losses":15,"wins":14},"gpt-6-astra":{"draws":1,"losses":59,"wins":6},"gpt-6-luna":{"draws":14,"losses":10,"wins":10},"gpt-6-sol":{"draws":5,"losses":13,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":23,"losses":2,"wins":15},"inclusionai/ling-3.0-flash":{"draws":13,"losses":6,"wins":17},"meituan/longcat-2.0":{"draws":29,"losses":15,"wins":24},"meta/muse-glimmer-30b":{"draws":21,"losses":16,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":43,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":33,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":20,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":34,"losses":30,"wins":36},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":1,"wins":9},"o3":{"draws":20,"losses":36,"wins":50},"openai/gpt-oss-120b":{"draws":25,"losses":9,"wins":20},"poolside/laguna-s-2.1":{"draws":45,"losses":4,"wins":21},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":9},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":29,"wins":16},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":19},"qwen/qwen3.8-flash":{"draws":14,"losses":18,"wins":8},"qwen/qwen3.8-max":{"draws":22,"losses":23,"wins":13},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":3},"stealth/ox-alpha":{"draws":63,"losses":85,"wins":48},"stealth/space-bunny-alpha":{"draws":8,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":19},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":18,"losses":25,"wins":9},"thinkingmachines/inkling":{"draws":25,"losses":9,"wins":40},"thinkingmachines/inkling-small":{"draws":32,"losses":8,"wins":20},"x-ai/grok-4.5":{"draws":24,"losses":41,"wins":35},"x-ai/grok-4.6":{"draws":24,"losses":37,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":11,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":7,"wins":2},"z-ai/glm-5.2":{"draws":37,"losses":27,"wins":32},"z-ai/glm-5.3":{"draws":13,"losses":34,"wins":13},"z-ai/glm-5.3-flash":{"draws":19,"losses":33,"wins":22},"z-ai/glm-5.3-flashx":{"draws":9,"losses":10,"wins":1}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":3},"claude-fable-5":{"draws":7,"losses":31,"wins":0},"claude-fable-5-1":{"draws":0,"losses":24,"wins":0},"claude-opus-4-5":{"draws":40,"losses":41,"wins":15},"claude-opus-4-8":{"draws":22,"losses":33,"wins":5},"claude-opus-5":{"draws":21,"losses":60,"wins":1},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":12,"losses":12,"wins":2},"claude-sonnet-5-5":{"draws":1,"losses":18,"wins":3},"cohere/north-mini-code":{"draws":16,"losses":9,"wins":11},"deepseek/deepseek-v4-flash":{"draws":35,"losses":20,"wins":7},"deepseek/deepseek-v4-pro":{"draws":14,"losses":8,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":7,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":12,"wins":4},"fireworks/ember-1":{"draws":11,"losses":12,"wins":3},"gemini-3.1-pro-preview":{"draws":18,"losses":9,"wins":3},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":20},"google/gemini-3.5-flash":{"draws":22,"losses":25,"wins":1},"google/gemini-3.5-flash-lite":{"draws":29,"losses":31,"wins":14},"google/gemini-3.6-flash":{"draws":37,"losses":32,"wins":7},"google/gemini-3.8-flash":{"draws":10,"losses":12,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":20,"wins":5},"gpt-4.1":{"draws":11,"losses":4,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":30,"losses":19,"wins":3},"gpt-5.4":{"draws":8,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":3},"gpt-5.4-nano":{"draws":32,"losses":39,"wins":9},"gpt-5.5":{"draws":28,"losses":26,"wins":4},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":4},"gpt-5.6-sol":{"draws":10,"losses":18,"wins":0},"gpt-5.6-terra":{"draws":18,"losses":18,"wins":6},"gpt-6-astra":{"draws":0,"losses":22,"wins":0},"gpt-6-luna":{"draws":10,"losses":17,"wins":3},"gpt-6-sol":{"draws":2,"losses":12,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":30,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":36,"losses":11,"wins":11},"meituan/longcat-2.0":{"draws":27,"losses":24,"wins":11},"meta/muse-glimmer-30b":{"draws":14,"losses":3,"wins":3},"meta/muse-spark-1.2":{"draws":4,"losses":16,"wins":0},"meta/muse-spark-1.3":{"draws":10,"losses":19,"wins":1},"minimax/minimax-m3":{"draws":9,"losses":26,"wins":7},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":24,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":14,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":16,"wins":7},"o3":{"draws":14,"losses":20,"wins":6},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":5},"poolside/laguna-s-2.1":{"draws":29,"losses":13,"wins":4},"qwen/qwen3.7-max":{"draws":16,"losses":14,"wins":2},"qwen/qwen3.7-plus":{"draws":10,"losses":18,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":17,"wins":0},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":17,"losses":10,"wins":3},"qwen/qwen3.8-max-0902":{"draws":6,"losses":12,"wins":0},"stealth/ox-alpha":{"draws":38,"losses":46,"wins":4},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":0},"stepfun/step-3.7-flash":{"draws":15,"losses":13,"wins":4},"tencent/hy3-preview":{"draws":15,"losses":14,"wins":5},"tencent/hy4-preview":{"draws":17,"losses":13,"wins":0},"thinkingmachines/inkling":{"draws":25,"losses":15,"wins":16},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":23,"wins":1},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":0},"x-ai/grok-4.7":{"draws":2,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":57,"losses":41,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":14,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":0},"z-ai/glm-5.2":{"draws":53,"losses":31,"wins":8},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":0},"z-ai/glm-5.3-flash":{"draws":16,"losses":15,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":0}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":22,"wins":15},"claude-fable-5":{"draws":8,"losses":41,"wins":3},"claude-fable-5-1":{"draws":1,"losses":43,"wins":0},"claude-opus-4-5":{"draws":40,"losses":81,"wins":31},"claude-opus-4-8":{"draws":24,"losses":56,"wins":18},"claude-opus-5":{"draws":23,"losses":131,"wins":2},"claude-opus-5-5":{"draws":0,"losses":26,"wins":0},"claude-sonnet-5":{"draws":14,"losses":19,"wins":9},"claude-sonnet-5-5":{"draws":6,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":32},"deepseek/deepseek-v4-flash":{"draws":27,"losses":42,"wins":27},"deepseek/deepseek-v4-pro":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":13,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":14,"wins":2},"fireworks/ember-1":{"draws":9,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":8},"google/gemini-3.1-flash-lite":{"draws":10,"losses":25,"wins":35},"google/gemini-3.5-flash":{"draws":17,"losses":45,"wins":14},"google/gemini-3.5-flash-lite":{"draws":42,"losses":31,"wins":35},"google/gemini-3.6-flash":{"draws":33,"losses":41,"wins":20},"google/gemini-3.8-flash":{"draws":9,"losses":35,"wins":6},"google/gemma-4-31b-it":{"draws":2,"losses":16,"wins":24},"gpt-4.1":{"draws":11,"losses":12,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":16,"losses":34,"wins":12},"gpt-5.4":{"draws":11,"losses":27,"wins":10},"gpt-5.4-mini":{"draws":36,"losses":16,"wins":28},"gpt-5.4-nano":{"draws":35,"losses":38,"wins":37},"gpt-5.5":{"draws":31,"losses":48,"wins":25},"gpt-5.6-luna":{"draws":20,"losses":21,"wins":11},"gpt-5.6-sol":{"draws":12,"losses":35,"wins":3},"gpt-5.6-terra":{"draws":12,"losses":19,"wins":11},"gpt-6-astra":{"draws":2,"losses":44,"wins":0},"gpt-6-luna":{"draws":10,"losses":24,"wins":6},"gpt-6-sol":{"draws":5,"losses":13,"wins":0},"gpt-6.1-sol":{"draws":4,"losses":28,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":15},"inclusionai/ling-3.0-flash":{"draws":35,"losses":9,"wins":28},"meituan/longcat-2.0":{"draws":24,"losses":32,"wins":32},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":9},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":7},"meta/muse-spark-1.3":{"draws":7,"losses":29,"wins":2},"minimax/minimax-m3":{"draws":20,"losses":26,"wins":22},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":3,"wins":10},"moonshotai/kimi-k3":{"draws":18,"losses":40,"wins":10},"nex-agi/nex-n2-pro":{"draws":18,"losses":22,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":15,"wins":29},"o3":{"draws":9,"losses":39,"wins":36},"openai/gpt-oss-120b":{"draws":7,"losses":12,"wins":7},"poolside/laguna-s-2.1":{"draws":40,"losses":28,"wins":26},"qwen/qwen3.7-max":{"draws":22,"losses":27,"wins":21},"qwen/qwen3.7-plus":{"draws":10,"losses":20,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":28,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":10},"qwen/qwen3.8-flash":{"draws":16,"losses":14,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":3},"stealth/ox-alpha":{"draws":31,"losses":78,"wins":31},"stealth/space-bunny-alpha":{"draws":7,"losses":15,"wins":8},"stepfun/step-3.7-flash":{"draws":14,"losses":17,"wins":25},"tencent/hy3-preview":{"draws":19,"losses":28,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":7},"thinkingmachines/inkling":{"draws":17,"losses":32,"wins":23},"thinkingmachines/inkling-small":{"draws":19,"losses":11,"wins":16},"x-ai/grok-4.5":{"draws":16,"losses":50,"wins":12},"x-ai/grok-4.6":{"draws":12,"losses":37,"wins":9},"x-ai/grok-4.7":{"draws":9,"losses":29,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":10,"wins":22},"xiaomi/mimo-v2.5":{"draws":38,"losses":64,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":30,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":51,"losses":47,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":33,"wins":11},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":7}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":7,"wins":10},"claude-fable-5":{"draws":11,"losses":17,"wins":8},"claude-fable-5-1":{"draws":1,"losses":27,"wins":0},"claude-opus-4-5":{"draws":42,"losses":32,"wins":16},"claude-opus-4-8":{"draws":21,"losses":23,"wins":6},"claude-opus-5":{"draws":23,"losses":85,"wins":0},"claude-opus-5-5":{"draws":2,"losses":26,"wins":0},"claude-sonnet-5":{"draws":13,"losses":7,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":16,"wins":2},"cohere/north-mini-code":{"draws":12,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":25,"losses":6,"wins":11},"deepseek/deepseek-v4-pro":{"draws":12,"losses":10,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":11,"wins":4},"fireworks/ember-1":{"draws":15,"losses":9,"wins":2},"gemini-3.1-pro-preview":{"draws":14,"losses":8,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":17,"losses":14,"wins":7},"google/gemini-3.5-flash-lite":{"draws":37,"losses":6,"wins":21},"google/gemini-3.6-flash":{"draws":26,"losses":27,"wins":17},"google/gemini-3.8-flash":{"draws":3,"losses":10,"wins":5},"google/gemma-4-31b-it":{"draws":13,"losses":6,"wins":9},"gpt-4.1":{"draws":12,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":22,"losses":18,"wins":8},"gpt-5.4":{"draws":11,"losses":15,"wins":8},"gpt-5.4-mini":{"draws":20,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":23,"losses":8,"wins":27},"gpt-5.5":{"draws":19,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":14,"losses":8,"wins":10},"gpt-5.6-sol":{"draws":8,"losses":12,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":10,"wins":5},"gpt-6-astra":{"draws":0,"losses":24,"wins":0},"gpt-6-luna":{"draws":12,"losses":11,"wins":7},"gpt-6-sol":{"draws":9,"losses":19,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":21,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":35,"losses":2,"wins":5},"meituan/longcat-2.0":{"draws":38,"losses":13,"wins":14},"meta/muse-glimmer-30b":{"draws":14,"losses":3,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":11,"wins":6},"meta/muse-spark-1.3":{"draws":7,"losses":9,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":11,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":17,"wins":7},"nex-agi/nex-n2-pro":{"draws":16,"losses":2,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":6,"wins":13},"o3":{"draws":20,"losses":10,"wins":14},"openai/gpt-oss-120b":{"draws":15,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":10},"qwen/qwen3.7-max":{"draws":19,"losses":11,"wins":4},"qwen/qwen3.7-plus":{"draws":17,"losses":4,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":6,"wins":5},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":2},"qwen/qwen3.8-flash":{"draws":10,"losses":3,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":4},"qwen/qwen3.8-max-0902":{"draws":16,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":18,"losses":36,"wins":18},"stealth/space-bunny-alpha":{"draws":11,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":8,"losses":12,"wins":6},"tencent/hy3-preview":{"draws":20,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":16,"wins":3},"thinkingmachines/inkling":{"draws":22,"losses":8,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":13},"x-ai/grok-4.5":{"draws":21,"losses":21,"wins":2},"x-ai/grok-4.6":{"draws":13,"losses":18,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":17,"wins":4},"x-ai/grok-build-0.1":{"draws":14,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":63,"losses":11,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":10,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":5},"z-ai/glm-5.2":{"draws":33,"losses":30,"wins":27},"z-ai/glm-5.3":{"draws":4,"losses":20,"wins":4},"z-ai/glm-5.3-flash":{"draws":5,"losses":16,"wins":7},"z-ai/glm-5.3-flashx":{"draws":14,"losses":8,"wins":6}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":37,"wins":14},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-opus-4-5":{"draws":31,"losses":56,"wins":9},"claude-opus-4-8":{"draws":7,"losses":15,"wins":0},"claude-opus-5":{"draws":3,"losses":32,"wins":1},"claude-opus-5-5":{"draws":5,"losses":27,"wins":0},"claude-sonnet-5":{"draws":34,"losses":69,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":21,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":31,"losses":38,"wins":9},"deepseek/deepseek-v4-pro":{"draws":18,"losses":32,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":18,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":20,"wins":2},"fireworks/ember-1":{"draws":15,"losses":12,"wins":1},"gemini-3.1-pro-preview":{"draws":9,"losses":21,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":10,"wins":5},"google/gemini-3.5-flash":{"draws":12,"losses":40,"wins":6},"google/gemini-3.5-flash-lite":{"draws":49,"losses":112,"wins":45},"google/gemini-3.6-flash":{"draws":53,"losses":107,"wins":14},"google/gemini-3.8-flash":{"draws":6,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":0},"gpt-4.1":{"draws":2,"losses":6,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":5,"losses":12,"wins":1},"gpt-5.4":{"draws":37,"losses":62,"wins":9},"gpt-5.4-mini":{"draws":4,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":8,"losses":17,"wins":5},"gpt-5.5":{"draws":8,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":35,"losses":35,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":81,"wins":6},"gpt-5.6-terra":{"draws":21,"losses":29,"wins":12},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":16,"losses":18,"wins":4},"gpt-6-sol":{"draws":6,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":23,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":24,"losses":18,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":17,"wins":4},"meituan/longcat-2.0":{"draws":24,"losses":41,"wins":15},"meta/muse-glimmer-30b":{"draws":23,"losses":40,"wins":5},"meta/muse-spark-1.2":{"draws":21,"losses":51,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":23,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":8,"wins":3},"mistralai/mistral-medium-3-5":{"draws":16,"losses":16,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":30,"losses":45,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":12,"wins":5},"o3":{"draws":7,"losses":89,"wins":20},"openai/gpt-oss-120b":{"draws":28,"losses":23,"wins":11},"poolside/laguna-s-2.1":{"draws":25,"losses":32,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":10,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":33,"wins":0},"qwen/qwen3.8-27b":{"draws":8,"losses":21,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":14,"wins":8},"qwen/qwen3.8-max":{"draws":20,"losses":34,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":1},"stealth/ox-alpha":{"draws":54,"losses":81,"wins":7},"stealth/space-bunny-alpha":{"draws":8,"losses":7,"wins":1},"stepfun/step-3.7-flash":{"draws":6,"losses":16,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":12,"wins":0},"tencent/hy4-preview":{"draws":14,"losses":38,"wins":6},"thinkingmachines/inkling":{"draws":26,"losses":34,"wins":22},"thinkingmachines/inkling-small":{"draws":21,"losses":32,"wins":9},"x-ai/grok-4.5":{"draws":31,"losses":52,"wins":5},"x-ai/grok-4.6":{"draws":13,"losses":38,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":18,"losses":15,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":31,"losses":43,"wins":8},"z-ai/glm-5.3":{"draws":11,"losses":25,"wins":2},"z-ai/glm-5.3-flash":{"draws":19,"losses":25,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":21,"wins":1}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":5,"wins":34},"claude-fable-5":{"draws":12,"losses":51,"wins":19},"claude-fable-5-1":{"draws":4,"losses":68,"wins":6},"claude-opus-4-5":{"draws":29,"losses":21,"wins":62},"claude-opus-4-8":{"draws":13,"losses":11,"wins":6},"claude-opus-5":{"draws":3,"losses":44,"wins":5},"claude-opus-5-5":{"draws":0,"losses":28,"wins":0},"claude-sonnet-5":{"draws":40,"losses":19,"wins":71},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":19,"wins":42},"deepseek/deepseek-v4-pro":{"draws":16,"losses":26,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":26,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"wins":4},"fireworks/ember-1":{"draws":3,"losses":2,"wins":11},"gemini-3.1-pro-preview":{"draws":0,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":12,"losses":30,"wins":36},"google/gemini-3.5-flash-lite":{"draws":51,"losses":20,"wins":117},"google/gemini-3.6-flash":{"draws":39,"losses":69,"wins":86},"google/gemini-3.8-flash":{"draws":14,"losses":33,"wins":27},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":7},"gpt-4.1":{"draws":6,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":11,"wins":12},"gpt-5.4":{"draws":36,"losses":55,"wins":33},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":5,"wins":16},"gpt-5.5":{"draws":12,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":37,"losses":19,"wins":56},"gpt-5.6-sol":{"draws":14,"losses":53,"wins":23},"gpt-5.6-terra":{"draws":31,"losses":16,"wins":25},"gpt-6-astra":{"draws":4,"losses":63,"wins":5},"gpt-6-luna":{"draws":10,"losses":7,"wins":17},"gpt-6-sol":{"draws":2,"losses":16,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":18,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":16,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":23},"meituan/longcat-2.0":{"draws":18,"losses":6,"wins":58},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":23},"meta/muse-spark-1.2":{"draws":16,"losses":28,"wins":40},"meta/muse-spark-1.3":{"draws":18,"losses":24,"wins":22},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":11,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":30,"losses":29,"wins":45},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"wins":11},"o3":{"draws":4,"losses":28,"wins":90},"openai/gpt-oss-120b":{"draws":12,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":24,"losses":3,"wins":43},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":30,"wins":27},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":21},"qwen/qwen3.8-flash":{"draws":18,"losses":16,"wins":18},"qwen/qwen3.8-max":{"draws":20,"losses":24,"wins":25},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":53,"losses":91,"wins":83},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":21},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"tencent/hy4-preview":{"draws":18,"losses":31,"wins":29},"thinkingmachines/inkling":{"draws":17,"losses":9,"wins":48},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":37},"x-ai/grok-4.5":{"draws":13,"losses":46,"wins":37},"x-ai/grok-4.6":{"draws":19,"losses":36,"wins":25},"x-ai/grok-4.7":{"draws":3,"losses":17,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":14,"losses":5,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":11,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":28,"wins":47},"z-ai/glm-5.3":{"draws":11,"losses":38,"wins":19},"z-ai/glm-5.3-flash":{"draws":16,"losses":32,"wins":34},"z-ai/glm-5.3-flashx":{"draws":8,"losses":7,"wins":7}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":15,"wins":34},"claude-fable-5":{"draws":23,"losses":51,"wins":2},"claude-fable-5-1":{"draws":7,"losses":73,"wins":0},"claude-opus-4-5":{"draws":39,"losses":41,"wins":10},"claude-opus-4-8":{"draws":16,"losses":19,"wins":3},"claude-opus-5":{"draws":14,"losses":50,"wins":8},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":39,"losses":26,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":41,"losses":20,"wins":43},"deepseek/deepseek-v4-pro":{"draws":28,"losses":28,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":25,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":16,"wins":9},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":14},"google/gemini-3.5-flash":{"draws":41,"losses":34,"wins":7},"google/gemini-3.5-flash-lite":{"draws":55,"losses":43,"wins":34},"google/gemini-3.6-flash":{"draws":45,"losses":46,"wins":23},"google/gemini-3.8-flash":{"draws":32,"losses":36,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":13},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":15,"wins":7},"gpt-5.4":{"draws":27,"losses":34,"wins":13},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":16},"gpt-5.5":{"draws":21,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":28,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":27,"losses":44,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":5,"wins":10},"gpt-6-astra":{"draws":8,"losses":61,"wins":3},"gpt-6-luna":{"draws":17,"losses":15,"wins":8},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":24},"inclusionai/ling-3.0-flash":{"draws":18,"losses":9,"wins":21},"meituan/longcat-2.0":{"draws":31,"losses":14,"wins":19},"meta/muse-glimmer-30b":{"draws":36,"losses":8,"wins":28},"meta/muse-spark-1.2":{"draws":26,"losses":20,"wins":14},"meta/muse-spark-1.3":{"draws":20,"losses":36,"wins":14},"minimax/minimax-m3":{"draws":12,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":18,"losses":2,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":28,"losses":38,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":6,"wins":13},"o3":{"draws":23,"losses":35,"wins":26},"openai/gpt-oss-120b":{"draws":39,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":37,"losses":6,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":27,"wins":12},"qwen/qwen3.8-27b":{"draws":22,"losses":20,"wins":2},"qwen/qwen3.8-flash":{"draws":21,"losses":11,"wins":12},"qwen/qwen3.8-max":{"draws":38,"losses":20,"wins":20},"qwen/qwen3.8-max-0902":{"draws":20,"losses":15,"wins":5},"stealth/ox-alpha":{"draws":101,"losses":104,"wins":41},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":10},"tencent/hy3-preview":{"draws":15,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":27,"losses":30,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":13,"wins":26},"thinkingmachines/inkling-small":{"draws":30,"losses":16,"wins":30},"x-ai/grok-4.5":{"draws":21,"losses":39,"wins":6},"x-ai/grok-4.6":{"draws":29,"losses":42,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":34,"losses":7,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":8,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":66,"losses":25,"wins":31},"z-ai/glm-5.3":{"draws":21,"losses":41,"wins":4},"z-ai/glm-5.3-flash":{"draws":31,"losses":34,"wins":11},"z-ai/glm-5.3-flashx":{"draws":13,"losses":24,"wins":5}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":30},"claude-fable-5":{"draws":8,"losses":16,"wins":50},"claude-fable-5-1":{"draws":10,"losses":35,"wins":37},"claude-opus-4-5":{"draws":10,"losses":7,"wins":65},"claude-opus-4-8":{"draws":8,"losses":5,"wins":21},"claude-opus-5":{"draws":10,"losses":19,"wins":27},"claude-opus-5-5":{"draws":3,"losses":9,"wins":6},"claude-sonnet-5":{"draws":7,"losses":11,"wins":48},"claude-sonnet-5-5":{"draws":1,"losses":6,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":52},"deepseek/deepseek-v4-pro":{"draws":5,"losses":6,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":0,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":17},"fireworks/ember-1":{"draws":0,"losses":2,"wins":8},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":15},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":1,"wins":54},"google/gemini-3.5-flash-lite":{"draws":7,"losses":2,"wins":81},"google/gemini-3.6-flash":{"draws":15,"losses":8,"wins":69},"google/gemini-3.8-flash":{"draws":9,"losses":8,"wins":47},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":14},"gpt-4.1":{"draws":4,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":0,"wins":26},"gpt-5.4":{"draws":9,"losses":9,"wins":38},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":18},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":27},"gpt-5.5":{"draws":1,"losses":2,"wins":13},"gpt-5.6-luna":{"draws":9,"losses":0,"wins":31},"gpt-5.6-sol":{"draws":9,"losses":6,"wins":61},"gpt-5.6-terra":{"draws":13,"losses":5,"wins":52},"gpt-6-astra":{"draws":5,"losses":24,"wins":19},"gpt-6-luna":{"draws":8,"losses":3,"wins":21},"gpt-6-sol":{"draws":1,"losses":6,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":9,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":33},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":37},"meta/muse-spark-1.2":{"draws":6,"losses":2,"wins":34},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":33},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":7,"wins":34},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":21},"o3":{"draws":1,"losses":0,"wins":51},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":26},"poolside/laguna-s-2.1":{"draws":13,"losses":0,"wins":29},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":5,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":34},"qwen/qwen3.8-flash":{"draws":12,"losses":1,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":4,"wins":39},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":8},"stealth/ox-alpha":{"draws":35,"losses":20,"wins":159},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":4,"wins":47},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":34},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":53},"x-ai/grok-4.5":{"draws":8,"losses":10,"wins":38},"x-ai/grok-4.6":{"draws":13,"losses":11,"wins":56},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":13},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":9},"z-ai/glm-5.2":{"draws":11,"losses":4,"wins":63},"z-ai/glm-5.3":{"draws":12,"losses":6,"wins":46},"z-ai/glm-5.3-flash":{"draws":13,"losses":9,"wins":56},"z-ai/glm-5.3-flashx":{"draws":3,"losses":2,"wins":17}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":11,"wins":7},"claude-fable-5":{"draws":7,"losses":23,"wins":2},"claude-fable-5-1":{"draws":1,"losses":17,"wins":0},"claude-opus-4-5":{"draws":22,"losses":19,"wins":1},"claude-opus-4-8":{"draws":5,"losses":13,"wins":4},"claude-opus-5":{"draws":4,"losses":26,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":8,"losses":7,"wins":3},"claude-sonnet-5-5":{"draws":6,"losses":23,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":14,"losses":7,"wins":9},"deepseek/deepseek-v4-pro":{"draws":10,"losses":6,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":3,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":6},"fireworks/ember-1":{"draws":12,"losses":15,"wins":9},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":7},"google/gemini-3.5-flash":{"draws":10,"losses":16,"wins":8},"google/gemini-3.5-flash-lite":{"draws":14,"losses":6,"wins":8},"google/gemini-3.6-flash":{"draws":13,"losses":25,"wins":4},"google/gemini-3.8-flash":{"draws":7,"losses":10,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":6},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-5":{"draws":12,"losses":2,"wins":0},"gpt-5.4":{"draws":11,"losses":14,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":5,"wins":4},"gpt-5.5":{"draws":11,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":13,"losses":2,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":1},"gpt-5.6-terra":{"draws":11,"losses":14,"wins":3},"gpt-6-astra":{"draws":4,"losses":16,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":6},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":15,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":6},"meta/muse-glimmer-30b":{"draws":11,"losses":1,"wins":4},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":3},"meta/muse-spark-1.3":{"draws":9,"losses":11,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":2},"o3":{"draws":10,"losses":12,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":6},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":0},"qwen/qwen3.7-max":{"draws":8,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":2},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.8-max":{"draws":15,"losses":12,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":23,"wins":6},"stealth/ox-alpha":{"draws":19,"losses":31,"wins":12},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":3},"thinkingmachines/inkling-small":{"draws":11,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":10,"losses":12,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":23,"losses":14,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":18,"wins":11},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":2},"z-ai/glm-5.3-flash":{"draws":11,"losses":15,"wins":2},"z-ai/glm-5.3-flashx":{"draws":15,"losses":19,"wins":8}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":11},"claude-fable-5":{"draws":7,"losses":10,"wins":11},"claude-fable-5-1":{"draws":1,"losses":20,"wins":1},"claude-opus-4-5":{"draws":3,"losses":8,"wins":21},"claude-opus-4-8":{"draws":1,"losses":2,"wins":13},"claude-opus-5":{"draws":5,"losses":31,"wins":4},"claude-opus-5-5":{"draws":2,"losses":42,"wins":8},"claude-sonnet-5":{"draws":1,"losses":2,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":21,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":28},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":7,"losses":10,"wins":23},"gemini-3.1-pro-preview":{"draws":9,"losses":11,"wins":20},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":12},"google/gemini-3.5-flash-lite":{"draws":5,"losses":5,"wins":30},"google/gemini-3.6-flash":{"draws":6,"losses":14,"wins":26},"google/gemini-3.8-flash":{"draws":4,"losses":3,"wins":9},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":10},"gpt-4.1":{"draws":3,"losses":2,"wins":7},"gpt-5":{"draws":2,"losses":0,"wins":4},"gpt-5.4":{"draws":2,"losses":5,"wins":13},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":12},"gpt-5.5":{"draws":8,"losses":4,"wins":12},"gpt-5.6-luna":{"draws":9,"losses":2,"wins":11},"gpt-5.6-sol":{"draws":1,"losses":11,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":2,"wins":17},"gpt-6-astra":{"draws":1,"losses":14,"wins":1},"gpt-6-luna":{"draws":9,"losses":4,"wins":33},"gpt-6-sol":{"draws":5,"losses":21,"wins":6},"gpt-6.1-sol":{"draws":5,"losses":35,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":11},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":19},"meta/muse-glimmer-30b":{"draws":4,"losses":1,"wins":15},"meta/muse-spark-1.2":{"draws":3,"losses":2,"wins":13},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":12},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":13},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":15},"o3":{"draws":2,"losses":2,"wins":22},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":16},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":9},"qwen/qwen3.8-max":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":9,"wins":27},"stealth/ox-alpha":{"draws":11,"losses":8,"wins":41},"stealth/space-bunny-alpha":{"draws":7,"losses":4,"wins":23},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":7},"tencent/hy3-preview":{"draws":5,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":1,"losses":8,"wins":11},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":19},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":14},"x-ai/grok-4.5":{"draws":12,"losses":8,"wins":10},"x-ai/grok-4.6":{"draws":11,"losses":13,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":13},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":6,"losses":3,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":7,"wins":15},"z-ai/glm-5.2":{"draws":9,"losses":6,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":12,"wins":7},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":14},"z-ai/glm-5.3-flashx":{"draws":7,"losses":21,"wins":20}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":18},"claude-fable-5":{"draws":0,"losses":6,"wins":8},"claude-fable-5-1":{"draws":3,"losses":18,"wins":9},"claude-opus-4-5":{"draws":9,"losses":4,"wins":21},"claude-opus-4-8":{"draws":3,"losses":5,"wins":12},"claude-opus-5":{"draws":8,"losses":19,"wins":11},"claude-opus-5-5":{"draws":9,"losses":19,"wins":12},"claude-sonnet-5":{"draws":4,"losses":6,"wins":20},"claude-sonnet-5-5":{"draws":2,"losses":17,"wins":29},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":32},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":0,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":3,"wins":33},"fireworks/ember-1":{"draws":10,"losses":7,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":39},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":23},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":38},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":35},"google/gemini-3.8-flash":{"draws":4,"losses":3,"wins":13},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":10},"gpt-5.4":{"draws":4,"losses":2,"wins":14},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":19},"gpt-5.5":{"draws":4,"losses":3,"wins":13},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":21},"gpt-5.6-sol":{"draws":5,"losses":4,"wins":13},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":9},"gpt-6-astra":{"draws":2,"losses":16,"wins":4},"gpt-6-luna":{"draws":4,"losses":0,"wins":20},"gpt-6-sol":{"draws":7,"losses":17,"wins":14},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":17},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":19},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":20},"meta/muse-spark-1.2":{"draws":3,"losses":0,"wins":9},"meta/muse-spark-1.3":{"draws":4,"losses":5,"wins":9},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":13},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":13},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":25},"o3":{"draws":0,"losses":1,"wins":25},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":21},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":13},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.8-flash":{"draws":3,"losses":1,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":21},"stealth/ox-alpha":{"draws":15,"losses":7,"wins":46},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":2,"losses":4,"wins":16},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":25},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":19},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":10},"x-ai/grok-4.6":{"draws":7,"losses":2,"wins":9},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":12},"z-ai/glm-5.2":{"draws":11,"losses":2,"wins":35},"z-ai/glm-5.3":{"draws":8,"losses":8,"wins":18},"z-ai/glm-5.3-flash":{"draws":1,"losses":1,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":8,"wins":23}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":15,"wins":12},"claude-fable-5":{"draws":13,"losses":17,"wins":4},"claude-fable-5-1":{"draws":2,"losses":32,"wins":0},"claude-opus-4-5":{"draws":24,"losses":14,"wins":6},"claude-opus-4-8":{"draws":6,"losses":3,"wins":7},"claude-opus-5":{"draws":7,"losses":14,"wins":1},"claude-opus-5-5":{"draws":4,"losses":10,"wins":0},"claude-sonnet-5":{"draws":17,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":24,"losses":20,"wins":12},"deepseek/deepseek-v4-pro":{"draws":17,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":23,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":0},"fireworks/ember-1":{"draws":6,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":15,"losses":14,"wins":11},"google/gemini-3.5-flash-lite":{"draws":31,"losses":21,"wins":28},"google/gemini-3.6-flash":{"draws":24,"losses":26,"wins":12},"google/gemini-3.8-flash":{"draws":21,"losses":22,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":7},"gpt-4.1":{"draws":4,"losses":2,"wins":6},"gpt-5":{"draws":8,"losses":6,"wins":4},"gpt-5.4":{"draws":16,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":12,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":9,"wins":5},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":18,"wins":8},"gpt-5.6-sol":{"draws":13,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":21,"losses":13,"wins":8},"gpt-6-astra":{"draws":4,"losses":30,"wins":0},"gpt-6-luna":{"draws":4,"losses":12,"wins":2},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":6},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":9,"losses":8,"wins":5},"meta/muse-spark-1.3":{"draws":14,"losses":9,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":21,"losses":16,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":4,"wins":1},"o3":{"draws":6,"losses":14,"wins":12},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":13},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":11},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-27b":{"draws":3,"losses":21,"wins":2},"qwen/qwen3.8-flash":{"draws":12,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":18,"wins":5},"qwen/qwen3.8-max-0902":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":52,"losses":64,"wins":23},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":7},"tencent/hy4-preview":{"draws":22,"losses":15,"wins":3},"thinkingmachines/inkling":{"draws":16,"losses":7,"wins":17},"thinkingmachines/inkling-small":{"draws":28,"losses":9,"wins":17},"x-ai/grok-4.5":{"draws":15,"losses":18,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":20,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":9,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":6,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":26,"losses":20,"wins":12},"z-ai/glm-5.3":{"draws":7,"losses":17,"wins":2},"z-ai/glm-5.3-flash":{"draws":17,"losses":17,"wins":8},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":0}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":17,"wins":5},"claude-fable-5":{"draws":7,"losses":33,"wins":0},"claude-fable-5-1":{"draws":3,"losses":35,"wins":0},"claude-opus-4-5":{"draws":40,"losses":42,"wins":10},"claude-opus-4-8":{"draws":34,"losses":34,"wins":0},"claude-opus-5":{"draws":20,"losses":71,"wins":5},"claude-opus-5-5":{"draws":4,"losses":28,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":3},"claude-sonnet-5-5":{"draws":12,"losses":27,"wins":1},"cohere/north-mini-code":{"draws":36,"losses":7,"wins":15},"deepseek/deepseek-v4-flash":{"draws":44,"losses":28,"wins":16},"deepseek/deepseek-v4-pro":{"draws":21,"losses":15,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":13,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":16,"wins":2},"fireworks/ember-1":{"draws":18,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":20,"losses":20,"wins":2},"google/gemini-3.1-flash-lite":{"draws":17,"losses":24,"wins":13},"google/gemini-3.5-flash":{"draws":23,"losses":30,"wins":3},"google/gemini-3.5-flash-lite":{"draws":65,"losses":40,"wins":11},"google/gemini-3.6-flash":{"draws":77,"losses":46,"wins":13},"google/gemini-3.8-flash":{"draws":16,"losses":20,"wins":0},"google/gemma-4-31b-it":{"draws":16,"losses":23,"wins":7},"gpt-4.1":{"draws":16,"losses":22,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":21,"losses":15,"wins":26},"gpt-5.4":{"draws":11,"losses":13,"wins":0},"gpt-5.4-mini":{"draws":39,"losses":17,"wins":8},"gpt-5.4-nano":{"draws":47,"losses":34,"wins":15},"gpt-5.5":{"draws":49,"losses":29,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":2},"gpt-5.6-sol":{"draws":5,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":18,"losses":23,"wins":3},"gpt-6-astra":{"draws":2,"losses":24,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":5},"gpt-6-sol":{"draws":4,"losses":28,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":40,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":6,"wins":3},"inclusionai/ling-3.0-flash":{"draws":26,"losses":21,"wins":19},"meituan/longcat-2.0":{"draws":64,"losses":42,"wins":18},"meta/muse-glimmer-30b":{"draws":15,"losses":11,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":17,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":3},"minimax/minimax-m3":{"draws":31,"losses":23,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":14,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":38,"losses":20,"wins":0},"nex-agi/nex-n2-pro":{"draws":36,"losses":19,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":22,"wins":10},"o3":{"draws":26,"losses":27,"wins":7},"openai/gpt-oss-120b":{"draws":12,"losses":15,"wins":1},"poolside/laguna-s-2.1":{"draws":75,"losses":31,"wins":14},"qwen/qwen3.7-max":{"draws":35,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":27,"losses":17,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":0},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":3},"qwen/qwen3.8-flash":{"draws":15,"losses":19,"wins":2},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":4},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":1},"stealth/ox-alpha":{"draws":45,"losses":64,"wins":5},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":24,"losses":20,"wins":4},"tencent/hy3-preview":{"draws":20,"losses":21,"wins":5},"tencent/hy4-preview":{"draws":20,"losses":12,"wins":2},"thinkingmachines/inkling":{"draws":37,"losses":35,"wins":24},"thinkingmachines/inkling-small":{"draws":20,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":59,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":24,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":1},"x-ai/grok-build-0.1":{"draws":17,"losses":19,"wins":0},"xiaomi/mimo-v2.5":{"draws":67,"losses":51,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":23,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":0},"z-ai/glm-5.2":{"draws":66,"losses":29,"wins":9},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":0},"z-ai/glm-5.3-flash":{"draws":23,"losses":24,"wins":5},"z-ai/glm-5.3-flashx":{"draws":8,"losses":20,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":14,"wins":13},"claude-fable-5":{"draws":6,"losses":47,"wins":7},"claude-fable-5-1":{"draws":0,"losses":36,"wins":2},"claude-opus-4-5":{"draws":49,"losses":78,"wins":25},"claude-opus-4-8":{"draws":10,"losses":46,"wins":18},"claude-opus-5":{"draws":13,"losses":132,"wins":13},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":15,"losses":19,"wins":12},"claude-sonnet-5-5":{"draws":5,"losses":27,"wins":2},"cohere/north-mini-code":{"draws":40,"losses":3,"wins":27},"deepseek/deepseek-v4-flash":{"draws":34,"losses":31,"wins":37},"deepseek/deepseek-v4-pro":{"draws":12,"losses":25,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":7},"fireworks/ember-1":{"draws":19,"losses":34,"wins":1},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":8},"google/gemini-3.1-flash-lite":{"draws":17,"losses":23,"wins":38},"google/gemini-3.5-flash":{"draws":16,"losses":40,"wins":12},"google/gemini-3.5-flash-lite":{"draws":43,"losses":66,"wins":25},"google/gemini-3.6-flash":{"draws":53,"losses":60,"wins":33},"google/gemini-3.8-flash":{"draws":9,"losses":40,"wins":1},"google/gemma-4-31b-it":{"draws":16,"losses":21,"wins":25},"gpt-4.1":{"draws":15,"losses":26,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":6,"wins":0},"gpt-5":{"draws":35,"losses":41,"wins":32},"gpt-5.4":{"draws":19,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":31,"losses":26,"wins":21},"gpt-5.4-nano":{"draws":32,"losses":61,"wins":47},"gpt-5.5":{"draws":48,"losses":27,"wins":23},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":44,"wins":2},"gpt-5.6-terra":{"draws":25,"losses":28,"wins":11},"gpt-6-astra":{"draws":4,"losses":46,"wins":0},"gpt-6-luna":{"draws":14,"losses":22,"wins":10},"gpt-6-sol":{"draws":7,"losses":34,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":21,"losses":9,"wins":14},"inclusionai/ling-3.0-flash":{"draws":59,"losses":27,"wins":42},"meituan/longcat-2.0":{"draws":25,"losses":30,"wins":26},"meta/muse-glimmer-30b":{"draws":23,"losses":8,"wins":11},"meta/muse-spark-1.2":{"draws":10,"losses":22,"wins":8},"meta/muse-spark-1.3":{"draws":10,"losses":34,"wins":4},"minimax/minimax-m3":{"draws":20,"losses":20,"wins":20},"mistralai/mistral-medium-3-5":{"draws":13,"losses":14,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":36,"losses":31,"wins":13},"nex-agi/nex-n2-pro":{"draws":20,"losses":17,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":27,"wins":17},"o3":{"draws":22,"losses":35,"wins":39},"openai/gpt-oss-120b":{"draws":15,"losses":16,"wins":15},"poolside/laguna-s-2.1":{"draws":58,"losses":48,"wins":26},"qwen/qwen3.7-max":{"draws":34,"losses":19,"wins":11},"qwen/qwen3.7-plus":{"draws":17,"losses":15,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":30,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":6},"qwen/qwen3.8-flash":{"draws":17,"losses":11,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":7},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":5},"stealth/ox-alpha":{"draws":34,"losses":113,"wins":29},"stealth/space-bunny-alpha":{"draws":15,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":16,"losses":21,"wins":21},"tencent/hy3-preview":{"draws":28,"losses":23,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":24,"wins":6},"thinkingmachines/inkling":{"draws":28,"losses":44,"wins":36},"thinkingmachines/inkling-small":{"draws":21,"losses":15,"wins":16},"x-ai/grok-4.5":{"draws":28,"losses":62,"wins":22},"x-ai/grok-4.6":{"draws":21,"losses":38,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":3},"x-ai/grok-build-0.1":{"draws":13,"losses":12,"wins":17},"xiaomi/mimo-v2.5":{"draws":65,"losses":61,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":38,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":6,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":2},"z-ai/glm-5.2":{"draws":61,"losses":77,"wins":34},"z-ai/glm-5.3":{"draws":8,"losses":43,"wins":3},"z-ai/glm-5.3-flash":{"draws":20,"losses":39,"wins":13},"z-ai/glm-5.3-flashx":{"draws":14,"losses":22,"wins":4}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":24,"wins":8},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":3,"losses":27,"wins":0},"claude-opus-4-5":{"draws":15,"losses":34,"wins":5},"claude-opus-4-8":{"draws":5,"losses":16,"wins":1},"claude-opus-5":{"draws":0,"losses":32,"wins":4},"claude-opus-5-5":{"draws":2,"losses":20,"wins":0},"claude-sonnet-5":{"draws":14,"losses":29,"wins":7},"claude-sonnet-5-5":{"draws":1,"losses":4,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":28,"losses":21,"wins":9},"deepseek/deepseek-v4-pro":{"draws":24,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":2,"wins":0},"fireworks/ember-1":{"draws":2,"losses":8,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":5},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":11},"google/gemini-3.5-flash-lite":{"draws":39,"losses":31,"wins":24},"google/gemini-3.6-flash":{"draws":37,"losses":46,"wins":5},"google/gemini-3.8-flash":{"draws":15,"losses":26,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":2},"gpt-4.1":{"draws":5,"losses":1,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":12,"wins":6},"gpt-5.4":{"draws":16,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":8,"wins":7},"gpt-5.5":{"draws":8,"losses":15,"wins":3},"gpt-5.6-luna":{"draws":22,"losses":17,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":2},"gpt-5.6-terra":{"draws":20,"losses":27,"wins":5},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":6,"losses":11,"wins":3},"gpt-6-sol":{"draws":0,"losses":8,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":10},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":12,"losses":12,"wins":12},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":3},"meta/muse-spark-1.2":{"draws":6,"losses":25,"wins":3},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":5},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":20,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":2,"wins":3},"o3":{"draws":16,"losses":28,"wins":14},"openai/gpt-oss-120b":{"draws":17,"losses":14,"wins":11},"poolside/laguna-s-2.1":{"draws":20,"losses":11,"wins":9},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":20,"wins":6},"qwen/qwen3.8-27b":{"draws":16,"losses":20,"wins":2},"qwen/qwen3.8-flash":{"draws":20,"losses":6,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":19,"wins":7},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":49,"losses":87,"wins":16},"stealth/space-bunny-alpha":{"draws":3,"losses":3,"wins":2},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":10,"wins":1},"tencent/hy4-preview":{"draws":24,"losses":19,"wins":3},"thinkingmachines/inkling":{"draws":15,"losses":17,"wins":14},"thinkingmachines/inkling-small":{"draws":31,"losses":12,"wins":21},"x-ai/grok-4.5":{"draws":10,"losses":23,"wins":5},"x-ai/grok-4.6":{"draws":23,"losses":21,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":38,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":3,"losses":27,"wins":4},"z-ai/glm-5.3-flash":{"draws":19,"losses":29,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":2}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":17,"wins":16},"claude-fable-5":{"draws":10,"losses":45,"wins":9},"claude-fable-5-1":{"draws":7,"losses":53,"wins":0},"claude-opus-4-5":{"draws":27,"losses":42,"wins":33},"claude-opus-4-8":{"draws":11,"losses":23,"wins":6},"claude-opus-5":{"draws":3,"losses":47,"wins":10},"claude-opus-5-5":{"draws":0,"losses":26,"wins":0},"claude-sonnet-5":{"draws":39,"losses":41,"wins":32},"claude-sonnet-5-5":{"draws":3,"losses":13,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":7,"wins":14},"deepseek/deepseek-v4-flash":{"draws":19,"losses":27,"wins":32},"deepseek/deepseek-v4-pro":{"draws":10,"losses":32,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":30,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":9,"wins":6},"fireworks/ember-1":{"draws":5,"losses":8,"wins":5},"gemini-3.1-pro-preview":{"draws":5,"losses":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":11},"google/gemini-3.5-flash":{"draws":18,"losses":41,"wins":17},"google/gemini-3.5-flash-lite":{"draws":54,"losses":55,"wins":87},"google/gemini-3.6-flash":{"draws":41,"losses":95,"wins":52},"google/gemini-3.8-flash":{"draws":14,"losses":33,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":13},"gpt-4.1":{"draws":2,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":8,"wins":11},"gpt-5.4":{"draws":21,"losses":51,"wins":32},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":13},"gpt-5.4-nano":{"draws":4,"losses":13,"wins":13},"gpt-5.5":{"draws":7,"losses":14,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":37,"wins":44},"gpt-5.6-sol":{"draws":14,"losses":80,"wins":14},"gpt-5.6-terra":{"draws":20,"losses":30,"wins":24},"gpt-6-astra":{"draws":2,"losses":53,"wins":1},"gpt-6-luna":{"draws":3,"losses":12,"wins":9},"gpt-6-sol":{"draws":2,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":6,"wins":30},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":18},"meituan/longcat-2.0":{"draws":18,"losses":34,"wins":30},"meta/muse-glimmer-30b":{"draws":14,"losses":20,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":29,"wins":7},"meta/muse-spark-1.3":{"draws":11,"losses":31,"wins":12},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":10},"mistralai/mistral-medium-3-5":{"draws":16,"losses":4,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":23,"losses":50,"wins":31},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":15},"o3":{"draws":7,"losses":71,"wins":48},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":30},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":40},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":35,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":20,"wins":20},"qwen/qwen3.8-flash":{"draws":15,"losses":17,"wins":14},"qwen/qwen3.8-max":{"draws":20,"losses":28,"wins":16},"qwen/qwen3.8-max-0902":{"draws":3,"losses":14,"wins":5},"stealth/ox-alpha":{"draws":49,"losses":124,"wins":57},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":12,"wins":20},"tencent/hy3-preview":{"draws":10,"losses":1,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":36,"wins":19},"thinkingmachines/inkling":{"draws":35,"losses":15,"wins":38},"thinkingmachines/inkling-small":{"draws":17,"losses":19,"wins":34},"x-ai/grok-4.5":{"draws":26,"losses":53,"wins":13},"x-ai/grok-4.6":{"draws":9,"losses":46,"wins":7},"x-ai/grok-4.7":{"draws":0,"losses":16,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":13,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":26,"losses":36,"wins":34},"z-ai/glm-5.3":{"draws":7,"losses":41,"wins":12},"z-ai/glm-5.3-flash":{"draws":14,"losses":30,"wins":20},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":10}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":11,"wins":25},"claude-fable-5":{"draws":14,"losses":39,"wins":5},"claude-fable-5-1":{"draws":0,"losses":44,"wins":0},"claude-opus-4-5":{"draws":23,"losses":26,"wins":19},"claude-opus-4-8":{"draws":13,"losses":17,"wins":4},"claude-opus-5":{"draws":5,"losses":40,"wins":3},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":27,"losses":25,"wins":16},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":31,"losses":15,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":27,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":10,"wins":3},"fireworks/ember-1":{"draws":9,"losses":14,"wins":3},"gemini-3.1-pro-preview":{"draws":8,"losses":11,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":24,"losses":31,"wins":15},"google/gemini-3.5-flash-lite":{"draws":45,"losses":34,"wins":51},"google/gemini-3.6-flash":{"draws":30,"losses":43,"wins":31},"google/gemini-3.8-flash":{"draws":15,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":6},"gpt-4.1":{"draws":7,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":11,"losses":11,"wins":6},"gpt-5.4":{"draws":16,"losses":28,"wins":8},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":11},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":10},"gpt-5.5":{"draws":8,"losses":13,"wins":7},"gpt-5.6-luna":{"draws":29,"losses":18,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":27,"wins":18},"gpt-6-astra":{"draws":4,"losses":36,"wins":2},"gpt-6-luna":{"draws":9,"losses":12,"wins":7},"gpt-6-sol":{"draws":0,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":26,"losses":3,"wins":21},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":15},"meituan/longcat-2.0":{"draws":17,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":34,"losses":11,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":24,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":18,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":13},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":20,"losses":30,"wins":14},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":17},"o3":{"draws":15,"losses":37,"wins":18},"openai/gpt-oss-120b":{"draws":25,"losses":10,"wins":25},"poolside/laguna-s-2.1":{"draws":14,"losses":11,"wins":13},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":20,"wins":14},"qwen/qwen3.8-27b":{"draws":7,"losses":19,"wins":8},"qwen/qwen3.8-flash":{"draws":17,"losses":20,"wins":13},"qwen/qwen3.8-max":{"draws":27,"losses":14,"wins":21},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":0},"stealth/ox-alpha":{"draws":60,"losses":110,"wins":42},"stealth/space-bunny-alpha":{"draws":5,"losses":10,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":16},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":6},"tencent/hy4-preview":{"draws":24,"losses":37,"wins":9},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":25},"thinkingmachines/inkling-small":{"draws":39,"losses":11,"wins":24},"x-ai/grok-4.5":{"draws":11,"losses":29,"wins":14},"x-ai/grok-4.6":{"draws":16,"losses":29,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":10,"wins":2},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":26},"z-ai/glm-5.3":{"draws":12,"losses":38,"wins":6},"z-ai/glm-5.3-flash":{"draws":18,"losses":35,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":7,"wins":2}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":22,"wins":6},"claude-fable-5":{"draws":7,"losses":19,"wins":4},"claude-fable-5-1":{"draws":1,"losses":24,"wins":1},"claude-opus-4-5":{"draws":22,"losses":48,"wins":14},"claude-opus-4-8":{"draws":7,"losses":35,"wins":12},"claude-opus-5":{"draws":16,"losses":80,"wins":6},"claude-opus-5-5":{"draws":2,"losses":13,"wins":1},"claude-sonnet-5":{"draws":6,"losses":16,"wins":6},"claude-sonnet-5-5":{"draws":2,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":10,"wins":22},"deepseek/deepseek-v4-flash":{"draws":15,"losses":16,"wins":23},"deepseek/deepseek-v4-pro":{"draws":3,"losses":18,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":10,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":1},"fireworks/ember-1":{"draws":3,"losses":6,"wins":3},"gemini-3.1-pro-preview":{"draws":0,"losses":5,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":20},"google/gemini-3.5-flash":{"draws":6,"losses":12,"wins":14},"google/gemini-3.5-flash-lite":{"draws":14,"losses":11,"wins":25},"google/gemini-3.6-flash":{"draws":10,"losses":40,"wins":10},"google/gemini-3.8-flash":{"draws":2,"losses":23,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":16},"gpt-4.1":{"draws":4,"losses":14,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":23,"wins":9},"gpt-5.4":{"draws":3,"losses":12,"wins":9},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":22},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":32},"gpt-5.5":{"draws":11,"losses":33,"wins":8},"gpt-5.6-luna":{"draws":4,"losses":12,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":20,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":12,"wins":9},"gpt-6-astra":{"draws":0,"losses":25,"wins":1},"gpt-6-luna":{"draws":6,"losses":13,"wins":5},"gpt-6-sol":{"draws":2,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":11},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":16},"meituan/longcat-2.0":{"draws":7,"losses":9,"wins":22},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":15},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":2},"meta/muse-spark-1.3":{"draws":3,"losses":22,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":24,"wins":3},"nex-agi/nex-n2-pro":{"draws":11,"losses":6,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":12,"wins":30},"o3":{"draws":2,"losses":24,"wins":14},"openai/gpt-oss-120b":{"draws":5,"losses":9,"wins":12},"poolside/laguna-s-2.1":{"draws":13,"losses":15,"wins":22},"qwen/qwen3.7-max":{"draws":18,"losses":21,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":14,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":7,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":6,"losses":17,"wins":3},"qwen/qwen3.8-max-0902":{"draws":3,"losses":7,"wins":2},"stealth/ox-alpha":{"draws":23,"losses":44,"wins":15},"stealth/space-bunny-alpha":{"draws":7,"losses":4,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":15},"tencent/hy3-preview":{"draws":6,"losses":15,"wins":15},"tencent/hy4-preview":{"draws":6,"losses":19,"wins":5},"thinkingmachines/inkling":{"draws":13,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":5,"losses":8,"wins":11},"x-ai/grok-4.5":{"draws":7,"losses":26,"wins":5},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":21,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":14,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":18,"losses":16,"wins":28},"z-ai/glm-5.3":{"draws":3,"losses":17,"wins":2},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":5},"z-ai/glm-5.3-flashx":{"draws":1,"losses":8,"wins":3}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":19,"wins":12},"claude-fable-5":{"draws":11,"losses":26,"wins":3},"claude-fable-5-1":{"draws":2,"losses":28,"wins":0},"claude-opus-4-5":{"draws":13,"losses":43,"wins":2},"claude-opus-4-8":{"draws":9,"losses":10,"wins":1},"claude-opus-5":{"draws":5,"losses":37,"wins":6},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":19,"losses":34,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":15,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":31,"losses":27,"wins":6},"deepseek/deepseek-v4-pro":{"draws":19,"losses":29,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":29,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":1},"fireworks/ember-1":{"draws":4,"losses":16,"wins":0},"gemini-3.1-pro-preview":{"draws":0,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":4},"google/gemini-3.5-flash":{"draws":16,"losses":33,"wins":7},"google/gemini-3.5-flash-lite":{"draws":40,"losses":52,"wins":22},"google/gemini-3.6-flash":{"draws":34,"losses":44,"wins":6},"google/gemini-3.8-flash":{"draws":11,"losses":29,"wins":0},"google/gemma-4-31b-it":{"draws":3,"losses":7,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":9,"losses":12,"wins":5},"gpt-5.4":{"draws":16,"losses":17,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":5},"gpt-5.5":{"draws":4,"losses":17,"wins":3},"gpt-5.6-luna":{"draws":21,"losses":19,"wins":10},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":34,"wins":5},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":6,"losses":15,"wins":1},"gpt-6-sol":{"draws":1,"losses":8,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":22,"losses":17,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":19,"wins":7},"meta/muse-glimmer-30b":{"draws":24,"losses":22,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":29,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":0},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":3},"o3":{"draws":14,"losses":35,"wins":3},"openai/gpt-oss-120b":{"draws":28,"losses":18,"wins":4},"poolside/laguna-s-2.1":{"draws":23,"losses":18,"wins":7},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":39,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":23,"wins":2},"qwen/qwen3.8-flash":{"draws":17,"losses":22,"wins":5},"qwen/qwen3.8-max":{"draws":17,"losses":33,"wins":6},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":47,"losses":85,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":1},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":17,"losses":31,"wins":2},"thinkingmachines/inkling":{"draws":17,"losses":22,"wins":5},"thinkingmachines/inkling-small":{"draws":31,"losses":21,"wins":16},"x-ai/grok-4.5":{"draws":12,"losses":30,"wins":6},"x-ai/grok-4.6":{"draws":15,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":15,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":9,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":13,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":40,"losses":38,"wins":6},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":21,"losses":28,"wins":9},"z-ai/glm-5.3-flashx":{"draws":2,"losses":8,"wins":2}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":11,"wins":32},"claude-fable-5":{"draws":8,"losses":52,"wins":20},"claude-fable-5-1":{"draws":4,"losses":78,"wins":4},"claude-opus-4-5":{"draws":45,"losses":30,"wins":63},"claude-opus-4-8":{"draws":10,"losses":14,"wins":20},"claude-opus-5":{"draws":15,"losses":58,"wins":25},"claude-opus-5-5":{"draws":0,"losses":26,"wins":4},"claude-sonnet-5":{"draws":41,"losses":23,"wins":62},"claude-sonnet-5-5":{"draws":6,"losses":12,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":20,"losses":22,"wins":42},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":21,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":13,"wins":11},"fireworks/ember-1":{"draws":4,"losses":8,"wins":2},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":16},"google/gemini-3.5-flash":{"draws":26,"losses":28,"wins":24},"google/gemini-3.5-flash-lite":{"draws":79,"losses":47,"wins":122},"google/gemini-3.6-flash":{"draws":69,"losses":96,"wins":93},"google/gemini-3.8-flash":{"draws":16,"losses":36,"wins":18},"google/gemma-4-31b-it":{"draws":11,"losses":2,"wins":21},"gpt-4.1":{"draws":1,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":4,"wins":16},"gpt-5.4":{"draws":12,"losses":64,"wins":40},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":38},"gpt-5.5":{"draws":12,"losses":8,"wins":22},"gpt-5.6-luna":{"draws":29,"losses":24,"wins":59},"gpt-5.6-sol":{"draws":19,"losses":65,"wins":28},"gpt-5.6-terra":{"draws":21,"losses":24,"wins":35},"gpt-6-astra":{"draws":8,"losses":48,"wins":10},"gpt-6-luna":{"draws":2,"losses":13,"wins":11},"gpt-6-sol":{"draws":0,"losses":14,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":20,"losses":6,"wins":26},"inclusionai/ling-3.0-flash":{"draws":31,"losses":7,"wins":28},"meituan/longcat-2.0":{"draws":36,"losses":19,"wins":59},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":31},"meta/muse-spark-1.2":{"draws":23,"losses":25,"wins":42},"meta/muse-spark-1.3":{"draws":13,"losses":35,"wins":24},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":22},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":40,"losses":27,"wins":19},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":3,"wins":23},"o3":{"draws":20,"losses":64,"wins":66},"openai/gpt-oss-120b":{"draws":17,"losses":12,"wins":29},"poolside/laguna-s-2.1":{"draws":41,"losses":13,"wins":54},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.7-plus":{"draws":14,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":23,"wins":32},"qwen/qwen3.8-27b":{"draws":2,"losses":14,"wins":18},"qwen/qwen3.8-flash":{"draws":14,"losses":20,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":25,"wins":32},"qwen/qwen3.8-max-0902":{"draws":3,"losses":15,"wins":8},"stealth/ox-alpha":{"draws":60,"losses":82,"wins":88},"stealth/space-bunny-alpha":{"draws":4,"losses":4,"wins":6},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":30},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":14},"tencent/hy4-preview":{"draws":19,"losses":23,"wins":24},"thinkingmachines/inkling":{"draws":42,"losses":20,"wins":60},"thinkingmachines/inkling-small":{"draws":22,"losses":16,"wins":39},"x-ai/grok-4.5":{"draws":43,"losses":41,"wins":52},"x-ai/grok-4.6":{"draws":10,"losses":43,"wins":23},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":23,"losses":12,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":15,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":6,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":42,"losses":21,"wins":41},"z-ai/glm-5.3":{"draws":19,"losses":32,"wins":21},"z-ai/glm-5.3-flash":{"draws":20,"losses":37,"wins":19},"z-ai/glm-5.3-flashx":{"draws":4,"losses":14,"wins":8}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":0},"claude-fable-5":{"draws":8,"losses":23,"wins":1},"claude-fable-5-1":{"draws":3,"losses":29,"wins":0},"claude-opus-4-5":{"draws":27,"losses":40,"wins":19},"claude-opus-4-8":{"draws":30,"losses":27,"wins":9},"claude-opus-5":{"draws":2,"losses":66,"wins":6},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":13,"losses":9,"wins":4},"claude-sonnet-5-5":{"draws":4,"losses":13,"wins":7},"cohere/north-mini-code":{"draws":10,"losses":4,"wins":20},"deepseek/deepseek-v4-flash":{"draws":29,"losses":27,"wins":12},"deepseek/deepseek-v4-pro":{"draws":12,"losses":7,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":13,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":9,"wins":1},"fireworks/ember-1":{"draws":6,"losses":9,"wins":1},"gemini-3.1-pro-preview":{"draws":9,"losses":15,"wins":2},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":14},"google/gemini-3.5-flash":{"draws":20,"losses":12,"wins":8},"google/gemini-3.5-flash-lite":{"draws":40,"losses":12,"wins":20},"google/gemini-3.6-flash":{"draws":28,"losses":32,"wins":16},"google/gemini-3.8-flash":{"draws":9,"losses":15,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":11,"wins":11},"gpt-4.1":{"draws":10,"losses":4,"wins":8},"gpt-5":{"draws":23,"losses":8,"wins":3},"gpt-5.4":{"draws":10,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":26,"losses":14,"wins":8},"gpt-5.4-nano":{"draws":22,"losses":18,"wins":16},"gpt-5.5":{"draws":26,"losses":20,"wins":6},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":22,"wins":5},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":4},"gpt-6-astra":{"draws":2,"losses":20,"wins":0},"gpt-6-luna":{"draws":6,"losses":15,"wins":3},"gpt-6-sol":{"draws":0,"losses":12,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":36,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":24,"losses":10,"wins":12},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":9},"meta/muse-spark-1.2":{"draws":9,"losses":10,"wins":7},"meta/muse-spark-1.3":{"draws":8,"losses":11,"wins":3},"minimax/minimax-m3":{"draws":23,"losses":14,"wins":7},"mistralai/mistral-medium-3-5":{"draws":15,"losses":11,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":18,"wins":10},"o3":{"draws":11,"losses":16,"wins":13},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":3},"poolside/laguna-s-2.1":{"draws":24,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":19,"losses":18,"wins":5},"qwen/qwen3.7-plus":{"draws":16,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":5},"qwen/qwen3.8-27b":{"draws":7,"losses":5,"wins":4},"qwen/qwen3.8-flash":{"draws":18,"losses":14,"wins":2},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":2},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":3},"stealth/ox-alpha":{"draws":31,"losses":49,"wins":10},"stealth/space-bunny-alpha":{"draws":5,"losses":4,"wins":1},"stepfun/step-3.7-flash":{"draws":16,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":30,"losses":7,"wins":13},"tencent/hy4-preview":{"draws":13,"losses":18,"wins":1},"thinkingmachines/inkling":{"draws":25,"losses":13,"wins":14},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":6},"x-ai/grok-4.5":{"draws":17,"losses":29,"wins":2},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":15,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":45,"losses":24,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":53,"losses":24,"wins":17},"z-ai/glm-5.3":{"draws":8,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":16,"losses":17,"wins":1},"z-ai/glm-5.3-flashx":{"draws":5,"losses":12,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":11,"wins":9},"claude-fable-5":{"draws":6,"losses":19,"wins":5},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-opus-4-5":{"draws":17,"losses":34,"wins":13},"claude-opus-4-8":{"draws":8,"losses":26,"wins":12},"claude-opus-5":{"draws":21,"losses":58,"wins":3},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":7,"losses":10,"wins":3},"claude-sonnet-5-5":{"draws":2,"losses":17,"wins":5},"cohere/north-mini-code":{"draws":10,"losses":14,"wins":4},"deepseek/deepseek-v4-flash":{"draws":21,"losses":35,"wins":12},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":13,"wins":1},"fireworks/ember-1":{"draws":5,"losses":14,"wins":5},"gemini-3.1-pro-preview":{"draws":3,"losses":17,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":17,"wins":11},"google/gemini-3.5-flash":{"draws":12,"losses":11,"wins":5},"google/gemini-3.5-flash-lite":{"draws":18,"losses":10,"wins":10},"google/gemini-3.6-flash":{"draws":14,"losses":25,"wins":7},"google/gemini-3.8-flash":{"draws":7,"losses":16,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":13,"wins":7},"gpt-4.1":{"draws":6,"losses":14,"wins":2},"gpt-5":{"draws":15,"losses":14,"wins":7},"gpt-5.4":{"draws":7,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":19,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":9},"gpt-5.5":{"draws":26,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":9,"wins":10},"gpt-5.6-sol":{"draws":5,"losses":14,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":2},"gpt-6-astra":{"draws":1,"losses":21,"wins":0},"gpt-6-luna":{"draws":3,"losses":15,"wins":4},"gpt-6-sol":{"draws":2,"losses":14,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":7,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":9,"wins":11},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":3},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":9},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":13,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":23,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":16,"losses":10,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":11},"o3":{"draws":15,"losses":20,"wins":11},"openai/gpt-oss-120b":{"draws":4,"losses":9,"wins":7},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":13,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":3,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.8-max-0902":{"draws":1,"losses":12,"wins":1},"stealth/ox-alpha":{"draws":23,"losses":41,"wins":10},"stealth/space-bunny-alpha":{"draws":8,"losses":9,"wins":1},"stepfun/step-3.7-flash":{"draws":12,"losses":11,"wins":13},"tencent/hy3-preview":{"draws":14,"losses":10,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":18,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":18,"wins":15},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":26,"wins":2},"x-ai/grok-4.6":{"draws":13,"losses":17,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":19,"wins":0},"x-ai/grok-build-0.1":{"draws":14,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":34,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":9,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":30,"losses":21,"wins":21},"z-ai/glm-5.3":{"draws":4,"losses":15,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":5},"z-ai/glm-5.3-flashx":{"draws":0,"losses":12,"wins":2}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":10},"claude-fable-5":{"draws":2,"losses":19,"wins":1},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":15,"losses":34,"wins":11},"claude-opus-4-8":{"draws":2,"losses":15,"wins":1},"claude-opus-5":{"draws":0,"losses":23,"wins":1},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":9,"losses":50,"wins":7},"claude-sonnet-5-5":{"draws":1,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":2},"deepseek/deepseek-v4-flash":{"draws":10,"losses":21,"wins":11},"deepseek/deepseek-v4-pro":{"draws":8,"losses":20,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":16,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":3,"losses":6,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":6},"google/gemini-3.5-flash":{"draws":9,"losses":20,"wins":7},"google/gemini-3.5-flash-lite":{"draws":39,"losses":77,"wins":24},"google/gemini-3.6-flash":{"draws":44,"losses":57,"wins":23},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":2},"gpt-4.1":{"draws":4,"losses":8,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":4,"losses":4,"wins":0},"gpt-5.4":{"draws":6,"losses":36,"wins":10},"gpt-5.4-mini":{"draws":2,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":18,"wins":8},"gpt-5.5":{"draws":10,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":29,"wins":17},"gpt-5.6-sol":{"draws":0,"losses":48,"wins":6},"gpt-5.6-terra":{"draws":5,"losses":21,"wins":4},"gpt-6-astra":{"draws":0,"losses":24,"wins":0},"gpt-6-luna":{"draws":7,"losses":9,"wins":2},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":9,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":17,"wins":10},"meituan/longcat-2.0":{"draws":11,"losses":25,"wins":24},"meta/muse-glimmer-30b":{"draws":15,"losses":14,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":35,"wins":5},"meta/muse-spark-1.3":{"draws":6,"losses":11,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":33,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":4},"o3":{"draws":15,"losses":52,"wins":17},"openai/gpt-oss-120b":{"draws":12,"losses":12,"wins":6},"poolside/laguna-s-2.1":{"draws":21,"losses":24,"wins":1},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":2},"qwen/qwen3.8-flash":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":59,"wins":15},"stealth/space-bunny-alpha":{"draws":5,"losses":4,"wins":1},"stepfun/step-3.7-flash":{"draws":9,"losses":12,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":17,"wins":4},"thinkingmachines/inkling":{"draws":27,"losses":14,"wins":17},"thinkingmachines/inkling-small":{"draws":19,"losses":12,"wins":11},"x-ai/grok-4.5":{"draws":12,"losses":38,"wins":4},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":12,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":1,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":28,"wins":4},"z-ai/glm-5.3":{"draws":2,"losses":18,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":11,"wins":5},"z-ai/glm-5.3-flashx":{"draws":4,"losses":9,"wins":3}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":23,"wins":15},"claude-fable-5":{"draws":9,"losses":22,"wins":3},"claude-fable-5-1":{"draws":0,"losses":32,"wins":0},"claude-opus-4-5":{"draws":20,"losses":28,"wins":4},"claude-opus-4-8":{"draws":2,"losses":9,"wins":1},"claude-opus-5":{"draws":3,"losses":28,"wins":1},"claude-opus-5-5":{"draws":3,"losses":19,"wins":0},"claude-sonnet-5":{"draws":23,"losses":31,"wins":8},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":26,"losses":17,"wins":19},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":14,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":5,"wins":0},"fireworks/ember-1":{"draws":5,"losses":11,"wins":0},"gemini-3.1-pro-preview":{"draws":10,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":11},"google/gemini-3.5-flash-lite":{"draws":35,"losses":28,"wins":27},"google/gemini-3.6-flash":{"draws":32,"losses":34,"wins":8},"google/gemini-3.8-flash":{"draws":16,"losses":27,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":7,"losses":10,"wins":3},"gpt-5.4":{"draws":14,"losses":24,"wins":8},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":7},"gpt-5.5":{"draws":7,"losses":15,"wins":0},"gpt-5.6-luna":{"draws":25,"losses":20,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":24,"wins":0},"gpt-5.6-terra":{"draws":16,"losses":33,"wins":3},"gpt-6-astra":{"draws":2,"losses":22,"wins":0},"gpt-6-luna":{"draws":7,"losses":13,"wins":4},"gpt-6-sol":{"draws":1,"losses":11,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":13,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":5},"meta/muse-glimmer-30b":{"draws":24,"losses":13,"wins":17},"meta/muse-spark-1.2":{"draws":8,"losses":21,"wins":1},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":22,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":6},"o3":{"draws":10,"losses":33,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":10,"wins":9},"poolside/laguna-s-2.1":{"draws":15,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":19,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":12,"wins":1},"stealth/ox-alpha":{"draws":47,"losses":82,"wins":13},"stealth/space-bunny-alpha":{"draws":4,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":10,"losses":16,"wins":6},"thinkingmachines/inkling":{"draws":10,"losses":18,"wins":16},"thinkingmachines/inkling-small":{"draws":24,"losses":8,"wins":28},"x-ai/grok-4.5":{"draws":12,"losses":17,"wins":7},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":10,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":33,"losses":21,"wins":14},"z-ai/glm-5.3":{"draws":14,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":15,"losses":22,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":3,"wins":1}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":13,"wins":14},"claude-fable-5":{"draws":8,"losses":36,"wins":12},"claude-fable-5-1":{"draws":2,"losses":42,"wins":0},"claude-opus-4-5":{"draws":47,"losses":59,"wins":22},"claude-opus-4-8":{"draws":17,"losses":54,"wins":13},"claude-opus-5":{"draws":12,"losses":154,"wins":14},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":11,"losses":27,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":36,"losses":19,"wins":9},"deepseek/deepseek-v4-flash":{"draws":41,"losses":25,"wins":34},"deepseek/deepseek-v4-pro":{"draws":10,"losses":21,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":16,"wins":8},"fireworks/ember-1":{"draws":17,"losses":14,"wins":9},"gemini-3.1-pro-preview":{"draws":8,"losses":16,"wins":12},"google/gemini-3.1-flash-lite":{"draws":12,"losses":18,"wins":24},"google/gemini-3.5-flash":{"draws":21,"losses":36,"wins":15},"google/gemini-3.5-flash-lite":{"draws":39,"losses":42,"wins":63},"google/gemini-3.6-flash":{"draws":45,"losses":49,"wins":36},"google/gemini-3.8-flash":{"draws":8,"losses":30,"wins":12},"google/gemma-4-31b-it":{"draws":4,"losses":16,"wins":26},"gpt-4.1":{"draws":7,"losses":17,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":24,"losses":18,"wins":30},"gpt-5.4":{"draws":22,"losses":26,"wins":4},"gpt-5.4-mini":{"draws":29,"losses":15,"wins":16},"gpt-5.4-nano":{"draws":38,"losses":35,"wins":43},"gpt-5.5":{"draws":37,"losses":31,"wins":22},"gpt-5.6-luna":{"draws":21,"losses":12,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":4},"gpt-5.6-terra":{"draws":22,"losses":24,"wins":10},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":15,"wins":19},"gpt-6-sol":{"draws":5,"losses":19,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":48,"losses":14,"wins":36},"meituan/longcat-2.0":{"draws":46,"losses":29,"wins":35},"meta/muse-glimmer-30b":{"draws":22,"losses":15,"wins":9},"meta/muse-spark-1.2":{"draws":8,"losses":26,"wins":14},"meta/muse-spark-1.3":{"draws":4,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":23,"losses":20,"wins":21},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":19},"moonshotai/kimi-k3":{"draws":28,"losses":25,"wins":23},"nex-agi/nex-n2-pro":{"draws":24,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":13,"wins":29},"o3":{"draws":13,"losses":35,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":37,"losses":23,"wins":30},"qwen/qwen3.7-max":{"draws":22,"losses":14,"wins":16},"qwen/qwen3.7-plus":{"draws":21,"losses":7,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":25,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":11},"qwen/qwen3.8-max-0902":{"draws":5,"losses":14,"wins":9},"stealth/ox-alpha":{"draws":45,"losses":96,"wins":42},"stealth/space-bunny-alpha":{"draws":8,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":19,"wins":19},"tencent/hy3-preview":{"draws":12,"losses":18,"wins":12},"tencent/hy4-preview":{"draws":19,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":29,"losses":27,"wins":42},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":20},"x-ai/grok-4.5":{"draws":24,"losses":73,"wins":25},"x-ai/grok-4.6":{"draws":15,"losses":36,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":10},"xiaomi/mimo-v2.5":{"draws":43,"losses":42,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":26,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":14,"wins":5},"z-ai/glm-5.2":{"draws":68,"losses":50,"wins":40},"z-ai/glm-5.3":{"draws":5,"losses":36,"wins":5},"z-ai/glm-5.3-flash":{"draws":15,"losses":33,"wins":10},"z-ai/glm-5.3-flashx":{"draws":3,"losses":14,"wins":9}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":15,"wins":4},"claude-fable-5":{"draws":6,"losses":17,"wins":3},"claude-fable-5-1":{"draws":0,"losses":34,"wins":0},"claude-opus-4-5":{"draws":28,"losses":37,"wins":11},"claude-opus-4-8":{"draws":14,"losses":28,"wins":10},"claude-opus-5":{"draws":14,"losses":72,"wins":2},"claude-opus-5-5":{"draws":3,"losses":23,"wins":0},"claude-sonnet-5":{"draws":8,"losses":11,"wins":5},"claude-sonnet-5-5":{"draws":4,"losses":12,"wins":6},"cohere/north-mini-code":{"draws":9,"losses":11,"wins":20},"deepseek/deepseek-v4-flash":{"draws":31,"losses":10,"wins":25},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":17,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":5},"fireworks/ember-1":{"draws":10,"losses":14,"wins":2},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":9,"wins":25},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":8},"google/gemini-3.5-flash-lite":{"draws":11,"losses":19,"wins":10},"google/gemini-3.6-flash":{"draws":15,"losses":33,"wins":8},"google/gemini-3.8-flash":{"draws":9,"losses":16,"wins":9},"google/gemma-4-31b-it":{"draws":2,"losses":11,"wins":21},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-5":{"draws":16,"losses":16,"wins":4},"gpt-5.4":{"draws":9,"losses":9,"wins":4},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":15},"gpt-5.4-nano":{"draws":18,"losses":23,"wins":21},"gpt-5.5":{"draws":17,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":11,"wins":5},"gpt-6-astra":{"draws":2,"losses":18,"wins":0},"gpt-6-luna":{"draws":4,"losses":12,"wins":12},"gpt-6-sol":{"draws":5,"losses":18,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":10,"wins":4},"inclusionai/ling-3.0-flash":{"draws":24,"losses":5,"wins":17},"meituan/longcat-2.0":{"draws":17,"losses":6,"wins":9},"meta/muse-glimmer-30b":{"draws":10,"losses":7,"wins":9},"meta/muse-spark-1.2":{"draws":5,"losses":8,"wins":1},"meta/muse-spark-1.3":{"draws":3,"losses":9,"wins":4},"minimax/minimax-m3":{"draws":20,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":19,"wins":6},"nex-agi/nex-n2-pro":{"draws":13,"losses":3,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":6,"wins":18},"o3":{"draws":10,"losses":22,"wins":8},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":19,"losses":20,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":16,"losses":9,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":14},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":8},"stealth/ox-alpha":{"draws":21,"losses":49,"wins":16},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":9},"stepfun/step-3.7-flash":{"draws":14,"losses":8,"wins":12},"tencent/hy3-preview":{"draws":23,"losses":8,"wins":15},"tencent/hy4-preview":{"draws":5,"losses":14,"wins":3},"thinkingmachines/inkling":{"draws":16,"losses":6,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":25,"wins":10},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":18,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":10,"wins":4},"xiaomi/mimo-v2.5":{"draws":37,"losses":17,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":7,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":33,"losses":25,"wins":16},"z-ai/glm-5.3":{"draws":6,"losses":7,"wins":1},"z-ai/glm-5.3-flash":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.3-flashx":{"draws":2,"losses":20,"wins":6}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":12,"wins":6},"claude-fable-5":{"draws":3,"losses":19,"wins":2},"claude-fable-5-1":{"draws":4,"losses":20,"wins":0},"claude-opus-4-5":{"draws":40,"losses":31,"wins":7},"claude-opus-4-8":{"draws":10,"losses":30,"wins":6},"claude-opus-5":{"draws":7,"losses":35,"wins":12},"claude-opus-5-5":{"draws":1,"losses":19,"wins":0},"claude-sonnet-5":{"draws":8,"losses":19,"wins":3},"claude-sonnet-5-5":{"draws":6,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":12},"deepseek/deepseek-v4-flash":{"draws":15,"losses":29,"wins":20},"deepseek/deepseek-v4-pro":{"draws":6,"losses":15,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":11,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":14,"wins":0},"fireworks/ember-1":{"draws":7,"losses":3,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":5,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":16,"wins":25},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":2},"google/gemini-3.5-flash-lite":{"draws":17,"losses":19,"wins":6},"google/gemini-3.6-flash":{"draws":23,"losses":32,"wins":5},"google/gemini-3.8-flash":{"draws":4,"losses":19,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":26,"wins":6},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-5":{"draws":4,"losses":14,"wins":0},"gpt-5.4":{"draws":6,"losses":23,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":36,"wins":14},"gpt-5.5":{"draws":20,"losses":30,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":16,"wins":1},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":7,"losses":14,"wins":3},"gpt-6-sol":{"draws":1,"losses":17,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":16,"losses":18,"wins":8},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":1},"meta/muse-glimmer-30b":{"draws":9,"losses":8,"wins":5},"meta/muse-spark-1.2":{"draws":4,"losses":10,"wins":2},"meta/muse-spark-1.3":{"draws":2,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":13,"losses":18,"wins":9},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":12,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":17,"wins":3},"nex-agi/nex-n2-pro":{"draws":12,"losses":16,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":14,"wins":11},"o3":{"draws":4,"losses":29,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":14,"wins":3},"poolside/laguna-s-2.1":{"draws":10,"losses":19,"wins":3},"qwen/qwen3.7-max":{"draws":14,"losses":18,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":17,"wins":1},"qwen/qwen3.8-27b":{"draws":0,"losses":13,"wins":3},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":12,"wins":2},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":7,"losses":40,"wins":3},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":2},"stepfun/step-3.7-flash":{"draws":8,"losses":15,"wins":11},"tencent/hy3-preview":{"draws":12,"losses":21,"wins":5},"tencent/hy4-preview":{"draws":4,"losses":11,"wins":3},"thinkingmachines/inkling":{"draws":16,"losses":27,"wins":17},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":2},"x-ai/grok-4.5":{"draws":16,"losses":28,"wins":0},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":3},"xiaomi/mimo-v2.5":{"draws":35,"losses":49,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":26,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":31,"losses":43,"wins":10},"z-ai/glm-5.3":{"draws":5,"losses":20,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":21,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":15,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":18},"claude-fable-5":{"draws":13,"losses":37,"wins":14},"claude-fable-5-1":{"draws":3,"losses":63,"wins":0},"claude-opus-4-5":{"draws":24,"losses":25,"wins":29},"claude-opus-4-8":{"draws":12,"losses":13,"wins":7},"claude-opus-5":{"draws":3,"losses":33,"wins":10},"claude-opus-5-5":{"draws":5,"losses":23,"wins":0},"claude-sonnet-5":{"draws":21,"losses":13,"wins":26},"claude-sonnet-5-5":{"draws":5,"losses":14,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":26,"losses":11,"wins":41},"deepseek/deepseek-v4-pro":{"draws":19,"losses":15,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":25,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":10,"losses":9,"wins":11},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":20,"losses":25,"wins":25},"google/gemini-3.5-flash-lite":{"draws":35,"losses":29,"wins":44},"google/gemini-3.6-flash":{"draws":26,"losses":50,"wins":34},"google/gemini-3.8-flash":{"draws":9,"losses":38,"wins":21},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":3,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":6,"wins":11},"gpt-5.4":{"draws":12,"losses":14,"wins":24},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":12},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":17},"gpt-5.5":{"draws":6,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":23,"losses":15,"wins":18},"gpt-5.6-sol":{"draws":14,"losses":38,"wins":10},"gpt-5.6-terra":{"draws":19,"losses":10,"wins":31},"gpt-6-astra":{"draws":6,"losses":53,"wins":1},"gpt-6-luna":{"draws":9,"losses":12,"wins":9},"gpt-6-sol":{"draws":2,"losses":11,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":18},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":16},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":27},"meta/muse-glimmer-30b":{"draws":20,"losses":16,"wins":20},"meta/muse-spark-1.2":{"draws":5,"losses":11,"wins":26},"meta/muse-spark-1.3":{"draws":15,"losses":16,"wins":23},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":20,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"o3":{"draws":11,"losses":17,"wins":38},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":21,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":18,"wins":20},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":16},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":4},"stealth/ox-alpha":{"draws":43,"losses":87,"wins":67},"stealth/space-bunny-alpha":{"draws":6,"losses":9,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":5},"tencent/hy4-preview":{"draws":20,"losses":25,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":13,"wins":21},"thinkingmachines/inkling-small":{"draws":22,"losses":7,"wins":45},"x-ai/grok-4.5":{"draws":13,"losses":26,"wins":21},"x-ai/grok-4.6":{"draws":19,"losses":32,"wins":19},"x-ai/grok-4.7":{"draws":4,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":17,"losses":6,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":23,"losses":25,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":22,"losses":24,"wins":26},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":6}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":2},"claude-fable-5":{"draws":6,"losses":7,"wins":1},"claude-fable-5-1":{"draws":2,"losses":16,"wins":0},"claude-opus-4-5":{"draws":11,"losses":4,"wins":1},"claude-opus-4-8":{"draws":3,"losses":4,"wins":1},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":12,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":14,"losses":2,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":4,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":1},"fireworks/ember-1":{"draws":0,"losses":4,"wins":0},"gemini-3.1-pro-preview":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":9,"losses":4,"wins":5},"google/gemini-3.5-flash-lite":{"draws":21,"losses":1,"wins":8},"google/gemini-3.6-flash":{"draws":21,"losses":10,"wins":3},"google/gemini-3.8-flash":{"draws":12,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":3,"wins":3},"gpt-5.4":{"draws":14,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":2},"gpt-5.5":{"draws":6,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":7,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":2},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":2,"losses":4,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":4},"meta/muse-glimmer-30b":{"draws":18,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":3,"losses":6,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":8,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":1},"o3":{"draws":13,"losses":3,"wins":0},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":2},"qwen/qwen3.8-flash":{"draws":9,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":7,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":26,"losses":13,"wins":7},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":0},"tencent/hy4-preview":{"draws":12,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":2,"wins":4},"thinkingmachines/inkling-small":{"draws":14,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":4},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":18,"losses":4,"wins":4},"z-ai/glm-5.3":{"draws":3,"losses":6,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":8,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":1}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":26,"wins":23},"claude-fable-5":{"draws":16,"losses":47,"wins":1},"claude-fable-5-1":{"draws":6,"losses":54,"wins":0},"claude-opus-4-5":{"draws":31,"losses":41,"wins":8},"claude-opus-4-8":{"draws":9,"losses":24,"wins":3},"claude-opus-5":{"draws":9,"losses":51,"wins":2},"claude-opus-5-5":{"draws":2,"losses":25,"wins":1},"claude-sonnet-5":{"draws":27,"losses":38,"wins":9},"claude-sonnet-5-5":{"draws":3,"losses":13,"wins":4},"cohere/north-mini-code":{"draws":10,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":25,"losses":29,"wins":28},"deepseek/deepseek-v4-pro":{"draws":24,"losses":32,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":27,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":20,"wins":2},"fireworks/ember-1":{"draws":11,"losses":8,"wins":3},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":23,"losses":43,"wins":12},"google/gemini-3.5-flash-lite":{"draws":51,"losses":33,"wins":48},"google/gemini-3.6-flash":{"draws":55,"losses":54,"wins":9},"google/gemini-3.8-flash":{"draws":15,"losses":47,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":7,"wins":7},"gpt-4.1":{"draws":3,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":6,"losses":18,"wins":6},"gpt-5.4":{"draws":19,"losses":26,"wins":13},"gpt-5.4-mini":{"draws":7,"losses":6,"wins":9},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":14},"gpt-5.5":{"draws":16,"losses":20,"wins":2},"gpt-5.6-luna":{"draws":20,"losses":31,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":42,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":35,"wins":11},"gpt-6-astra":{"draws":6,"losses":44,"wins":0},"gpt-6-luna":{"draws":8,"losses":23,"wins":7},"gpt-6-sol":{"draws":0,"losses":24,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":19,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":3},"inception/mercury-2.5-preview":{"draws":24,"losses":11,"wins":19},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":20},"meituan/longcat-2.0":{"draws":22,"losses":14,"wins":20},"meta/muse-glimmer-30b":{"draws":34,"losses":17,"wins":15},"meta/muse-spark-1.2":{"draws":15,"losses":25,"wins":6},"meta/muse-spark-1.3":{"draws":14,"losses":40,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":16,"wins":4},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":25,"losses":34,"wins":5},"nex-agi/nex-n2-pro":{"draws":16,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":14,"wins":14},"o3":{"draws":20,"losses":42,"wins":16},"openai/gpt-oss-120b":{"draws":24,"losses":25,"wins":21},"poolside/laguna-s-2.1":{"draws":22,"losses":21,"wins":15},"qwen/qwen3.7-max":{"draws":16,"losses":20,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":36,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":23,"wins":3},"qwen/qwen3.8-flash":{"draws":11,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":29,"losses":26,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":6},"stealth/ox-alpha":{"draws":58,"losses":112,"wins":40},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":4},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":11,"wins":3},"tencent/hy4-preview":{"draws":16,"losses":39,"wins":7},"thinkingmachines/inkling":{"draws":26,"losses":18,"wins":26},"thinkingmachines/inkling-small":{"draws":33,"losses":20,"wins":25},"x-ai/grok-4.5":{"draws":14,"losses":30,"wins":10},"x-ai/grok-4.6":{"draws":23,"losses":37,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":16,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":18,"losses":22,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":12,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":45,"losses":40,"wins":21},"z-ai/glm-5.3":{"draws":13,"losses":44,"wins":5},"z-ai/glm-5.3-flash":{"draws":33,"losses":31,"wins":8},"z-ai/glm-5.3-flashx":{"draws":8,"losses":20,"wins":2}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":24,"wins":19},"claude-fable-5":{"draws":14,"losses":21,"wins":23},"claude-fable-5-1":{"draws":0,"losses":51,"wins":5},"claude-opus-4-5":{"draws":21,"losses":29,"wins":20},"claude-opus-4-8":{"draws":4,"losses":9,"wins":7},"claude-opus-5":{"draws":8,"losses":33,"wins":3},"claude-opus-5-5":{"draws":3,"losses":29,"wins":2},"claude-sonnet-5":{"draws":29,"losses":25,"wins":19},"claude-sonnet-5-5":{"draws":7,"losses":16,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":35,"losses":9,"wins":26},"deepseek/deepseek-v4-pro":{"draws":21,"losses":15,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":11,"wins":3},"fireworks/ember-1":{"draws":11,"losses":13,"wins":8},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":18,"losses":15,"wins":19},"google/gemini-3.5-flash-lite":{"draws":43,"losses":33,"wins":25},"google/gemini-3.6-flash":{"draws":39,"losses":33,"wins":40},"google/gemini-3.8-flash":{"draws":10,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":9,"losses":2,"wins":15},"gpt-5.4":{"draws":23,"losses":14,"wins":27},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":11},"gpt-5.5":{"draws":8,"losses":9,"wins":9},"gpt-5.6-luna":{"draws":28,"losses":12,"wins":31},"gpt-5.6-sol":{"draws":10,"losses":22,"wins":13},"gpt-5.6-terra":{"draws":29,"losses":19,"wins":26},"gpt-6-astra":{"draws":1,"losses":37,"wins":2},"gpt-6-luna":{"draws":11,"losses":15,"wins":12},"gpt-6-sol":{"draws":2,"losses":20,"wins":8},"gpt-6.1-sol":{"draws":0,"losses":23,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":29,"losses":6,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":16},"meituan/longcat-2.0":{"draws":30,"losses":10,"wins":15},"meta/muse-glimmer-30b":{"draws":22,"losses":14,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":17,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":8},"mistralai/mistral-medium-3-5":{"draws":13,"losses":10,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":12},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":9},"o3":{"draws":14,"losses":23,"wins":25},"openai/gpt-oss-120b":{"draws":31,"losses":5,"wins":20},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":18,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":21,"losses":29,"wins":12},"qwen/qwen3.8-max-0902":{"draws":9,"losses":15,"wins":2},"stealth/ox-alpha":{"draws":56,"losses":68,"wins":52},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":16,"losses":26,"wins":18},"thinkingmachines/inkling":{"draws":20,"losses":11,"wins":23},"thinkingmachines/inkling-small":{"draws":44,"losses":31,"wins":35},"x-ai/grok-4.5":{"draws":23,"losses":19,"wins":18},"x-ai/grok-4.6":{"draws":18,"losses":30,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":9,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":31,"losses":21,"wins":28},"z-ai/glm-5.3":{"draws":14,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":14,"losses":26,"wins":18},"z-ai/glm-5.3-flashx":{"draws":9,"losses":12,"wins":7}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":2,"wins":6},"claude-fable-5":{"draws":6,"losses":19,"wins":3},"claude-fable-5-1":{"draws":0,"losses":26,"wins":0},"claude-opus-4-5":{"draws":14,"losses":7,"wins":13},"claude-opus-4-8":{"draws":9,"losses":7,"wins":8},"claude-opus-5":{"draws":4,"losses":28,"wins":0},"claude-opus-5-5":{"draws":2,"losses":45,"wins":1},"claude-sonnet-5":{"draws":8,"losses":5,"wins":7},"claude-sonnet-5-5":{"draws":11,"losses":20,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":13,"losses":1,"wins":18},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":6,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":18,"losses":12,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":19},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":11,"losses":5,"wins":14},"google/gemini-3.5-flash-lite":{"draws":14,"losses":4,"wins":16},"google/gemini-3.6-flash":{"draws":10,"losses":12,"wins":12},"google/gemini-3.8-flash":{"draws":5,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":5,"losses":1,"wins":6},"gpt-5":{"draws":6,"losses":0,"wins":2},"gpt-5.4":{"draws":10,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":5,"wins":5},"gpt-5.5":{"draws":15,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":17,"losses":1,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":8},"gpt-6-astra":{"draws":1,"losses":21,"wins":2},"gpt-6-luna":{"draws":18,"losses":13,"wins":15},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":8},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":19},"meta/muse-glimmer-30b":{"draws":14,"losses":1,"wins":7},"meta/muse-spark-1.2":{"draws":2,"losses":3,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":11,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":6,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":12},"o3":{"draws":6,"losses":7,"wins":11},"openai/gpt-oss-120b":{"draws":15,"losses":1,"wins":12},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":1,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":3,"wins":6},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":9},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":9},"stealth/ox-alpha":{"draws":17,"losses":21,"wins":24},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":19},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":1,"losses":9,"wins":8},"thinkingmachines/inkling":{"draws":9,"losses":2,"wins":9},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":13,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":19,"losses":6,"wins":13},"z-ai/glm-5.3":{"draws":13,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":13,"wins":5},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":78,"losses":41,"wins":83},"claude-fable-5":{"draws":56,"losses":146,"wins":32},"claude-fable-5-1":{"draws":12,"losses":200,"wins":2},"claude-opus-4-5":{"draws":101,"losses":74,"wins":65},"claude-opus-4-8":{"draws":30,"losses":44,"wins":30},"claude-opus-5":{"draws":19,"losses":147,"wins":12},"claude-opus-5-5":{"draws":7,"losses":75,"wins":0},"claude-sonnet-5":{"draws":75,"losses":64,"wins":59},"claude-sonnet-5-5":{"draws":14,"losses":49,"wins":21},"cohere/north-mini-code":{"draws":19,"losses":8,"wins":33},"deepseek/deepseek-v4-flash":{"draws":134,"losses":59,"wins":71},"deepseek/deepseek-v4-pro":{"draws":103,"losses":70,"wins":55},"deepseek/deepseek-v4-pro-0813":{"draws":91,"losses":82,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":40,"wins":20},"fireworks/ember-1":{"draws":25,"losses":35,"wins":16},"gemini-3.1-pro-preview":{"draws":25,"losses":24,"wins":35},"google/gemini-3.1-flash-lite":{"draws":14,"losses":3,"wins":35},"google/gemini-3.5-flash":{"draws":79,"losses":109,"wins":54},"google/gemini-3.5-flash-lite":{"draws":147,"losses":102,"wins":143},"google/gemini-3.6-flash":{"draws":116,"losses":144,"wins":102},"google/gemini-3.8-flash":{"draws":77,"losses":104,"wins":35},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":28},"gpt-4.1":{"draws":15,"losses":10,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":46,"losses":22,"wins":26},"gpt-5.4":{"draws":87,"losses":83,"wins":24},"gpt-5.4-mini":{"draws":34,"losses":19,"wins":19},"gpt-5.4-nano":{"draws":30,"losses":20,"wins":44},"gpt-5.5":{"draws":29,"losses":24,"wins":15},"gpt-5.6-luna":{"draws":99,"losses":57,"wins":52},"gpt-5.6-sol":{"draws":45,"losses":121,"wins":32},"gpt-5.6-terra":{"draws":108,"losses":65,"wins":53},"gpt-6-astra":{"draws":16,"losses":162,"wins":0},"gpt-6-luna":{"draws":26,"losses":51,"wins":27},"gpt-6-sol":{"draws":7,"losses":49,"wins":6},"gpt-6.1-sol":{"draws":8,"losses":73,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":22,"losses":2,"wins":10},"inception/mercury-2.5-preview":{"draws":66,"losses":11,"wins":71},"inclusionai/ling-3.0-flash":{"draws":48,"losses":17,"wins":37},"meituan/longcat-2.0":{"draws":62,"losses":28,"wins":87},"meta/muse-glimmer-30b":{"draws":108,"losses":33,"wins":73},"meta/muse-spark-1.2":{"draws":53,"losses":55,"wins":64},"meta/muse-spark-1.3":{"draws":64,"losses":81,"wins":49},"minimax/minimax-m3":{"draws":20,"losses":8,"wins":20},"mistralai/mistral-medium-3-5":{"draws":58,"losses":23,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":89,"losses":67,"wins":54},"nex-agi/nex-n2-pro":{"draws":18,"losses":7,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":10,"wins":23},"o3":{"draws":49,"losses":93,"wins":68},"openai/gpt-oss-120b":{"draws":95,"losses":38,"wins":71},"poolside/laguna-s-2.1":{"draws":81,"losses":37,"wins":58},"qwen/qwen3.7-max":{"draws":23,"losses":15,"wins":16},"qwen/qwen3.7-plus":{"draws":14,"losses":6,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":62,"losses":74,"wins":60},"qwen/qwen3.8-27b":{"draws":46,"losses":43,"wins":41},"qwen/qwen3.8-flash":{"draws":68,"losses":52,"wins":28},"qwen/qwen3.8-max":{"draws":71,"losses":86,"wins":49},"qwen/qwen3.8-max-0902":{"draws":18,"losses":40,"wins":14},"stealth/ox-alpha":{"draws":245,"losses":380,"wins":216},"stealth/space-bunny-alpha":{"draws":31,"losses":24,"wins":29},"stepfun/step-3.7-flash":{"draws":26,"losses":13,"wins":25},"tencent/hy3-preview":{"draws":22,"losses":9,"wins":13},"tencent/hy4-preview":{"draws":88,"losses":95,"wins":39},"thinkingmachines/inkling":{"draws":71,"losses":28,"wins":73},"thinkingmachines/inkling-small":{"draws":122,"losses":41,"wins":85},"x-ai/grok-4.5":{"draws":64,"losses":75,"wins":55},"x-ai/grok-4.6":{"draws":99,"losses":108,"wins":43},"x-ai/grok-4.7":{"draws":6,"losses":55,"wins":7},"x-ai/grok-build-0.1":{"draws":20,"losses":9,"wins":23},"xiaomi/mimo-v2.5":{"draws":58,"losses":34,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":18,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":28,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":37,"wins":6},"z-ai/glm-5.2":{"draws":132,"losses":86,"wins":98},"z-ai/glm-5.3":{"draws":48,"losses":112,"wins":28},"z-ai/glm-5.3-flash":{"draws":78,"losses":114,"wins":58},"z-ai/glm-5.3-flashx":{"draws":15,"losses":56,"wins":15}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":5},"claude-fable-5":{"draws":7,"losses":0,"wins":1},"claude-fable-5-1":{"draws":0,"losses":23,"wins":1},"claude-opus-4-5":{"draws":12,"losses":13,"wins":1},"claude-opus-4-8":{"draws":4,"losses":5,"wins":3},"claude-opus-5":{"draws":4,"losses":20,"wins":0},"claude-opus-5-5":{"draws":2,"losses":26,"wins":0},"claude-sonnet-5":{"draws":8,"losses":11,"wins":3},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":6},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":9,"losses":5,"wins":10},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":5},"fireworks/ember-1":{"draws":14,"losses":18,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":5,"losses":8,"wins":5},"google/gemini-3.5-flash-lite":{"draws":15,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":14,"losses":17,"wins":3},"google/gemini-3.8-flash":{"draws":10,"losses":9,"wins":3},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":6,"wins":0},"gpt-5.4":{"draws":10,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":5},"gpt-5.5":{"draws":10,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":3},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":8,"wins":4},"gpt-6-astra":{"draws":3,"losses":19,"wins":0},"gpt-6-luna":{"draws":6,"losses":9,"wins":3},"gpt-6-sol":{"draws":6,"losses":24,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":5,"wins":7},"meta/muse-glimmer-30b":{"draws":10,"losses":5,"wins":1},"meta/muse-spark-1.2":{"draws":6,"losses":5,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":15,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":6},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":8,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":9,"wins":5},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":9,"losses":2,"wins":3},"qwen/qwen3.8-max":{"draws":9,"losses":8,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":15,"wins":2},"stealth/ox-alpha":{"draws":26,"losses":32,"wins":8},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":5,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":11,"losses":9,"wins":4},"thinkingmachines/inkling-small":{"draws":8,"losses":5,"wins":1},"x-ai/grok-4.5":{"draws":4,"losses":5,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":4,"wins":0},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":20,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":13,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":3},"z-ai/glm-5.2":{"draws":24,"losses":13,"wins":7},"z-ai/glm-5.3":{"draws":4,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":7,"wins":0},"z-ai/glm-5.3-flashx":{"draws":14,"losses":15,"wins":5}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":10,"wins":14},"claude-fable-5":{"draws":0,"losses":30,"wins":2},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-opus-4-5":{"draws":8,"losses":47,"wins":19},"claude-opus-4-8":{"draws":0,"losses":20,"wins":4},"claude-opus-5":{"draws":0,"losses":30,"wins":0},"claude-opus-5-5":{"draws":0,"losses":17,"wins":1},"claude-sonnet-5":{"draws":7,"losses":25,"wins":24},"claude-sonnet-5-5":{"draws":0,"losses":7,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":7,"losses":18,"wins":17},"deepseek/deepseek-v4-pro":{"draws":8,"losses":23,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":6,"wins":2},"fireworks/ember-1":{"draws":0,"losses":5,"wins":3},"gemini-3.1-pro-preview":{"draws":0,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":8,"losses":22,"wins":10},"google/gemini-3.5-flash-lite":{"draws":30,"losses":45,"wins":55},"google/gemini-3.6-flash":{"draws":17,"losses":79,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":25,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":15},"gpt-4.1":{"draws":0,"losses":4,"wins":4},"gpt-5":{"draws":3,"losses":3,"wins":2},"gpt-5.4":{"draws":9,"losses":37,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":18,"wins":4},"gpt-5.5":{"draws":2,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":19,"wins":19},"gpt-5.6-sol":{"draws":2,"losses":34,"wins":10},"gpt-5.6-terra":{"draws":5,"losses":18,"wins":9},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":2,"losses":9,"wins":5},"gpt-6-sol":{"draws":1,"losses":11,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":6,"wins":19},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":18},"meituan/longcat-2.0":{"draws":8,"losses":30,"wins":30},"meta/muse-glimmer-30b":{"draws":10,"losses":13,"wins":5},"meta/muse-spark-1.2":{"draws":0,"losses":25,"wins":9},"meta/muse-spark-1.3":{"draws":3,"losses":22,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":8,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":38,"wins":11},"nex-agi/nex-n2-pro":{"draws":6,"losses":9,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":5},"o3":{"draws":21,"losses":66,"wins":31},"openai/gpt-oss-120b":{"draws":6,"losses":13,"wins":13},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-27b":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":7},"qwen/qwen3.8-max":{"draws":1,"losses":18,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":11,"losses":34,"wins":27},"stealth/space-bunny-alpha":{"draws":0,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":22,"wins":24},"thinkingmachines/inkling-small":{"draws":10,"losses":14,"wins":14},"x-ai/grok-4.5":{"draws":4,"losses":37,"wins":13},"x-ai/grok-4.6":{"draws":1,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":6,"losses":13,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":5,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":14,"losses":18,"wins":20},"z-ai/glm-5.3":{"draws":4,"losses":15,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":14,"wins":8},"z-ai/glm-5.3-flashx":{"draws":4,"losses":10,"wins":2}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":6},"claude-fable-5":{"draws":7,"losses":17,"wins":2},"claude-fable-5-1":{"draws":3,"losses":20,"wins":3},"claude-opus-4-5":{"draws":23,"losses":18,"wins":9},"claude-opus-4-8":{"draws":21,"losses":15,"wins":6},"claude-opus-5":{"draws":24,"losses":49,"wins":9},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":15,"losses":8,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":13,"wins":20},"deepseek/deepseek-v4-pro":{"draws":12,"losses":8,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":10,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":1},"fireworks/ember-1":{"draws":5,"losses":4,"wins":3},"gemini-3.1-pro-preview":{"draws":7,"losses":8,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":6,"wins":7},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":5},"google/gemini-3.5-flash-lite":{"draws":31,"losses":5,"wins":16},"google/gemini-3.6-flash":{"draws":22,"losses":16,"wins":10},"google/gemini-3.8-flash":{"draws":19,"losses":12,"wins":3},"google/gemma-4-31b-it":{"draws":14,"losses":2,"wins":8},"gpt-4.1":{"draws":11,"losses":5,"wins":6},"gpt-5":{"draws":18,"losses":9,"wins":5},"gpt-5.4":{"draws":13,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":20,"losses":9,"wins":19},"gpt-5.5":{"draws":22,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":7,"losses":6,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":18,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":0},"gpt-6-astra":{"draws":1,"losses":13,"wins":0},"gpt-6-luna":{"draws":6,"losses":15,"wins":3},"gpt-6-sol":{"draws":3,"losses":13,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":3},"inclusionai/ling-3.0-flash":{"draws":18,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":23,"losses":10,"wins":9},"meta/muse-glimmer-30b":{"draws":12,"losses":2,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":4},"meta/muse-spark-1.3":{"draws":3,"losses":14,"wins":1},"minimax/minimax-m3":{"draws":20,"losses":10,"wins":18},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":3},"nex-agi/nex-n2-pro":{"draws":20,"losses":9,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":6,"wins":6},"o3":{"draws":13,"losses":12,"wins":7},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":5},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":17,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":20,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":2},"qwen/qwen3.8-flash":{"draws":14,"losses":8,"wins":6},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.8-max-0902":{"draws":5,"losses":5,"wins":0},"stealth/ox-alpha":{"draws":26,"losses":22,"wins":12},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":2},"stepfun/step-3.7-flash":{"draws":12,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy4-preview":{"draws":10,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":18,"wins":14},"thinkingmachines/inkling-small":{"draws":11,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":16,"losses":19,"wins":7},"x-ai/grok-4.6":{"draws":20,"losses":17,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":5,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":43,"losses":15,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":6,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":0,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":44,"losses":25,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":10,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":15,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":2,"wins":1}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":13,"wins":29},"claude-fable-5":{"draws":13,"losses":50,"wins":1},"claude-fable-5-1":{"draws":3,"losses":55,"wins":0},"claude-opus-4-5":{"draws":26,"losses":37,"wins":15},"claude-opus-4-8":{"draws":8,"losses":10,"wins":12},"claude-opus-5":{"draws":9,"losses":48,"wins":5},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":25,"losses":22,"wins":13},"claude-sonnet-5-5":{"draws":2,"losses":8,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":18,"wins":20},"deepseek/deepseek-v4-pro":{"draws":24,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":7},"fireworks/ember-1":{"draws":13,"losses":12,"wins":7},"gemini-3.1-pro-preview":{"draws":9,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":23,"losses":32,"wins":21},"google/gemini-3.5-flash-lite":{"draws":49,"losses":31,"wins":48},"google/gemini-3.6-flash":{"draws":39,"losses":43,"wins":28},"google/gemini-3.8-flash":{"draws":17,"losses":23,"wins":14},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":12},"gpt-4.1":{"draws":2,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":9,"losses":9,"wins":8},"gpt-5.4":{"draws":21,"losses":17,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":14},"gpt-5.5":{"draws":12,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":26,"losses":12,"wins":26},"gpt-5.6-sol":{"draws":9,"losses":45,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":23,"wins":21},"gpt-6-astra":{"draws":4,"losses":42,"wins":0},"gpt-6-luna":{"draws":7,"losses":10,"wins":7},"gpt-6-sol":{"draws":0,"losses":11,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":24,"losses":5,"wins":21},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":16},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":28},"meta/muse-glimmer-30b":{"draws":27,"losses":8,"wins":19},"meta/muse-spark-1.2":{"draws":14,"losses":22,"wins":14},"meta/muse-spark-1.3":{"draws":18,"losses":24,"wins":14},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":8},"mistralai/mistral-medium-3-5":{"draws":22,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":31,"losses":25,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":4,"wins":11},"o3":{"draws":14,"losses":36,"wins":20},"openai/gpt-oss-120b":{"draws":20,"losses":14,"wins":22},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":24,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":19,"losses":16,"wins":17},"qwen/qwen3.8-max":{"draws":19,"losses":17,"wins":26},"qwen/qwen3.8-max-0902":{"draws":9,"losses":13,"wins":2},"stealth/ox-alpha":{"draws":56,"losses":91,"wins":59},"stealth/space-bunny-alpha":{"draws":4,"losses":5,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":15,"wins":7},"thinkingmachines/inkling":{"draws":26,"losses":16,"wins":22},"thinkingmachines/inkling-small":{"draws":31,"losses":11,"wins":28},"x-ai/grok-4.5":{"draws":17,"losses":24,"wins":9},"x-ai/grok-4.6":{"draws":18,"losses":30,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":18,"losses":3,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":30,"losses":22,"wins":26},"z-ai/glm-5.3":{"draws":11,"losses":42,"wins":7},"z-ai/glm-5.3-flash":{"draws":21,"losses":29,"wins":16},"z-ai/glm-5.3-flashx":{"draws":5,"losses":8,"wins":3}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":22,"wins":15},"claude-fable-5":{"draws":8,"losses":36,"wins":4},"claude-fable-5-1":{"draws":5,"losses":47,"wins":0},"claude-opus-4-5":{"draws":57,"losses":59,"wins":26},"claude-opus-4-8":{"draws":17,"losses":49,"wins":14},"claude-opus-5":{"draws":18,"losses":111,"wins":17},"claude-opus-5-5":{"draws":1,"losses":25,"wins":0},"claude-sonnet-5":{"draws":14,"losses":21,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":17,"wins":3},"cohere/north-mini-code":{"draws":11,"losses":18,"wins":23},"deepseek/deepseek-v4-flash":{"draws":32,"losses":34,"wins":44},"deepseek/deepseek-v4-pro":{"draws":10,"losses":24,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":13,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":9},"fireworks/ember-1":{"draws":18,"losses":11,"wins":3},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":9},"google/gemini-3.1-flash-lite":{"draws":25,"losses":19,"wins":36},"google/gemini-3.5-flash":{"draws":11,"losses":24,"wins":13},"google/gemini-3.5-flash-lite":{"draws":38,"losses":45,"wins":35},"google/gemini-3.6-flash":{"draws":39,"losses":74,"wins":23},"google/gemini-3.8-flash":{"draws":7,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":16,"losses":15,"wins":23},"gpt-4.1":{"draws":8,"losses":10,"wins":20},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":27,"losses":34,"wins":11},"gpt-5.4":{"draws":17,"losses":26,"wins":5},"gpt-5.4-mini":{"draws":29,"losses":19,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":39,"wins":27},"gpt-5.5":{"draws":23,"losses":50,"wins":21},"gpt-5.6-luna":{"draws":11,"losses":21,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":20,"wins":11},"gpt-6-astra":{"draws":1,"losses":36,"wins":1},"gpt-6-luna":{"draws":7,"losses":21,"wins":10},"gpt-6-sol":{"draws":3,"losses":23,"wins":0},"gpt-6.1-sol":{"draws":4,"losses":25,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":10},"inclusionai/ling-3.0-flash":{"draws":27,"losses":27,"wins":36},"meituan/longcat-2.0":{"draws":24,"losses":25,"wins":33},"meta/muse-glimmer-30b":{"draws":16,"losses":12,"wins":16},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":9},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":15,"losses":25,"wins":26},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":15,"wins":13},"moonshotai/kimi-k3":{"draws":24,"losses":36,"wins":6},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":24,"wins":36},"o3":{"draws":7,"losses":49,"wins":20},"openai/gpt-oss-120b":{"draws":8,"losses":11,"wins":17},"poolside/laguna-s-2.1":{"draws":31,"losses":36,"wins":31},"qwen/qwen3.7-max":{"draws":24,"losses":31,"wins":11},"qwen/qwen3.7-plus":{"draws":18,"losses":24,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":2,"losses":20,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":22,"wins":6},"qwen/qwen3.8-max":{"draws":17,"losses":19,"wins":8},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":4},"stealth/ox-alpha":{"draws":30,"losses":80,"wins":26},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":9,"losses":31,"wins":18},"tencent/hy3-preview":{"draws":24,"losses":16,"wins":18},"tencent/hy4-preview":{"draws":17,"losses":28,"wins":9},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":31},"thinkingmachines/inkling-small":{"draws":7,"losses":10,"wins":17},"x-ai/grok-4.5":{"draws":34,"losses":54,"wins":20},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":9},"x-ai/grok-4.7":{"draws":0,"losses":21,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":12},"xiaomi/mimo-v2.5":{"draws":58,"losses":75,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":32,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":2},"z-ai/glm-5.2":{"draws":47,"losses":52,"wins":35},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":17,"losses":33,"wins":6},"z-ai/glm-5.3-flashx":{"draws":5,"losses":23,"wins":4}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":28,"wins":11},"claude-fable-5":{"draws":13,"losses":31,"wins":6},"claude-fable-5-1":{"draws":3,"losses":38,"wins":1},"claude-opus-4-5":{"draws":23,"losses":34,"wins":3},"claude-opus-4-8":{"draws":7,"losses":12,"wins":1},"claude-opus-5":{"draws":7,"losses":30,"wins":3},"claude-opus-5-5":{"draws":3,"losses":21,"wins":0},"claude-sonnet-5":{"draws":22,"losses":38,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":19,"wins":3},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":5},"deepseek/deepseek-v4-flash":{"draws":46,"losses":33,"wins":7},"deepseek/deepseek-v4-pro":{"draws":35,"losses":23,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":11,"wins":4},"fireworks/ember-1":{"draws":9,"losses":24,"wins":1},"gemini-3.1-pro-preview":{"draws":10,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":6,"wins":5},"google/gemini-3.5-flash":{"draws":24,"losses":27,"wins":5},"google/gemini-3.5-flash-lite":{"draws":47,"losses":43,"wins":30},"google/gemini-3.6-flash":{"draws":32,"losses":50,"wins":19},"google/gemini-3.8-flash":{"draws":20,"losses":28,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":16,"losses":11,"wins":1},"gpt-5.4":{"draws":29,"losses":14,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":11,"wins":4},"gpt-5.5":{"draws":6,"losses":19,"wins":3},"gpt-5.6-luna":{"draws":23,"losses":24,"wins":11},"gpt-5.6-sol":{"draws":12,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":26,"losses":38,"wins":4},"gpt-6-astra":{"draws":2,"losses":30,"wins":0},"gpt-6-luna":{"draws":5,"losses":18,"wins":5},"gpt-6-sol":{"draws":3,"losses":21,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":25,"losses":11,"wins":14},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":19,"wins":8},"meta/muse-glimmer-30b":{"draws":35,"losses":23,"wins":10},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":23,"losses":21,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":21,"losses":9,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":20,"losses":27,"wins":5},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":8},"o3":{"draws":23,"losses":36,"wins":14},"openai/gpt-oss-120b":{"draws":29,"losses":21,"wins":10},"poolside/laguna-s-2.1":{"draws":35,"losses":16,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":28,"wins":3},"qwen/qwen3.8-27b":{"draws":12,"losses":28,"wins":0},"qwen/qwen3.8-flash":{"draws":24,"losses":20,"wins":6},"qwen/qwen3.8-max":{"draws":41,"losses":38,"wins":26},"qwen/qwen3.8-max-0902":{"draws":2,"losses":11,"wins":1},"stealth/ox-alpha":{"draws":72,"losses":83,"wins":25},"stealth/space-bunny-alpha":{"draws":4,"losses":9,"wins":5},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":10},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":4},"tencent/hy4-preview":{"draws":22,"losses":29,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":20,"wins":8},"thinkingmachines/inkling-small":{"draws":36,"losses":29,"wins":17},"x-ai/grok-4.5":{"draws":20,"losses":27,"wins":4},"x-ai/grok-4.6":{"draws":22,"losses":31,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":19,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":24,"losses":13,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":42,"wins":16},"z-ai/glm-5.3":{"draws":8,"losses":21,"wins":1},"z-ai/glm-5.3-flash":{"draws":23,"losses":33,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":15,"wins":3}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":22,"wins":35},"claude-fable-5":{"draws":17,"losses":54,"wins":15},"claude-fable-5-1":{"draws":1,"losses":85,"wins":6},"claude-opus-4-5":{"draws":59,"losses":56,"wins":59},"claude-opus-4-8":{"draws":26,"losses":18,"wins":18},"claude-opus-5":{"draws":20,"losses":81,"wins":21},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":64,"losses":23,"wins":51},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":17},"deepseek/deepseek-v4-flash":{"draws":29,"losses":27,"wins":48},"deepseek/deepseek-v4-pro":{"draws":22,"losses":38,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":30,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":17},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":30,"losses":34,"wins":34},"google/gemini-3.5-flash-lite":{"draws":110,"losses":45,"wins":133},"google/gemini-3.6-flash":{"draws":72,"losses":127,"wins":75},"google/gemini-3.8-flash":{"draws":21,"losses":32,"wins":25},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":8,"losses":6,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":18,"wins":16},"gpt-5.4":{"draws":25,"losses":75,"wins":28},"gpt-5.4-mini":{"draws":21,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":36},"gpt-5.5":{"draws":16,"losses":21,"wins":19},"gpt-5.6-luna":{"draws":43,"losses":45,"wins":44},"gpt-5.6-sol":{"draws":15,"losses":88,"wins":33},"gpt-5.6-terra":{"draws":24,"losses":32,"wins":28},"gpt-6-astra":{"draws":5,"losses":71,"wins":6},"gpt-6-luna":{"draws":15,"losses":15,"wins":16},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":28},"inclusionai/ling-3.0-flash":{"draws":32,"losses":9,"wins":39},"meituan/longcat-2.0":{"draws":36,"losses":32,"wins":58},"meta/muse-glimmer-30b":{"draws":29,"losses":10,"wins":33},"meta/muse-spark-1.2":{"draws":30,"losses":32,"wins":36},"meta/muse-spark-1.3":{"draws":12,"losses":44,"wins":20},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":12,"losses":12,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":57,"losses":51,"wins":36},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":21},"o3":{"draws":16,"losses":68,"wins":82},"openai/gpt-oss-120b":{"draws":32,"losses":10,"wins":30},"poolside/laguna-s-2.1":{"draws":44,"losses":24,"wins":52},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":19},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":30,"wins":24},"qwen/qwen3.8-27b":{"draws":6,"losses":24,"wins":14},"qwen/qwen3.8-flash":{"draws":15,"losses":14,"wins":21},"qwen/qwen3.8-max":{"draws":35,"losses":33,"wins":27},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":13},"stealth/ox-alpha":{"draws":67,"losses":113,"wins":84},"stepfun/step-3.7-flash":{"draws":8,"losses":11,"wins":27},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":44,"wins":20},"thinkingmachines/inkling":{"draws":45,"losses":19,"wins":68},"thinkingmachines/inkling-small":{"draws":34,"losses":11,"wins":48},"x-ai/grok-4.5":{"draws":18,"losses":31,"wins":9},"x-ai/grok-4.6":{"draws":32,"losses":37,"wins":17},"x-ai/grok-4.7":{"draws":4,"losses":3,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":7},"xiaomi/mimo-v2.5":{"draws":35,"losses":8,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":22,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":4},"z-ai/glm-5.2":{"draws":41,"losses":36,"wins":51},"z-ai/glm-5.3":{"draws":18,"losses":50,"wins":12},"z-ai/glm-5.3-flash":{"draws":14,"losses":40,"wins":24},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":10,"wins":21},"claude-fable-5":{"draws":22,"losses":42,"wins":8},"claude-fable-5-1":{"draws":2,"losses":54,"wins":2},"claude-opus-4-5":{"draws":26,"losses":19,"wins":25},"claude-opus-4-8":{"draws":13,"losses":10,"wins":3},"claude-opus-5":{"draws":7,"losses":48,"wins":3},"claude-opus-5-5":{"draws":3,"losses":37,"wins":2},"claude-sonnet-5":{"draws":30,"losses":27,"wins":15},"claude-sonnet-5-5":{"draws":4,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":29,"losses":14,"wins":33},"deepseek/deepseek-v4-pro":{"draws":24,"losses":17,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":6},"fireworks/ember-1":{"draws":9,"losses":7,"wins":2},"gemini-3.1-pro-preview":{"draws":10,"losses":8,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":26,"losses":22,"wins":16},"google/gemini-3.5-flash-lite":{"draws":54,"losses":21,"wins":39},"google/gemini-3.6-flash":{"draws":39,"losses":34,"wins":23},"google/gemini-3.8-flash":{"draws":19,"losses":30,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":8,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":10,"wins":10},"gpt-5.4":{"draws":25,"losses":34,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":11,"wins":8},"gpt-5.5":{"draws":10,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":29,"losses":19,"wins":24},"gpt-5.6-sol":{"draws":13,"losses":38,"wins":11},"gpt-5.6-terra":{"draws":34,"losses":16,"wins":18},"gpt-6-astra":{"draws":9,"losses":53,"wins":0},"gpt-6-luna":{"draws":16,"losses":10,"wins":10},"gpt-6-sol":{"draws":9,"losses":22,"wins":3},"gpt-6.1-sol":{"draws":6,"losses":26,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":23,"losses":8,"wins":17},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":13},"meituan/longcat-2.0":{"draws":26,"losses":13,"wins":15},"meta/muse-glimmer-30b":{"draws":32,"losses":4,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":10,"wins":21},"meta/muse-spark-1.3":{"draws":17,"losses":27,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":19,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":23,"losses":23,"wins":20},"nex-agi/nex-n2-pro":{"draws":7,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":7},"o3":{"draws":18,"losses":31,"wins":35},"openai/gpt-oss-120b":{"draws":32,"losses":10,"wins":20},"poolside/laguna-s-2.1":{"draws":26,"losses":13,"wins":13},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":26,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":17,"wins":3},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":31,"losses":24,"wins":13},"qwen/qwen3.8-max-0902":{"draws":9,"losses":5,"wins":8},"stealth/ox-alpha":{"draws":76,"losses":102,"wins":30},"stealth/space-bunny-alpha":{"draws":9,"losses":2,"wins":7},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":16},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":6},"tencent/hy4-preview":{"draws":23,"losses":25,"wins":12},"thinkingmachines/inkling":{"draws":20,"losses":6,"wins":22},"thinkingmachines/inkling-small":{"draws":34,"losses":15,"wins":21},"x-ai/grok-4.5":{"draws":21,"losses":29,"wins":10},"x-ai/grok-4.6":{"draws":15,"losses":18,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":21,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":8,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":20,"wins":29},"z-ai/glm-5.3":{"draws":9,"losses":39,"wins":10},"z-ai/glm-5.3-flash":{"draws":20,"losses":37,"wins":17},"z-ai/glm-5.3-flashx":{"draws":10,"losses":11,"wins":3}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":11},"claude-fable-5":{"draws":2,"losses":15,"wins":7},"claude-fable-5-1":{"draws":2,"losses":19,"wins":5},"claude-opus-4-5":{"draws":10,"losses":5,"wins":15},"claude-opus-4-8":{"draws":9,"losses":5,"wins":10},"claude-opus-5":{"draws":6,"losses":19,"wins":7},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":4,"losses":5,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":26},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":15,"wins":13},"fireworks/ember-1":{"draws":6,"losses":11,"wins":15},"gemini-3.1-pro-preview":{"draws":5,"losses":14,"wins":11},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":12},"google/gemini-3.5-flash-lite":{"draws":6,"losses":11,"wins":23},"google/gemini-3.6-flash":{"draws":2,"losses":18,"wins":20},"google/gemini-3.8-flash":{"draws":5,"losses":10,"wins":7},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":10},"gpt-4.1":{"draws":3,"losses":0,"wins":7},"gpt-5":{"draws":3,"losses":4,"wins":7},"gpt-5.4":{"draws":9,"losses":4,"wins":9},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":2,"wins":20},"gpt-5.5":{"draws":5,"losses":11,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":2,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":12},"gpt-6-astra":{"draws":3,"losses":15,"wins":2},"gpt-6-luna":{"draws":7,"losses":15,"wins":18},"gpt-6-sol":{"draws":9,"losses":25,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":20},"meta/muse-glimmer-30b":{"draws":2,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":1,"losses":9,"wins":6},"meta/muse-spark-1.3":{"draws":3,"losses":4,"wins":11},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":14},"o3":{"draws":4,"losses":5,"wins":21},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":15},"poolside/laguna-s-2.1":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":5,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":7},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":7,"wins":8},"qwen/qwen3.8-max-0902":{"draws":9,"losses":14,"wins":17},"stealth/ox-alpha":{"draws":14,"losses":21,"wins":23},"stealth/space-bunny-alpha":{"draws":8,"losses":9,"wins":7},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":15},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":2,"losses":12,"wins":6},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":13},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":8},"x-ai/grok-4.6":{"draws":6,"losses":13,"wins":13},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":9,"losses":5,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":14},"z-ai/glm-5.2":{"draws":7,"losses":11,"wins":26},"z-ai/glm-5.3":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.3-flash":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":18,"wins":17}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":25,"wins":17},"claude-fable-5":{"draws":8,"losses":63,"wins":1},"claude-fable-5-1":{"draws":3,"losses":73,"wins":0},"claude-opus-4-5":{"draws":67,"losses":94,"wins":45},"claude-opus-4-8":{"draws":40,"losses":90,"wins":12},"claude-opus-5":{"draws":26,"losses":138,"wins":6},"claude-opus-5-5":{"draws":3,"losses":73,"wins":0},"claude-sonnet-5":{"draws":19,"losses":32,"wins":9},"claude-sonnet-5-5":{"draws":7,"losses":40,"wins":1},"cohere/north-mini-code":{"draws":27,"losses":11,"wins":32},"deepseek/deepseek-v4-flash":{"draws":48,"losses":50,"wins":60},"deepseek/deepseek-v4-pro":{"draws":17,"losses":23,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":26,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":45,"wins":10},"fireworks/ember-1":{"draws":24,"losses":28,"wins":8},"gemini-3.1-pro-preview":{"draws":21,"losses":27,"wins":14},"google/gemini-3.1-flash-lite":{"draws":28,"losses":32,"wins":44},"google/gemini-3.5-flash":{"draws":21,"losses":40,"wins":19},"google/gemini-3.5-flash-lite":{"draws":36,"losses":53,"wins":35},"google/gemini-3.6-flash":{"draws":37,"losses":80,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":39,"wins":7},"google/gemma-4-31b-it":{"draws":21,"losses":37,"wins":36},"gpt-4.1":{"draws":22,"losses":27,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":35,"losses":42,"wins":15},"gpt-5.4":{"draws":10,"losses":37,"wins":3},"gpt-5.4-mini":{"draws":35,"losses":25,"wins":36},"gpt-5.4-nano":{"draws":25,"losses":70,"wins":61},"gpt-5.5":{"draws":45,"losses":54,"wins":15},"gpt-5.6-luna":{"draws":32,"losses":21,"wins":15},"gpt-5.6-sol":{"draws":11,"losses":37,"wins":6},"gpt-5.6-terra":{"draws":26,"losses":39,"wins":7},"gpt-6-astra":{"draws":4,"losses":48,"wins":0},"gpt-6-luna":{"draws":21,"losses":34,"wins":19},"gpt-6-sol":{"draws":10,"losses":48,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":57,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":8,"wins":16},"inclusionai/ling-3.0-flash":{"draws":31,"losses":19,"wins":36},"meituan/longcat-2.0":{"draws":32,"losses":50,"wins":36},"meta/muse-glimmer-30b":{"draws":19,"losses":22,"wins":17},"meta/muse-spark-1.2":{"draws":7,"losses":23,"wins":8},"meta/muse-spark-1.3":{"draws":11,"losses":40,"wins":7},"minimax/minimax-m3":{"draws":23,"losses":37,"wins":40},"mistralai/mistral-medium-3-5":{"draws":9,"losses":11,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":20,"wins":9},"moonshotai/kimi-k3":{"draws":24,"losses":57,"wins":13},"nex-agi/nex-n2-pro":{"draws":21,"losses":20,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":41,"wins":46},"o3":{"draws":17,"losses":59,"wins":24},"openai/gpt-oss-120b":{"draws":14,"losses":21,"wins":19},"poolside/laguna-s-2.1":{"draws":25,"losses":37,"wins":28},"qwen/qwen3.7-max":{"draws":24,"losses":41,"wins":15},"qwen/qwen3.7-plus":{"draws":9,"losses":25,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":31,"wins":15},"qwen/qwen3.8-27b":{"draws":2,"losses":21,"wins":7},"qwen/qwen3.8-flash":{"draws":9,"losses":16,"wins":13},"qwen/qwen3.8-max":{"draws":17,"losses":36,"wins":15},"qwen/qwen3.8-max-0902":{"draws":30,"losses":29,"wins":7},"stealth/ox-alpha":{"draws":34,"losses":122,"wins":34},"stealth/space-bunny-alpha":{"draws":19,"losses":18,"wins":9},"stepfun/step-3.7-flash":{"draws":18,"losses":31,"wins":33},"tencent/hy3-preview":{"draws":24,"losses":37,"wins":21},"tencent/hy4-preview":{"draws":18,"losses":58,"wins":4},"thinkingmachines/inkling":{"draws":24,"losses":40,"wins":60},"thinkingmachines/inkling-small":{"draws":24,"losses":16,"wins":18},"x-ai/grok-4.5":{"draws":22,"losses":50,"wins":14},"x-ai/grok-4.6":{"draws":23,"losses":42,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":46,"wins":4},"x-ai/grok-build-0.1":{"draws":11,"losses":23,"wins":18},"xiaomi/mimo-v2.5":{"draws":76,"losses":61,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":42,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":28,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":26,"wins":1},"z-ai/glm-5.2":{"draws":57,"losses":80,"wins":41},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":57,"wins":16},"z-ai/glm-5.3-flashx":{"draws":18,"losses":47,"wins":7}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":5},"claude-fable-5":{"draws":4,"losses":28,"wins":0},"claude-fable-5-1":{"draws":0,"losses":30,"wins":0},"claude-opus-4-5":{"draws":19,"losses":38,"wins":21},"claude-opus-4-8":{"draws":17,"losses":24,"wins":13},"claude-opus-5":{"draws":6,"losses":81,"wins":3},"claude-opus-5-5":{"draws":1,"losses":33,"wins":0},"claude-sonnet-5":{"draws":7,"losses":18,"wins":5},"claude-sonnet-5-5":{"draws":3,"losses":7,"wins":2},"cohere/north-mini-code":{"draws":14,"losses":5,"wins":19},"deepseek/deepseek-v4-flash":{"draws":28,"losses":27,"wins":23},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":16,"wins":3},"fireworks/ember-1":{"draws":6,"losses":6,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":12,"losses":17,"wins":15},"google/gemini-3.5-flash-lite":{"draws":14,"losses":28,"wins":18},"google/gemini-3.6-flash":{"draws":18,"losses":37,"wins":11},"google/gemini-3.8-flash":{"draws":12,"losses":20,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":8,"wins":18},"gpt-4.1":{"draws":6,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":19,"wins":12},"gpt-5.4":{"draws":7,"losses":20,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":15,"wins":11},"gpt-5.4-nano":{"draws":26,"losses":20,"wins":30},"gpt-5.5":{"draws":20,"losses":23,"wins":13},"gpt-5.6-luna":{"draws":7,"losses":7,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":22,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":22,"wins":3},"gpt-6-astra":{"draws":1,"losses":25,"wins":0},"gpt-6-luna":{"draws":9,"losses":20,"wins":3},"gpt-6-sol":{"draws":1,"losses":30,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":22,"losses":13,"wins":19},"meituan/longcat-2.0":{"draws":23,"losses":23,"wins":22},"meta/muse-glimmer-30b":{"draws":12,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":7,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":4,"losses":29,"wins":1},"minimax/minimax-m3":{"draws":10,"losses":12,"wins":16},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":10},"nex-agi/nex-n2-pro":{"draws":12,"losses":10,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":9,"wins":19},"o3":{"draws":11,"losses":29,"wins":16},"openai/gpt-oss-120b":{"draws":14,"losses":12,"wins":8},"poolside/laguna-s-2.1":{"draws":20,"losses":21,"wins":19},"qwen/qwen3.7-max":{"draws":13,"losses":22,"wins":11},"qwen/qwen3.7-plus":{"draws":20,"losses":8,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":20,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":22,"wins":2},"qwen/qwen3.8-flash":{"draws":8,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":7},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":5},"stealth/ox-alpha":{"draws":22,"losses":61,"wins":15},"stealth/space-bunny-alpha":{"draws":5,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":17},"tencent/hy3-preview":{"draws":11,"losses":16,"wins":11},"tencent/hy4-preview":{"draws":7,"losses":16,"wins":3},"thinkingmachines/inkling":{"draws":10,"losses":14,"wins":30},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":16},"x-ai/grok-4.5":{"draws":8,"losses":35,"wins":9},"x-ai/grok-4.6":{"draws":7,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":33,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":3},"z-ai/glm-5.2":{"draws":33,"losses":45,"wins":22},"z-ai/glm-5.3":{"draws":7,"losses":24,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":3},"z-ai/glm-5.3-flashx":{"draws":10,"losses":20,"wins":2}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":11},"claude-fable-5":{"draws":7,"losses":20,"wins":3},"claude-fable-5-1":{"draws":1,"losses":27,"wins":0},"claude-opus-4-5":{"draws":13,"losses":13,"wins":4},"claude-opus-4-8":{"draws":10,"losses":7,"wins":5},"claude-opus-5":{"draws":6,"losses":34,"wins":2},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":9,"losses":8,"wins":9},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":19,"losses":5,"wins":22},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":11},"fireworks/ember-1":{"draws":8,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":3,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":7,"losses":10,"wins":9},"google/gemini-3.5-flash-lite":{"draws":10,"losses":5,"wins":15},"google/gemini-3.6-flash":{"draws":11,"losses":16,"wins":15},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":5},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":4},"gpt-4.1":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":8,"losses":1,"wins":1},"gpt-5.4":{"draws":6,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":4,"wins":5},"gpt-5.5":{"draws":8,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":11,"wins":7},"gpt-6-astra":{"draws":1,"losses":17,"wins":0},"gpt-6-luna":{"draws":11,"losses":19,"wins":10},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":0,"losses":27,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":10,"losses":5,"wins":7},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":7},"meta/muse-spark-1.2":{"draws":3,"losses":12,"wins":1},"meta/muse-spark-1.3":{"draws":6,"losses":11,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":4,"wins":9},"o3":{"draws":3,"losses":7,"wins":16},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":6},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":9,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-flash":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":5,"wins":5},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":11},"stealth/ox-alpha":{"draws":22,"losses":31,"wins":19},"stealth/space-bunny-alpha":{"draws":6,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":6},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":12},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":4},"x-ai/grok-4.6":{"draws":6,"losses":16,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":24,"losses":3,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":16,"losses":17,"wins":9},"z-ai/glm-5.3":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":12,"wins":3},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":10}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":12},"claude-fable-5":{"draws":2,"losses":26,"wins":4},"claude-fable-5-1":{"draws":1,"losses":23,"wins":2},"claude-opus-4-5":{"draws":17,"losses":8,"wins":11},"claude-opus-4-8":{"draws":2,"losses":13,"wins":9},"claude-opus-5":{"draws":5,"losses":24,"wins":3},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":8,"losses":7,"wins":9},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":12,"losses":5,"wins":19},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"fireworks/ember-1":{"draws":12,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":14},"google/gemini-3.5-flash":{"draws":6,"losses":12,"wins":10},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":15},"google/gemini-3.6-flash":{"draws":10,"losses":21,"wins":11},"google/gemini-3.8-flash":{"draws":8,"losses":2,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-5":{"draws":4,"losses":0,"wins":4},"gpt-5.4":{"draws":8,"losses":7,"wins":7},"gpt-5.4-mini":{"draws":0,"losses":3,"wins":11},"gpt-5.4-nano":{"draws":8,"losses":2,"wins":12},"gpt-5.5":{"draws":5,"losses":8,"wins":5},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":13,"wins":9},"gpt-6-astra":{"draws":1,"losses":18,"wins":1},"gpt-6-luna":{"draws":11,"losses":14,"wins":21},"gpt-6-sol":{"draws":10,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":33,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":11,"losses":2,"wins":17},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":10},"meta/muse-spark-1.2":{"draws":6,"losses":5,"wins":7},"meta/muse-spark-1.3":{"draws":2,"losses":8,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":9},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":9,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":13},"o3":{"draws":2,"losses":12,"wins":12},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":16},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":7,"wins":5},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":13,"losses":8,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":17},"stealth/ox-alpha":{"draws":17,"losses":22,"wins":17},"stealth/space-bunny-alpha":{"draws":9,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":10,"wins":8},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":14},"thinkingmachines/inkling-small":{"draws":6,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":13},"x-ai/grok-4.6":{"draws":7,"losses":19,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":19,"losses":3,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":10,"losses":8,"wins":14},"z-ai/glm-5.3":{"draws":5,"losses":11,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":14}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":40,"wins":26},"claude-fable-5":{"draws":26,"losses":73,"wins":15},"claude-fable-5-1":{"draws":7,"losses":81,"wins":2},"claude-opus-4-5":{"draws":83,"losses":124,"wins":61},"claude-opus-4-8":{"draws":42,"losses":75,"wins":27},"claude-opus-5":{"draws":48,"losses":170,"wins":28},"claude-opus-5-5":{"draws":4,"losses":66,"wins":4},"claude-sonnet-5":{"draws":50,"losses":54,"wins":22},"claude-sonnet-5-5":{"draws":20,"losses":40,"wins":16},"cohere/north-mini-code":{"draws":17,"losses":6,"wins":37},"deepseek/deepseek-v4-flash":{"draws":60,"losses":37,"wins":77},"deepseek/deepseek-v4-pro":{"draws":33,"losses":49,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":45,"losses":43,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":30,"wins":16},"fireworks/ember-1":{"draws":26,"losses":37,"wins":13},"gemini-3.1-pro-preview":{"draws":31,"losses":30,"wins":21},"google/gemini-3.1-flash-lite":{"draws":28,"losses":20,"wins":64},"google/gemini-3.5-flash":{"draws":39,"losses":61,"wins":46},"google/gemini-3.5-flash-lite":{"draws":77,"losses":95,"wins":76},"google/gemini-3.6-flash":{"draws":73,"losses":86,"wins":49},"google/gemini-3.8-flash":{"draws":34,"losses":66,"wins":22},"google/gemma-4-31b-it":{"draws":20,"losses":12,"wins":26},"gpt-4.1":{"draws":13,"losses":16,"wins":23},"gpt-4.1-nano":{"draws":1,"losses":5,"wins":0},"gpt-5":{"draws":42,"losses":41,"wins":41},"gpt-5.4":{"draws":43,"losses":50,"wins":29},"gpt-5.4-mini":{"draws":42,"losses":18,"wins":36},"gpt-5.4-nano":{"draws":47,"losses":52,"wins":67},"gpt-5.5":{"draws":54,"losses":63,"wins":37},"gpt-5.6-luna":{"draws":47,"losses":28,"wins":37},"gpt-5.6-sol":{"draws":7,"losses":87,"wins":10},"gpt-5.6-terra":{"draws":54,"losses":52,"wins":34},"gpt-6-astra":{"draws":4,"losses":83,"wins":1},"gpt-6-luna":{"draws":29,"losses":44,"wins":27},"gpt-6-sol":{"draws":11,"losses":54,"wins":1},"gpt-6.1-sol":{"draws":7,"losses":64,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":45,"losses":8,"wins":45},"inclusionai/ling-3.0-flash":{"draws":45,"losses":19,"wins":28},"meituan/longcat-2.0":{"draws":52,"losses":38,"wins":80},"meta/muse-glimmer-30b":{"draws":60,"losses":20,"wins":32},"meta/muse-spark-1.2":{"draws":24,"losses":39,"wins":29},"meta/muse-spark-1.3":{"draws":22,"losses":47,"wins":23},"minimax/minimax-m3":{"draws":30,"losses":20,"wins":24},"mistralai/mistral-medium-3-5":{"draws":43,"losses":8,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":24,"wins":14},"moonshotai/kimi-k3":{"draws":43,"losses":41,"wins":20},"nex-agi/nex-n2-pro":{"draws":37,"losses":13,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":68,"losses":27,"wins":35},"o3":{"draws":24,"losses":71,"wins":63},"openai/gpt-oss-120b":{"draws":45,"losses":29,"wins":34},"poolside/laguna-s-2.1":{"draws":70,"losses":46,"wins":40},"qwen/qwen3.7-max":{"draws":33,"losses":33,"wins":34},"qwen/qwen3.7-plus":{"draws":40,"losses":19,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":43,"wins":24},"qwen/qwen3.8-27b":{"draws":21,"losses":34,"wins":17},"qwen/qwen3.8-flash":{"draws":36,"losses":31,"wins":25},"qwen/qwen3.8-max":{"draws":39,"losses":36,"wins":29},"qwen/qwen3.8-max-0902":{"draws":19,"losses":32,"wins":9},"stealth/ox-alpha":{"draws":90,"losses":162,"wins":74},"stealth/space-bunny-alpha":{"draws":31,"losses":17,"wins":18},"stepfun/step-3.7-flash":{"draws":25,"losses":19,"wins":28},"tencent/hy3-preview":{"draws":30,"losses":24,"wins":32},"tencent/hy4-preview":{"draws":33,"losses":50,"wins":19},"thinkingmachines/inkling":{"draws":50,"losses":37,"wins":53},"thinkingmachines/inkling-small":{"draws":52,"losses":35,"wins":49},"x-ai/grok-4.5":{"draws":41,"losses":83,"wins":28},"x-ai/grok-4.6":{"draws":35,"losses":80,"wins":15},"x-ai/grok-4.7":{"draws":7,"losses":57,"wins":10},"x-ai/grok-build-0.1":{"draws":9,"losses":12,"wins":21},"xiaomi/mimo-v2.5":{"draws":88,"losses":52,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":29,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":24,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":28,"wins":6},"z-ai/glm-5.2":{"draws":91,"losses":74,"wins":67},"z-ai/glm-5.3":{"draws":31,"losses":63,"wins":8},"z-ai/glm-5.3-flash":{"draws":35,"losses":74,"wins":29},"z-ai/glm-5.3-flashx":{"draws":20,"losses":32,"wins":12}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":13,"wins":20},"claude-fable-5":{"draws":13,"losses":44,"wins":17},"claude-fable-5-1":{"draws":4,"losses":60,"wins":4},"claude-opus-4-5":{"draws":26,"losses":19,"wins":25},"claude-opus-4-8":{"draws":9,"losses":13,"wins":12},"claude-opus-5":{"draws":3,"losses":35,"wins":6},"claude-opus-5-5":{"draws":1,"losses":27,"wins":0},"claude-sonnet-5":{"draws":27,"losses":13,"wins":32},"claude-sonnet-5-5":{"draws":8,"losses":12,"wins":6},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":31,"losses":9,"wins":26},"deepseek/deepseek-v4-pro":{"draws":22,"losses":19,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":23,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":7,"wins":1},"fireworks/ember-1":{"draws":14,"losses":7,"wins":5},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":9},"google/gemini-3.5-flash":{"draws":20,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":41,"losses":18,"wins":57},"google/gemini-3.6-flash":{"draws":26,"losses":37,"wins":37},"google/gemini-3.8-flash":{"draws":15,"losses":30,"wins":19},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":11},"gpt-4.1":{"draws":2,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":5,"wins":14},"gpt-5.4":{"draws":23,"losses":38,"wins":13},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":11,"wins":19},"gpt-5.5":{"draws":9,"losses":6,"wins":17},"gpt-5.6-luna":{"draws":31,"losses":20,"wins":19},"gpt-5.6-sol":{"draws":13,"losses":40,"wins":9},"gpt-5.6-terra":{"draws":28,"losses":19,"wins":23},"gpt-6-astra":{"draws":7,"losses":57,"wins":2},"gpt-6-luna":{"draws":10,"losses":12,"wins":6},"gpt-6-sol":{"draws":8,"losses":15,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":27,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":26,"losses":4,"wins":18},"inclusionai/ling-3.0-flash":{"draws":14,"losses":0,"wins":14},"meituan/longcat-2.0":{"draws":17,"losses":8,"wins":27},"meta/muse-glimmer-30b":{"draws":17,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":8,"losses":25,"wins":13},"meta/muse-spark-1.3":{"draws":14,"losses":25,"wins":15},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":19,"losses":7,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":28,"losses":15,"wins":19},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":8,"wins":9},"o3":{"draws":7,"losses":24,"wins":31},"openai/gpt-oss-120b":{"draws":28,"losses":6,"wins":28},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":10,"wins":18},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":16},"qwen/qwen3.8-flash":{"draws":15,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":22,"losses":23,"wins":17},"qwen/qwen3.8-max-0902":{"draws":14,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":61,"losses":86,"wins":58},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":2},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":6},"tencent/hy4-preview":{"draws":19,"losses":17,"wins":26},"thinkingmachines/inkling":{"draws":17,"losses":9,"wins":26},"thinkingmachines/inkling-small":{"draws":19,"losses":14,"wins":31},"x-ai/grok-4.5":{"draws":22,"losses":15,"wins":27},"x-ai/grok-4.6":{"draws":19,"losses":36,"wins":17},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":4},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":21,"losses":1,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":38,"losses":22,"wins":34},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":22,"losses":30,"wins":22},"z-ai/glm-5.3-flashx":{"draws":14,"losses":7,"wins":3}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":7,"wins":31},"claude-fable-5":{"draws":16,"losses":41,"wins":9},"claude-fable-5-1":{"draws":2,"losses":65,"wins":3},"claude-opus-4-5":{"draws":19,"losses":27,"wins":32},"claude-opus-4-8":{"draws":5,"losses":10,"wins":5},"claude-opus-5":{"draws":6,"losses":47,"wins":11},"claude-opus-5-5":{"draws":2,"losses":23,"wins":1},"claude-sonnet-5":{"draws":21,"losses":24,"wins":23},"claude-sonnet-5-5":{"draws":3,"losses":10,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":39,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":24,"losses":13,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":25,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":11,"wins":4},"fireworks/ember-1":{"draws":6,"losses":5,"wins":11},"gemini-3.1-pro-preview":{"draws":5,"losses":6,"wins":9},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":21,"losses":34,"wins":23},"google/gemini-3.5-flash-lite":{"draws":37,"losses":40,"wins":43},"google/gemini-3.6-flash":{"draws":33,"losses":45,"wins":36},"google/gemini-3.8-flash":{"draws":18,"losses":32,"wins":16},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":2,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":15,"losses":9,"wins":18},"gpt-5.4":{"draws":14,"losses":27,"wins":19},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":11},"gpt-5.5":{"draws":8,"losses":12,"wins":8},"gpt-5.6-luna":{"draws":26,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":18,"losses":39,"wins":15},"gpt-5.6-terra":{"draws":27,"losses":19,"wins":24},"gpt-6-astra":{"draws":9,"losses":49,"wins":4},"gpt-6-luna":{"draws":8,"losses":10,"wins":14},"gpt-6-sol":{"draws":5,"losses":12,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":15,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":15,"losses":5,"wins":24},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":16},"meituan/longcat-2.0":{"draws":17,"losses":16,"wins":31},"meta/muse-glimmer-30b":{"draws":28,"losses":11,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":14},"meta/muse-spark-1.3":{"draws":17,"losses":30,"wins":15},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":8},"mistralai/mistral-medium-3-5":{"draws":15,"losses":9,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":26,"losses":16,"wins":18},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":10},"o3":{"draws":16,"losses":30,"wins":26},"openai/gpt-oss-120b":{"draws":16,"losses":9,"wins":23},"poolside/laguna-s-2.1":{"draws":22,"losses":10,"wins":14},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":27,"wins":12},"qwen/qwen3.8-27b":{"draws":20,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":21,"losses":18,"wins":9},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":17},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":4},"stealth/ox-alpha":{"draws":61,"losses":101,"wins":60},"stealth/space-bunny-alpha":{"draws":5,"losses":4,"wins":9},"stepfun/step-3.7-flash":{"draws":11,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":20,"losses":24,"wins":14},"thinkingmachines/inkling":{"draws":23,"losses":11,"wins":18},"thinkingmachines/inkling-small":{"draws":28,"losses":21,"wins":31},"x-ai/grok-4.5":{"draws":12,"losses":18,"wins":18},"x-ai/grok-4.6":{"draws":28,"losses":22,"wins":20},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":11,"losses":10,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":21,"wins":34},"z-ai/glm-5.3":{"draws":12,"losses":33,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":6},"z-ai/glm-5.3-flashx":{"draws":3,"losses":9,"wins":4}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":2,"wins":18},"claude-fable-5":{"draws":3,"losses":23,"wins":6},"claude-fable-5-1":{"draws":2,"losses":39,"wins":1},"claude-opus-4-5":{"draws":9,"losses":5,"wins":14},"claude-opus-4-8":{"draws":7,"losses":16,"wins":7},"claude-opus-5":{"draws":9,"losses":30,"wins":3},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":10,"losses":5,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":17,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":19},"deepseek/deepseek-v4-pro":{"draws":5,"losses":6,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"fireworks/ember-1":{"draws":17,"losses":15,"wins":8},"gemini-3.1-pro-preview":{"draws":19,"losses":8,"wins":13},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":8},"google/gemini-3.5-flash-lite":{"draws":12,"losses":6,"wins":16},"google/gemini-3.6-flash":{"draws":9,"losses":22,"wins":9},"google/gemini-3.8-flash":{"draws":6,"losses":9,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":11},"gpt-4.1":{"draws":4,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":4,"wins":2},"gpt-5.4":{"draws":10,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":11},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":15},"gpt-5.5":{"draws":9,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":13},"gpt-6-astra":{"draws":2,"losses":22,"wins":0},"gpt-6-luna":{"draws":13,"losses":14,"wins":19},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":30,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":12},"meituan/longcat-2.0":{"draws":14,"losses":5,"wins":15},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":7},"meta/muse-spark-1.2":{"draws":3,"losses":7,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":10},"o3":{"draws":4,"losses":2,"wins":26},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":10},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":7},"qwen/qwen3.8-max":{"draws":13,"losses":7,"wins":8},"qwen/qwen3.8-max-0902":{"draws":18,"losses":15,"wins":13},"stealth/ox-alpha":{"draws":15,"losses":28,"wins":27},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":8,"losses":3,"wins":19},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":9,"wins":12},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":0,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":12,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":11,"wins":10},"z-ai/glm-5.2":{"draws":10,"losses":9,"wins":21},"z-ai/glm-5.3":{"draws":8,"losses":14,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":7},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":10}}}}}